From 343aecd6e098fecc750311006445d9c04ae09cf7 Mon Sep 17 00:00:00 2001 From: Morten Hjorth-Jensen Date: Tue, 24 Oct 2023 06:52:53 +0200 Subject: [PATCH] updating book --- .../_build/.doctrees/environment.pickle | Bin 530597 -> 535509 bytes .../_build/.doctrees/exercisesweek43.doctree | Bin 20983 -> 816178 bytes .../_build/.doctrees/week43.doctree | Bin 844572 -> 844494 bytes .../html/_images/exercisesweek43_11_2.png | Bin 0 -> 27610 bytes .../html/_sources/exercisesweek43.ipynb | 1456 +- .../_build/html/_sources/week43.ipynb | 1254 +- .../_build/html/exercisesweek43.html | 13871 +++++- doc/LectureNotes/_build/html/searchindex.js | 2 +- doc/LectureNotes/_build/html/week43.html | 130 +- .../jupyter_execute/exercisesweek43.ipynb | 34689 +++++++++++++++- .../_build/jupyter_execute/exercisesweek43.py | 1248 + .../jupyter_execute/exercisesweek43_11_2.png | Bin 0 -> 27610 bytes .../_build/jupyter_execute/week43.ipynb | 1116 +- 13 files changed, 52141 insertions(+), 1625 deletions(-) create mode 100644 doc/LectureNotes/_build/html/_images/exercisesweek43_11_2.png create mode 100644 doc/LectureNotes/_build/jupyter_execute/exercisesweek43.py create mode 100644 doc/LectureNotes/_build/jupyter_execute/exercisesweek43_11_2.png diff --git a/doc/LectureNotes/_build/.doctrees/environment.pickle b/doc/LectureNotes/_build/.doctrees/environment.pickle index a98aad57d05ad7a9b8981a94c7f6dcc525ddbef9..ea91ee4d9737125684fbeb6aa0fc21031acfc666 100644 GIT binary patch literal 535509 zcmd?S37i~BaWA~Px<}XOKK80r@2*BG^^DFvq&*m&yF0opX?Hnx8EU#~rn}V_UEMR9 zJ+ScsySOpefVrM+j19)-G&UHF!C)Ks3^q2l@w4&6Tp#{?^UU)F*t~yaR8>}0R?k%C zbPInLzaJ~9Dl0l7|B;cA5s{fcwCJ^quDbdv`d@pkTQ3x=mj<2cWU*1JR-9^crrm$I zRV?R^g&w_TX2*+Xo|+kGFR<(NnbYmQd@a{(I8MIUm}x&a^pNW`+@VULe#Qh&9ny zGwr@Yvr-;y7Mu#6uHmPnW3}2v|JhpEV6;|m7Hd@|zuHAlc4M^ZTtZi`J1?GC z%|g+&h{WLF;7of}*=|*-U8~vjzg=5JkBJ{CR+~;^+|J?0m*mQ}>lSm6bgWp-JB>nX zY_!!V&$QPUn$5aG9&2I*44Rpw=Qma0V&x3YX&9oOmk}+rInf9_=t!(r6g>9|& zin`q_j5cedK*yaaY-_J-IQ5!aY}Ojn{38$fKa#6e>h;1jIB^FjicL@-EY?!PPrWrn z>|YwBzoJh=KQz{`(G}?ZitU1NblF6$Hc@s)?W$d#ZsHe5i+SR11v<20k5=tTbni_2 zp0l+nr{UzSv1#jW+bT4i@q4!U{Cd40IvoA7?cN8uTdc!?;O-&&-Wi|Vcn#g&Ao~4< zTE!WyLper^Rdh>k=IQo^mg|g$nH7McE7#Kt438#%z(C^p8hT!I-In8e=*~RTYHt+! z;?`P?oKr4VFOIsc@$up%`qjnNR)tjg>GtNjU3JRtsGZM~vNc^uTOZB2E|GOx^?Ji` z-O(u?YVOQq5TP>dHZis;b`c6_`+8e!k~ZHqT(6gl=%1r@)3%1GGhOJQUCmqGu(kYg zi_W)O%|Z>my8cwH(R8ZT{U!Wa$UZ0r{0wPMeY#PcC_tqb?%ln24;~4b%C(8wOnWK) zF<7rc0sEaxxpFH{9oa<3g0IJ5R@UEk+hDOiT^$?E6`b6~dJQ@bW3X)S==ss}&^PeA z>_VYc8FL5oV_=8v#*EXx4xodIjp10!jrz1J=wa9!bj%9D#kf6Lgb5H@A|8y{u0z8F z9lRR4%fs9=5@hE33e)u(h6Q>AMEZcLLuv>sL1+<%l~%clk&qh&K4VUUe(mY@M(XfU zr)rNuKZ&!dE5<&FxEzD4RvjI8Kn5lxUn`gGMg=1bqnI!+j!y$Iw>9R1Zi{RN`mJfZ z7t2Mr2}%0}Z7@CRqK_(Ig{Wdw6w6I?@j_BLew^zV%A=C#vZjq!sq(Vy2UQxDT6VZDU#VUGeX+1wKp3Lwl3k}&(e*QG^7DAuQ z)lB=a@w_oaIy5*91Jr6Sa-C*N%ycmr*Lmi?S(|_n^2T*A3D7X`pDhu9RiUmc{H`H; zLm-QJgeD7^-S%qlpS~W#!g)`^(#^Ct^3y>)9TZal|2vrEFrvsl%oH}ZH+uxsK645O z3bz;5o-V8_tS@XRY%FXlY%c6AY%A=0y0HJ5!kvY?3I_{^3U?RoDcoDQukftGaN+nf zg%fCSKmPwf;laYGrwgYGX9^D$9xgohnZom)DLh(utnmDi8w#Un@PdL}7%Suo`Sy}a z4x>~Uf4VSHD6}_(du-Ho%J2ioqI_nMU+l65?R=$HEt2XF<{PzozBX0G)22N!TEGkq zs|)qC^2NzPSjjT~GxR~p=Fa>@xON&wZW%2Xj&w_^-EuN9i!;V*qP)=z7 zHDtb)j?x@igynq={_*@rvrp{X_0-KXBi2i1&dn5_q({$JAMFf3dg)AiIgb&~^;quV zOOqCUx-`abY21=3)4&tPqrJ+h!!N*8F**(o#N4n-*ulu7mEut;)MzD7N&a*sY#8At zj9Pp7nFcI{lRsL_H6hiGbFfDX2OF?f?S9Nf%|=UjdU^JA77SMMFm*I2vNR|bv%#M! zyrI=z$&=jZc#SNg@Wht5{5vp}=lO5eEf8oi=0bRnAauMqF(@7_YLdA{r(U2x#iPDl zE$?K<%C#K&rSBvRDC{%6X@yJ%92uB#8%A?e!gw3B>qY#^c{DnOHi5&qh`k}2Bo<*5 zHfl44x3!lZt>s$6cNXmm?}BN@<0ThrxeM@;`Rf6Gxb!$6cmQTsC<58?d<*RV*vyM( z3Lk{UC*PUW#(S`gdXMY|KfydOJO(v|!{}H!I1H{c^Ynw?!~dRn=IQ3lSmFI})Wt7- zu-)%A?Iy_%r%X()KFt-FZ|w3!=%Ld-e9oCHI#X6{+&Uk8W=+ADv(7oLU4gHFF1+C6 z3f1BZ;k^h);Up}z-LQts6As)okCCSpMpoqtb{%73Pv{pRtN(a!^5cEUkM~C(Z}Di8 zn_VeB4uN4kBGURlb0GBCY2S9dQL8|-3G$lojn%AK=ix-bt+5^!rpb4M+&SgCJw!Pq z*Bzn9PCI+l$rZ&fkxIC`tYcU!RY+q`IqnSCNTC-_ zd-GAu*}@C4%f;q21kPhrLf$!l;I0rI{J?4-!`&U8$G{ER$IuO)hv9YF8;&|oJ#aYv zF6qeR26z$;bf@D^InKp>F`ZbE^f2~GSQ{W7e-e8b`y>W4e-e8b`y{La!LP&~#y*Jw z%fAwP82cm!6@QZSaDNQED4qQ=2nC(^!`LS=borCm!`LTb;Qc})Jhn_F>(CIVeXvv(zD#yALUHWIsMX^vG&ryIv3sp zvsyZbpvhx1{3@{1{OV!(DrB+w-E-wT)g*J1=gTHhlm3R(jS)Xm`wEbN9F4n znW#Q|LbhWv(bu1puVZAQD)GCr9g~T^{{7hNz~VAMpO>$rzY>^PZubS*PW(#j^`Fbv zF)~rj`jTwNWTLOXDqqLQMAh#bvK^C&zWy8e+PAUMA@C1sgD4~a6g0rfd$fVz)=c5O z_*=zk+E@*=SBQ0szdUF!DUD^tQo1$P?&Gi^dF3;OcePhjM5Sb3+K1(q2m#~kB{Brt z?#JAKFphga;*3Wqb~@AE4G()SJ{k31J?W8%{QF5>8jjix$DVQB_G(^g;a7#$7^f?5g7}gT64M|=44z#E6uHgHn zMBmc~|6$=(h1dFjN5Dk{S`lf&GLZsz?Paazc=pb$Tbu~kpwLI~#frQ$ZX@6a)x=Uw z_QYn2#f~FXPkbT%(m=WZK|`SWbntCIwW-u-k%!nc#qH#~>zj>Y1!`Sul7E9h@;KJh zh!2jsbqeo46A)P;*7O{Nh5Y_=isA%-uPq?{TBaCm(CyHDkMlsT_8Qqtjtie)dlkh4 zNw-}J&=y3D@%izHTBTSmVyQmi>>GlXBJnegKZeT1u_0FfeS>!m(ds%2DJ~*j?hbhi zY#OwjBSEaq|Dl=o3+Dd=_31pq*yuOPW~o2n1iiG{|J~6sq;D%5CR!>5bLQ;gmgtb#rTarT`M#IW&}On97Vu$ zBCH=Ur^SkmYzxQm5lX60OC(oRk$^*XinCIuPm_h{=Vur`e(d?F8S!F8#jaBB!WEet zslrPUaH|({7pG^Q5$#ra{~j$)R4MKbf0yX4k3NQ~PQb+ROT-R??pfzWauB`2-$wIJ z9ZEEEwg0~Grox;3zq76O;^#EjrCzt!kPRMnUWmT+t-fS=xp>Jx6dFu@O(aKP^eB)n z8Cp(H5u|n+NGM1eeTd;VM$sS0cgm;BUG#SIg)LfaglMb{Js!1r`P^Rc!lRDFVtu%Y z7u;sszRb6C!d6~WvSIs|inJ$1c_@az0MH;*M>cQ9X$9T0QUvWNQy~mzsgDdhVX;EI z@Xh;)XDt<}+^gCP={Z@%cAsd$QNq%X;XCmkdb3u(31udO*WQOBLnMAMc(Yu5=%s-$ zB@tC3$Xxm|LPMSEOz@K9j^GMmNCdTJLf?5INjZ<*6MVH={1hU-)n;+LNGZQ1t?I=p zqQR0fv%{H?nbPaSA}$r5w~!R%=l^CcL-Xz;nSI%q zDcGS=*b5Bu&`?@0x}yUBM!XuGD&}cO%5Pa#F~K0aL^0N46~R9IgpV<|5SdF#(t;`f zO}`+H?0K$H6nX9#7W^Kr7|a~IBV_a1i>CXe>UCPwaBQ0;MVf z`?^}hsfBj?la&9C(iy?uk<9S_j^r(Tq)`ajXpSPkhFLuHlJohTBa}dsgrCzj!hR}F(!LOaqd)g{uC-! zFhu36QIWE5U-O9%NO?GG6}CivA9w>CX^JL^0W0-P@T2^W^m~+D|B!(EtHS#6I}%a8 zr`%{jhdYCQ9TphTd#dH3g;SIVGWCAOEU+e?bs*yEJEkjmkPAE6F@f!x@_jw|j_Vu9 zz>@bsS*eY39McN6Qis8#cUUN1tG+6_?8;FMz)hjowQ6}#DhJS$Cjl#!oPLKNE-WvLrp3xc|hQB42b*TKX8*r|;*yj3BQ+N(oY@*a6NUD-B z>q9MgW^*Se=*7Cw3z=qKLwVz1>0`lb$5J%Zl2eajF*ozuYn?gM%ChngV6di9L<5D=MCPr^S-5+jktYhK8)0Z?!58R8CIZ@>a2GabTn`=q~QaBVhCbXb#ZV zM@T)Z&0T_h=KieEOlq+Uf}nGqOLglWYuqlo&Mu3zk0@}flcaihiG(uVvC{Dy`II{5 z7%5w{F=-k7y02tMpktu4ZQCx3wCZRrca#$K;t_!=P@O~@vA(Gv3jQt7ImGYLhevDH z6!NcBt7Ji7i+%^v$sfWyPn$VwvF-k2=Z~QLz2_ z1KX{giE!fa_8kL*x9!-zLy&#SLQRU}jh8v-MMfGS8rPK_3U!tmJ?}O>O{C5wy?EYZ z5_o1_v0vWY*62xE+cL6>H! zf$fi0x9_LK1QIuU@<}VqIRDdQHB6Mgii*!P2Pxn%KtCm^ zQ`?A0gY}kM7zlkHZA;ulhvTichJP&12hnG9agsn{>O!37?R_jtT2UMNmj0)FuZr-L zP&{sKMS98WTc?_LA3}g~>(% zy60XC{{gEs4MfIGXo|t;3HM3~b)-DbctlHf&k5HBGb$YJB06Kjf_bA(A%kg8){1$H zY8JDNR#liuG5=zArFCk+XXuAfK=0|)wnwYmW??Vp_f1I<=nT%I`zbWZxlX7QCWQ@axf4MwujH8$33)Fvf$k4`-Y7T>M7~a}4XCP1 z6mAguJV7-i?&cC z@R~;l5J7u%$4qEp=r_w3F>N4G!|k3&?H&uY3&>&Gp?Yx%lF!6maN2` z@(R#Y#MAxY)+WE1SOWW*pc>+WTaG_;@}zZo_|!4$?qjEhA2|7};iE^-9Xo&i-kE@f z4f1O*7lqP|3f8bEhfkk)X!ry^J$dq3E@ww#7i##NyeDm|x2;VCJ}7nJdOo1m3Dty;!@KM5HE{ux3TrTKvcs{<2xCmz_xm zQ7f*0gylgjp14@g4dRP-@y??u7Ly##yQW&>82&o`OuV8v0D|iX6pF8~;RISditL~$ zg~vh?_1EwtsXlGy*{_F&2%|@~{uZhaM3Ed;27U_*NhX+1u^iyYKsHo)oE5aKTLKE! zqmbB34L$E9RH?e_1WMvAKK4Y5yk@bb#c|~<9%}wXtBR-qYCCCE$QHL)2z`oA52hF8``%_QQ^iThK zO8(HJ*cX7XJ=KOk5zwYyL9x1@PP~V7eOL4?3YG9cm-CCtwmlC2_Fw6A&oO*6Lm{yN#LfkB3; z3w7a$LGxCM6VGb=rbyq2w#%S~UWg869`yu^IiZRS2-gKz=!C){d*te-M|~xIAqP8; z=B@OwVqZiUicJTl>hU-1+w#WyI@%sncEqe2#0^V-8J<6`$$q{hMLN#uu+ z(Ru3v>?6GK3|uEj>cAER$pBVsQHzH}(W#`h2FTh&=XH*N?@4pI}CDBbA z{TGQAFkoDEOM9uGV`t6U;1j4qJk*#J%P@N_uWvT{FLR9=D&~WvypKE4$1WM}Su$7% zh%UM9p6rXZ?RPey3t_n~$=B<|Yl^D|E*N=d{**@yir+w%Q}NFHMtzqk zUJ7rq8BTbv&S5{?C^lD#j0;phG?T8S!~{%Uhu8hIgNh>17oBO0f;^`ummumpQME}* z@weJIq(LSh`}CHOmrzEmwY`i&aB$_JVeO@qIHtfDZB5~H2!*8@*cY&(iG6r>epFP9 zzP983n2k- z;vqgtUO=n*!WQ}%NzeRf6ElrhFcMTEv^QXsVAwk4I-IF$-YY4Y5ks-PEO;rB!0Up4 z`fcHwoi6_o z)n8hS!7rE9r6u@hummnG#lK|JWs!gNMgFxM{|b>=5&h@N=s#ECpQY8}KeUX3&DnhvkG2b$;p`FHvLe;4H zj`p01tf@a&ti)Rm9negOf(ZVHoW0k|2Iyf#u`pzjb@jie&9vV4^>Pc-Vys$Yy?ig` zdCZ`QMYNZRy>ZA26$4VVxiUhw;$V4hXK%rQaRBwm2eX-RFo}LB6)=P(7m$B=FsotYp4yPot@-5hS*&v z+HkfTo~($>gh;Fxuf6A^-hy$abT!#&9|R`hTPb%M^(3N7&wsD(r!G7ke9S*U%L@3( zIB9_Wei=pLj_}{R0GTs~vc)RFqHwUiD&~MVcYyDaa%ro`&xa&jD?ShJ29Ibc3y0S- zC(6#+)lbZ{uYM}zS#1!6#6(89^-;`yt)??G@@bzP?9UDUdMfxUd1@%G@IywFSYB?I zr|fAL{*R3i4>rdHTX9#!|yy*qJ`=>IcH(d8hfXG=GvR0=QLofddDn{}SR6hQL#+=d$CSA!2p)L^SzTrgGCP!HoLWBmX=eU{M^ z{$KByc_kDv*zG`;s^8Nq4iC74xtWn`{4){!<4^`6Llu>h4vw?9+TQ^#UlwWIiuDlQ z`9~xL)NlgQ$ikoo%74s7M`*t#_Uk2k(&mr|vEiNV5d0ENV)T4N>?`(xXGRt%zfT+N z@j;v|9NU4%1$X4?!upXrTkZAUI*leUj7hElgWX;md5+`|Y%?}gcw)eGl4WmFo{KEf zKzo%4-6Ny`BTj|x?Q5`%L=7_H5?PcNb@t?p^C?1>pKF<#ni^!eDHuP5b;1x@x}n4ajQ>* zwgJH6qAaE{Sah1>ObO>s(Ns*7=(`A|RbrNsiL}yfa3k8QU}?nqZS)d(h}3Zu^1+lF zeY(aEv0-)_r@YifH0>+c*eoKV_n2qe8^y8(XYjz}LaFdmWbpIoiFM(!aeo`lW8Utc z!h-f(8${YG{j3}?rsV)FRdK)wm9dZdb?mM7QiM*Zf{GFKN6wy^6T^Qt(tq*W_q|*W z*xmea`lByfDIa<*pZU?BsK|$Vx#g?BSllNc?&F7Vnp}EMFhaeCZ@&2}_Xp3sc0X6$ z_PyZQe*X67zw_RI4W1p~XK(w=z5f_IyPcoC{R6($zJ{JXQibyfV82h6+g zc=nfqiG>@#@5c`X^MFU-J%gXi2G6`N-*a&D+0c|HzJ1TZ*Z)OicH*aB-SC&8nZSGY zkDm?CJpAx$zdjyJo#M%RKl<#S@Sb>G`o7n^<4xWZuP5L4FF*V#?}^ue@BhSae8PL; z_1mxh&ug}LPrUB>K=H1>;wSq(wg14sJo|RWn04`n$%qgAM*G5F?4f_K zk8^7(I1AZp*-7{&~D%D)Gj=t@Xx?W5WMiu- zMKfPK@q4}}BR=upByfx|f?x1khe!%Z{0{|d(!awO{JWyN`LE(v6TKs%?|Dt4hkZW| z&%>S^{u%9HIBe=OLBS^{#1=m84P`(lR_EZ(td%BysKxqDu77MI0eL^~qasvX595}U(g&^ zDbhh^VpW7Tk}l4Cp{=)3!uy^A$>1DE5oaO7UfX@txH{%7hOkzl(_fqhwUETb+zm!} zKOMb;kFxD4tWx{9PfD-x{=})8SDh+tD7_AUj$C_%bi(qaPT07DJ7M(|(g`b)I^lCG zxf9l2A)T-?sT0;L%u3@&3$SaF4P!uq66*m{LIOB<3p zq2F_s)?6W)uraX{Hu7+|?h5IIO-Y?#FW^pCc!hMr=A=&8b%k}pmZVPj_BB_QCTta* z5Dh0>^7>#w%Pn1-@P6&p+(%dA{dEcNZw|e`UVT4Om7m`rUJpcn{}&f>gT+_KXuMJF zqf;;U`tTa`v6a+GZ}b+q%de15x+$p>{_P5LXtyP3%7cL-xTTExe&lO%wB4N4hkxR^ zg8f&BBHg0)(WxH|jka48-oGXEetS|UzIrG3GIHQoM4(|HsS{ptBX`2U719Yik~-n_ z>$nrPTp^usTT&`Ll{Z*AsIu&$6!$R>5dhrQu&rL3_B zlRDw=yoAKfSBNGIaVK=jUVmy+D0_Xw71AfWMW1x)lD}FQ>XOA+_)vYzECm4n7;S%L zcwSWHgFYz@EapFN!=I;$+e$m}=g6*ByAMT(blhLv!9k5b@WeLn2nVsNj|vISii!nm z9}ZrsPjlNHRFdG=^hFC1q6HNDP=atp^m41cSX5k!+C@=^B5E^fH=8?1hn%5iYLRHc zM-2)kZP-(Mnje*(qf!Q!jABC$ZH2uZ*t8d3KtTu9U9CBZeJ42X3+GyS_W+4Ik_gm8 z)G*;a_GHr*+9vk&phas8*D8iK+tRNuD2ko4-sPO&4+WizxN04LTZ&^{{un_$ap?m7T6zfofjm?|GKV~S&)3S6B+k*|xHuubi92DeW7sQ8<+QHF z2M$GU5Q@rXLV)FT1d}Fmu8zq`H6nA!dHoS=%fJC4B$a?Ej27Sj6=>!hZJGO~G57s3 z?y0zA4(@lJ!-bO#8X7oDNpOzia!AkIgVq_;deLc_1R`BC7KKOaOP1_Mj3rwWlZ+}h z=8$abIXWqxZ#=_J_F6}CFLBLebKS|>gt(`!W5*`8U{2p_%qcFljr1rLE6l;^jt*DE;mFF6hTBE#&7}ML zg3+q+9ZU5wW2u(Lq@wDBIi#|JtLfq)9Wn4>2T9JXvTUF^M}M^TEB5Q9;vv!m?~JmSsgu7Ru+(ALG zVTWgAwn%u-Tn=b+8J*!M&92MafjM|PFvGmvK2P2#`>o5{?Q`&UyT{wndGbb?cU|7@ zn1i=FJl@XDlQ+ux>+*Kz9K7A>@%Dmw@n1i=NUR1@q7kZa18Wb?uvez!T{s-i zrjBr|GdPV82fJB!;XLnRzDl>Y?bv1Q-Mx2T6vl24G#ed z{b?*P=v+H%4`QFEeEFl2&zBfW{j2konyNVFkb1zs3dZuU3+8wfaK4BO9%{iY#!>mw zf5wvh);uMlf|EHUx%-%R{ws}BU^!-w;cRT&8h)YR;Os~-X3x{X2z2ZO+|Q%fG8ila zqSDQe6ifVv+7kOC_v+Zlr8<*2WM3~(#7Qzj$`cK7@=sKz<7F6!xN)C|6k2a1bL3wC1-g)BbtNLQ_JST)a`*$Cd+|yajBt?aj1LDpaoI=rZ@;ii_IAaO{rdcCoU8BnVaCV;kK;{ucT6C2Lhi7Wx=$qV0%F5a2OZ=Y0o}jB@Hh0Qg`U^(F_z^(qST;fey>CcqU1QDl4kTilUvk9K6~f8gIJ zsQ79A<1PHhTltTl7k_vz8}}KCjmk9~W=&Vy%1RkgqQVs;RItId7F5zu64eM)9#9gQ zeM+a7L?)aP)FqKyrW9~VWN#_OS`yh&N=ueRMv;r*m1wxI zdJDX9>9=<%n<#AJ;-uwct#aAn8=HcXrdXMesA5`1cRGz0aiM*OW&=2Ll~35j>3d$O z)EYXnpDu(#?#RaVkM%-_kC~Ze!BKggnu&^|ggUA4G+8=I`XCC2K7$_6Tbj^GMmUuR z6)`w44@WVNw;DJgnGPgE<&`*@SCmMh28!Z#rStfYXZS3BAS?e^XE_ zeHecv)ng5mKGxw)>32H4_}xw~L{F~>FSw(2D*B4~`#TWpNq4tbX2KrAj2C(t7+ElK zH7>Ci6<%M&k24#8t<8o<;;R9PZy1tjhlU9=^EE-KBQgV~&}?~xZd=8*tZ_%-z9>$! zv||R>F6$L&TQXDNFFo4&n0It?%Nda($AaNOo%JyNDfY1#= zxKjZa4&rR+Mh#L^ScVQegTrH&r`=*K?vVN`#%jNI$E37p?SYJ)9hdxPeg3n!mXP?* z2K-41YoJK8K3)`-dLFdByHfrBI@~?yEz7nrq0L z-cEWm#}Ez{9y*D$k&(VVjjMUwA@88eJ%iZRP#wcY_T|GDQpW1 z1t(6(!3}g2CheHqn{fr+S>nlVWO472hc}N-Tz&++vr$AiAxyr_0(EM9+OW?{(zp3B zR*_C#WY=xxx-*RlyIOplG#hY>=`gC{i7gnL-_e#gEjH^jIQHA)D+|8FG#56PiN570 zwE0oY<;P4(Nc;2=QxY%2hupEO1v*Oa2_m`ZzLjJnd6SaH*=6AXca(_+ck_jZaXUqO zmib?_yDhCU-IP&BxL`ROupIK67OLa=TiUECdi6~~;yUZGIRS}ZMeGFk9+M(xR@pMK|T5VdFL1G&>JQuTjvjH<<{Ymn> zHyCzKXl7VzN0r9;y@ALq{08fED@SWgEQ*_S z-%JERLmCYBdF`%A3-;}qah45BtgIgt&eq1W$cHtZEM&{#EO*z*R#`T>jhJMM=tF{I ze^#4g#iE=tB@x#Lok8MpA!jPKYX&4F7jw*1rmMkS=aIc(y(Gs*R45gz*zaK%Das*| z92an9aDvOD_bKb(k7~n_RtK{gT=(v2q3;T1i`6XZ{)Hq^&3qQlc2jYZ7O7L&i?!KQ z6z@f*Bzg|{jWp#Q#_k;~*$TK?m|zz19p@6&n8XscbGBw+-=QsTT3{_PlZ**|vmU=3 z&++*UnUTdRmT%MMOu_Q4rX+ff<;MF%0D5~}l$?8~MvUC=YYUeaxs90!T*4tB=0bQa zQSthWHa`kppEf1YbG#0nb5J5cBM!Y`@nzNI1mtN|?TGDT2w^(7Tq?S$P~8JOFG`I3 zx3s${E%JvlxSU?dnI+U&PI3r5Iq9#SoY~Oc$*d4Fq#jFE_4uYX(~5fhy(x*FtH)h5 z)%x0T%E8s9)_LUE(V5mUy2Zo74nyCYCbgl>g}9`Hu2YTpiSwYtsPDj9G_d%-U|SVjw-C{HrHpNHdnHnz2EfXGJsCnv&?bW-JQ|P@+hOo-=ay zXp4|`Q1@kmiz34&yiY~qpf(Q*5_g!A=s6O5eI%?ss8)5@cW%`!x|bA_vA;jZsZJIV zx~?FZ7E73!5MXS_v^ym&wtE9?vwO1Mb%xniJ?jbOT`81}2o)NQ%T*m1)#g>vfk#bA z^jrrH1v;?zAhxSqB$GW&>!;dO)z6jYE!>Y(#$DHV7m1EXEcLu7u~xiPyPMK##UZH` zd$DFGF|#CQ7GnA-)qFM(vttrqg{mGus?D^b9xpZ}(R1~%0`)+>-D$cny*yj)VD9D& z^gFc$P7Aapf!>#`N`@1Y3M*AK-=WQ!g67*yN%S1eOn~P8gVu1KZaDY0smQG>(MdVg z7mVp2YKxr~(~QJ)e-`y@G9?h7oNvgsj&XOHggKBpD`uTb6Dl5!_FjeHV1Fg zbNsUgqL|LzoB{n8ZGqDQ8XBYrxRymQ4EyUeayZt(4WqeQMe|$QoGEC2)09LUO@mOV zjHYr8p#cfW#jhI{$CZc+|4=#Y^s{lLT-vkd!mdT>v7m-@_loYU=I8>)#2V6kP(xah zHH=y9Usd$&HbKH5A86duTaV(>ZV~yW08I{2$6&!7wFk2`WJ_>HTmEEAp!9nC+6=D4 z<)}6X)ezP8!vfL>tV&9;oz!MZ0p$TxP)u_aw;tob^g(NkcaG-DI90AVj=iyz)r}m`%h_QO1cDJO(>Q+p{BCMWe=Ce`evp(~|Y6`F=0aw-LPyz0uDG6ye3ygiY zbEE4oV6dI9jW;Xyr4HjQxe259I&HzyqPIaLA6(`vd5k4hB)&$QAqA{gnv#fvWiU_5 zsg}pO0SU>)@!3_z*isK4btav1txoQ^&HL~uiJq^~gKG3ZP2QnLXUCGUsM{05a6}Dy z7wEAzeo7m;wAy$WcHfsdYa=q6_mb-*bCzYsAAE>tb_z$CWl3hTF@ek>JCl%c|7~sF z6~+BHi!Oo>yFg0|0jonb?j5aUV0KYhmzEUl=bXQ8NR>P?t--NU7yJ@ry>^} z;xv|$UNw?fmHrKF#uRM6W=cX1=Pxt7-JSt9iHZXOA>{`Ic8Ej9LZ=;DF?6d|_Q=m| zZ_bE1f@l$e;4eI$lBR;?+B_+!Ej1<4bJVUE-m>FWe$)69hZf_A3My`n+SfVSGJ^ZG zMNK>SZeX9;@v4@o8YIGN1jmG`<=xtxDL7_LN%S1Y#V74))UHPX^B*!Y&(>x>Eiy|o zW&ZUD1PKME4{5WYKyc2KM9(2uLkG`Oshl`?zK#V>6pe)U49rv7BBcdpZDu^gQ z!6>0}>Tzvu6pW@!N%S0}ZAS_?^*9z55OY?IPdtg&Yo_^tQT$nLq0^$6$>apra2G>i z0x^?Gt|PD}6jA-OHhT)JZ#E^-b6BtQ&a0t?!yHkc*_$$ypVAgIEtJ=1JjBS|pEdGx z%}7FJ)o*JvrhxcyQxZJ~aTSs=tuk`(k0-3{;x8Gfzta{bEl{gb{}kaSGQJY3n*Lgw z6$P4an3Cu@G#gRM-Y8zOtV*lgETT%6<95;cty3e0YR#%%dG;GKC`Jc&*%)&X#1g8F zR%vsjAhz6;L>w`L_>2tk@Os^Vgydq55RYlxcf$h}Eak;THaNK)u2BWYSHxBo9on$g z9MheQZlTj{gH?TW z*r)!A5uMN$KP{pI8OP(_TOo${&(^SyK;1g9Y9wKilGo-?!Pqt>(Q}M94(CfPL}v=q z=p8x`2M6IP>&8xv7{Ru-aA^_Tl(7YO**JHhL7A{(c}ANd1+bTxlIS^LD<3YpEvi0B zaEfB@7@qfOi;@ z5UtRw{`t7_2|j7Aq}S z>oa4-SFmM;`3m8*N-cx`f;Kk_PJd)dqUSg*If_!RTB{iivIS2WkN?zWKP?_hGkNd# zLl`7%Mfi?32MPxNW=f*x7_12{yEsxV)~P-*ibleF#wF9=t2M>i3{I}j7ZGDX`LV}S z2%&y;lvvulCDE!NRGf4uOno|9I2uJx<2y$5e(f$u zJJN2$VYj{vl!5SNpinit$w47#czL)+Mf#XFj|$RsQ=l_Ce$#NisDJ8=Dj zoOzX)r&|&H(%C5LhBR0MD%xF>Rs(Lwd3}Lw;;^mYe&67bYFC>iR@H`*HouBC zOqi00YlA^fQl>R|>yQBn$;EclYFTfS*m7)_>bQ5Q;~AyK1@U{&dv|mk4d2mm%)g_< zVnvT!{}EC2QaRW#_I7OuleLz5AaTQ(o3vr<=d^!S(Y?0_5*<6e`^D#5gS|<|F7Z9@ zMO^flcXD=YMKfDNHWi=L7C&XDx3>m+kg!)@Tt*KjaTX6T8MpzflXe~bmNricB)@4& zLJq{=U{t$ZbH3%ALq!Fs8Vb(bK~7)YN;XS7M(%I5MNE$z?(dL1ilQ%{#}IM}J30P8 zZJre5{$EoPJx8uTaIw7`*&>Flt-fZQ`qy;D!G7(6tFFF^{wMASirBaI8tG~Ktc7q& zs0mrA&69#tpDBr+<8&QGduW@IIN#L2Lkg9P)|sQnqL|Izl<_;DEojC>;c*vn1D6Z3@fG(FKMl{$38gEKXiKCh-UUITqr=qEOEs3Sl; zdD3i?P#N`$+UzL`_I6VeQo-hc)_Atrb>3UVl9NCaO}>cID7sz-%c`@rqU*w5_(zOK zEr#BwjP>WWdm=5?IFFhoVOU|R8xIUn@t7t&k7Qk&(PmQXOm(( z2KLm5G7Q`e+^RSYy3ZcR;T4=ptdKiJdxq@)X!k{0$hKjBw#PG1;x{amzM^S&{=?QL8XlV^*qL)^=rO zn6MzcF@sS+++zHXk2?*zTo3>7O<1USYjslX-ZpK<6n(l;kmxw_yB`x%?E^7 zbX8)p0Yj{uP@CL@aVl#ImKLWC8Gi*8;Vc4HLZGXt&5#1txG9M^SO(@&T3jBd1|%dG zz4FR#45Hi=3?M@WN4BFQHfL+rr2nDa>uELV#vtAeFH+cD!ERu5!`@ax!R#Bg8B;Xs zCk2U)Hn;1`>N`RQQIqHF$7{rT!y0ZiYg7Pm$Rha0aa}fF;?fy)wh(nQ89Z3@y6<#uQti4!0l2E$+ z_u7mq>i0LMB&7PyF>9Ctf8d{*rQ2tVgX$*E(|gbZoZh*oy5zRa@|s-HqenVs<|}>1K1)YG`%e zpX7dA)aFQmqF_owjx~qT?Dj%)3m+;*J2vtZo)_EN5>T6^9pm;IZ4uMrw$(d&jCN(< zcEDOz@Tee{u zP6zOjO3C5yBoSCWPo=)~np+g-pVPUUXOX6;<#E6G@md3i-&zC5aZgVXc~P9JT6L*} z%-s=nt$X-8tWe+6?&7ox^+*SW^1CRghW5Ki6jz|jL>JK^i|8W!A$o{zi1m6%#)U}n z60H7rwM9}C@83;H#1+rLy_Oz2n=}Iwl8YXB4Vx}Z)xxP#>&#dQ+cV;xUZ+;9db`(m zXXU3j)^reXl)r4v<1bj-^(WPcWwkj{H0L%`5B*pjJ$Ltd)KI1Is-P+@gWnEnvS~^pHIT;s`gwBDQIm;- zxG@m(PSY-yckzOY3NS+M7ko!vs`@Dc@!8zxr1az$SZ97(yI<4l%=rwh!RZ!wG5on- zc#TKLt3AY)Yc% zVC_8HK^>71%8`V~ z%u;PO6~Gsnl86Ituo9AsDK^*!BqSF-T1<&cvyMD)eE8h%J$x@QjAzV7knvZVup-^9 z-M#5;1le?K8nGL@_wbol#97EjB%EV+mo__!!rX33A`X=S+EQUSePTdDa&g==jNs+R zR?e0m>zuza_E2}8b8@W)RX@i4&x6*PNt|NW$Q8&{oh&+25d|&1EJ&A4YJ-=ojwE|x zy6ja+=`vUQR~4`UU#l%@$_~c1NIT0M`SD*l z*4HG3cweo}iqh+^FeM>JS(}0Dw(GWe7<(8lA?}C}xHz&X8K%z77_JX%3z!zJEg8EC zph6rb!It2}eNdYv1-4%?CDC)(?tv4B5WCnce%hI$?Ik1?XF6z0QZuk=gEqd@f2-Xfvoc1tq9sFu#AWoaZVdJMa31cfi=A$w z?u+kUjoSJ-TQee$Xm>@S1^-C~uhXr-9Sx&t@$o8-XH#j!iQ#yiVEiQm@>AMUrUhhmhNIVX>F5NC z4I8Sn2Hf`&qBofOv+oW}`#==(^&w+(5q zrCPA5JHEdHRr~f(g(Y?=W6c+mjn)D+Pc}MY64Q$7$rc1|7bcmrtF-x5K>iO?J&{BB z+pH&@{0GySM(nAh14-!iNsI0fqYONqB;eKOMS-8YIb%Ga-DfF>WBVqNPxU#@3XbV8 zz!1kFI1_?Aw`jAbz`4zoM9<;eaM*THMoERnG?uXvw$49%G>Tz|HVoV;ZPC&Kw-KkE zgSRa4Mq`muDDGrldJ_wi(rgcE^P`}3!jweM(OPo^YhG8JE|-W@!h1%kp)FEcl-8m+ z6+BUuX%a#SR|eL!c~KB5o08}`Lbnn^0w4?{;gCE~r3Eu>AIJE@REjfU;)P?+|vleNM!Cq1~Z|Ga7LR!1>jeilIS_W+X11!CnIDr1=N&- z@^1T$`9G<@Vu(MYEq+>v2SOf?h<18bmB9}4AHq1H!0C zG%@rkisFlga~UC8c*;#UuIo$M+$y^8MN<+z*M+U89H%M#q9e6Q3VY(xH8$gyqF&N$ z4H?zNn|rm6xi(V)mty|S1zfVZz7z&8p~_@|Hd6|CSDBLNIe6<&7ONL2)+x?pOLUo% zn=oKIwFOH%3^(951Hl=m7(F8#hAQEpmH};c6sT@7CDC)J(uQ!_vo&Pc&T0#p7Pi>+ zqYIM`xj3c$>k3K_nv&=_O2htuqOsHnf^6PYSakiv4_yimx!6yOh*31E5;dA#pvRcE zw7V=V=7)o!N~2WD?9GwIph_Slb1ae+9@hy6VKlUPS2U((N}}f)v+F4KAx?^X)5-JJ zc%xRaY;jVaJytAZLkmtyaj~ix6K6?8l|%1S)`K@{cSKq}$Y%1MB-vUS>s?5awZ$2G zo+Q|*6Ott4J||py_>qI#0X> z;h;7fN>ATmN`8Zk^`+QOxUX%mj7WA13X zd*FhHYEBjAk81zA z0?Ug9iH;VlW9^A)K785XTCEAc->yd&FQMn$v+vNBEp5;CWyS&?LUt;M*8y}CV$ZQQ+XZ~EfpVI2g zwW2B_!X=#y#9W4yC?S9Qr`k*@D)h&uB%})U2)zCyjhaiym5bPXAFm&4tFIZT?`aE^ z7N|9uT%4m2JPFy??`pH6!1M2>Bzg|d##40S2mBED-iR%d>rH1QM8{R9Mhw->TYKb- zw>JgH?x6mSxr=QLUo?`CO1(*&AqB7-OiA<{upI(0Dz*}tacmfioUQ+WxZ0{hJ2|2l zYJA7AKA_zNX-D7=hBYLEzdKMQ+;GML4p(6jLL)OFPkLONMFr?1rX*4WZR~VzJa)-x zGJB;&w=WGj}1x5|X1AwHZ$p%*BUr;^8606p$KVO$8j3qMY<%RnsA`X{75mTuhj0sw3r?YFikGg z6=8ZT3Lz$<^(1CC5Hk#WQVH+NwYgS+f0-!>IaFWDy3_3i{UNC#hgCNfg-Cl4T%|1kc6V(U)E+@QIPkT zlIXdDoRkV;#r1B9dUr{)3jMiuN2XPw2c-(d zz3?p7cd{Qss*~kz;4|1l-4M~Jgk9o)sx5`0QGaYoqURcQSZWmKf#e3A4l|L(r3A8z zqk7a0f~-B?)9$pi+A}P*hx0?B;(_FOiK~G^GDnmqVJ-e$ZRQoF`FB$ims4rtySnDB zG{yv3X>Pu@SBuDy(!`U?6yZ*AW@cBKgb2Y++RQ6TbAu^~o+}M*V`E4EpfxP&b5WFp z!uy7UN+dN@FlTFq`vGln)7l8SyN&sUGeYIWs3#IV@TOw40{G%1hW*8WvR#h(!*F5@bE&R%UNwqSGfZf${6c5^$Hgj<}n_WdR8 zUst;O7feaWQS|eSShv@{i^YD&Sn}F`$i4qZ+RUfz{UyAkF_fHMoRpmY18oKr0DjMu zM9%@(K-safZ*qcwOr+AILmP(Y-?T+b3(rQ86Z3gX2o^0)%31%jHa`kl|71#{=V+bv zuj3&fs$9J2l#7L0Eg!@SUB2!LN3r|e7Oe`;$B(~^uHw2+o^|B<>$>BfEAv$Q2jH)H z7y7_WlRXk>i_4d5;ShGeM?&SHBH$FeJ573ci<3?j+o~;!qF$R!N%UO3Hat>vaV$MD zDAp0$ScSV8lx$vyHVpJ(ZPC&jgDIc4Y)uysLakLDaSm_6| z!(>20a`6&VtLFK^Yc8)JyaTsP(KblyVcfri9iFFbI-=KccUiU2fxULI5_KL*pA5X? zC$*7FRz?y$(L4UVB=2}y`&Si}n-nArykp~J;pY2s+G3+#w$Z^N*+u#t<7jPJ?$d@L0&#%{JNrB_Frf`_13^$Wc7Q5)l%HigT z=xp7&8KdzV+M=gNgW_H>4q=wTVHk}hJU*<=l!C_xO-V>w_$v%)w^uW3hOIHDi5=RO zT}MhA7AuNa!h445tJ)%^g=#I1zGj}X0Z$Q(5|U|usm+ao(O;O7h+||h<;hu-N3H=0 z$;GRCqbauyTeyxRcM(AzS}6n*Dc}-#pv|b*7=ZiYu)wTalVyl zu)PzyC8U5$EsMU(ffT{Tnj}R?=@L|~Uzk}&~Ii#JcSTS$cG-#=0!nhuPKS1BeZ42X;g7~vG9GW$m^h#(LuFvJY7CZ zJ4Wm=Z4uKVwl#B+dE`ZFgvSta2}#N4YV)KZ_lPNpo+CGKv^YMFOM!3>jMqN`!&6A& zI1TK1b*Ze1c8W%a+^w^Hwq1V2sQ$3F_-Rqyp2_?CXT$hb1pnD!pKI8BCaiORP@6#o z;wMc>^c>r`;LmCEq9F7ZQxZK# zC@T-)LRz<0Zx$=X$N6dz#3|{bL+6r=QAS6i=C_ROXSKT`EwY251G$j%4a-7_V3tKj z7sIG0loSw|gIPt!Sp&4x2~ z*y&G#u+!ojy5nz?yoq6_zeox@Eztf|MboYlBn-k%rg4sbPX19Y!xp_9wG8TO9{jgx zi<&(6l@7)|QR0YGQSxD9|CJMpXDmyKW^B`DMd|e$O-aa+bsYoO?Px|n-$PKgjyra< zg(|ohJj!c^=Rs|O(!;~|2$ZwqK1YG)yDTYldqSHP1)ig(BvQj;9JIamaI07rCB8g* zc7<|%QK)8Z$*9$|TgbFMzY4w#@#6J+q_dN(*-vP5qICCj zCFi1!T+EG8)WRk^@otO7+WaYyEife^N7z+@MAy&q$naf;Q}(o|84vZBK$`k1=98xS zf{`867CY_WyV<+JkocyUL5S}F=TJUm*~r2q3%*mEKLyzVQxb7x4a~2!;A|2MNJuVv zWx)rA%M&$3`3n`k#Nj-Ww`50Jb-DT{dlJ*K^q;Y+jcVhNR@HW7>_7s(Cx9i$w(4}J ziilqb%OBCVgaGoR+AJ#C_8dXtGMfHdC@y?t_}m36=mc>Vd~{Nd+WwT^Fm5l_?v%8+ z-74b8IlIx!2D}UWI-CE*gU(*0&7lI@6Q(5O@VvyxciUsXsRO=puVNJ26zv(;w`q%< z7T0Z^aFtsP!&7?VS!i$7=1#%%XG}@-9MjE5aP$by7WSOA6UAx~2U6#q*x~)1n=yi) z(H1Z*f?IIsipQattS7)>mN^Wqxe`xH`?NMw3UI$;N}}h$-E*F9Q*o@b(>PfZ<-v5V zPP0b)`0@Zy)Cr5kE6NCQA4g?Y2YjBiSOvbR-BoE-;NFZYWX;xvtjPJ~QS3&?3fp<8 zf~Y$dNqA4z*h(upz!R2Pf3MBCq9=c2N+PZ&25y=3?0CjEAR)Qvm1lSTF*+@@J}q>T zmW2---6!3I=)5sUTUNK5tX?eyZ^)o{fp`@<1zxko{66Uxgw-h_uY7|xUy3qaD@a^M z$L&yPbAe?~*svef+7ur!5MD!(cB?k70b_b@lBX?&)8x^ub&Mf5Q z{ozsXTtLtF-unlHhGv_@ZGq3y=34>&9#ax>{2pZ8>9*^Kz2c0zx4UPTSnzWVi0H`Z z2%ft+V_nb|I4#yz#%7NFauDG>2!pMODR_>Vl8EDJVAAERz~;n&gyf=E zv%+-<_j8RO?Q#;=#nI}17hQl6TjS5(l-21C+WnnYovzCeN5U!)rxZmJ(JsmWM3(Xi zH7Bpr=1Nhd*9a0FXN0Z?`c@t-y0{k}m$}&!@nB2r9rygNYs;9n=U1U1FU(8G3@=H_ znf;nJCrWSsswoLMV1C(@gdDbvc^8JQ0SU|_19jBJMEU{GSZ<9)u{?k-hzq<6Qt9bl>N08`fpt^sGkRfCP8OXhnm6L0Mg5UETeB2aue!fY?nsvQNfN&_dpMqwWfk|bFUhK1ug#fa)wY_F zkRy4MAkp>NX31fD0%4trC}zP^#^#td`^htmGBnytQDnxyAIvR%Nej zsk4we8(hzj&3QtL)moW^7Opm8Fp>4ST)aUOlI-O(+T1I;@DfuJa;*M{DGBL+u}03z z|C+;U8(WN3=WvcS93zC69k&^?7x9;@RKKC!A!(Irbp|^%!3`zt1UDgDo)Gf=ur?!# zetb}nxO}!EOPLxQr~6yJrAFAFgK~WJ8>4YN2@TC}8LYq5?xVC|WkpU0vSfV|PbW9h z%HKPyu``rOgZ(eG8CAgiGgA_Buz$gngdFUwQvW3f`}J~JV_S!djl9^(cWm0R9)?F7 zorJE9x5fUwpe5^8|F#}2blRwH_7-5MvK<4X*t6$MJ1F`An<1l+P;;?Tn<+()`UHuN zMxp!bpnD#`=>{lvoWxP}MNurXD_l;Cfn=S3VGBbopLH4y9NTgPt5fTE;&Jx#q{YbY z)$YW!R^y&b(U&zl&a#GUaUp8f4U39Aq1z00hDESXvLZv;j4SBxG9@9c$PQMZZpZHj z6VxPHmLoDd!+Beb-ROAM{g@Tu5$(=Ms|bS$iV&^S5rJAeZwpfpMLyxIgA3Z6D#-tU zDT$sVzYCaR|0nE&Zx?a!uLtukxDswLX9ZPvQQY-DWz?V4?ufLg<8TX45?U{a5F3t? zXNciPK#rswZQn>@X~?uTn+oKUrX=E!8_f68W#9?NfP~~?j`e}*X2OvZxGt?o=K%O{ z9b|QLIk9}c={R+`>Zt5=b7(f?PfFOa9DM4%i|S=pDYM$XOB>9zYCDp_88V_Dq}qC$ z8pX}XuGbA%;EHYtCM;}r4!-o>g)Lb^>A^2*3!y0W+f7OIT%C3VI&nA%u!j%d>{NuP z@g1we=e4^att#wDP=)YmnMpN?eIp4O#m{N8r~v(0Qxe}7pkuCzhkMj2Bmv#wI|lk+ zwYy+GK*t;u5BKnhPPkv||7f$Q0R6vBN%S1(ZO=X-hVns#oH=!-4Dl$!X+B_Rugmmm zdATifX+q3rh)N5lrIGfhxiF^7)En)$X!E9Ey3v$G&oNys%`i@^bz__Fl(&r5u(mj9 z2Vy^Nzn(xmkdBRr9f#OA(x+l`uQn$NHit|}#IZ5(>7-l8`B(!Il8b*c%?cA2NZYT! zylMLbyp$>C9bCZWB}&dViq%}P4u_Irr?o0Mqrs&o180v6?}!+f(zk*{{1e(JCaWZM zLSiER+ewM|OWMDxs9#HvxQqd){SQ#FY`&HAQ&mT5!L`m5eL7NWG@LST$MsLMkL3!? zNU-gAqjs021gd=?QynWQjqBb#3|5;%}%YxigYEO++Ti>MhV_Ou^Tlp?-GyK^%JZ>P3^X-CwS%oKB&_3JHYR0$5l zLn_G<4rnu_0C$TiiJk*Da@o_QeEOBY81MC6^hNlZE_NKe&~%kDtH)XGZcM8lCsAM>^n) zYa25h1_N)|4pVzVvCfOM`B8M{2~!e1N9)K5r-mBf2GVd?N#V|qhSTKL60M$a?Da)2 zU4kj5Rkj<}!*;pl&~X?v=v+)awQ6*x=?X>GgtuvTTUt#xnwjwB#unbN++uA-a&s*Z z?miN7XD3N+DgzA39kMnF^&D^2=3dd8pD`uTbG=zlW1CdO%@r>eo7pmsM~^8&auY`O zGuncsMRr4mMz*NN2y+&KDj{|CX>E2CsD8(kL~5wamt2Q!+$;evg4~DDUfbxn-PEZS zBlb;g`O+e`8I{(#i!{4~zvRojmM5j5{$86S1+>2rBrfBUYxM)w9BtFV&NeYUMj=q% za@ViDrB@59egv5UerQUR$pdtG(pqY@HZMx2uP`McN6IomqU-hWUez!h@;v!2QE=if z8Jjz_g-JUs{E}kgMujG!j%dF&D+)AwOiA<{nm)dfLxm;$f+2ZSTZpufEcfo*P~k{e zYCK1q4F!&eO-aPzFjyzZr3M>G0}_&p9xXNc`9Q#?lPgqvh@+6>k&t13nKmnmlDsrT;ZCHeTp&!QP&>b(Hp^i8NVGG+zceCi70&vFe)#}qu ztAXjf>fi>v#>HqbrgY5`f0OE`LO`X%Ct2-Cyu_s5GW?VW=@)~ovA?bTtBQtwT#)G4 zqusA6zwWq$ISAx^U$uMS?B*SV*vS^IJxejDT$sVx5@L1a7C^tMoFBR+8tXlY7c3Pmln0nzL!M&(FWUqzra~q znRM6sIc<&<%+8pSNR64X8?jN`@maQ~aa}A<63jVu6t+~O-bA}oBZlm8ZRyfNwkcDg z8%PCr*)Vq@#1cZFQ`!tEh&2U?%jkUE%B3UONxo+s$9Qo(TtqwV9QLw^e@ExAv>!1} zZ`SUXv^d?0&Fxh9;&G4j<(PZkktCT9!|?eUtUWK}U4D zg)X@XqxW%b!P26)AtUuGsitcsb`vE8em<(rkOJ1Po05owWw7v*YeydI1|%dGbGWm{ z)|v8{mb8IZ$V6KMr%s-YmU6b|ZqB;&Pul&SR+nzzD=Cw#cD7QkhaKC5gvdW?^QEZN z-w6^O4R_arw|9$UvQQ5}nT`q_jwNO*oaRSqk5(0X5F0L*BI4TfOGVg8ahYFIdU}4O z7}@pPd$nS@J2Q?0!LpE)awa5cmL(PWlR!|u-`y9K-ibVX$nqziBf3VLZw2{PrX=Jr zUT#W48WYyP|B}Y!=uxLpob)S}Df>kyPS$afsnAKPjS@E(*kOw!y)ImSn|I1l2c$bB zS#^(TcYa!p6}M?O+oXQOiA<{ z%^jgDp~yrZj?djek$QA`*7%MQ{(^QFq(%6)j4LmNBEzi=Tq#2Y>x9zCKhow>!TJwO zNyM=>@bsj!$P>N+3CRVoJPk-lE;!L8^S!vA@KihiUKzG(()FFx4 z*3I}SPn%`7b&K||Dg$DpAaNOe&;H;j6#tx$$dshMW(##lThwF=rF1Z^U5}qiBBK?F zMQL|xv!e9+0aFrk=K5Ndd~o zv{_N`c`kRZc2$RI{(Aj+l*LRCyqwdDB(RT&KtG6C9UGD%~U*|=%8Ozrbh>J!nTf|)aFG|lo>&y<6!Q73UcYW zQ|Cn*I@;gzF?aJvv_(tX&C4>4iYqcm;eog`X&`<`n+c_VKVV8i4#f8}M4bXYrt8R6 z!$*ftSv3xfI*lkC@s|wBSG0vm3(9Ib_8P?|0XHGHWNA{Y=S$kGDA0V-ltdgF0|O^* zBo9CX5|WD^Emv2aZBU&cov_g?)?*HD{3R>M+S_{N)2_zVq#id}!A(d(5{@5Tt<8v{ z9xF^q^cwkG3d?duV+gr~!%6pR z^Q0iR$CO0Rky~}nsh91XW8sPt)J(^0ZtNvv^r*HlX)(giZ{{XjYfuGucsg9Jo*Mfc zZAKJe9yTS>dti9wPXmiWb1`6IFBzB@YYUSe7+$~A5E9&kM$8Hom=|d?q5$)RDT$r~ zv-`Y_1c@kB9BW~RSZ#_A3i4g$U=^4g1lRwZ!F`){hol8}PX-5%p^Oc+m03uHfj7lR z0QnLH>%^px`AQZ3w`#Mh!2dI*BvQj~yiVJPlT6C3JcZ?E3)YCc;gUzM5e3$Q&uI5c zS}oX5C!(-iNRjv<4F!7Ej3hg-N>zkUYjdk8!tV$Y9an>05A8hbJOZk8+}D7M6R%K@ zT5F(kH%LL#aNpslMXkvA$K^gJ6hl3Ka*X@mYxiVY-0#aEqe>EISzt`P5ID$i3v1w| zfuq&|%cJ;IuqtWE`ZwCFD@yQJrX-{___`?xxh`T={I9hx8Ytbj7-c#u!iRxJU4`f? z)}|YF(xQkzUGU)Wv!h>#C*g)VBBxb5I)EuSzdT#AFNJ-*)v77ERhy=lh14Rhaxx$xxmahKt|Bgg`=-lV>UQ&yatld!Dxek>{ts2%7WQ-? z`G+W{U)UB=!IBkJvpuE_TCxU`%!$=(+mouNL;>&YyA=UZ@h(KxDJDj z!om2lK*>#bq(7-Gams#fZ@@Vd;EXroO3s26#EPUzV_KUX1%OFY5^|uqrX=KWXEm7D zaKA7gE->6TU*6%q=GY}{;>X~|eRGa;(b~5^I<|*`vHbyU!IE{31dNSsPa9-?>ie~S zOHruz3KAVhboUbz%YvSa^k6&moCoipXbYFJBinr$$47HU>C?|^|E$udpED&P2kB=S zmTo5__WGS~?KxNw+92$ii1p|TO76xjbon>_{gZ<&(lIqZi5*!Ld9X6lRNv`qUq4CL*m zEnFDqQoURg4o&A%fagVt72*0_-AP_32C{ufD#Bjuq$V-5BxbfYRn3x^V!95*%tpji zG-9hZpNd9oG9}S-jo2M%#6B2;dKsG=g&xqY1ayt6*tFWf7En?ZdJ{F)`kyoQ!`dB^ z)(GsD*ze1_BoHHxO{^pk?`!o05^q$?f3G%k3gCxKNyGs+@U5hK#&fy>3CYE~Ol_IB z8r$-HcFzt(^tE(P;GR9MjZm@%l7Mr$XH(k0r6^QWkhqNQ8LrP{N0&SValIXDTz4X1{1ZM>v@7OAR)PUp{XF=T)*}EJlEeIo$E(}xqfT5J1Y$maIU$2llE^Z z3bkI4xQuiC&NJ9cV>f6sHiFp2N^sR}Fn8kMnj%NMB7NM}`jXATUD_R#Yz`DK+Pg9} zDMyy%pi@ZcEQCM~{Hy3@DRQTJ1Gj54rXaV^l!P3FyBYjW-hgppe{KgYV(jN`&S*ZS zEpb{j4g9(1YBQrC_y~7@rwz&74})&Acc8CvKbN>pT$~Sfu9%;2EP2OxbjYRofU$Xz zc6X%3W?RO_nDUtx8!sBfbZCE@I=-IJW=BEik|_x}zFG`$r}1T4-JKcRAr6Q1FBY@J z#bPLu3STT18DXiuU?6{1TkNzzW-?>KK>BPa-iPMFAkz&$t<8^u4g-n_+Sf4(x-TCSD$)9Sod$YD+J3F^! z_?$LBiaveTltdg!17(o<#Gac03CYD8Q$ai@{Mzrc6MjcTD@)G_obcs?-EqQ6z`308 zrP{xxDAXcB;=ijCew%g&C0hUmjQKj@+qD@}kh|HGgdBu7G5Fnf5{?BX8ZlKkeK?9< zY$IW3!4=LQ3KVftUjxS+JJ={~xj0A?zM&<(tym(qOEh_6IIZ1vY1QIbI64bqe9_tA zaD@x$i%z$WB2(ju9&$8Y)u|lO=2+2}`%OvoTwnGD`T{4QgTBnZSTLf%y3o+>mbALC zPwK*6LN`el=5`ut+WaZVmrY5;kvEv}rPIJOjR6VC#WkjacuvE0-)E=c&ZyHc5jYLM zq%Byo5|V&(ISs#{{acDc{k$O2(P`*%QA^MYEWv`I?kpcjz_~2JRocI$DAa!l z9R8bHf^FLUlWYkTEaqzoZq#N>0q#0e64DZEF(n}_0jtlvEWx+uX$fwa%@TA!4jwP8 z-oGbm34SE71kcm%-em0~0q3#=&({7eMWG%tB_S2+oFMW4Z|~tL?QTek+I(%s_H$?5CSNLru`4k1zova8LVf_UAOM9&f5e^?wgIq@ISl)guLGg5KeM|%!E0a zJP8C4Coc%*WhNn@pq{z+%*>tK$8aAr859(&w)&gaYJ;c8H`T`>eCp{_efceyqKgF89qj3_0aj z0#DRBM56L45RFROh5frC?Q-iuxN!P8y@#zIA%D_Tgmv;p;i8o8ZX^N8Kg_NcUGioD zr%0!Nh^-(&{~=Qm*3t9FX@xugafJR9yFzrKpP4HbHq!q4B>RN~;+IWDScDivXIcdd z8xa}|ledZG5F~u_j>AwcH=ER{*Hnd((9Dfud4mz0=3iH>76$!N2_g~ta3499AesK0 z6v5d**M+=ZgiaRAJ2zS>xzb+Ts2YmYb$z&PT%yh43~Al8f<4VJ6=AVCAg<|$gj4$X z^u=Lw=w(-!ZgZG+ggG+i_po&(!$r5L2#f6_94=r_~4s(xWQA`#owOW4(>J80|@IT7S0TClMu?G}EI(r#DSjf;ae!Aj|uWrD3R89ByG zMObVq!N_sGOrQ{bblVIYZA&8Cw@EvvHD;g)8)L?0n4KXql{aAAXNoW$Fy3q`!hS25 z-3MW7Wis>9grjzS^(W-~nFQxEMFUbF!9OL7+Tgh$2Vr#FKxwg$p0Q{CxM`Kg)IMn{ zLYtbwF|=6>*PkV@wTW{LhUxDLa?JP-(>6b>hj!B5cVyw4nLw0 zfLA13@a0uUFb*z&yJ(y^eg@+R*(Gch$(MAYsff5Y&XXcK?)S5x4+z)F5E?IZ3{mN3 z{EpzRW}BotAzBC*iUXZO#}5kSO7`msl*>&;SckH#&nZ`HK1_ngyh#Q87;TEtG6I5r!Ih_yg}5Cajh7U-5_ zAR^WR{Ra(12rXbE?xLsJ6?Bu*2}WKQxq?2(ZYSC8T^Kl(E9e94cadiOR#Oo%%C|@n z9seY-u7fB$bgU@nHE2?st}E!L*oqOvkD7`|BR21?PP^XPvgH^|?Q!*dRgj#! zuQcQj)Vv<&dRXj0y6Yivl-pOUc@yX!CBJS#T;V;w*J#4ER<&QhHR{(tXV+qO3lUY3 z>en(d`^dZCRRO!$hxDiHw-Wq6mLg7}4{4MDqfx9@ln+;cnW;Ca*vUCj z$_sqmVMt|h>&dR?oSqc`e?D6cQqyxxMZ_I#mK4#lN0^50aQDh}lUHdt`@Kf3ctX1W zjlnHf*y9`yJIAP(Kkf~sy1*p!S%i88yDBt$%jEhTE|b6(h@&iQkzRjjiyPYFMz%z0 z4^Gd@A-a{VC!xN{RD?El<8g4w4zCUwA_L@^Biv+*GKle3wr#o?m*ybBaWNkv91KU_ z1g>^0urEH6J2`tIgK{FRM zLk>c-B!H}O@+EAA2!aVy5pjD-7P(u0s> zNjk}@lgLS(2N2;uvW?b7n9Eg#*5P<7HvfZ9W;ND20re~j_3zlq5vYG-Dnc8o@wamE zbzT$V9fF7F?h@qZt4NS)$IC8)~RZVaF0pNaD--%&uT7NdPW26%lu~MW!O+&nz~h4t!<}M8sO)BG^DgTo*quU5W=g zma9+g9>@;xXc~dqL#DwnBnN9B+WUko_*w4{nhnS`K8bFVPx*OV-5! zG4Xy%km8}$^^%heR@d*1S1m5YJ%2yu(uL1{R zT5op_hLH^S$w-F%GLoUw1=sPq#V9G}8+&SAznq>ZYygk5D@wNkT#*|E zOJRk7vleY)uHc9#aw4$!(Y9d?2@@ z=+$NP72%5HG~lw64|5#Y6i}zt4L?6zDc;sh@3Buu5E8$UT}iscuSDX$JCL-|jciO$ zx)U~%*3i$^lC*|HrXsAjhUduEFbJ)|*;%XBMSCa}Ap@wGuY2|6>ME`x2vLNo3gltG z*qSN%CyI@f_h?5YV|%%sU5&c!<$7!{gKj=m2`+Sz#NsTjgz%#v-Q^N>K$_1uTWQjK z8m1zwHy<3?hs4)DSk8)7Ud@N49Ze%URbhmDKigPc$iZh|C|-KQ_My zSFmnt5y$DFZf-(1(!u|ltpaH#pEea?9nhM+l}4>vXv&ql)2NDj0)DNShYk)m+r(~Y zYQIhA0YvvRw$Zxia*CId+o*~Q0I0PaX-zo(D_bAJ@rR}&taIGDr&@z^61fiZOMtCb zt$-g(0nWeRFlYitZFvzy%>JN~;O=`lh1O68(q4MGt!3KfIk;X4w#k)QY#W>!p>1N{ zuI3BdaONM{MjF5(wu+>A|} z>~^-vy4`pUxYMA{5*+I6syY*h+t}(5h+9lWq#+u7apR9Rp0OB+h_$%cbeAYNUt4o( z&)1$6p0911;(YA@WB`?MR5xyRy7q@BY|5-*IK!`pQzo zsXSXdx>M|I6$jy~j_W=cAmZb;9*poJ4mLg9=P6Z(igif4o=9FPX9j+=2GfFy4~IOp z-dY;5MVM+!dC)V7c2Sjsrx4gY7kGHxvWANgMbxwz{MZ{E4ZE_?z)w zY(||vF~qHXaX=&*i#V;1n#%zkHxA&qAsdL=D45S8{QtwQ3SIcYvA}?Y50=FED@r$) z#3|-~U@Jy2|E;MA>zI4xm>^Dnj`;A20L+Er;GkcFVBU@gYsfMD!h}b`sgDHvX+-^B z?CQ`(y&n5{-ff^YapYDvwkA6B&G6ayC0jKD`xmAnti#?WVT&`M)C2;S80g#LG)2l` zm=d&^85m1J_!n*K%({}y?k2Y){DMoS0Dv@uxm(mKS{9!Mqlq_h++J zB+cL&QxVpi!B*J}2D{-93BK-PchDE9(Q&jFeqZ1QB=TE`8#__JqtxhcC<7b75W8x0 z8$d7&h@&Ai&5ccyE@9yO6POmqip=;F6xbRP{+_9bG=GC#g?M8E7a9g4Vl7@RziH3B z(}a826|CEev`-UGvQ;3>X4tS&@2VvNnxY!cwKCD!f6v6C#IrQk311=IWNDWGm8>o_f%WXOW5xs z?QEeG(Q?bVM?#zgKTAg{`bhLmtQx~7w&V2Rmk`EV78g+5T4JS+k-arxDIVPMV z!+sS`zQu89e*;!3;z$D)F1x&j7kM)&Epz0HQ3oGo*Fkn;6m^m6;PM*d$dmA@pb5o( zsb%(CNh=(YBKTe1_~O=zU6Aw$&TM5pgI_^V{gCNUsoTjm<*@(1mTkOdl~1nB6;Q{} zKOmuFbgA^TtShCHY@G;@SGNb!`YN62vCTD!;~BAT^#(-BP|*v-B3-b8y&7-`9&JD_ zO7W*c5w1Xq{5*NDo^s8arYr>ees(45g1sh}IFN~Km6X9SxHnuBNqW#$d5I@971H;B zsY&)(^xwx;oY4OxQxWk;;oaDPI(=ZX5Qa){mTy2ul>_IlJ*f_xRRDqh6Wb_Vpo?-a zf&^NLy_eC#U?RKT`<+C6(MJsaI)VM+=@)~E}aJuqjP0v z)*56gGMN*-Eu1dF(O0Z>;>b(Eni03=LbiGY>q=7**0C=gOd){Hn#Oshuz*Ak7Z8K7`h_rXsA!1-{E-e5#3i=&&pZ zr#^8t^*DL>ML08w=r9s61Vv8e^_{jfYyl(e>e6ii*NPBRf!A}w-e~$0+v^7Af}1;- zE82`SSLxar5pjmts*}c2Fco3FvCKUT?V?%^GPb8i=k$+=^0jPZbWzUB!R>O;Cdi|n z`k0m-B4RCGWjdXUwZQF;X=yPu9W7wH>ylHu-L+Wm zT|;~?`CSt!8^HrdnURcqC)&pPPj*wu?gGNb)HYVoEaT0qe`mjowCtZt5iK{bI=@%4 zbT3?xsKMnYi0NCb;58GNv@6v)*{TqZGAp)EV|sq~=`&87A^!6_lQV1nV6#>{Dch4$ z*OSZOx>KkoT#ty=Bn+0al_3lknTm+}^?WI!aYO} zK1Vegf@@OuA%uAi+j!0XGPyR_2+o|~#&M`UM3OCmJ5iv$D+7oTrrX&%5vJQrMObG# z_fSnZTEf0O_}-+qHqt*LBady2E~9y{9#*s=EMCBVH(~L7QxV!MjJNX7&ia~6Mt{ZX zeiwlsM9XhW$49GKdn-=8SuT6ERNRE*4_Kw|Vq2$M zrRTwy!wt0{wfYYBdr7Un%~V9(n(s3e5zhjV?X+fr_{}m95o>|77XuM-UHsH^4kfgJ zx#*?s=AxaSKAn5SKhYSdR#TV3Mt%`ZK!3o7o87d9ValXvcnxXJ-(|mxH0N)biii*C}a4#E%COI39mYa{^&s5w_n zV~(4c+7gPBTXNFpM%)~sS!ZNlwqsh#L= zc%e~hM|$0jY#m6|_nV4{d)*!g+foHBgCgTMoM$Td~*OR2+_R)vt#V{GGeDJ{zZm{>bE(vC3t z1X~Bf=n+#9))~#&Dd$@b1`txaQ0g}%@;$aGxe8W_P zbr9!-JNqhw_|I7VbFS{pWSmT{CeOt^N?1hDnxDmfE2;UjO+{F*`8B(O%no%KKMTBK zWZ*NWs{w8T;CeOYcdJZv9za?f*+%Pjmemlu9`jMuWn`>SYq-lEC`~D@XKOl(CQn`i{{S|o}Wvj2tqs{i^VfIT&wI4JUVZGYtABJWqq5x!Gnwg|OBZvvMLAoFo zKo$ZT&B6KSz6H<|c5GPsXzf-Zwu@F@wm21(_=nf+Q) z`S+NLuwMD+huxvx9D>BK!UweOi1jnB1 zNOiQBuM1yWs00zd5`1qV4-~Enwky}Tq7XE~y|W4lh|0y=qi_^7Hg#u3V>3AS8e22* zeYu9L3D^slH3429uon)wq=NMkI6s8<* z>$z-$ba5@nl`&_aTY^xUl}t~D1MIgGBF`}uVVy|N?h_60qxa$Jce4)eY$do$4=J>I zARrWkqaK1k*F>gIaLb3_#40V`qe!yJt_WR{Jvo@Yq9ra`0wUzEi>47l%bh=|Y;*9!e@t}%)I)bnPyop^&x(#4^ zko!5XQY3*BUkivJAgz?!`svOt4y>ESjMM2iu+=2Z;SWqjSZ@w}=FI`F;Z!S)l(%gM zK3S<0EWkNfY@?QxVpi$O1?mDL;o!wb_7SGrh*j_#F{` zoo$jX!i8``hdQ~DP6WzV*{>&1{>4;;bttowP9N&Ptp0>3&U%)uway&yQH)cN(5`Vh z`^|*He?Ma>?C#s!yMLctoz$UYz(fhQEb-bR#7~AT)d^?V8}prEXsrdOORROrhv8#d zsES*u6Oat~eMxJ{nToL9XIC5(>|sMBJ;AzG?Z9oyA=UkC6LqPs$Vo`B zRgs<^(Vl$+TMNSKI#Ut$Ssj@e#n2jQSSePm%OR`V*e2?-TA6DI9mPJ;)UYaSH3+QZ zrXsAvTE4qphf`CC_~w9jZ4^yv|2~yf>tcxNZnlBCs8;0sP(wG=P;x8LZuNS$7KGGm zO+{EIb#Wi$nNRHY_Lhs4ck_;q=T+RK=5A7Rk+w`~9-xR% zD*uA55uy3NO+{Fzxwa3I$HU2s=zEYa#2bZbfGso;f>A8DVP1rL+bU4)r;zDa*yigp z?aFzO7e3P84fPl9>~gyx(w|`cXSPxV>;EwoVIAv|aGv5hL)B`*DMMy$YOEL(afK$OYvT8!2Mi zPa(rgtTDValOe=(tH1#^qy-e}yTuIm!8L4^NT<8VRD^Y?8VUUr$0&{R2y!pmWZm)8 zC;{LewmJmjPE!%qAuc#H(HMp;^&knNaK%)hW&Dni%50N#AuY^}N}b$kI+SHc@h~f3Qz{PBAg*S57qew41oS$#dAfj>=Yk`ufK#j=!Ss79yc^gMNjQaIu9Vc53-Hcg?AC`eui4RH8<~~ z#%{Idj!2CO!#`*1LKyz3sR-)~FK)@OM@H)M9KVrQDe66f9KXaiT$iKMf+K`z8}MAA zGy(ZfY-I?@zc&?O9ptki7T@TE5Ib#@N0I3={A5q5shzj!VN8!8`j0pV&RGm7Rx`P#jv-H7Q2zf zq=oz^TU*jX{@qlB^%gQ8TZlN)@M<-0B1N43j09Id+t$)>K|l~Ras!PBkyY%s6C&rE zim*;(q3o7<*tG`7OPuVey)df)QrXQmO1EDv0;ekII-nIyKwX^T(6Mv}`~8H=wWcDp zxftKnpBIIpJp_%@OZ61;D`5dPofo?ck()at$E;Ss+Aha$aU)V1E= z94mC@=q*(9y}?cF166RG?-jQPHg8#99G$2PoE-T>kaokLKQ(8DV!Np5;WbG^hSwwu zaH41Ew%1L$x&#a1Zw1(7?rsSdT>N0oAbh)G3ZzBKgj0TVmd+nq`?FWRFsP^`$?U4F%{4Z)&!y|V+>zJpK{&MyiOa}Rba$`H~n zxQ(AKuJ#s-@4-g&D7%Vv8_`YRk`KN@qV+%uP`SGwRFNCl?1ok34u~3pf>=Ysc@S$z zPXE%S>BsD0wh?6Te8^OU^`^GyU~R~&6mJ)+bkXEQO{$F~vjpP(7TYXcyo+P1F@r`QS*G*6m}u#V=EzRN25GFtVljK)yDOa*9Rkx$h z7iYG`TD{RaF5>0vmy<@Z*;Ise9M>Eho^bZz3^$R!yURQ7IR|U-sfU1-4$Sf3IKKb3 zrWZ!p8T87<(nQMBaGJ6Z^{wox(nWnWoD)uDO!~l7*k46c#iU!b1vFKDpwU$NS$-Z{ zQPM1qnToL9EG|j3h0trE#}T&=y;^=)e5}19n_Ywl!gM0mc~RD^Y&U0OVyy?fQUm;Pf&^+9$8=u+*{qUsilw4*-2 zR*HaqtEmX91#>Rkjl)fSTJw*y-%4u!lcpl9*L>G?Vu2@< z2Fd*)xp#mu=z<+1uQcSt*|17R|1l)@BX$MolIzY5p#|YL5iO7(y+x*CSmz)l%iH?ULqo}!(Qn!xqK#u3=r+B0=7TT#*^&NCHZy-DnyMw93Phev2M z1;61H)4>iqC>NW{R(2KY4i|f;(_Fx>vL<}-unNdYHqu$*?d%s4 zz~iPOtOH(g5O1f1``e>l%_~E8?X)Lnn{wD?-_ABs7t6|Aa1RA^lzZI?9mz<2KU)m~ z>t0h4)?uwX2qzGDxCar`xtBVr=RAlwA7fX7F3!tx;#dk#GQkQt1h+bxqMh** zY`qBIM@&Un=exFLXKXh|(|!ucevfUwF4?uMJL(kkt8cS)B2>R&D#AKd7eW{KH3*a^ zf@6vBig5N5UJ9IQ*kwM8gy-zEwIo{)Zlj7Vaxu;ro@cRDBcRVV74bh0^hS17=yqi> z71~5c-}USl5`34Lim;BayI+K~z{?3DI&jM67jjkyyY{Jb1;%sOKaaAjKo{G(oD5A7 zT(F={yh$4ZGVuY!VYXTX?m<%#*5NV-Qe~Hn`7A=7U{{4MWYIS_)4n;zej&kEHx*$W zU+&;|1;TF?V7C({zS#%A>XcXO2}E@t+iYD_7w4+u6$qkLkU1h+oZ?cHZ)Ph*P~KxI z!aBK1>r-sTF^Gyf*v+CK5jt|nTmMYThK2%)PiR0=I$N0nFl?!sXJ&vfqJ|a zgb&$jL08Zg^b1q`aSQsHsR)ZL2=8WY-4pnULD;O_;6E-_HX^M^zldWiw^eqD8!izbp>G(()PneS(l!xqQpV_&=>`kJHa9$Hgq=}g z8(B*AuvH91#0{X^RD|^gaE@4-i@hk7Y5Zrz)Xz3R7ZW7x6w6tm0jc>z?6;Dd-)}0y zdd>IrkCuYYC+-mL60ss7X2FqgyGtAh9)aX*8Mh00k0QZwc17qCbaVC4lIYfe!i&H~?u1bU`$yU85$qo}6=5CwRT1`0+u_XixHvq3X#8-^ zAI^)!ooIQk0LPxCYE2$2B!ea-H*9zN#NX{revEo}Bey%dUxBSPE{n>lC z>n2_H8)EjGUHSP%;^MO_zO>4rQ+61DGug@!;HR02NCW3A=K?L_YvWt4618j~BGzJ~ z6k)K@FSLM@hOV>V*ytk=H8~Ly2TrAeC^)SmofyYb+H*|i;@!F(B9B+giIZ<~B^rW| zA1)S#Fs0c(2yp`cJGyA9eCtLQL_wdQ&BmJDY(=e1&hjex;cBe{4#X#i*97q5bE<3D z?;@>myA;u~`nyItUjGXYl{|3S6J7_H6?v;tm6I927TLL=r+^C(}^PiVW32{K%R(d*%j3yldRJQ{wHkpNdtecsff6N zTWVTeVy7(JN5sKD48Y;Y031#bfJ1FA`j24~_y=|c=r)0FxziR|AU_qM1!@QpO7?Hr zS`o6JHx*%>>{8qVtv7m0)jE*P^zdm_2&w&&ZJaK(Wx@U^bULA38<(G7uyr7eer77d zIwPjLt+I+|K8r*zxUMs6H!=yHoc4W*6>QZA=%uD2{^x;yHoGcxyKalCqt~!sNbqep z6=5A82-IL*^oJ}f~#NQFb7uY7~f)J;EQU^EV z%HHSLuO*fLgsF&ASNWS;RQ~3ZSouF^o4~L9j5}FBWxtkG{*O&XoVv>2(xURW1eL%1 zdRz1BxaDVfwJ%}6mQ?;iQxVoHzgv8tMNaWxE27}YyGZhQtJtVRG^cQAR^c$7!=7_B zy9#uB&N}&J7d8a(ObgL{ssiLgtV1}a$cBJS{Mo;ftrmfMxv2>2aF-rz3`3~;;3{&> zFX2YGO0rcU#P%Y#ak|)+<*GtE2wCk9HcPNy7-~lt-OAR1FnXS;2B%ta7vyxJ8-91Ol^~ezG!H5FkUF3;Uu;mdmz5nsWs2;H7LT~GC`Y|RMeO{OBO zQO@yJRH}N9Akmkx4c8@l3FOUG z-I`;~(d$(>zf+obur(qyZ#NZTohF25FEsPQZyn~2km9a9AQIRO!sZSn5P=MK@Lvbv zzZ9xvHTTI_(H~bKPfHTAerXs9! zS-qzQu8e-AQJN5Y;svLkhvo{yU)Xq47cMo*BegATlXW}RnjCzv0-eQ9c>(&B)H!nM ztJ6_&BU>E;alNSs>kuyrck*D;A};4a*a655UW;I=J#EU;2=FGhxw-(IXb%r2AL5oB zgc6YYh9D`vqikgezQd*>tmB)vAHEIyy%X>)lkHf=MSev*FJYUbiwAPLgFa>NL~9%q z?3WW9W2PdkT3d2K(U%wH~CuEI7L{u4e4qES3p76Nz-}QRD|`Wv+_t4+Ci~$+>v>xdxG4@kYOdY_t&lAW zNL{!qMJ{`(rHk3JF(I;4lJxX%vDF~Bo-!3-9oHP$(`8k_z^D%8soxOF?C028m(0Z; z7wJMkoXdVS0Ws55gmn;e`y0hl3A+v^U|J_c#kx*bvRbA`zU%U}@M@Zw|n=H^grac2A|R+?ZEt`t@#foP!`>!#@1K zBFtz@6W6M}sZ&Cc{SkKM>9XGimp$RSrm)_PtcP6jk@3;&38Kab<6Y@+r`k>%%yZca zlLm9ZRD|^gvt&=R2IyGQ8N_*lZJI95rLZ9wxASt9hfNqUS>NmUJF~^pA+-Eo@_Sk<81D2ikyBYGy?LH?iMMSiHehgmo4h z_K`><;=s7aky)+s{%FG)hMf`Ik1N*dsd*#+apd`Nc7^Ej+>irZVJ99uSK$;5&QYpC zh7Ot9N*LsZ2Dx&gNk_+zv6UmhKVmAvI`E5*z`Afpwcdd6pu-S4O>{$X#uP3b)$in# zr4i>h+2-ovbfg#gfYjFw^u+*4!9thf`#M`0g72%QBCO+EdVPW!F7j#2&sK#H);arZ zEgF{Q6hiP3ZV?XjEVc>+(dniltRw0IPjQ%~!d{GUW-a;ohDh3eWVl(Y7rcocr>{BG zgm@&IQ}_JzA47~i>PZE#Qw{3F}M?yGKik^O8HNdvgS zRD|^gF!!)uFBY26v*j+l`l(F+h{zgjV|0Zyp=$}dRajchY?Da_6V9*I&9G9KQ|elbDtdQ%bB5x_Ui2ba>y5UjCl5Q-P} zAHa7_oYPe6MVeV_>f#9Nqiln9VXc;v$xvh5F##{Mq{f8chuPW?f`4Hu!aBi~boFz_?USm(8LPw_;!;~6$%a_HNt z5OO+mzpdH-GDy=Pw3AzsN$m)u)7Ux?M*r^_%V^0CuU^cH48y}>QV6pur~k%X>Rh2k z86?!jt{vT;v@|y$bQ4!ahsC50baU%t1v+!MgslPrw8m6~^-i=(e6|2d4_t`Y19uJ~ z3L^08D-A&m@y2jjB{fxHM7ED@tS+)u_{kb8z}<(zP+8ZDlqG#@FIyFYZjY%5>*(h1 z&Q~kd@&sH1xjmy>(Vr2|DBB=iJPUF#dx$j3?o4I&+X;~oQxVpQEZ7OV#TY{~bEM1o z9hsbDo21KRVNUFbVF2ZpBi!rQuP0D`&s2nUDCZxj!o@G?Od$q3XQx-nXP<+$Es3B$ z#5PkG)CIW;=ovVDz<0=nliFBMGO~S;tq4K(=cXd8BU>BqEy;^NL1)5%FR;*sQ*5!K zN=?hPpF)&hW}B~zQf?Ur`$zS})Iz2&5DWE4e}eT(Y^4a+e=-$e9qZiCEgJBW=ppGJ z5z>qUwkGKFBBy7V019mgi(i{oWSk)FKTSngXK`^NZ;T=iqU1fH3x@f zp=EMMC4m|&gA?$`vd9fR<968ZvNa_1Ut=o5I{npcXlKogG|D5_53o(v<+=t|k>S81 zXR%3+t>#bfXRAXXzRy%dMR% zJr{90!ICC5I=3r`41dKoQkUWR$-atxGrR zjiRDiLWB`h+gpXq-{i9hnfgL_LJ;N(Ph6GT*v~evQ{qD znzDFlHEzF}tsmk3DpL{Gxi1C}8JTuk4%VWVlf(S%BFOH~*oNt{TOzz-WJonRFpD0V zd6fSrYz+vV_nL~ZPG@0!HxRB8iK}m^dwy93kjy`@jnXBvFmY!Ot`rHa=w#<_*{>&9 zK5r_*B9^WZxk8-N2U|LWMc8|Vm_Cj=5T<@Z8o!jbjI5reBwn6eb<04tRH#ps;hz`Z zbcg!CUU1}On3q|;bgIJ13xKeq-3<%dkr{`$bKU^M2GDfm!E+%k@}AzKb-z~cEf0@C z5C*@}d&KwhaOZxgcfb7CmvO?$}c z!22g5T-i72h1*lobF*8rpsvwMl?xlM(CVmYe49{&QyeTI;pX5pZI_zK69EwW}C;5;zR5T z(509fGSgo`x6P3GA+}Nk><3Lnq``8gb%7Rl!t@Ypce~8(Y#<`mVw-7tXrV=OV5Ivj zQ061&D6{qWl<1KbKXi>e*5a3uCtCd=r}l@B!A#lNeED_}SF%wQ4%=`EPwmRW*`8i! zftfC}@4CpJD8D6sez;PE$erp(WaJ`vJy!0|*@&~7uBf5OS>Tp1T&-2SvVU@T4H;^F z%6=DVkw2CqTB7J0X~n`6#ezd65spw?Z5GQHfTAw%GJeO3UG!Y;QcJU9Cl}^Mg-+5j zM(E^%PNc5qvtLi@dXA}xxZll^B03J`S~%&6ubhirDiIoK%!k|O5R+Ood~kshp)l&s z5or5x4P91Bng!_E9vAS?qWnA|Y`xPyBIB#OBLeL#G6=5A+)&^#B zBWp6N03v!R+bCT`T05LCVZWYWnJ^V$5sT>#=R2e=r+$a?k4)>Zb32@uD?6M!=A02s zwXjM!^H|*mI*lF9x0%*gyu*2)sR)bB7I!!=6}PqI+)Z2y5_99d!h2lI48-(V`insF z5p_DC`w)&g|HL+47wTF#sV=}dG#pEc%R=ItAbsCuh%dO!D$gf{_T=OK_iUZWQ1k^; z5!RVrhzNZF@GzV%ctJb{2{VJnT9TV@_j1GrG>R}Nb8?R+6LXcf;D#ALl)OIIA>--7PAiDx| zVWze_k*3}WQJ$?70sA6T5!S&jmN%SX*3vrnR(28WeXn5~rVDHd-f4!QqwOKo6T>r-f582J*}4#RKQR?yon7|nwK8GPE`mL3WxuVdy6yq@GPVYU&SFy$*6E~Xd~Hsu z6=M32A;o90D?qomrDlAb1MaKXN)fPEn2N9t_Fxe2GYI=F)?knn1p+D8;OMJG=-r<5 zGA-fipw34+E*+c60J}PMo5{g2?r2aSVyzd~M~iU1>D6Fc*TEOEbtkRq7E=+{ThsjX zQc!IU^k?MxDz-toJQoCRo$=a^PE3D`{dPj+Wu_wR6G;!%DI(-&B=TOiLHb0}V=pE0 zhwQf#BJVU6VV%gLoBaly5me#ewH99bRiR{-KrWwWo2AQTac;tI!0x})E4=1Q(fl=A z0fOe!rXsAPnSBIYJj6~Ujef2EgfM=_HbfW392uTc>@{Y`zy4SDn+b&zT{UefCdc@Z3f1V_P8-&>`7O~$=Sj;ySVV%W_W6JGJ$gdFwrcj5hHsz4ecD9MS zePtzNnvyq2r7KGwQrblEVCe9*jjaZOwZ&9~by&0TV@^9w@(0B60=5ylIL^!A_dUC_ zJfHnuQvWxZim+b)a%_^xuOKvNJ(WHo{UdUCIolXr4mfaO&ev=fFJ-@*uy~272JO zPhH>iIF;%+o>_U$Xtgu}vAty`uVO0kA?HCv`D1n^=%QQ)_j#*gl@_jsTrdI;xI8yD z0&e_f-01xQTP=e3yQU(n6Zs!dAlt&xavQLa2Fo6HLqW%`nr>3 zZ1vCvcN?8W&SR@Z;LbJ`VIA&7TcYznybKuZD5ehfk}aHW-CX4Z!i^M9rzVT{KUEruONxs z;KPtj7(y>Zt_Eb=Uj=V21{=Wh*cGJP0ItYERET(0h!>hf{_nuT$Y~+Hkxv`KF}9MV zAsjIkVZ9;r!F?7Plm|X~PP}6do0aHI5PrbxEiVhIEusVRuxZ@Mt}@-Gu_Fri12!kl zZD1o5Z4STp37b=C9BCtYFo+SgfPmk+9#(fjI>s}B1o1HX&a;p6ju%+Z3(+ivUMTsK5i<)BD>(iQ?5Nc`88GvYCVA%zc1}3m!lRY z13uj{0I7EGP(wat6-X|w!!S=jGp*O?64c0t;T{2oXxeeJ6I@_IwQXEr+B`+;lT(94 zlkw{YM;x37>b!=O(t9yn!OD116jT#0jVs2bwe! zDeqBiq8Hp~YlY{=QGmojn)Kd>b$e`yt5`zDofT}&$hfoARD^ZP?%qnlhuM9>hom0z z!kYMRBK!kHmfIx=H-WHUfZQL&LMpun^I7ElY<5-Xeo=bh_ETgFUSErCLB?o{3#QP{ zd<|PMf_b~C2)p`Pv7T9L% zB3%QUGg5E26zT245-!l&EtfLpcph6F0`di>BCLa4)aO+EafpVSSgEVig3J;K>UY>? z>4I9E^IXsi;@KwF*R+qllC1zi^Kw%W*3qn!yJ9i}Y#c_XE(g^e-h^L&>Sb>d5g}lw zDU}1YYl;WgMvo!JKW0~fE=EW*CpN+`i*2;ht;@l5K-eHooTLE(mw09M9=1{h?Ym4x zSVy~fzgHU)@jRVF@w7qhcG*P`*caG_=>h|v^gy%Zgobv!&#^Tibe=F3VV%zMoz+SK zcBZQWP-{Z1iy@_-vklaxv>Yx*MH;pT^;5PI1k{gBMOX(lKN<&*WQ~J!<+Zim*=c;xGX!&^uc9hGdwE2xIuQPVU)Eu4(y5dZO_nw%NKI*F>pO zfnQVTtpV~@wmJml^Grop2f1)pRh*+jnEkxSmz8gnCe#T=RskF#U%@s?7t^9#L1^Vd znEhC*pi<+h-(BqY6E1g}im=Y5H|k8mXGu=z(JNW(m$Y|2a^=&}_&C+G$n)Lo%FyNM zs$V=guSb_=vGqQ+uhN5T%?RlSOhs5HJuikTsj1zM{EDnT%Qi=s)%-*t`T;Rdp|kqW zuwPDaJZ>t&J`U_zqK{?aNdJmBe!@0K9|v|1(NS99_!0Z%1jqMHMWk_X4ow0r;sD4P z^wvN`ti=yZL+=Iwkk_5s0LWKi0OW1$0wCj7P9oUxe!nqXEvQi*M%*aUaraG~S-6O* zm@3lorR;Z+rk9f3G{o?Bv(8jm_@lq+&B79cMWG?PkB8)b$Qi5pf5* z7IAet{PZ=kXQnvugE6mxaj3;O3>l>Tu`v5PtS#g(a8Bf(@N4-ZgalSUnbVYouuJT! z(uMu3gy*M-=p}4*WqfNf#)r1blVGq_{!*F%7vRv=fNDGsF0xf64P($$g!P8e0Us`9 z71{xL*g$@tU1hor#EMVY@3Pe;jpQ|^BCIzO>hz^Br#~aY53mi=MX2Kw_I~!;36b}i zim*;(DmO2M&s2qx))(2v>eAx-g#9C17sBrEOhs5^cPf0sekJX;=M#43&D`m4fF|+@ zn|A8IZAxJ5g>O7P@GC>pIqMtU7Tg)Xvi~q`lCfXeznO}#*s9U5Y+XFVgd8Vr?hI|* zqE06{58_DG%Wi_YoG(kv9U)$Jn_EL*MbNI}iDD01FEVO%n~Jc`m*@Pae1CY4BIAB` zMd&h~uHWDxwq}I#ep3avvrXg`3=62tquWsx2Xv0ATzxJ6>ym)5Y!`Vvvfge`VD@RtpGvuVN(&-(VQ~B z!EdmuKo{dQ{06_qR*Ingim3?eXtSLHm2Q_^1pD3D&*Ltkbb;ym4W7x?fY3S3RD^Xp ztsMdtLamD-rOVg`>QZ9(4R*1WAfPTW6=5Bek>B7!wmG_3rt}-!$9^?|vDZ|Dbr=@? z2J392b&;9)4UV$4Ar#A|BCJ!i>Nj`~+iYEqMt*}Q+3FCGuQL^49b}eUpz`_3Du5rZ zhuB8xV$$;){1E&7gv$p_MOf$ZH24iZ$*v4tp40Uk{4!fJLi$UlBCL}po`FjDBfnzb zJLCDbruG_sgEQDKCpdon%*B!R3{-KXe?=T?*)^iub>;_QP}}$oUd(b6rS#ErILInK^v~xr4f(nk0Y_4bPKp5>d z6=9vx!h};}SOZG0$tr+ss%)cl*(}QGa4E6hPq-9KMOf!@d4dbXV5?QV{IFk#p!5}I zz=wMx<|7cNbbm z`sVMmbtG-zcTGiDZv)G-$4}>4^>Dm(G35A{Yy)*Uo|!8aHqtZh53pZIpuFEygmoy3 z`xBAx!U%CHknAD|<6qc@>B3l&i*D_Er6_hCrSnC$287N(nu@SaC+lma`8oS770fHPJ3Fe?hR7;5s`i&D%3{aK-C}FibYb#q6zJ*> zM5+dr9?u6IwkCwzg{C5`b6Wvd9i5#J2dV}E74{X&a49vo{HQW(Qx17u$2L*7JFS%I zSn{YNLN6E#9oB+95cW!}ti**32}^~P@jJpf&NfLG&cfUv>Le2s zNH}!l8)maFG2Ldk*jCUm~rb# zbfOIZnEb4T!5Hr`t(C~}c4Q%(sADk3O_K`(r`bTgYe9?2bK}f9Nez;JPugU|(^d@F z$$USul47;UfIVqiE3r@Qt4&2%Y;M>b7VMRg?gl5sIB>+Tl~XsdGJZ!skF!nE9|MZ9 zPHsc$M4)_<{dzJ6eB4xobtrR>!6au?5P|P!Gd0~w|A;ug&o)LE$2>@mh1!T<4xkNT z@g4TN35#!*uuf+aET=04uU2sSf?X~LLeN3bQ3y>bW;F+@wKB{^WjNBzfU_n7knARQ zrRes!&0;Aot#ZTNEfHAHFNi!7U=<{h5mrqRe72XZAK~6(D#AMVuD0t#Xao7AE2CUStN)gCna?8P+u2p2 zi`dOVj8QVf-GR28$Jv?@&J9x$);V9A#W_YCj(ckN)qM!b-p@8(m+YlkWTP#gXwarJ zrF+>b5u|T46=5A|u07Iv!yipeoV1=mn4e&qtqU{P9ww?y2H{88`Vf*IH5Fl<r z%1i%*INSDR{s=LbihC#Sa;kk(^BJW1ZMNyUG%tl&alwz$?G3^eOEF`LJ7=If0s0NL zN(AWFOhs4+y7W+~+GvDZeb+;9{_0T8O9hi|RS1#IdV#Hl%(C2Qpq)fD9BD@woz2#P zFgnvzgmp$Mk3b(AD0=lMk&Oep=mozzIH>ltb_J2udbW|e-Rpe0d9G;bMp_bHm$CIA zyt+(9Sm)K%=Zt$3PNNFB484L}ZSD~CZuDwJPwW;P$)u!_&+>sVJFg(NRExwRs`gyV?>m8k)?O+keBX10;K@XpV{rbVo!E3^!g zOw#qlJ#0M)ual-Ctn-@H-z=8}sq_wb@(1McFxv=S9_QsCF`&>QbLaaZ_IpYFf5=pX z_4?nC%D|18y!!LS<8ThJ&-ZE-$V*a(uit33UTjorsi@QIr+j>^@-UKoid`MLBzs9N zZkf-kj`oyx+537PO;+TYt_1#jFyT8 z88KfSBsIz-(U~u_wQyLI6Dc1-XIJVBhafJ|nLs>)tqy@W!&HQIh%0ucmp!z1@CON$lKvn|AxdhgKnz#ZnQT=k zX`>BKk!R7(B+_`r?VRJ%2#vw#Ii?jFyOLaQD#BuWMpu&U@|Y&rHLQyh*l5>HW-mxr zo&2L;t5s{MZQ&y4V;Fj}TJ*d#b|7@^frsby;4Ns|amH z-wm`yhGD0s>+C1kx)64MWhx@gj`N`lw21RFV5oir5wRAIX?)NiKf`6GHa~-l`5CU* z?(C}$!O=o74=dK8nqRMr^tEDsb#N52!WM6*Yn+j*qKphPU(}gJj4*zxj0|V6-$feR z3@PI2%*b$sI-HY?3|9mh87^TPo88Mv#b#t=xPo@9$gn+* zm#dMHVXz2$qascF2&52G=}kuv4(5B=m86RqCS)G?2p7R0PVVPSk&8iEDH3T)D+8GE z7SA5Go}@kOG!kzNJ9wyLm=veoK zYq&giOwT>#kyVtEtQYnbWatXDPftS*LVq2*igclG&ke)08jdBwM%Z?j2a{P@RTTRj!{+Fo;>y4q!KAzH(+mu6?A7q=T3zN0q_vdUi2&_Lf6=4z9 zsoU@SlC(a(-#2m-EIyQ5U@bQMzHVB1(T3l&GcR1BWL|jSRi_1;hJj_B+B8IQoQ05X zgYWpJ;Xj!|i8l@Z-c*FePQlFSuxX?E{nF0q01x6AH{Y|ghMUyS=>Wu8qk6jP?+ zU@*pya17fVM1!h;Cw=r;7+e7%TdTMH}izdeBj}5(Lv>QxVoNtxE1s$qlPr zzCQ}-Z@^&zHd@urG*w}Q_7b+Sy3j7lRTH~u^6aAk+CrL}KwH9Yf~^Z-H)blrI=h)W zym~R8+Wrpzh%Da5R$iCI*^shZzMa(hee8FVI)AgN25^EOgCh~p$xY})pghWcJ%RGDsR-*(miJfT9Iy^qVDk;QoeM+xs9$Ro(|KQ8 z7ehqfWgDoAXhp6L8p4hPYA8N7p@xLix7b<`QcszRuuf`je^K802@b>5zLWkDsmva* zHL;$Tt4nRdGgmr8JD2@#!eXYW2Ay=;yjnF0s(ZuRD^Xvhj!z=NAPACbV|kJeyKQItrj9wb*Cu; zOn_r$SW^(BI9x)?`FW-3i|}U^zcF5|9Z${vIxilZ#R+zW>Nbn#hWAOpV`2~jriC>U zHITY1YDBnkhBcB{RLeC0)`%O`2`0s#C|tn@di^7)>$mv@0}=?o8?5$R>$6~0?6d!Y@>9UEP^v^ zsa2wP(W%bI*zYG?K4L1uI+ydsXE9#|4}|cO2&1Zq($?@(AIG*Ok<>TYX6ll<0E0(@ zp3&$BV_m2x=}KQ`D?*Tc)l`IaWEbo&R)ph}@b+s6dgAVZBjRdSM^kr!+80G==j3gz zA}-98BTW;B$)To%+F5K(2({BqMOde{qR$aAXk-j{FW&$c&C$RaP8|o^ltW%UY!h`m z*-E&WEaT*eNbaDch~OUTNMLod)gZ7gH5FkU)&;vy!1#wTTC2znYNAlg!*#pVJfeM3 zM0SX6s4lV#VU8GRDjYW?y@aNO+J3esgxU?JBCJzey0?-qH6=CdYT_Itz17vK5Rz(W z7MT8qs$V> z~@X#T=fghe!g+tP-9IJ(FWi)o&?qbQFfVS59- z=$j?De~XUu&Y@_1o4T;be;lcPP1Z=-m1*+qTS{Jeppc4c9sM=w_7+}a{H|%;MqW)L zKL!UH3~T-JU(E_Ul2Ab#E=1dM^{~q2W~n?=1qWx?XG&CgVi6C{kFrik%lwL|>9Oz7 zKbwlM*fP;~=)CKobHb1zTBkZ#D8FEHT3E2PyqKLE0zF`eka`dV^VlyYgTri75!Mkb zJq$N!s;~%z9nqFFS`|Vtm$Qx29le+3YLRwu*3gF0X0{H5(FRiy))_51R;)v)=sN6J z?-YTlYR)bXvH~PW%E=aGkkIqkrs)z|ni~&w6WO~!Hy2_}c=QWqw;*3=C&B}3nf*_se)Crm|H zr*;tp70)-pfi44`Y{W_jo3b>rdw^}OE;}bzi1Z}@vpd~e*~$=nZ!r~N9pBXlVb8J# zNkzSS6E>G*z#GNi5CY-A8s4vOPmY?7;|+Pm)QEHqUHX%3JxQDRxTy&1ZK5yfYT1LE+CeTWI52C717WW+;p_+B z1@Px`WDG3P{k_sq6}*`m!>Nd>9gv5u3F<6gNzbB}^74zF;zp@Y3YS zkJC+@43FM#fr!~ z5bE!O{+UPiQh$Q=JhoB<>p7+(tYckz1WvI0+nRFfRhJhmtEF^8+*XAU+9tMfx}9{H zJavq;lUF09c7#zcTL;3Z$5e!MMr-@QXwmQFEYvyRk2fHM$6;@DxL(CrgqeZK+dTy# z2!m&k;f-wLbs1g?4yICjaFziZz!yep52=-e_7HinRbcXdwn_x)AyX07kzTe#1gC?e zemJ3pu%{w`j3(CZsh&)uy`5bNx@gzsWcWJRoR+^<7~AE-iE0N>v-oVqpG@; zP5p-b?|!x^x{&6oV<_EXxR?EE0^*IPBCLbBDDdhY^1;g;wiWWQ-T_}UIHJWg@G6=q zOCzjLu+7zl<%E9Uk-o5MQS=S!KE6fy2wNF~@1v$7tmDg3KY+$Cc!O7A6(VAwdT=pL zMX2=zV*EDSY+Z~OXLtn&y#zd z-005;Y1W{v6~O|?HisIyp+(F*ho z5VOQ7NnOU)f{^Mm6=9v!xnep2xj4O&+G!GhM;3?KCg`%5C8rUn1L-CQ*{>y)zt2>J z^~&!Sm0$Pa9H~(p^D7WQPwa;^;E#|>2sTP9Ek-oPa|myYT?M-E)=7AZ4Pt`}Y=GlI zw4wDFSZAw6;EtM#unu=VWVs#lPejhwDd$4^GopGk+aO(33q*EX&?s`V&hUu3hy8X! zqO?Ih^QkT`4xFQ%r-}t$NV%8I&FK1{c?iiL#86E<5&ea3NZ4)Il9=Sz{c6C zyG&IWVLin*Ru|Sq0#=}{*o;7J+jXTU*}4#RUp5tCon16@Yfr6pG2}IK$kr4*p5RSQ z>I}9PgwzaE5!Oj9#xMbR13ilOq8y}W7ePYn*oNu$s3k#o0KAPJX%2>i`rse1wIXDH-&BNk zvI_;->qXdk*tgAc?aL~Fv_8T%N|)9mNoyFjYU#%Jm+bcwE*~%zVVz4D(gwciFb1U@ zc+x*2kFTHBmn^ zS1e>i@ceJn8jWvR{K`~>MJU1jpEZ4uB*TLxFSsVxN5#StTrh(0P=PCk%17q`Bz37I zHFEOY88f=?I(f&*u92%|LV}Fh$)t>GrZV*>Wo4lLgfCdnZVEwnc_*ke@}T&C@ztM& zuUj5m{R#9I!H9>~B$WuS9AN<)cY{P4%Yy5{nm&OeoGk^uB}(;?AtYy7Cvj_aOhs61 zt#~JBC7J3%bvcKNg`v~|X}f~hc5Y!CsXNS{Pp7*AD%?;3EeWri*?N#6|3*_0)_JX^ z)1pNB0=Q!sUi?q?vPtcykmSqQ=IfH|%9ubUQWM01p(xfn*h&$sx0{Nvj&=JXoK8jG z32}2YT;qi&-WaqF~D*2Tm-X9c}{UB3_T!v`@uiUPr z|C8Yx;UaV3&#>Qb3|9;4fHblfz7u+nTQH zTyR^$emfzu&{TwVBIF920)+gEJg#P&quX^fF1TIEemTK$xv2>2IHtO@rqG$HFv5Bf z+gM##{0nZkvUMTso@Xk;I=g6sH@ypPuV5Rf%PXGXO?|=bF18kg)Sadxtdq*Vy{7c7 z>>}8s-pw{lmyqrSw+Go85IPT-im*;+MSlbQFuhs3A=H_#`j%lLBWkJv9KIKFQx z!a9!S>CFWvjI5||XfSPM6;x`4<6>I}_ds2%_He1;* zBv3Y)im(o4!Jc9Ta_Yp1?o_9<$&BBzzudw$Nf*Py+@R1Yk$f*B1k26r*Apl=nu@Rv zg^pFhttZuwt#vU(^fI=Ax`5!KA{bTH zte{OfWc5zAiMp&-ikK{@V|+!R)lA{-Y&8h1`%Ojs=D_+i+eBSh;uExq`i4Hnej&l~ z2~!cjIaq$kHj#rRBmLg@*e@hlzHKVvHwVl7vaOl5=q+1lZ<)h>A;B`sRD^XbT`j*j z@(w`}f)!&b0d=mR{}_Icwy-New=Z?K{vJWbkAj=9AixsOB{s6PB4pQ_im*<$%^X2l z$+jtn>~3P4sLM`txUICq9c90eU^#3m;x`A&OV}oIuv|{DOt4=_u#B0C_|3ucHnxcz zEZZoS``9leSl(ijbXY zD#AM1tVnDM!>j^GYXjRT-F~MRs?BA;pKw`cD#ALKbTl@FN%}|RafEG*E{~~0wLO>p zZo=Y#sR-*V;t$ZYLbaV>8>q`itdXvuv%V(#g#=2?RD?w+_CvM3MOtk!RNFgEt2GMM zHo2$wXx*>Xd&|Qkkf*}0^d9kL-qNAoAZ2Tqv9-5Q&G+u}^9@M-d!X9z>%Af#z~(F0 z7e^;511CrR@Z1?QZg~Ao%Yr};f$gosy%C}wnDg5aFJKKC+lG6zH_H(vU1nW;tMOeo= zohWSz>FEeU_~%z`t(Q6*?rk|+PtqQin2NC89#}!!lm@_h5{X~St_I!iKD}^nSF`mZ zgs(IeVV!W--ZBI~l-ZcWV0da+$1t)?QZlR6KE!0eN87^7(3$yR`%dAq3y>uBa58}=(sp$fsUp|?~= zuT{CwpApJmvklUPGCwyC8o7lk1j81Kq>R4uY4*zrkjG3#SO;=`f2lY$+$c>rh2r3# zUlSSZy;0Z`f-^&vP1}-)>0jAq>SBTkTA-&J>FGv#2K629P5qFq2toEeQxVpY%{x+r zy{Uqq_a+?huTKqan&{E2CvQ5$@vM?8( z55S%x=;UVY_q>GtdIDv_RD^XXtM^xH&^sWxuL>vpRHw&3jq(WX9c+_zp{)UEHDBzJ zhdKxF5;~Kf^)|LT1mbV~|9uO;ZupS*+-5HmYTa$&in?`-(C|gF1U?Qw|Bem2ILfp_Mr=)G^-b3v?u~ z-ojRczql;x;kn}gwhOqcJ``v`a$4o_7XVE1( zj-U{_0m3R*oI;miTx-DQ!(g)lV_db88s79DLw?_3SAZ_RZrQEm_egH;$u)1n0ynmR zko_iGD?;|`rXsA9-79x25;YOCbeeUMwYdRDyne|Sp1k#7(N(NDUTvs}e<~DfaEYok zp?1&?%Eh*EUftH};0D|QNz_5y8eCZiG7)rG2f<>lSaYK~fRQ?=1JZcTVXI9V&snA- ztT&#Gd%}Jnv=#Wa4*T*03)7vbOF4tJYFV5OjHVii!SmP{df8Q?J5X%OMQR7^lQtz9 zhOkMT5P(etdJkJY0=?T*gmvh1tSaY%GM!FCXhuE(sAoiPz zunuBgA8dx<2f0+Ork57vSA;RnHb)l*Ebk#?nEbk;I)p}p{cb|zHd7JyY2b7fz5~r# z9i~F+=Wt&7SEO+-+ZsK{SuB zP18lQG}nxEi@zxJGxAZk3Ix!HO+{D-v_ZHI)+Z_r?}X#6FH{>{1Kr>$0Pax`a=H*s zJmK$R=eW?!r%s#sk0aJ^uq#9t>jvp~h!%nK0BG(GxYD~SFi6fK#h*iiNRRv)TR8&! zE2bi>17Ca?jzr3^W+=ddu~Burv1&23s?RQh;LdK?n*T2WM}kN*w^4ObGeYM~wg!aG zX{I8q(^-ZeD0Q8Ga9_Xr8EaVz8C}LUPq%X|Pwl_pJfm952uI(=R)S!<#8iZJO#GXb z%KV)FID$RMt`J?YB1F%X^wYPG{Xzn9uc-*@5V!1*cWU8N2aa;EV6MYvnpcqSb@LXQoiuq%C4?Bmhy?+0~+pa&r!E)`CAVxXekrT(ArLyvw6t7k1f- zw9Box%)2tm){l@cn~Jbbe)HZ+zSNYnn>IJYumyxeu{r`9NkH=Vu&YIv{FYoXw5#1s z+rY0f+|UoW#cs8DTuwkx-PJr|L>&P+I^u=MX%`l2+Ugz|pj>C9XOhu%TajGC_ICnxsRjkE}isDOTAR^Y{ z0x7~9*)wy-j5|(tja(1^-g>B&5E5|n1kzU zmAafV37uTfiPZJy*{>&c{nw@<;?DMI#MNmiJNujEvR9ix2ayuQ8iR}R{_&o`n?$&4 z6~&G0R8Q$~O0Xuu5G`tlnCyr|1pf=j{F+uQGrXs8($cR3tfXMhAar~5Rk}eLd z=yX43zn(z(fvE`VP%>lBDOfT~AebfNwx;Ep(dibl6(DHlnToKEhK8S0xX_;w%9U(` zbbE_Nbh^vgFDF1Yn~Jawq;1SOg-zR%i0M|gnYx&m(dnMYR)iosW-7uuG7^7I!9;#V zG7o=>gaTjv)@fve9}~ebru=X=M)?nzaxU1Hataa~zy5!Ml;Bhe`!(mx`Ox3i7W#W8i5y8GGhCf(s) zQxVo#m_(UVc$o-5rjM~JMVDzu!qk0&tscSth^Ywc*wc~d6r|}N5!d(F#^~ajI!xWS z+3zMSzF{iDI*T^p=M*e$$|0dS6Sn5%tT1)6*lG}1XPb(!4l5mrP9c>35wUD!8>8QG z(1omZM4a{PcM}$unToK^LO^%vO&;zsFRB zb?B*3bPCYaZwTvAwkf)>rVLZ}F#FX6#6zYctb-td=oA#>SA_8`wmG^mrVdm06#LzT z#*?NZ?9)gGqEl(4e?=PS-fn9hp%JETCi~?C#~G#~tm9}Af=+?bq70&O*{11s6zwo| z>)0v~Kx<7!SO>(9GpDfQKaN>()z}&kI#p8<*6FkiK&Jp|Sqd4wiEW-PBSx6IH?Wl;nEt?2gmp|$Q?R3tu`5Iu z?8aOjEw`yRWkKBjo?Z zRD^Z%MiJ?h;o3+74&`UP*w)IVLow}6XDdk1|MxQ%{nIqeceCqMx4VmIq#NnTeJT5e z1Y*uqg!TSA{TOsgXP&+|?AiO-6{ZWh^C9hSVCzcS$91M6thbMj1fWxzNJk`ME4htb zZMv<*Qb@ZBTVc{vj+=_G*i^!(TfC5VcS}pOLfToTb9C(_%Pc%T|SJEb`Pf z=ir|p_*~Fk;vkaeu$3V_?krOg*6}Uut2K&)#e7l5-)q)Le#@)^2&tECl>%XCso~d3Wd4a} zRmxPpWhn&p4Yql@pqA&VLO=Xwi3~oGenB0_v%asfl^~eDVk*KqrltFvr3PfYm;hFz zel72hLR9W_X7g5s5YpLq*qWj*%atST+@yAd(V1)=2&2oT^Px?Sr0-1zW>8|&GgSQlFlLhKS#5!Q+A*;^_#>kUYNB9_81`gxAXE?@E! z?3{A7;Fo0Va}VhzDhz*A;dV+Wwu6K0%F}HJ*X4={>&4jWxoCaDKv!DtiX_S&wi)sx zo!#tX>rC3rUQ-d)+sx|SC%p1#$*+s{a?`=XJ>sYlt`5Qb$_5!M-Y@2Ud7jD#sp0aCy^1Ae0c-`N|g z1F3PF@fXf8st{6ph;5uMwPiU^YB%+w<3ns62%`_0im=XT;eHQh^=0_%=3!YcKQZbzG^+rz zd6I3EE*l6Jlh6u3e6;U;nf-pk^2pl4Z=8ARn{j#*`vxTfZvQN z+bRx;t&~KG{X#;bC`FvYTvSWpn_MfNaL4?71JZ<6s+h`1{VumEg!TOUY_oOi8FrYG z+ChTXK)ayc;$6VsW$Qqy{xzl|;!g0}NUzhWsV>cCyds=G0;(y9na?BHJ)sTuX9Zq*;_%IpcKX zAK4lZI)7&>!aAKzS#)~hodeiJaju7h{@OsbRLncoN_zLlL;#Zg6}wV&$wJ(*46^Z7 zg4h`vj*N1pQKVD;2U|UY{ohPQSjT?uVZY>$LB2^}9ZC~_M@Y^~ZLNA{!3kxk1F8HA z*{>y)ztU7hy7DJ0qz$}mkB4RBt@27!?Sc~_VW+@a}K;qZ+r#A8H zvyRDhqZ>n)ittobP9(sU0nS94Fh)R@VlQ=u@8sb)MClbHew6RkXE&-`0EsE4` zVH>JXjpx67Gg}iv?M71()~U7eOIDDzDTlmX#x_xx7t4S74z?Nu*6pSutix*QnXI5{ zSqeeDlWm?ZD2D&?+u2GGO!u3Lu#TyfYqCPARUw4*X|{2?ko5hRA7kr47=6N2gmp%3 zy^ySz*a|4w>G>t^!@A)A3(E z%GQdoJ!~q%I@?yR$qL9;g^=1y*v9En)AwJVVCz5_jhTwD&M3>(OyQGN0NK2aZImt> zJ^$tV*zYG?-fSx3nat%=Y@>9!v9~_ZE)i=dxc&K+H51p$+2c@L%4*wu;jwGCav$_6rG#byCDB^sQ*+nyh@6 zTNT1@^K;o|>(;Zr|MCI04y5XzV=5x<1lJ?IPJ3JEx*{vgbRR;7O}6p642}JlYiyMW z(yFNl>qxVmlNEs3MG)7U*oNui()C|{16u<^=MPLpSf^v+eyp%F5rAYr#;z1yvK{eX z{s>z=g8eT|MOeq4@KaW3CjO3)zRos57gAgQ<*%||ODg|gOhu$C-@xrR_8i7pj)90+ z3rmiT;LzwNgV7`-nsn{occ@$SZk)O}Hkbv!WouEeDhF4>v%}K3<!+y2q zmsPaW6NT8fvMWk=oVYqS2$qUVCL*+}u+&9M!PC`uBST%qQ1P2IG$0y#zHVYGN*YD4 zsR-+hV%ILeRvZ&v`JxdFc=_WF&>!_6go~grJoBY49W5*?&_ZWKVk5bkU2(dN zWOuF*ST0+Iu-r{pjv0`^tv-xVBrVqnRCFU-W71msO+{F5E$8j>2aA=WXd0;tg~~6; z?hdvYy6k2HyI2p>VQ*)@m>?K86=5C0D%oM7caA~0A#qnw^xOQfSFAX-W=Xw9GdWdZ z1od{dvAUox!cKfXHRU%{g=#1RQGbtJHM*#`<^}@W++qV}O=z1dO>@b&F*1#G-*2-uB>cZ& zD#9ZFATh=Axc}B27;qt?TUo~JQyI4|h8X9(;{WUJO5o%w%6t-%NhZf6lRF_Hopi|E zIUornqAmV$-%R&QU-avq14Y3DCfdl=tRO}}KmG*tJkmJtL~nvB9+~r`Tg>$YP#O{{@?en`@{~9Gk@%`VN0*9TwYn? zyru;fWk2|@5q)cN{EN2@;M;YhQYv+@*lbqe;>}3u& z^=kO8b2sb}EpJECqKrAO%=BT^4g9PV*oeY=MCqWi31lf<7IjI7SSeq>m+R{wkozuWSOU3k z*A?-%L+(eFO(07yu6U?(PT0N59~5Z&u&#)|9on8$Hh~Il>&2Sz8_FLPX#1+J2;;P! zRa2B&5q9kWjmXx{AkdlUc#uUrZMiPq{8Xp^^y)-Wf%|)9L&=i++S&rwJKVhf$RRr* zBc!QN2LDzWsgNputt-NKs+diKiG1ie-gqFSSwv!V=DSQyA)U;J8lfE|G5j%28Hd2v zWL*))`C7zJsoxmsf`(#YAe2vW-k>WTo+*-jiFiCqS$WxN7=^4Kh3I;dvSPAyO=B~+E+K0&-gsCUfxyni zx+09T)3L?wwbQvgc0w$FDlU=3KZLHqiu6HGB-Gc;WrJe@$3Y(P{!V3+$@0Dlid#=- zn0dqLM^;fXox>;G$57``e-(5VvhbD4aD_zjR$URs6A4^Wm&Svf*j!M)U}H%Zw_P`q zu!>fY|K?GN+K(tJDogF$Xq=F;d7v7kF@{uN?QUfx0&5@A6=9sU83zhDW5?$2Y?wVj z6F^@*G^yG!7IF1;W%Xpani+))j9_#XkL`rf-Xf!j;S*^3iZTd+rZ4M?Fiz84){ zPQ2DGl%2dk5*1UgGSz1o9c5jWNg(C*%AXfVxlmVxaZ>oMAzDtGhl9S^SXYRdMv;h~E0mR!rKh^Jh~4N|gHGV+ za%BtxN0;e}FwW6}&BP!QKekSOmBx=}S1xwYW(S!?AZplj5Z4`!nBSyZYtcolnZPDHU7J-OIls_#H@daHG#)&xDji-*lUV$_& z5pP$T@l793+0c%^5f8NM9cU=Q*Cx!ym*FK zy|gNSP%wXst_b7iUwHu91vmzgE5RB!Z(}VENF3U;Z$)I!J~p(}v3pAdHs6NF&Q)I~ z0#_>=LpEQnjAAPX$0}S==`ZbBFk!lo1NYm@+hh>Sekjj8i=g*VQ1C zIKd0-M$Q!(Z4ifuJD{wZEOFD>${LRxYH!Z<;*_t~%l0k%A`42gMg z3(UYrV4Z5Hxz{WrQPr=kq%2h@!=RIok_`yrI)PaIiTIK-4uP+Nt_b6N%>`y^H)HI! zO9j|lv)eBAawG8BQhzta_AoVb&* zB;1UZUCG6|Z$Gsf*~Y>kZB1hmX#SlHvrcfmF~E>Qc-%pG)1>1mKC z16Ps;OB8CKu{D*cY_X6_;MJu#w3CY*fUUByNufKP>kA}c#|0fIo&Gt*Z3%vX9ld?z z43P6?axQ01{d9_^se5N>xwT+-+XWkM6Q)o8aWL3aANrG&7Rv4MTqX~fH+SNYLQlcU zC%MGmF^LVCS>iOJ#(4}>s@d4=llj#~Kb+kHiiWQ$4PBNg{!E(BKB}s@q_M@DOsgmT zw!$~*>ob(U&hy};s)(tYBFe4llw0hC)o2+`Sv!+-+=*#&P3eX}7AQB3Nd`MxSzB4U znq6qR!7Iak=FUSHzj{BALSwWlQ$iy(zoTJ7pxe2N}vSf8S?d6hQtpLLXN) zfGn9yq3w$rc;}7?XHfVWa9Vt3-=vI6VD_-C2; zi%5+Ai?WikjLK}3^!fU_G7f>Sujq;}&X??-#{hS-FA`YZgAh6S}E5bNC$6;e*fXd?_k9dELvdLt# z>2cgB=_isimEj7BWSy=E{IBN~J zKn4hF7>l@ihq8LITn)KV(x>SPWe@^Qm+Oi!PSX&Z9|L3!5tk^tM_E-_$|N^R`o!I( z3`HRB4qXw(iSzbE1{m`GNK|}H8N4hN;f<2M&7V;IreO2ObVV4qdA)s*0sGgBKwSJr zSt(gAnr)QydHI#{_XS>_*A-!$mpU6E1GLonomiRj9#hTxCL1MvQYI;XULa+Ht_b6# zc)Lo1n>#|QG#W)Bdd^T*PBzmFwNcXNXst2^ful9LB8+n+v+psGlVn~X?%trRv@CZj z8zp@n4=Ljjcs!^p!Z?r3cRvOgY#x=kdz-SNvfRmSl=NA9i!u^{wE6U(NW>Pj0W zeJaN*0}`lg)fHi!O6e_+0Xn7MB1%tJR$n$hDsPnZXXF^Qzxl+~0aNou2{PuT~Qfe4h{qAS8UWug2LASv`4(elsAs>srU8zt9>i&wv> z{6WF|pVt*(-2AG09RvKRzDxu@t85He0yQ^E`Z?`q%FqO=f1)eGIMod{K?WFY5Qm5x zca5p`{16)@eS*d)Ll6iWr7OZXLCy9*23Tqqk*HdwtfXunli4Wg^R+@5hrriTT@l9l z8e;QffU+Ut5^MXFRh4B;a-*bA++JlU0&%-^MHnZp>GsC}ZB1hmX?@CS%919vQPQWZ zs0>7)?9#>}ZW=ah_%Qqjo9pWBs^hYZbGLd^DV0v(_SW#N3~Tl8&VVv=? zKC8hUaJ4@WOaG*-ge*(r;0z9r39*atkILT_?EhI^5ytI5?jYMuUMDjJejx^as;q`A z1LLE#Tf9LQ__6Yb1qyzkE5bMh%@@fAYOLl_iKNl*HPw*EE_9upyCao9D3CK;SA=nL z7U8iAn+moC$JuShgFp-HfRh!GEL1~mTYH_XBl{8&wp>|x*<7`V9mdeb(8uBoJ-dJ; z2H@$=p9cADi83UC(o=Os7^id@TqkVDiY2^{JJil-eqy1@i$v`nWh2N^yBseW_OuAK zEgGF{=r<{LD&rFP-L5ObIKLClOC=I^Hp1@?2^65A--snwSru89+M-E@g)Zr=-ecku zkyrk-Ktx7YgmEGkUzAM6lMy%*Bh|}J<*nX~7jcuhQaTaY4u{#;X9pX8(r*!Y?^9M^ zmb}H$KExmM@mKH9ixK`w!}>z z$>dUrr4c%$FPTfl!$iLtLB#z(C>u$Z`!k{`mz@)q=33TI1*9aM+{aWD)52$zF$!tn zle!{|rv=u~N!SIJzk6-(l#FW9=q|yzaN*k%WnUtWf26FuEXRvk>&Qp%osdzb+(XX^ z@k{Nel`#pNeqUFFaZYDqi+A7Fod^BWy4%X6(gVR_x^Xn(?WAi>bwg$`-U@cQ0KVpfF5`dzOP3$%eqi&q8bgG z#^)*H5*Xg9E5bO#Q#M&eXd3Uv+ePZ1!Cp58F_u$SOO~;z(JsUV;{&z0gi1i?{bN3 zPN(vCRdSYpH@~$mWs(yIL47-f=li>CV`YsD1TlcGr`1hUL717ri`6Ry*wE3jPbjk_f<58SQ-7i6*fMR3TQ%~~XEI}d~3>?G|F z(V8-d^yqb_x_#@TXWT;_0RO;f>2rq1 zb-^`acCi!BtPPwntS-y(;k>AM?6Gq$GljGI#2!AqtRoM%=|ZYzw+(b;t@MDKq6@Qk zS#Ys@){d}~(ZkIM=V~}PnNsTE5Qj(M7g+7_9&)ZB=UQ^EXHNa%2{o5ITl!+~AX5f4DzmwO7iQZ^CHG0meA%Ey%zm8EKK6z)Xv zk+LOdHAn^4zNCyqVC@lI5z?$_UuO`(VedHH!36h|CoP!b>dQsq&>h9wQQ$=X@O3sr zM<@DzsjRUqee?NE8;Cdth+}{_#u3K|u|VN-%4h@%f6hdlz}pOB`>{QXGmXH6Ra?{Z zJHBaZ85+BIr%y10DZWdTjlVwFggtHzgYwF#>+1sfjan@%~5mWxUz{oOP5n)FB z4#3b!mQa-IbS5Z+tIKkHI78H|+GX^#eORv+pxJ-GjwiD@oT&}Bc^br_v|=fnS~jgr zhieuH8{GO^gH6c7mncIJ63iQzh!a=@x9=S&CSiOi1sDBT(D@8sviIASm6f&k z?SiHw+M6$NQF_83$b(ZWNDjZqli)f(4hMhX!*R#v+0~ ztgN0aK{H`RH{y$No_u@)O?N7T5NNtxS45a5jdJe*e4DIE8B;@qkAfGS{|o~T<P$E9J2TtIzx0c@Ew$kL*e3x++J@Ewpa3GFYC# zKgs`av^*wT%5*`$B~jS{<1WQi5uoI)V=@hi}dK#GUWwhQaLs)N4#%foSU>R4>KP0J}M}@NqIe=Hg=>KIX%tSq50Pt&qz^_SrpfU#iRRz}sKS=W~T( z zJ#k=JSf5fHfMm;WZVcJ*@ZXjVH!vHvdS%M$V35j~>aSGDRD)Q`)GILZXzv0(iumZo zM?XB8l@-&r;QU;5c$X*UknP_JLjDGdg^6~*U4UF{yM4BOYTWb8F2v{)hE>i^Z zhaynPCFrgpc>(;}(3}ijQOXxD6k7;Nwnw+>MWW@Nq9b?#IUi_;?T>58>ls ze0&lf%@XTEya_fv5Xo3r?pSHu9On&vSGf(P-G2a?YH7EAYw!QK@sTg&9H_c^Y4H_@0+4q?nOdr4%t4e-4aVK9xZi{Ja9xkwEWe(&di?)WsKD0MlX8VMFYag(95 zwt6KOERM2|xRJG|v!e;tt_=)bI=4b^j(UiH0v1bMmg9BZj?w(`ZRFfR&Yk4k&7AuE zZB(@Gq_guCc#FRE2jy?^ZuOU{B3{xJ@rA00-!Ksk2aC1G0@v(;wOv*L$7g#YRw~1m zyA)v#r&{7P<)p0fKACm)jfN;JpBByeI>k^YZ%ay5Cs@V?=`6PPbT(-K>5Nn6vpz!^ zp1}H4CgKFggYMNmbT&&a;VVsMp9d$Mm2aCh{ zQHYmA%8JSIGA&wfYp}@9L1hF2JNtA+7-wfPEX;(6CpAR)C}^NWLxhilhRHNU_$X*_ zR6_)!fbs4}n~irL|1sCYIMD-x+#4f->B)_e%{f>ZSSUdygM+c5vJ6($Cu}w@?&i|H z7$cGD?uHdSa5fMu>4s&KEKdbn2+qfR$b9FmP#T-nF!YOGrXBhKx;wEm5|ZWKJkY`1!k*hc_0+%Wd!1 zCZ{Tc5$Ic>E5bN^D>uQGtq9EL=B*yuUt(nwk*al?v#I(rk-Jmb7_#K9f>T}MM`AVF zu-T)kHbZm0T^XCe^)_7*#<^a$i?3T?MQC-Z%_~e<%|!)ka9X#l@*;7ZS2lty$8gpX z*Mb$gRV}>Ymobi7#Oh5NW|VOW{5rZKjPtwmqC$!_Oki_gq&roBQ3>kSc;_Fm2Fi*^ z1lFvuc&TE9B?X*K-m{PKe+XPC2*RuDkFRJ-BNb&s%BGR?qkUuvc3>s5M7<$k*ucW< z5KF;;2~^-kB{K-s!S%|pg(UP|T@l8UP=m?mz=TYLI7I4alvR@@ReFN@ zlgbbTg8p7tgmHqJ%{vEJY8H{GdRkdYS*p|~sK2j_L*VOsx+0A8HN>QIfU+Ut5^KZ$ z&QxDUd4l>cx>onsUH!MN2;;;xopuh;)-)!Ow$K=9iWAiHm4OI(?G#-R<|*3=D^yEx zpy+`loE4C;1|oZ4vk7dWik!ASI8tzOvzSELdCF?amX32^VwB;81_$Ac!S*-A83UZ$ z-hTIUt1=LQvQ4@oj8oRJ#qPD!IXndshSS*i84m9xa`=Z}F(#agay! zr5qN;PuVrvmt>yzmmYNon$&R4isD<+bZGF%~%bnA*Ro=BQs1{5fZn@1&T zuTxf3mfE>6`3k$n<3-kofJ0|+C?XD<-~y*y_*wfJWh4S?@75JzoV6JT3Km>uhr>zO z&tiv`xOVt>nTD~5t4}DaC(G5$D4ckcf)ksew}v<8F&D!e}u6)!7;m!)EKlwUd|*!<7R-xO^AM_m!dZ9e%TJJpjc^25$j z7Hs7U=8$?3h>OVkO!eEQMEeL8%Mo3KO5kO#^7jQ^X6uSD&P)3?+fHCBs?RDU;1n}A zL`$9DiIpwND#_-M$qOg9u#{Smfs1CDK=6(u2N z8bu;{lFG`-(lZ065dd8*j85RlR>mN3)TJxJI7bUMC*jBdJP)vD2_tI-@Z%!vLa>07 zd4aeqD=RI_T{IeJsG;vvv(%B5em-h}$D_)41Rk%_6=9smIeXynnM~?3>^9?UPJquK zgUzE7cOO?)RF=EBQBDycWfLv|4#g7k0c9itYxn7jFwR;VoRLyW!(mpJ)mdy8{*jpZ zjF1(5;R9yx0PNPV~&7YK&ljUZ5{n|>*E`Lyl zAW-y@t_b54P1~M<@f5bO4i5W=)?Nm0`VBJFAPx~U=VnuF@afT%hYjy(sA3cH&@5#L z0zuPtMHnY2x(!b3kL0@WqzITv$4hSD2urX`+J-ZB=(dI+T~coldFLprEt|U*M&bCr zbS#8B7Q!u1`C4T_0+kzeMHr`Y@z!1|4eM3CfuWj2jTfj?NA!YpO20*vCY05erF2Qu z=J;bYSX6@_FHfnC_=!cRr3^}-^%7kX#%Z12k#OMDtmfB$H;P204Js=qOWKU6#n3gn z*4rOAf0r@_fupzUiZIU6gbPz{sljD=q2Gv+k1DGo%Sc-kuGFc)B9wvmDt}ra;={Tk zj1zIP8&4g9wPEa-?xxjP)0jlklget!k~Ak;i*v|o>l?~I1j@duE5bNsq5Kh;8w~wM zwESLK6th2qO$rTTHd<*Z8Lh1a}C!a2_|bB0P=Q;L{PNkx)iXQ${B+K3P|UamL5`tOlEc zwLcI`XDKToo7KieeI~>lw?X;4g8kR)iZE{fakTxWPG$=HLJYh~Sq)hR#`A484YI&t z1s7 z&t@DhDzKaM@Z`=uI#s+*){%XQ2>Xb#^0I_2Vq4R@82VV8p=Zlf;M(dwS{c?Lzum12 zNucyYx+08Ix@;S)SBVu%S#gbE^M0+$i$v|$m5m@v?eZvF$wFF$R{ag#|NV+GE`i@K z>xwYW?}YPGiG-bv@D(P30yOj+vGk&{DzYrKMd>z%SfkZ0FDQRnAmTrDMHnYy@kPm0 zJQ?v1E~y@J6LFKdQaTaY9)Y`0&JH&Gq~9X)roP`)+kJ7g5Anx*{MBP|VuU}IiUEGH zMr>EcB(U11E5bOd8@I!qe^4pzggd41vbnnaF4>>z$>dUrr4hJsvk-y#cDPzRMD(i> zMBJaLY$Vx?dqy+`_XNUzKD;>#wXB~CNJ+L!kW>`Y!a8M)LRvUYSA_Ajz#2LUILo{j zCZO?Z^zLBN=q|z06}fCMgUh}|9KTUnd0CDZv(}N1-aDMEO1X!g6XFjazg`)W!0Cm$ zB8+o76I;Cdw(dOWm)6}@CI$Bf1!~g9(TKMzlogcaZ5HFLV5duddCU$6Slw0sN)$}G)l{!zOfWIKa8v~In^xoi@pDq{n zbz!}<+b-dC@4IcdO1%JAUIto*vM&*Rhm@6QJa4GjMBj7D>dMoX<9KV2Moh>2qiTiR_j6@10)5ZuiZD(eJAWLu z1wz{h(sfB3`>Yp%NE-hEQ#}egpq!zKRZ$7Nv?_mJ;H5=ZgmGS`?n-5GdmEil$`92D z7KQbr5I3up6_d?C)1sLgWZrQfVxbpPMj)`WOjm?)b}r!TVB-X5mI9j(VE_~V?)Ai= z;o`=zm&i_<@DAZ^e$1=^`IIgWD4SF^UF`GH1?VnrbA%yL{JUopXz(zbutkIlht*!7 z3|~l8yLCkvPgJwF_FK4dXk%n+e?FImB!i`L!j4;^iHv3uiROM~C1q)z9kmH%%=SS7 zod{AWp-ajz1iA{kB8<~D3um2R!VUVOxIHL`^(Ray!bZ4YG2J8{k@W#(73Imo31JT- zbU?8-?S;PpMuDtblwk;D{hh7|<7Cxq#RP_c>O~-WzNoB}EIqh7vCiT7pI82%K*Z;C zMHnYy(tf*G%Hy;g(I*^dF-C^4!D>#exm$!fsr5TiZIT| ztbI0a-i2NH?1XG=&Omds3pTI@sc90AI2v=zRDWPLY}Bv8$eI@(Mxh)Vr3^zLYlN-{ z<77=?^Q>@GSrUebVIHoS3ZKVRHwF>3LRl@@Of;3|O+&Z@YL+Sk5U5$CE5bN6;~6yx zyJ)4-q4|a2PejIEWkqDkm_THBNCXykDSugD;e1^Y##xAUMDjVfDhtZ5(EdfNbHcZ{ z21_`_cZtWMvMFSFTnTdqo-Uz1j#yiT?|2oftxJ`m2}EagMHnZ#?Ld=4F#ID?b+fWE zvQ$lk?O1^#S;%xZDSunw;s#w2#<`dd`xBt68ni)VdoXu3ibUM}qq1_c+|0mz2UZ%k zF4i&>ONsgAv&t9*jy|O;!Z=4W>T?t#sbMT)>Bq|I$+9%F0ZVmg`hhYCfu?`g6=9sF znGI+P@zgjP5jFCIrrP4O8WB~8so}~f1g2j3f6G*Zta4$n)N2@vcv_-tp;w!sdc|_@ zRAmqXO$&5I7|&3X!q>e8`4N96Vsbf~T3lL&N z_?Z~VD=Q?=NO)dCWF({fb%7B_SA=m!=HO6v^(qP+Blae?U`$@ zD2_a4BXWOH1{Q^N8?h;6L;{=Lx+09TxvskCX@5<(0~@l56r7;!!rB@bS>BsVxh^z0 zyj8lvjHxMu_`XirG_riJt1gua^i!ZES)&@v@G#Y?3y{Uq_Znq{0{`#U6=9tJ1z4!^ zHh8?sub-bGvjoYOd4ZVygtF4I%tl#h?4hnw=jUZaEtJX+DdQ1%{Ftr?<2*)dv#*y; zn^vb%ZxEADDXT5Z+(TBd-&F=AQ2A|L5yq*Uzd4u5!xbIg#w(aKFJ<7w z6j*N(apOri*glveCE^o}FDt7oOXC8#hLU5ZUOr5YdzfP!vydPEtPDpW@sGM9jFUJe z)CI&bvmkACV-Qi1+f8-;riMFz43|L7Tx9?PHM4a^7^mixy;gxO?UvavHB@9GY>Tq8 zvN>yB6p8{wE4^K+Lm7*}-RpEk80T){fq^_bG|C&a2z1$nUx}ThvO2QtOo|o(4-Q#+ zc!aEED}P*|qf1wWaXO~*MZ}Q;RNbipyK^P9_O5;uBBrdYm@F~VqTZl$0GYtfQDp=I zJ6Gw7FwRbJ*<&E51b-qnKCY~YEE_niwN7l1KcM_U!T9&-iZE{cdDV_J_OKGLHy5^G zHS9tU8Jj5jjQ)H+4lAXKyOIquQH=^$Pbu7OEeG zc>0sFVzN99bACwUY?7XBa!ZpCzt4oFwV&t3i%UnHuUE6f+HTZWEVF=wTsi0Vk&r-GDaa4 zyj@p>`BYGC($)?(_gS#(+8ep0bx=(Ydpko{3Z;UNDw{_>71(@heeHY^s#k3V)8OWi zr@`H;j8RAhAJ!FNJQc8GoO!#m$vjcxXvE`_$_mQzNT)q>ghR{;eM1?Az|>cDMHpx5 zRV;D&y|PlW?BH0yda>aAt?~y2B7Uta!Z;B#u-$6GMEU^S3xKmYbx(R~7>hE@%nzCB zlgwn(sXo3YXFg3+1|iTiSyzN{nqJemT8pt3X>HS{>D=n8l0}Lg)`(#>;`3+LV{SYE5dk!Shvr1;WCoA4JTt}Yfp?yR~tMoTfoiE#;hJd7#Jqf zltGE$P0FT`O$6)VNC&PPo`H%3es+P5JgT;KT(E!U@23wzUi! zc6nuqb8O78VTUWuZRFfR&Yk4k%^Z&6vk)L#|EPlHtA+?4#nViLRUgGo&hlaGpECrU zQdg-wv6zc@!W4QZPy)BwyA@Qbb=0t7JEl2f(K*E#hfcdQ9-TI40y?cu8#)u6iResn zCZW^fw4*cDnT*a9XA1o`6`hIBG;*e+GtHTS&Io5FI-{If=!|q`qtoJ?OrbgGjBw_X za|$}sop}_BpwsHiN2kqMfX+B4O1~{cXRLE7IxWs3`r~4B&Ucoev%^`6&S}mvbk;k| z(K*{$fzBZ(hRzmeB|4j(Rp_jBR--f4`P4{oCOD6xW0lHnXgk-A(|!VGy7E{TkGREa zd005PV8`%xRh-+;gg1uo7=Bg7d6av148OYKJnIEUKw$g^inQY-2(0k}BO!317Z?SB zH+z8=2;A-kMnm8+FEHlnN~zqE#@*08NGPBf0Vo!p4j&l7P;4jf2mq8N?@8djj(Zul zM<_57{{9Q{jsowvwM<3}cw^j)u}kGK@uZb6+J!azgD1fU{{m@#$4Tsi(N^Zg4{qgN z_7%qqpanib0fh2B?q!iik7X|-l(V^){XO9Y@a3B*fFM6dUIh6g@{R`Y$Z<@{81OD7 zZ!36rlXon5UGk0t@6F^L58ls{cLI2yA#WRaM~`R1CSFye`e|JCk)Zn28Swi^ruqi* zqUx8B7ZrR5c~Pg2kQb4EgS?3RCGsNj88ewMM1B@|5xGTPM1B={5&8Y(MdVMC7m@#g zynx(i>U0iw6u{j*3%)Rl!F9=taBn6r!u=fgGQ0nh0*HOmZ1y5zUq@cVeld9w``gHi z*ze$8CgaOq0J;067r>-H>0~By%nnTY>%0Ia{foT-Bz<3xwOo%D(Bq#lMhny9XXHga zTIaC8q8=;Bi_rIz7oeBQQ+Vpl<%`wBIJwx-Aa>^x5HOmFy_CEt_D1ey`h1B3_>Jeu zi{EHl%3ehCoK9Xe&mr=nc`oB#CgXkzpsl{az3lHVc>%OlbQu$gDd0TvVhYHR7gN9u zZdI7|BjTb<*zCZ!gej|cGAU~U+X;C60P&r)m`Oo>PUT(}=|T#ia{b)P{(j60;LDGC z0aWf;F95}6sod&S$E!K|HbDO-thCw~`nPj06MByqK%q}j0QLHB?q!kYO<*sN*nyF@ zcme!!$_rqD{a!DC1@^;U0NW~0c>!#z{KX4ETg6$>#znV6U_S-WnEm8MV;&l*T6V!e>OSVF#;yjVisPF^e_A0sc8kpD?uEFmXOV#1(Mbk>r0 z5_n%v-gfZ5mAsQNom5TjHGL+6ss9ZlOk}2hnY?Jw`R(klsM|L3qHagXi@IIIz0BfY zpa9F288^UV7CuhK$6S2O!^eDlY{bV|_&A7(;}(3}ijQOXxD6k7;Nwnw+>MWW@Nq9b?#IUi_;?T>58>lse0&lg-^9n0@UY$T zr0!JOb~}r?&Vt=lN~IH6yf7uN1sD5C*D-DV5UTBmP=7y!hVVmZ5kG{c@k3}MKZM5e zLufTWgy!=@Xh%PU2K7T|SwDm(_CsiEKZHj2Luh?Jgf#de{+DHj&F%scgb3TA2FE!{f{u zSIFgxo$f%UE0?Y~KOQ-3Sh;0Cg>I}Yy^c>(-KonONf2F6}wPN~b; z36`(XW)$#e_t&a2Iy?deZ{r9QI5+|Y4vs*9gCkJj;0P2rI06L@jzEEfBT(Sr2oyLt z0tF6^K!JlJP~hMQ6gW5n1rCltfrBGZ;NS=pI5+|Y4vs*9gCkJj;0P2rI06L@jzEEf zBT(Sr2oyLt0tF6^K!JlJP~hMQ6gW5n1rCltfrBGZ;NS=pI5+|Y4vs*9gCkJj;0P2r zI06L@maO352oyLt0(BT`qY)0$yu^74%nS)&bS9U8&8D^K##ud?MV$ZR^uOnQ`AbdVYJD6{8LX3jxo%|T|&L1xQA zX39Zk$w6kwL1xE6X2wBg#iPuKgUp75rE2yXksqkBq_gp^Kyp2);If>_4PAZfB)7ayXKSS+T-^w?QS_0DdPo?K9#;O3L5Z2!u14kqhtDD^rI z6s)WZ`3=PEE#&$KDmMbTdmwgsVrSaAY@oBqBiQguxrN>b-a)ht*WOjiqqehrRjgbI zEopeqIe?FY__z=rS68m8bX{F3kAZ|jSOEDztQtx#a4vvoOG59KVHr0jtVm<&m()ma zac!#*Pga}+{IQY9ar;@M$X=_*uGGV8*GLS23_~tY**j27!o*1cB=&;FV(IHs!0gVA z4=uYl!Uvqg3?hUOD+dgrBN$5a-@H^(9t9mnCv zECl5kP85hrqQCp2VS7p&wA9|5LoOQc+e%N@uTA)=E6 za?0aMg>)xvqXd{2mM11{xcM~O1Fe{NGFQO*zuo(jn=bWq;*}Hd$JS&qlkUvGk=PaI zQWP|$8`@&o93Wu@793xm%L14QZmA3AMvCnEDS*<8aogaJoe7&=p$8WxR-6I+>m<0o zGvRi^9f6&24^gRTS9UxBji>3^E-)qQW+lL5$2;?&Dr+;&grAr}q1DKKaZBCZseVuy znwrV?CvU#4JO!d4>p-d7*_TT6*kDZHhzYgh43?KhXc`O)?ok;S6t*kpc6@)wq$5x7 zSX>@mD8ZdA_@{G59=rI#{#RZsw}A4=T%uAQi7Trixw)ly+=jMc0_3;ag+i{-na)Al zx_H$=NJZ|dOwxh$U}skyu%Y+>8?V~MTze-Ji%?JWtb)R1)lO(AmJ0T6u%x@HlXbXO zp{-XH?0l|JbXR%9JWz-9Ko-LW6SfDwa~EVa#5?ejyB>1Bi=lINyrF-MGwLGedk}K| z4IfXz-QYj zrgz@jR=#oH3B`39$AvXS0N1V76SFw3j&Xng$nTeb;)LQlo#VnPD}d_*<2QYg;~H^a zdEk%T=Y()U6ALT2z)N@SFZ?@y>6|wd?^wLz=Fm$#QJTpso-SD724LO&!iukPSTmkG zH18|Zt_Z;bU9fr%y!7FJ7(bD}H2O1F7VmuL7eg-@)ny&$1)B>2SoeJSw^KN*iO&49 zzW%i^FGgXl=diH(5`guQ1qWUxSZBZV?3~XWJ2LDa#NHp4uMiD@9fZJ3AHS{eZvN8f!p_TY*JteDWm zD?hQT6#(_{1G`V*nw;FZ?(s!q!kQQ~uUC3v$1ectlaGvjEeAF4sok%A-Hl%iB@~08 z&g6L>yP*M4pSqy`eoo&j?O&bHxAFwiw}FGgPH_;_j}~@vP=7i9na=o^PaLSVUQ-;q z=mAiV%@aWpE(7ET#9RKb|?v?Kf8OS+n zy#_Q6Jp=*o`qx80xM5E%;EucQ`_3P(drcK^(yHyYfz~*1fu?G|oAsu4{cEEC^y$uI z44t#>*X#fKn~vL^DG*9p&Qx%M9X%7;@uq93JWJ@Y!n6ZU861;Zi5 z0ibS)mCvVPR{(a!SM_ESE1gn)0LHUcQa?D>o3i_sJ8<}3r98bhs$=z9ZoH7n7ug_6 zf01=SVX}b@udH%=dzSZSVA!UW!g*LvQ65WvCvQVw0uHjQ!ZDEq4A;PqER2&1{ayg3 z7+{bEJ}?zJz1TB{u@TmVFX9*ln-EIDSWSV(i8`wTZqsW2n#%UV6hf|muULo1U@3f_&L>&F}3vic`R`B{#)JS@M|{|kf?o)7>4 literal 530597 zcmd?S2Y4jMbtg_PHwSEvOwApVizP7tH!&=Oh>avSdUqKl2DmZPz|8DmW;g*@Fq|bT zk@8p(N|vp^qh!gHWZ70YODEZqE!mb&vMgJ7mXj>`oP%tgbw10s?)U0-cU5=w09}Qd zmH%FT9~VGZ_3M}F)vNbjRlRi4n-^Sm`DOH9dtIYeC{`{EdX>pyy;_;@D$SYpnggw3 zIe%Dr^ro4eFPnLGroVlKTdU2SY%kAObIrQv<%{*1_5(u?HoSUcXrfT^Dh;nPbk1{g zfI2>OLj3fOdv3i#f8(v8<6f@Ws(UA^O|LODGD=?>8uY<6X4;Dz^_+luhc#3H$yF<3 z#qpW;DxbXI@5KkXA*5$nb<(TXi+Qgh$Xi-=E8{J9+yjk$wdrx&FToG)0io2Z}-)`TD4JZR_oLJkq3j1eGXx$yDxRYS-O#ANB z)hVy;<(<)K=PuVN)V;C0w+Hz8To4QgU$)=#0JFt801@0Zn*BPy~&U|{72YQXSl@(V0TJYP%Ci;YIhYxvTgdA`-&B=n_G zZPjyLxmY3VUz0F_?2`?E4NC0~R9EQCCV^#_*#@xvwOn}f5@nF<#cr;AF z;MLGw9_GH0ATzhTFkP!+Sb!q{vK&(NNDW~nNLnPriB`FZk&qjKd`7)GeeJpSCSv%A zS8+$7pM+VZA;vzDxB`Q#S{WJh00t%`UoDs2`UFN8Mls2}I5rK5HCm$$z-^Ju0N3 z>K>rNKd7d8|&7B&?&7q%337q%DnJXhHJeBt)O9fkdcI}3Le?k?O@cv0cr!f@fp z^M#}6a3B7^zwkie#B+s{g;RwG3l9}u@_gaZ=L?S&9xps`?3%&|I(%=zEsPd&g?xL- z1&^gv7<;ZTUMRFTsvH|>cxCtjWKljh$PEL|pqrnlR*IzhgZX;3mak4#@U-cUj}$ON z!|FmkoqTa}5LU9xe=6#$bsHJFQ<^_KAT^6cqcF*uQjsiQ%Wr9rWn4gO5w z?XC7Ip5#Wxs$>y`C$^-)-+`$-%fC4{fS|>g3*kKi(2?T!pm?;XN#+(zJx4#qqvg43 z-ph`bt2yvx`EeLf*k@{KDJBDs49vI-qq#X@ybZdwBEE7Kolc-n=rAr~Z-^#|MHq$k z>P+EX?WKpRxt8#qMZd!PV4CrG$+>Fo9K2+HyPqE}JpvKj53?&2foyrc1@vDz^Rk)3 zM_}>EcP6#*A1ov8k=@`YmJz zDUZE&_K=q=iZ78$GzOf*SSwAC#-8xtTjiOf7|KFf=ltgF3UGXL4V)@+k0B(b!E0|h zggIMyA#SvPU&VVHy zk=zJRq7HU?jVaGNzbB>>E0Z3^UQx9HF;Vd=Ne}nNgcpUgHzq;>C;l+@N=&-^O6+0m6;<#7Pxh)0z4rAFL#pLz2a^F* z+AR+_=!YV~RfLpVlG@L0vpYcD;`or6)%;JlNso*8W~4XtzG12C(l zGYFbIKEq9+o#v*8WRqgCx$PygO*hHhZD4|DGIPa7_qJt^4e2mSH%YJMG zq9S~kY>t76O6R?@AA^ZDzh5@Tz(i&EbFv?Ui8g;&Hpjq3CH;%CAA^ZDe?m6Lz(n=o zQ?eg}i8g;mHpjq3RpK{fKL!(R{(P)Cw74vw-OOz(h6c zk7Pdv6K(#QY>t76s^6ckX$OyOto+l1G2 zu^MQv6zi5?dC*=`8qJEObZfM|oWp|TmCqF3*IrE#m6Cg550+aZ1dO+r$PjFM4dw=f zaT@m_&Ulbwr!(za;9>8^DGd_sO-_P*UaKx>9?o6Z6Ud>A_d{y}UA{c|uFGp~- z00$HxX9{<8h?W)LsJrdOlWrM)G%t4i84K&1(*nRu`wB$lX{w>+cxlCg%Pzz3SY7gD z1>%Bm8zL_V{UByReX(pWt@isaL13HQO~hux_m|YM>_+HIeYU7s&AZd;lV#$`$k;@4 z=49|HLI%OFScFz{E&^N#(~G6#68;+z#<0s4UZx>X!{Kxxzluxo@=Z^Ze4ibBI%s?L zX{>OboeAG{#yy1FE;RkP)mZDPr=~{`>#Q`ua}Y!^tR;RQqPp~LXiwpN;rmMozON6# z!@?U1Zw`J(z(oXF5oy9Qkpg$^Wv%8|_V#R}I3A)wp^xy5m3eQ>MZgcLiKUw4#1@Lh zjv-V}cp?5$N4fw(LrC?x@ZB}kXQE1rJjA9cZYSHWZq|zvQ0r=w{2K(4$FQD8d~l>u zqwxOoA&`|~P0vAC&>uXfC{8Hwbp^y<%M^nR*$&odaC1!u85}?ztN}bga*KjfaA>(1U$!8{eU?w zPPoXna10-zq}sHU@Z}{dOwnb=nZ}w$$K>@(Xq>e z_QE>~KOFqdw%U)M(_oi+-Cj#Jc*J`WybY|rM0tg1X?YXL5g0uRq)UWW&{G7d zy*d&K62@}G@arSs2lAcr>52xp-F&h|iwy29{uK}nLUm;GX1rF&o>d}fN0|y?I7`dPu#+rSiiW_vAH8>} zNabGEUP#Z$BDR-{9vmesy%O(t-Xd0O+=4nXEcbQf(!63UtG1g)Q!9IKKoMuTl2+NUZEIx%-+;WHlr7A-Ex?04kg?0y% zRM1B0jPQ3PGlJidyoHZ60wU|p5#-k}iz|(s&*vAmQ&nSa@yt`|Ap? z4}K3mLBZ2pfLDL}@%hhf!K9{SoQ9C4qwmbLAMF}^nY)tEzi0l?{VbS-`Oy4f1{|RT zngsmft^p2GaT4~qIBeq@7gE3>=!MAP`_fa~5}}`%0Z_rA^xXm4Nv3y+kdr93TGnE?!%5uh0DtxBi5H-XvI??H{~2dLi&eEjD0 zNbv5B%DeQ8*61+&EwQXa<%e5`bH&9rS1VoNIbgAgQj0LDO2lkXdhpEFm>j2u^-6&!Q|%FJYx3P;}!W<5!z@xWK?cu}-cG z&)v%pIu94iWoOiLYKUk61|v(g+8=ri`Gg=SKZ z0T2S_dKYTW-OiX>Zg>L@X&*u0UdKuG(1?UG+F0qhMLs3Q942Lpb|x*OuLnwY5IP1( z+qVxmq*aHixkHqw7mrA&LaLMKBi1*yJHx+)bnfJK@bFO8nL_@RYLy%i?9g{Wo%|5m zd~N2e#rFFSpE;Zj!$sR)6ha0c31`9*Xk2$)63S}l`xtN0SEV7uEr$?Q)AK2yv?kP- zDlVb(WDR^NQ%x8&Szs=}7ss6bKoWs|vyS_+sUSP-kAfXf^zU$PP825|@7UQtc+<`u zI|bNh9n_?F{&<-KUSy<^MB}=$Q-jV_gY%81uZhG=(u+qQm(pX(k5pSIZu6B)HjY=D ziU5QLMj9o~wA<+eR2tQv?uk>j)_cDk%2Uztg$jUDLURyn4ooGi z&zKl}cv^8vC{-XHJ6PzU*v~EVdjeFz;&50EHc)okKk3|kkAr`JDoq2CaidHz7(FUi zN~j~{amFKBqI*WTE|^i_a2LUhaR=s&m_i2Aovaq~4%IAX>#d3~lVbkG>`Lp@5Kra9 zD4_RsYWriA?X#e#zSF?;?e*U>;AD5P_Os^tUWL*V-oQ*NbTipyWjd80_979)mcB9< zp;Ofvyejx$4FtfXGX3kDqt!gr3jXg!SaNT=3!T)AC|CI=2Nqu>|4 zBW_U_&YcKi`6bVkNXYw<39w)Fyisr%l6;j|8&Fl3DC!a(Wu+Qa=9fM~v5@FTVO9!o zZK)<6AC)0K;V|zVp^yWf%QXVxqaty{tFQK*L8W*uUl}Yl$n%`64_3V9P^C680gmKDg7J$6JWJENWS=b1C7b}k-jxS6Qz5a zqJ$`HTN$*qDDL)r_@;Ga(8a<=cKP3Z)wpSi>G4K6&)P;iGu< z`0;zoMcN-BUn}GblccAm1*BS65DO^Uxt!B}qN?2wxbqWii-E3*#j_tVzmgkZ=D1v$ zE5=a--kPZRv35U+NL?;q&5E$K_{dg%vstZ`y-5#IE3SWp^l*@5g6R~?0geo0mCEC+fbHB6LU0}f#eQn&(c@61%D_>S#GQZq=@xm- zVoQtHkh8eb{pnT(Q32F;(x{LBUhMGh$u3r zko41!!9sXb6z;*kho>LI03iphK>_z?pQh=b{(4q^=rQaIK-ivY!=Dae6IW2I9;6fR zCS4zhw!(l=XeWFqA>M#G!2CRzInxjV+{6M@B0WLGnVJi)F0g9(D!{Q*X|M%|H4K8= z{1}v~99X;v(Lg!;{;=0#2^7l}T}g(V8-nn6xbX2)Ms1~!*q(q%0F}hWI#itkSpIiI zIFxq?Ufn9e*F7plZH^Q?7j`~;ajn_|P7VSW$1WEjm6l*L0}m;sVX9g`Pr!~XioZe| zk!TME^Ky&)ir*ml&|dJwbu+Gb|0>z7jzNa03w7a$LGxCMqxaT-Nu+N?-(^rkKST#J zk9vZ|oKQsugzEwvFrjd#d+hS24}BHAAqP8;=56$F!aa{L6q^o8)#Eqp+w#ZzdfFaS z_Qb3j#tlncym zGR$7f=gpR&F;}mmVm?gD2XZI)*d@c9C4+^4=#rc6&i|YstM24IqZiU!R9KFae?Y9GwC`? zOu*!IXkJ4*s3-z`-kZiK$a8vf38KE^6_=gfe2S?PU~#gDVdW zYcHk5F$KnGYYL}BC@fXSzJQfY?89^OBcfsi-b+AAU(T=g068O*dzAFmmYm4Qk08?? z7z)3S6?M`rH%!giXA*VCKaAoPuP z#RhF#DKJ22DVY&NvAry86iMLq;h#ZYxMn9ye~sZPoCw*R_a-R{jENB&$h=Ax z!!zu*MRxPQ7$lzCm+z9@`eZi|wom-d`B91$QvrHt(6SQ58VLd&X?I>C5DGZJj7Hlx z%XhgrBQVv^hlFgET~NP*n0S3+qzpd*6N~(g!m|eaFCGM?H;`Qn_@#X@NM^f5St|TO4*M*8d4GrT=*L((^oK3_#bxTG7*gH0H;k7mLMPNIo=GndZ^W? z4`BoFP@#y;fJmqYuP7V~;qp6c!*_xP`IaL;g!M?c&C%b0Sw;3(GJFlxiZwM-!ayZS z;<-@LwKN4qd$pJGh=9+4aK2F0uv2nwMJ!VV5SnX)rL3|7dJ;|z4Vefc;hJZS-z=)L zMB$Zub*0}XydsQ_N)`KyP%Gj>I^cR{ZA<|yLU~ZuOgyHYlUl{(5J%{1%F9}T~ zb|eN*)vc>+n@0o7yq0zvBMMce>O0zVCbFi%T(JtR96F$x5CswZhn&6F$qwK!qF5NR z$hrpa(`H)#{aU$&X)#uLd6giZLW-fo$#*pc-GMv5e-A+4`3#Y;^n+1qGt*rdX7>5DShEh4vG8DB77b?mgI*>d< zd|2k8ufe;u(V5J(< zs3#FsdO^FspSti+_%eThmKE@manb<${W6Ngj0oBr5He>DWsg3AqHwVND&`P4Ga&Ft zxwKW}=M@UqiPzQL;1LaF;?OK}qU@|){`5@y@@Ey#YNG%oCNj#ck6`X=HNBZ*zZRf_ z{kh?39nQd}6^O_RQj~aQ|0(F$@&8%)$eJ zN?_A(d%4_ji3vh{6W@tpu?H}GEN+cA?%C(RN53H0CU`=q`Y+(!7&J7B4-w8mFZ{~S z_R43s#oyecKcVjaH^C|fq4&DOZz6U^k=X-!0vtlT@QgVDMl#3{fWisD3f@F>C?%x_ zkP9Cxy}_sTK65B^73}t%c|8;{-0eV?YK^Z~93E&4=4Os92+l+Zjzbv)qzWn}Jsf9o zd9VXqHWq2!iuDlMf+LbbXgC4s*ut;|DtOFAN9eyb_VtoG>2gSf(D2W82){&=7(L$@ zdy9SGnPXRI-=_`scp;7!j_ttXLgU!wg$>7UZ?!l0>ol6cFebSI40d~6Mw|-W+Y7LaL=7_H5`N+aeh7|r5r2ysN|gG7tIxyD zgSk168X&}1=+qk8X$>>?91a#jojp0@e2S10rI9nu-Y$y%&MhCuS*`NGsh0H=^AKOC#2A zBNxa+B*sz52UBkJ>DnN~hS_b5@>1u~b$P+XW)Ts+$2`;CB$h2Wg9j!TN`+66!Ow#e z>(#RHU>nWj{_dZ`745k;h_qJ)Svkm^KL3i>PRNJ5x#t^yzqm&}+`|vwF}d{aaFqKU zfB5=8xi5U?_xs7p_V0wx_VT+w_3fYiKjE`|{OnzyyXWu2XSedRcYpbTFNDu-<7Yp; z=c8W@pWW_1`{mvL8a}&&pS|by*L*P9m))@Ot(P( z{n<}n7H{$e^Zwf&`J-@xWE$nC zU)%V{$}H?Z`}^Ni=Wu@b^^c8(Q<`}4v!8h6wf+;Ir5}9Ld*0zc@j3ayZ+-t~{U<&H zfBsYd?Nj~}pKl-fp9{A7PkeTLxOm5(^OL>4+JE?4kKF1%@%i@4Lo@sRCqB_%J3YCk z^h*mbyA0T!c-gfd{ne)m@8e%T@r73D%R$3U@4oDpafTYo`zZ-s$x#-f@W%EEe?t~> zg;X2MTR~uL8yNI78NCUIbkIR6Jdy62d7UyB-a>!H=HWZ&SumpckI>gaOE4cRo%X12 zh!5~wy-$3L7NoRItD*L~jsA#!c<*lg8T<^b9~=cdQ^yki3}<(N3xEFhgm?GSv#@iN z8RGl=s^}K*KzvX7HUJQ`Bw&ouK^;Qx3x6<3K}qnUKutP>VJE?E?k~QY=$$AC2o49H zB%Z6zCjN{v7+#+KOh5?GBC<=LgucBF=h`gwOOmkbW%nX1gZJSd(xmn()IU(jomX#y zTw0LQJn47cgRbp`zCsG^D=ot#n*5j1!V$;JAc#bNF5-abiO<}CgM7q75 zjL}T{i%)MSFMa!dXFJd5sJGni`yKQU8w3Y;-9is1kO!m16g?%?8@iB{Z_t!BQKWOr z#3BfNBwQTvLOX4vfcHELkm0e7BCJAy{l0ssb7jLG!NsTzpz_Bm>U zOS1i0EJ~L%PfD-%f4&hvPn0&6-h`jWuDnE;up)^Gn^rOtR$n4aSee9xFRWrFth+>* zuqufOYnL(;mR}-F=u2Y4_?66r%q7Bv)k#cvb{jJR=g7)6%75b7VNDVfesIa9H5}F^ zF=1jkGhx*wq6zDgnDDzk6Z$R@Cah0l!r(I2gq4>F6E-99T z!lpzfY~tZ?)g{7&%}GpfuV5xDyhNC=C5Z_GmlzYaCNbe(7F=4IuuU)_8cw+2^WchB zqjY6L`?|}SN0+1hs)Y9ImG-Ok_G1WvlX&>MzAL!q5>ccZbRL~} zg)-W1OlbcxrF};d6W@3arThC0`dWkUMrX(iZ ze2FC_Zcbvt{tc`N+b$7J7)WBmH@7eooJ)iW*(4_XqCXril{NNY5)=N$Pe@#UiD<$Q zGoe%V`m>vr?DaL52v4YB1+{%068i7ETww_oK85$8gxXmwiU3O6@$1dtG!qh0*aD4Q7<7%25FO3W020?LP5_W(SuLG6V()TcZv_0 zql##hap3Mt>=U6Kngif%d*L}09#B!x+T+*`fm5h(+>(Dijkvmpc)p7|CbVO#FzxJY z&Xk7Gqcw`#{**nS^z|!>Vne5YXC&}Lo#7%brp9keaoVW-gElInNK*7!7Vc2R8^^A2 zTkR#dl8gF=6t+f1bwp_ppXQ4~1)kW%vl~x9-af+mMscku3QHZ=IfA2$og>vct}Dzt zCvg`a4uLu8HBn!3K1yoZmr8fy6Q$$$2eg;&!cXGXJ@|>w-^)J^@Q*|M;|Tw_Py9HB zGS|`r__cHl|9~DUbeMyl-Dj)iNh0S^aZDWC-NaQT&S7lfq$V~LYM>lo6q1L z#5xTP9PuMC$0;tPXN~>NDbysy!({PVn7VQN|~AU_9Syjpw2mo|Lbj1JCux ztK;JOw2q8T?7^76%NkSMwHo0lCDrG^bZ3W~%W#sSqTy~4TL$S`xp1@^yvJ01$eOC9 zF{&s_J_l7!cw-uEs>h9KvlBCScc$T2tZ7&lqk)p#bI_1GjH-Y2mbd+mxOmQW&cf*6 z*iX6)j<)}va4XZ|4?ZvQFwSAXSv+(fu{d*Vz&U|U72>GQ2U_AqoWGMecrMBpnUi0# z=H&7iCn-}t2PgL(aB;n~gH6vk&XkTN#R)&BvAsE0tYK0*h=VAq6*BVSO~(DF4-W5) z>boTjruJ*r)UJq8ODXX=s9o**M8RAYr9*3F4FACz!&Na1DPKJYhQp_nJy-)m969ix z968!3NFpMYj^8EiU>6&x zz-_mW+e_z(8)fR}!0k>ys^VW)JmB1iL;tX2bDZX?;d&j18weXdf#a*3(_(uG;uPZK zrkLM6FGwtl*BaAX@*@=sVwRoK^K(#sz~5Kz?84FN+LSziGuvEZgy)>XA#pfw%((-{ zOc(PNx=d{6fV2CS-Fu>9>;^#Q!;cvAAv$+ZUVaYh?+K{iJqPtCvB03?)|_2?ocDUIipNFuuEnEgfshb}truehQ6bB>s z^4Q3wdWbn_-yo!j15N~$N9*E1nkY@lT^QFd8{--sT~v`V2ZqZiXw5rDBeRh5oN@Wn zdE!FVA9LU`O!r2^Z{6?QPp5SFSDllx(`pg>7;$v#fD?pun5U=d(h<@d9KnO2c!Y*7 zz+>9~ah|kO(Z?LLA7R?}`2mJgbsSxU;}{)((vztKVn^D@VYh%X7cRrKDrV97s5Vm7 z#~fTZ!(6y^Kb=w>S_E;756-XPLp{ih=v;v>fH+^n#etUO5;VPBp;DydWuq$5iw`h& z`sT?UDhHW^J9jd7ZkvreJSr4UBu1I$1&QgsYM%5`<;NWKW|`jG_lIL%3FQilss=Hl zf;N1YX}W2iG*KbP95mg`G~I#hg%W@f#5iJppdeVH%#7Y-dTyU5Jyer12R%mxJ$rB2 zFR`a1go%m?P7a8xRB%K>%ggT+bmELA1ej)xkaZ0z^Wn%m`9NhEbMWCF=EJTyU4mll zS;skII5?F|lN(E9VPeD4FOi9BzQCC3bMvH{>M-V@`WREa8v)!1h0&C-ppe~Har~At zv7f_6ecZM)R<6dfcU^_d{1}b$!#1PNlUh(6fLt@xX3W8-tD8}AcjBb{G zOv7Y1X((ky#2J@w&z||eX&A>A<51(MYc2?g$A_bOZ1N)0_k5JT()ZzSQ~R3?@a?w#-4z)g=*drpRzfgm)vEZXMSxGFcXhl>K%NklAl!TK{K5|Joy5tX* zgi}YJQc1WwO@%DPs$)lgFXfhs7gL}X%L;MgY#if^MaGwa0c*L ztB#X->1Z6(R*55FMG+LLoG3C^x*z}erd>gvKmK9kkNc1kxW*8FRzNJh7eA6JuKG(K z=+IL7P^X4p?9?DQy;5CLM~zgpiShdb0P6|6+p99F4>02gSNe}#aqM#3o-S&*K8KGp z8oy_Zh7aPmLl9rK1kqN82_y3*0jZ;8`fWwC^2`*Y-~wHM-?8L=Neb{^ne7*EsO%UT8Bi~H~h|7?iAGWHfEjlS!Q zanwfNHMStW4XHDyt`s0T4m;aXw=o!XE^c!2-&xVSun8eYbt9r0h7#XR)QVU;90-8b6(Tn>H1*&%DN<79)HBA3f?z;h@-D@qDq#wiu@Y!h;El zwWCd{PZfVlcvr8qlzTfs48I^epF>UgeM1l8pxnmLM4?2NtXGDDMAnc$y&d;wjv<_A zJ9Hd}^5SZpleiP6G31{Py=xFB{#8bCO%X!5-pm8_wU_&*z-I|LG==RdQE=h}9o)f0 zVbYGt-I<1vcb0H+>seg5aLSi_n=ACG@q#7Km8r4CD$;3c?7Gcd zf2uz2R*FxNW<%U!I*e*~Vh@(hhm7e>E1L}&oHy;`l?7g6np4eXqHpE6GOkIxSH%;NawN6oQ7A!l}c!ouWU}{Ab2&ORG%R zW%Lm)P|k)ZD}K{LeO!Ot7&T3=zA8Xml+~d>n=M2#J~mnLBWCx~<+QT!w>gP3?}IBI zct_LX$FM4R0>wb;927iMB^(&)bpoKt4jA7{SSY?;dNXPNTj-y+;-3e8{QEZhgTcpC zta+C?W338;?zjj*#i6Y{SIILOL20#VeFmv(TrFJ8?#_nDsQQ!ScQ3MJjxsYWumvG) z!gp8+yB&zwccdt;C%`f)+-yZDT}t@UHRE-JW#KnCCtEpMV`5RD}>0?zROH z*9Vh9;$tCaDz-{m_mNG$oU8?z~`j@;&VhJ-F z04&=x#!N{o+ufmTv%9kXJ$l(zE$b8IUv86)5T%U96}k?bGR9TYf#bFydaeU^hB~l& zKQ^SCCzCx*>!<2eCCHWL9o*DY#wE*Wi$upGmU>>0SSzNC*_2i*?vz@w8*6qVGfQM< zL1vIr&1XY0J0<~E>gv%nMp{#kCv8FWTs@pnJy2|Sk}m2l&z3uwyE_Z|hm8qND`-aw zdQY|@5l&1htkR|Vc4N#mX}-l4M9-y}38je*I>ULoTHD`O9`3i}e%6$Z2Bzm@SB&i&c&~>^%~vZ}2ueFE~vgD$}{U zvq1mMnBcSmRR-xku4NGj!~S~p91d=1sM1`mOY`f-m}%1dsx64PG%Z4*GMdUYgccwq z7C&QKo<&#$$Hp0_pRFt9(w-)#x)!CgRNX161DuuJSe#tF zX1e7P|~ny_AK3nDHoi+NH`wLI1> zKu9cZon2+DE%oprZ_+DQYvhi*ywi@7==mx=s6>y<R=W7e{v{TN3I&X<%!&!*Jvc9tY`1a;`=>g7Niy5)tMY)Dss^Zrm>WC z-?7B1^e-DDrpe|@wjkti{w)@7w`YLOqT)b^kn#gUc8Ej9LZ=;jvFQHYn7p*2+maD= z1koY_fuA~_lBR-h8{?!&?VoKy^jvCJ3vb!;E5B*{iDQXz2n7{4NA2qzeOZE;RXtj% zw69^G+4HNGsTw4LYebF-Rm+YsW||zYwgu61IW9i#PNQ}`DzM-oOXfafB3MgD%TuYGI9k4j1x{2N3GFPH31gDd3T9nqOu;EDaEiz% zp>nEZjEyFvaa#~Qm(liv1)OUf3k!%jtIB7Z#OpQFyuea?qcPEGrI^X&1lDjDl`w&r z$t2bhu_hEzz0MdtO{{HO5Iq;`RsM-Iv~ZXs>N9&+7Uf5b2~8`?t24gD$laec^0VMr zLS@x27$c?$@q@M?dM?C1Bx71-cpbDysuY&;ie3V(ScnyhFnBq3Drjb zZp&`D!TZ~`AmS3Uh|kCn53koPKu9d+2=Um)eK+1efu+2-ss?A1!!??~@fEREMTb7D zHM@JLHP{r%xMfw`6s<{ELkt8<0)6X1-?4;6$~j{UH5q@8Er_1Wc++sc)IxNoFb(d| zfjBtoPFpv2>ckR!#+bOY65O0|1$NmucFLekSg}kSBcusz(iTL|1-9y;VxvXXM+r_* ztc}IOoHenCMj~Sz+iS3=XAbKvg^#|N0MrN>=C1ItK*n@@j>&9fI z71oB#DB%@uSz){sIrZsf@SicpMw8R0Z9(*0PD>7<)T`QRMuTkOQo4F19vM9*cgHoVT_V7XYM`oyR-653fV>(}&ZO|dS6ldJPZ#28S1 z?Bk?JXpKHf))?cWNobWVh@MMm=P=H+t!4AHTN8oIMh*2!#YvCC)F-2bqfyBjyvGu~ z-IxVwN7_v|>^7i*G7td`6sl%7IV=QKqXTPoN$)epQIqs;TM#{$^uFW8i6RHq#Niss zEw{lz&b&&@)0GH8>1Hi;jp4d?*51_%R zvV7=YY(ex~JXcYWhju54V@-p5qfoHuoH}$kDyrGLve<4&5ZjwCyX^AI=sz6%elI2y z{5Zfr4)Kp8;z!zXcD0E5gd3`Sl*Mq1oLILyspMmO0)Dfjr46-fZ9$}#rL|k}ViKnB z8M6z48N?}8YOSUt3ik&bT6|zTE>0*mS4Ibh2QIMJyJj#YFQVzpo7IB9L7i8lt<`6$sXXk{{m7~TKX^MA9 zfavHjb@WngYx<-cbh=s-GcOk1**da3%f{5Fm8bNVY9W$YA4$cmFG}*5 zipE%JG8wZ4A&o)K7KB_tv1ZI`0o5bF?fM7BnYF=QnZvCzvc9;ah^)3JD)_Z&CfzHn zS3hFRyR>?BLxwNQ@G;MNggISLBrs2!Z4xS@e#jU-O~Kx33qmT`9HOs5L^w-hZq}YyuJvE{X1GoRSCcHY`SdZiI3f@GlkUK?x7TKQ~ z^CGRtwqt*`k26o=E=|^qGtRaXI4kCVNs{^h6JzW&N&S&62st``-xh>4|Ew>)H2>B% z;+oUAN1MVd$$_q@RhX+YE7itzy;>Pwo53g`Y%%`F#=JURu7^JY6Q&&6wK}PGZ=Eq> znm(--AUclx?#IMdpF?>#9ZwuYDk24vS}RN7He*854(m0UCh(yMd4P{Hh?gb};=RVW zXiVQ_3qlU!L6%#$qh1?M@&O?ZU6oj@!w_pH)FyXfIXz}fSXw!4%mgc_2xbvsB?P)& zY>bd5tcPqt#D!&HE~UlgacTiVV$mzF?AkEOO~C*%WN>6VI%0G7W=;A*W3H#wq-(=? zH@rw;cLlnk(N(>zgo4@E7$c@>)T;%EjyAXJ%j(;dgQ&@K4&pUpz2OYEnpG+QxYHr= zjp4d%GR=4rJ2TB13JdfD#(YaF(AzS~nbaiHz*6vf%Ju0Jt~QZJmR^vj7>{L1mi`4} zlr>Sm#}ZNz6#UC~XsSfK~L4=)V-iVJ^Mik0V^zRZgFRbzgp zRm7pls*b1$jS4RrI@VsSK9*3r{fEYgYU=kDTM$zH=9o2X1;6i%$9JQm@&c!#E8cIY z0Syrs7PS{aIY!ibw}ioJuxNd+ocdd_zu%{g3T{-|LVe(fuBg2TX;aKmLT&c~V|+Dj z_)fR9!NQVAW5ii_3lLH#Uu&D(A}nw~@5+l?dvW!_YGtxoZqa$9SeVXc(@IYwGsOz} zB4dFk+bJS8vCQHEKIQ9(JeT(_*9JPPCBRGE4HX+=356CvWsHp`s2>*~E~2#? zQf3p}J0OmaZtO?;qdZ-yPEh1Cc34d$z-Ih5i|sdz8I@LSLx`(~vm>r6V0w@P3CQVq z_RbpIAb+`Dr21K7R5h9YiY*8^_UW0Ew*`%7C8amBN6uce31Cd~qb z#G*%D!{&2SRW()WoEj}*dq&*T>(q-?&)LwOm7nHV!_&j*+A4n8s*hi|wp)`_BX+eh zMw;eqvjx#}nQb{yty8uh3Ar#?57UGjX(AI-=WZ;u!^Q-rH5gkn6Tpy{>M;xzu_aVk z9WX{o6WfbyLG)Z~*Boip;ZEVi1XXO)&KY=q_46^|&DEJjSTZIytq8Bpj4`(A;KRkI zxXp^ORRoz(H8XCEm?p@)Er`^DwD#A}l7o(#OdQ0GftdH2Zm~ST3oa_aP~0#0j=WS2 zQUv0)xz9=I$ro5>UT4hLv^sM(Lu+ul1zrq)<_oX!=y;U~Td;JGuHff9Y-LT-8LMq$ zVl+K_UVylW%Z<(FkQF*{^8T~uf@Aj`+>lYMM6GwnUM$5A8WWyYikNbd@tLR;aeOh| zQ;$?omhn@Dd}1-q`;BqZgz+=BAmpI`X_jZV*9jZWPB)soMn@_iw{6o}AS$xtE-bGv z8xxjRUK=xw5Hnck0JDg&5`60~86%_#>$hw{^jugspRS|y2lWO%_6Zk*bf`|*;VkIOOQ*5v; zKu9clw3rf?W*xl$$ncq4cJaN$FrG0RLB?O}!iqGou~*9|zE=yIM%?->yZFp2!c4Id z3Fp}DG)6~Lm>X?D#6@KxZK*JvKCu8HvAESXjNs?TR?U_l>zu!__E2v=GZtR5T_f5P(`BztN|)t~zp827_X-df(W6^4 z>@>u2ow$QsL|Y>)ZR^cE-d|}q)Vzc;3Z;G~~pmf%Gm`<4-ra(Im`O71E5*WH@&N?~-=Lw4y;0wmAN~-|( zkfZ0*ik0ycZCC-V!L|q}2GI)d-lsLTdR7N_g6H>}#&~O5^6R!Bdafn?r$kJRYT!lg zw39x>;%n(&W7+?2V+N#^{mx94D9BRPe1lRcousT(H>^#HdH;hkikg`J&K5*m%ofg; z^w)U)wg4fqcw7+DvF_K}uUdQ5tH65_$5)-eR`qgBtrFT*jm(+XsDhNIVX>F79$4I=DL8gM^gjEcta=WId90ryH< z5OU^ZvCnJfNzS-g}9kt)urfoY@%#VAby8bw>60KrY zGLDjU+O!q1UZvNC(UspZmUgoG6QzmKmA52CSH5WcRZY`BFF;(x*?*s`j>MdQe+5?{ zVYS4kOwzX3Q+3?l;MS*|S25uK7nX_*gD zqURF2kt8GpgkdBclKU&PV5aTk7+;u5aVAWBc1-&c%ktI6#HW?z4k1e+N(?lS<}L=< z(+I>!Wb74#nNUUe3S$H{0l&-^M9&4h10oFeWGEI>h?;Ux{%yZ8|0nfZEaDf8$xkcd ze#PSv(N5p0vanVB6&WWK7{13CLruo-vIWs|8Se`!MX|3QW%N|q>-0mo)q2xKMi-_I z2Rqgwa<@F)KpV1JUOl$oz!C<_|BJ?~Nh|-oVO^=DjjlRm(!|iGC`v#Y&SeB?>Xe&s zT-WD~vDI|pbG9IQt_#~vcwSTZMF*>s6!yfWYi!0ZM7^ZhISmvHF%hJmHKsZ!sluDZY zIkFg52`DtjB1!7FPB;i-)EIY7V@7O2^ju>G4q+eSq{ufNKkJOus}qhZPResfi)CzR z!AU6%tSUyuSrSp@Fng8t;5EjKNUI0gOx~v?TP6X-{1vt!dM@&z1Malf_}WX~PQgFy(1FB}mr5C;Z)e5ZJJP<(V*h|KGt!HFl&B%! zibxUbq&j6A#BXKFHYi3x9q9>|Cca>drY83H*n;S}*l!Q!22K3J`${YSTO(kk9?S)V z72$V`*^^cg=mIKs*`f+TcxBURM4!I5|BJ@>Y8vr*TM%)LuuS(c<2fy50YYN&IoqU% zpLAS(ag&bgaNrkJ8`Io&!fO_)`DoCm^v*EZ*tfMi3kjkyG1>T2Ny)|)#$VNRYpDQn z5tEH8kzcG=gH2SC{nXJW*1D`QiOIuVV{Cg>27ar=B%IC@Z$Y@p7!8fnJ8VJ7@pC;3 ztJ@jBP1qn^tibu9E$?Ro$3Cj-?M|IoOlORVODm?$IGT>JqwVgY3$E0hEJ`}r;*>E$ zn!t|Rf=Dee>v9OyGEF2{rgl;XmeiCnRcR#^TRSgGO5Qb%zpjbpNdcmx#p+mlVw(?N zcA#2q!tZx$(Z!4MoH_e;W7^Vkc6nwr#6huBiDwDD#TW~X!*8+$Ar=4iwjgAY6U%vC z{zi}NBg z5>lyajSW3k?0%!0Hda3_mZ zp&{5EC=zZs;{b=NFbT@YOvsboYK)>L=smU|QVZJJ>D+Yqf>+NKDIYFQ=&M%~4l?W1 ziDmeNF?DHWxEWU@_}GcK9g^RSog%S>r%Mtl2?wgo4;0JvrN%5wE7SdFt8c3lzqBIF>@xL)fUQ?RCv;}c7l_tKcYu-v@4Um;)!tL?-dY;N9ZOmIpzw_{1T#Yt=5cNl+NWB1!^LC8_`W|mmD z*S?Fze#cnyI(W$3|FkjkX}Q0IcQh)=>BULO>0dHNKoh`!vjx#}0c@n~SUE5`VL&EQ z>CvGNi{~$lNlPo9O(G{2;Fb_9TAY-#{$IxUXwv$cEr^~=>vV7(5BX5#;(4!JEL5xc zFkaZ;>#lGVd%(76Rd_yr{AF|%*M0D;Bdf0Jj(e`nQ|<48zvf@)12;`_B-EA$U#^AY z)B}zv<)I?r6gzocdU%VIP8C~jOp2ynOKd^(T)j3vTx{T2dSp z(7TOEOK%LO0^G7Wfm_TUUwkZKX*Fbwk0z}FTM%(+SvaxM4`zqS0))h3($=c^e(>6h z>j&?|EmO1&(s>B??_h`L373xO^%?_CRXMQNElxz8htkJG@3?F%xnyM|!V|sYPbYcD zMdPn(DmNxTSa`?Q$-*u7;k3nit?YuqBH7^LlI~`~jh)urxf>7vA26mpCCA%aGX;sE zFx$Wo(HCGCuE>`rdC$)oqoj%BmA2xrO&M+>pDcFKlas^E6Vchab2pa8`;19XFAa)& z#V~|f28OCMlH~DTW27{ByxSIpw1q#(BJK8SX6>*u>NT-L+i`11X~SYgC6>_6qWW!P zlG2K59geU)4pJgjV7btv;`5Dk;RlJXH6ct79b=R-`^WexoOzJbsV|# z2=d5c?&Iz_^5Wyz)9##Tm7BP35mzWir?zB$T-_b#Tbl;kH$%4s6>zC#(RVqd zBD`3Ws8EzHLFFzpMp9F`f1AI`^+?zl_KoUT)5%c=p*RMiYGxtc&Z6r#=8B0~pl@as zoD>NqMj;G6K>BkZ~VN7CLiEYcA zXB>Ia8o^PKTtZUv0b`sr$sM%?(R0c5A1aQG;Zh)+1LN~Y$nXS`I9?rlUK>o{M-bxx*7x z#3hn1sz_*OvAxxpq_kpN$CttpPC@ahDxrkD;EXXYnuOk93!>)|%F08ykk+l%n#GCY zQ+%}u;*@mJp?5*XD5E3M@LiVd$BkK$Rs= zAGQS%m%4=;EInxsNmzi8SmbQ|Ge7>c?&8LuoI@U}r|F!)X5E`R?DV-X?DQ>TfhFrE z(VG}{`t78!(>IO3s%hFc1PF_;lWm-14JZF7m*EO7M=gWi%!7a9HQiazXbi?ZQR0YG zQS#wp|COi2GnOSqGu9cSqH%q-EeJWXRtgYZ-%7cL?;$8VM?AOLLKR$0JX$l0XTLE) zDfJ)X;d=zi*|7kl(DPlEl)1gl7!^%Cdu>6a7LRq%_R0gTVp){<^5_{*a(z)z&DxWt zHeyU?TB%)`8TIkR`8+hHlmwidK9?osavw8BN|WD<1&E7i)K;Bv#SwQ&7A@AsoPU`y zk!d;K2VaJ8@%bKMc9J#wFUFW??0(u7gd8pxSYq9d&0cdh=bsa+6jnK>>(w0Y2(HIM z>vMHx$-T>%*tC+nHq!{ORYnV)ZslXE*u5)~EZ>TtXdO2R~oFk7RS~`>5hxO-w7;`wS{%k^IHi+yoZkjif5GeW`V|+BF z`Jw=E5zX!O4;33N>^y#owz?qHgNqP7Zy+X^s7%tm!Xo;=#w^!IHh^+Fq?9 zuJ>;+B)lnRpx_biJGL;%f?sKjpC;KYwjkn?wJ^WZg0o4m03osHl?Cq~E{|6c z#(q*^`)-rGJf8?Ub<`(i)MS88@VW?+IWEvaK53sUqSR!tzJ- zEg^t>+!#eo+wK=2E~4qbf#SjkhtHgILMDi_;G>gr)b^)*hvoL9F;mjY?M4wl&bjqw zHpE@Xue142Jm{=qjG-pB^R^)5@GP+8yKVlj>mXmbS1~Hv6#ZGQZ!so0tz5TvlB?Wm zs7~pLXQ92x7&}d-ueSx!bD3^Ah@(evwy^K49W7RhIFLH;#SZW9+>IspF=GPLN^mRg zT=6j!ll3?-%rb_`nk(_Nw2vAir3vmswjg>gxVz8NZ7QB~dKxEdqCA+c)oE5~A735< z6m`NP@rp7++{ZC7s{=kySgZnHHD*;>6}TtU5VU4%f>z{w@+fwrV};#3R6*1oizK{H zYiy+z9pDMetUolyT+@@U*n)`biG^DxJv*N9EkH;tdga+&eV9%QtxXG^q-Ej#hxSM} zAv$l&(U;Y2t<$UJ!ZjHbFA%Omr+{m=nBODa0#%(7^2&Y2cxlSCLV&o4j@zBe<^snZ zcVRy&)hRw;Ak4Z6zgvh;+y|d{q;Gp(kXW#Lj2W2Lj@*?|HY#KVomtSy`@^H&xez_y zdmkJSs?0Wt+X8Pf##WAsxFjrLL$neq3-xn+5hL%7=*15E})wjff=z&d%3;y%HI z;QZm3`=vLtSYBdGQChK3?VrFX@Zc3cYk5*}(!<86X!1EHKy)-?UDx~rer?h;U6)&( zs?g-YmnH0X4i;$ZnID%u?oE0quc7VI;|+)OLj13?uOQJn?V+3C#RkYq2Xjj`8sVbT_a9IFjm5Yqo*jhvVNHHX!(`BZQZ|Ml)tF;*G3S?=xmdTBTZ@!A?zJLrFVWwTj<0@WX&gzChT*#`tS=bzD6O!vBBujdvVn=GlN)K}@1ND!S(HhG z{Wpyf)r9%$wjktS|BNjNIoMgH{zDG-tL3uBbq*Bkd9ju6@U-VV1dld430)cQi~W0H zPu8u=w)e`@Ms>5l07I4SC=kV-J#X4W(GSp6j6y=q#lP7~@VA#U#J(KL+ znPNa|c8qCNYjHtpwxN=WJYl05?hK2_KFNw)YmB&NMXs_1A+5+(0ix@U=3s)FM9XqS zW@k9>im@9V&!#W4A{;elM%w9PFhLQbbvhzY>*ify3ZjxvIP2h$F{Ya2hiyUhT=D~u zDfWNDJ_L3V2mktF9)K&+DCV57>MkmGvsYQ_Wn)I9l{yZ$@F}77f(WtUD0vn!{0PvI zl%rjKEU`4CXpE*N@-bTwagkfh_tItH3C9A2#A1&1f$e6(V@GjaT9M8H2*kCY)vdva z<+DxCtHD)AWoILYZbQMOgdNM_tA1NlFS`nv)%Hh>g_%}uk7aO%jNpS*TYpodxEZ_c!e;02O}|aGWC^7QKV(dVrqpk>1<`YL+8OG^fiS?X9=_SB2+`m@R)tR) zvmmW1>`YJv^|Z{Sn#ASD5;BUPG)7Sq^v7*Md{+b=b5(q~N3BAVpgX+Bg8p-37R*P` zF$cw$yE>v1?$`QLV-z((|A{S#o(p>WBS*zh-j9$or_Qt?9+hyK7g)3_Grd|~ZqHm8 z7xNjS(gJB|q=RWrmFY75M*C&PxM?z7Yzw02GF>grFixy(#5Uh)tt_ow#^j_Oh-+~B z^*G{zbZkWIIK<`0mg}+^G{!`e&CRwT;7-l8`B)1O5{tjE%?cA1NZW6?xM}-+ zyp$>CJzT)$CrVD&ixX@zpN*hVLJMlz;}l1Z|9-!w){lg&45LC691 zw=CXnTfHq0W5Y5{enAZfjVaoq6!9(Eox8E{uDrfGOBT)Jz)|f}jA1sYx1doaFjR+B zk|o??jFcw0jkX|qF1TZditcz7m&z5N5`)eWm$rJ4UFg8@bV0?Q)zKzxi-9ddZF=BU z(#}NTRmL2eu0m$@xYwACX~*_)6j+CR5Js2z01XNFkYzs5o;&6P+vb1|=o#`MqEQKE z`fg)7G>zJC3nH#j7Rw{K!s5xo0))h(M{d|gj(X*=>>*QxIYyt}JM>{)d(xP}X?1N= zhQnaME!$ygPbk)@7~`Yq%z0Z7J(t$Oqh1v?z;&eIu#&=^A9b(Et0h`J;n?f*e!2ux zOsnkHorm0V%cJ8kXwWq<^;9d-nWifcSrgu3%(k?ea0o{S`gCIpuS&OATM^w{3xvCm z1l`$5qMOP96}lB`lTgp`CS&Y1y?MPYh@R`s1{&L>B8^<}e6g7=<9PI#A|!WV$$re3 zu(Xohn4ys^sxef|6j3Flu0CpvjwY%P*@8$dD*GkZ0T(w*z>6UFLD_2?9k-i1^)d&o-GN{7WnL?i(olbBjFBd^uLuwqamls%{z{Iv>0oD@m>#1d&{~=G z3vTF@Z@vaWrVt;R5@qrLEKgcXeP{km|5sZOa-{rUmRq;iQhwDi9P&K*E>Ypc8(B6x zdM2Boq?oYLMUzlRbiFYu+IYCm7DUfQvz%|_(8Z!Qut<&@6OqmT)} zV5B%62^sdMj8V~)WXcvqTs#&MmP*2j9}5r?i&5Jco1gL9xCmv???o;2&X>(RJJVm< zg&bF5duca*JU-L0q}AH1T7A-M)iH}#JY0NNKhH6kH!r{J^2_MI0D;m!he^GU7z-*{ z?TF6Aq~3Rul6t>j{8dfEJ}5wRWNr7W%C9=&Va`J|nlc5mUr{`JS03+QHfBLe#<#D| zj47CAJ6;{UD#?}lk}+DEWPZyQgdBDMorT+NSL&*RxaFl<#?fvR;&lA6a+1eN)Uleq zD~s^k#)PI9A>H8;Vj7d7^oLg^1*reo7%feN|6~iI=OWyC#>=&kyF}FjD|Xb>1s1M7 zOFtH#b7ObbFPhx6Kwr&n36n_ls~vt|&%{Oi`iS zI`(3z9X2K}?U36Ncu9mGZLkgT3!SA^Nq4OuFvdue*^6vJq?VbrKe0*N@mY4Kaa}A< z63lru6t+}ishv)pSY#z*>e7mAb7q2WAQjkURqParC4@l7jSf<1`!29_e?+VcxV*hz7jUs8H{exO*g3wQL&>Afp6h6BN}pp`$Z>C z)^L)k&`GL|5;qsPs>P9B7cRfed*!GD(jAbjy8Db(Agxh4oXPu?3tbg?KZSBp6(;UI zaQUwIxWAcY$`u_>*q*lA7=2BHhXja@wyXOQuWN)xK>U+fu~Ax`Y!*%e>(n|4KmLg*-JWF6pXD8t>bb+lZpCs?{oH1&egucfXgtRdyS;*b?F83Wk zVVXEOtJuU;H12^p^#NzBSjT2#ZLE7ZGD5GRv4p{bf5wg8zZc#!=x>Uo~y&PM~V~xjS3#+x*>NW_ruNEn??L%#^k0I zv6C4id}GqYosl8F5ospmJ>O}JnZ15gS_%p^V zNGsu+G7Wht6d7)9;7S@IvQ8+C{IoHanyi1x7DQau7M`AT7J0(A03os9m8S&=i3KOx zEI>#s-fx>uAS|$La?_%VnnWEwg~MScicg6-kXLGS7zgE5aoAjwc2d$x?u45w6tS{9 zPF05FHwzVQ(oJoVaaLNgBsdCdWq)_pU&N5aY-=Aro-P4G!C{GxpqRHn0X0CC0hix=z!&#JvJACmI zEzWTu`$Q}kliY=wUpJ;WE%P^K8o(?YTuBvR7S7ZVK+=+{YK)L3g0d|LIYf%KAmkj$ ziZHJ^a*ly&t1?^9HnDQ2ij}~8If({!mVT@}KVi(Jw92y$mX&eL1~>)>KdB}*!K?pK zW1KYo`4L+XQh$0SIat_I3(+^v3C_H7_+b2qchTP3xgSgJ*NjO_FFDv;#!(*m;^U}{ z{RAKVSB-JfB=;#>5IvV%{}~V0Da#G8$KfSnlag`_%-L$00{>A#rhkp)`nSdmNGsQ! zs9*^w5F2E%^#~NGCyO?G3KTIXq}u<=7)4FYe{Kt+=VHG3LE48U2d8gW{XvQpPZ^5{ z&UD8lZS*D!d)>|+tsL4nXIeyu9Kb#u!7UtFl?+AP2?@H@#z<=7UTF&=wYaTa-s{db ztB5D#l+B!W7^BmF_UNHlx-~_AmhElEG^ZWN4yM)sXI;RJ@w__0CS)!48e^sjbe90p zapls8E`;s}2DJOTCLFpb*WIeW8&UTn;V^b&#}Pxy)qlf*ZaRzyNcPV_^@ zxM?yvYYRdSy3@8Gq!Z1W(n}}Wdg!k`f#pr5*_uGeyn%gKM-N5SD50Gd=QYM`Nvk;P zG7~;dbkHv<)1!kqVOz(mjd9TwLov_g? z)?yBCypa`T!A-sLX;XVXBDsXaNv}7?NgLSL*@Eb~dK*f1QQ<7Gs8_74EJK4jw}p8)_@Fpa=tRijM#aC<@n!Ng?x9y7=E@jH)L7*V}?f zEq?2D+8&%_Qf}obEH_)QM%)dTJbJAluoisGm@jFyU@x7B!gL`;5`;7~(X(bG*?~S? z5k6{+t)>Vc5+FLR2D={Gx%Vsrs&w2}e*-68p&qqbN9Asqf~MiVGf0a%k@1hqeU55| zdj8;8?tf^^$+U8RQ3e@RqBzS0W9kLLVTM~+13wKMwGLPw#ixS4q$TTDj8WH=;D6YH zkk;ULY(dC%5v$^VtaVX;Y2RX$>8w-_1CP22(I(cWzME-L#IIiQ!0;o{H^dXQqY24r z)s7Be3ePXkmfQ=fueVw^B`XBVZs{(NOB;Fb!A~4+aWDTkz&{T0k0auTrbSC_K}ap) zb*%|Md@Q6Eag~z=2#LiNw&^Ou0&?GcaZBB9Tgxh-o&-xApAGpLNQ!}!A9X={8*sm zEO&UdGbTk2s*@BP*EoTct4tG|Ac@6hN^T7hc zeapoi?rRTUz$ShSZrnHLdFP!yd!u9fhHz}Z%b2iaog)HcW82pTS)ck7#^2Hu>PH2L zjw8DJiHT()CnFqeE6;iG{;Dx?DH+*bp78={&S*USl<{XZo_^96gdC(FXR&lU8L>NH zzO!q;qilYlv$?CShI4wlS-?f$US+a~(<&%)7mG*R0AO+cr7=^|igR};&g?Gu`{Lf> zY^#Pdeg#q4njk70AxabbpBba4iT&%gAbKwLJ43PW-jB`H=gDcA4sIC8yG>WPFy4h) zxhfo*&Zhv+3lb~Bs)6n#FEj($zEdi~ZtSEcGP6WxwmMbG5}9JU4#~_$$ka4qxiOxa zMl7)f(Q}QsCDe#LFa)(SHa7}Apj!#(8db4rwT>;Iq$<=BHP+^@v+Q>nGbF7MxJAl- zPqsk>vBa^7l?dW}tv*4bMYsHe#>i;`zu6W2vy!odk~NSBoXb5MH~yBUP*5VLn+$)WH08mi-rv8Io4^U6|`XZ;YHK@Xy(T zhzs0eqLy<#PY@O$Bo?kMA^u#y?YlhJ-x{6khr_vkdA2(%4I*%^xqgZ9w={)XC_r4q zx&G!;*h}NqX)`v0*u{zPs@rhx#KAR1j(A0Q+%|fX&B0D%1|^#VO&INgOjXj6B|7L7 zQaTGEqyv8y8(E6n>E6JN#)xT>%h-aDgV15&ck%|T6Z>;JXc1#ScXyWN31f=WO4Guh zd%zeOO@c?6{hc->cRvie-Q5XZ<9;r2owzt3>`XB~?m6;~@#v6C^8(AJV$6=Tve}+- zF{T2f#m0*|A+79h)5q6&V{|m>6l_7r@#V3AJB=^f>h8?wPH{M7aIu&pE*3+PlzOpP zWQ3)9g9Z6UW3tljy-IYb{aTH6274$y{%Xxwo5R1Vz|ecbt%Va`>-0F1u+5X>~J)M3mK43 zw~iuHcSqW3%g0W zNxCq%(=cL;pC%oJaih~VJx9! zB_smpavI)d{4GtP-Yh_LbQ-!op%{hVBCAiMH`yTkqA`C`%3{7g!$*t}(**Ymwjksf z{GcreX$e?;=4A=qI3FxfPI>ir*%I6lwFKuwOYlu&!jiR*2%O6je8c!#nnL}p0P&yH z6095Q&gwyv#e6NnYGcGS!L76fAuYi&TM*I`u=>o)68x2|68k>EHM3cQ?#IF7h1Gj^ zMJ>T}XbFxPvp3li5P@@9g8PiWr76^5TM$yA4hRtc|MngxjM>0Rf`pl-+%kcTmViY^8RcldXwSY{kXN=qFHY zJL)!Rhm$i^DCP&ey#tcm>--9e)qC4wmD}ruH)K5sd zvx06>xG(lrg~fcdC%1^*2)Y7%z!+am0bZ~LA&2pMSckfuT}(I~EwY+RXlE&Y*_foX zQcOBMO&gV8GXA_Kl;5%i(Q~2f9xjh#n*=T^;Ejo5BcO=kVzWFc>VSi@*RWZ!CM+!; zMsGD}+W=s({);hF(u#F=CcGwuH#PG1MqJvCbe^Cpi{spgC}E26Y(gK4|Hl|TP3-^M z7DUg*9zTgIG7#g9EUs&A>CSpd^H|&3F0V&`*lUPa8U zr;eYE&XTF$V(A?)CO_?9>-P^1rUOR={_^ZDfj=KdQY|OsJzivtlqS}@Y(ex~tmdZ( zMFyey>n!LoV}_&^w8bGr+Ca`3W2Z^{du>7VT;h8Vh{LA53OT^2*lgeoDz}1js3vM2 zj_()a_@p=0tX97E(ziDfPx0TK8pMte0L%R~#%xI|_dOXta>}dtm8cDzMCDd+8kL}n z$9F~0m2LRPh3nJltBvu~B>(@&I}Fh3md3VLvf8pF%ZGffj5enKk3A;c&;(@I#_ zsL)`TyiF~KAmLkZ1iEs)*4$_f+W7Rv zVRcxw$<+#M+7aeRpMMTpSJGW9lZtRyKjQ8J_C)sUJ&}0#q*r$_#lr}9hqiWF-35wp z(_JL{C9%Q0?&3Nr%e1?=S}MX}bwFG@;vF*BVDg|}g?RMip>lo1e4q`LyGu|0djumj zN0=Fri1n(%E;idSWT(oBpf}N?jWunz@_W>F`^s)y9P|iQN=KG5TVc|33`s>etSV8@ zu|g+MNCw>=-A2zRk?pIrozvf!aq;MfM0 zAt6+oZ{E>h0-OZAa&@c@$-3c$c5K3IHc}zj&`#g%YBGLlVK@r=7FmabCRi$}!`o$^AgMQH9WWv15oycOLy6!EIoh zWIG|64;P9fonpri3S}Mp^90HTQW4IfEa~^E^+pJj;PIeVgmxMEznEycK81kxv(2*w zv=jg-{b2M${kmh?%T|J5x=|`3i-|KZL|UXynAkT9M5J1vKZrm?ss*|w2}Gn?p#Pvi zMC1y(>M?c&-E1_1(K{1Y(7W07B)`5Z1E+EYy^H-VQmtPp6_KKx)FOVnT|xhxT@04g zrt1p&KDJ^6@q45qvWVra)$7$-yVe}R)E-yQS4PRX`zyoYU?bSz-2jUnNOwJ~j&l1O zjbH-Zqx9$&#T6b1gH{`^wVLhv?xbCRn_Y_eHAEFfrd{jE?4y4OpNiO}KBV7bf0f|> zh8A%GeMpl87_D->W)x?dHbeh}6NJZYnVG3KDcH%glav?uxf^tvioPeFoEHFp7F!Kc z(vM1Er48*7gf-LCYk#+1HwCqpw>M}t%Ez?(-#FZIg+0!ZxN(dH#UsIRrU^_k-$kf> z?9#MsEt3}&aG3Vcu_HdJ3oAV4OKi=F1$WyL%c)q@Z42_{CqVH(rkG7k07~! zXIo}VZc$-4(##J#H0xk>8fEpbY;_2$Z)*`JZlGMZ=VotbXKX?^O@)pBat#8gg6}P? z+yclCq9%MM6~=pr>a0s#EjZQ{Ds4#F+7Vw-Z|_GYD1Tenu|yL(@#PJ(XRwtd08f*O zNE_SZq$1K`7OT+=46_0esTQ~h7Klj8;;YitU9@Al`o!*mYzL2~Q5cuJO&(-T+6&p~ z%C#`b{%Q%t;p}| zREcD^LZV8XZh-7#e~Yw(Jz7N9j;#A7TJc!2J`IS87i60dsaj1GV1G&7AXYn3)ezEI zl`=C0&WqTY-O4T>OBRzC7SeFPF!O`^u3&|p0;X0(_XBb+1J&4i5pGAM+@wpjwL8OR zu~7!cCulM1(#O#{+!&P)TwU8|`A!`Yi-@7rS6=f%O$2>tn3HzT9EzpQIS3 z$C$5VD@ABcN=2kS>`M^%OmBW&wI93+Jcwz%&D$48GTfsh86MP;481=hq?S6a=3i(nj{E5btFx zNh-v)@7FHQ|eF z9Z602oK%GKn&9i2P)uvWo}k&RYy4C81IoO> z3V#4yqhe2I$g9|z5OU{8MK~w7O_K|O-1c(N)X`UzE0WiO%T6K8abQ!xoL0BO;z+H0 zYdgEgJ{>_we1Kg@woUg6Bp&*Moi_T3joC?ehmE8*>|kq2YQuF>5zcGF6LoDEg4*Ei zXw;jkK2*w(0aVS`gJ$RIDlH-iQG}@q^kKi+nyG}x%B_s|=!{Cn`ZCHcM%(&w1J;)z zznCcmADT$V;w&wMcu>&pavfzrs?RW6X;OVkQW4Ip5BBWCYP64*vuc&s2w`bQ)5uQs zFhYI>+gMx3(J(NaF1=yYSc?@y>j>TKkFC zgyTQ6^&uR;CKchF(8|ANDy3GB7?MG!UngF=G4@6`-i zp$w#b+NG{$_m>vndL`JVS7xbgaB76MseQXfsBFWTe{3760FPskv0J)*5S_2BIkD$!*Tm;*o2NKmy9qLY>Nu*Kws?Je;}bSx z)-Za1a<*1v%Zo+=! zChRwK1u-iH^Ie4hzu84$3qLv*7}W5=k`#Zc&nI@F>&!3uRyhILs~@+X@hM1L|l9P4iRJv`ZK`|3s#xu_AMZ zf#*_jVXqLsB3j)#7Q=HB7V-T{y8D(S3(PeYs=UYeIgmQo9m`Cxwl^BTco{ z38zhPoS2DHJ^Ha^%lY)nXJ%2N?4D}N`Be6|NIg4Qi|D%LJmcf^oWqdk4FWqJj7rzs z?jgTolV8iWGr!4`GM$`TPJXkv3*TJ*~$4YiX|( zHRkh9Y-7G^S0#iCC#|MB@|p^>l-C*SHg^k55CD(XlB7A`x3R*-lz z88vhCQ%M7V7MnzVWmIL6Y2f-AW$gJE!QxU7=&pso56Pi!ir?*UUg+2_%JBU^Do{|}@h(m~;MSb=8x zz-B&lmEbJjf`+O)&Yc692AlT)0{wfoQMN!A6rcx*v{HL7W2K>v@G8(m^8yn64O<<8 z>0?q6?lJ8;HU{2YxY4Gz+_L@Z{G106(|@pyvd0vrS}BimrIpc|asm;3m#q%L^c|@P z=a|-XPCRzPRHIRboMFnzejvIPnQ2`%FCfObSIo>>gG@yx3#zrn()#k*e%QFaXE88^NHn^}*1>N+hma1kp z!kmCKo7wshS{tPzoYT4%fV2%G++pdoXP7u zZE08op2jXN+Zu4K3NaOVJ$KlfOn*{){m5K!a|d%(ozdnRO*lhQLjcB+cUj$_D4kd9JVpGDCZR5b~$Jh25IvW>L>B1&7~*;h+dx}f%L*#jZ-<7-cxiUPr&DlmVkg_})nZ&aolCXA?T%?_ad`&*=De_M;_x_LG8dnJo^!v%>3Tz-O>zU3NTGl5CFQJjQMcjBPVBJtsvxxdd)G#oEEGh*UdL^rx|PAVvQ;sfe^W&(b1h{4n8y>$FUg@Nwxy+ zM3EW34j@M0u4n5+;I5U5a1M9&{)Te2gnfDNy~%EEWPe0PPhuNm%V-X)hYf8Ai<{Wr zCM=#P6=BUnyp{j>ywPMb`70KGo2|cX@t&)FX zui36vgGMH9Lgx=yq_1ULXIrFCfFZ<>wIHSX8uoWdslG}oBCX9Ymx@Sdfyj1Rvp^iY z1R_!`aP}e)k(R}`q;n{x1Ll#wlZw0 z3Fw#D-y+rd^HLEh!iTho8ShTE?1_C-U{wqbs&L<;2)B}&>SzylC~vN*o8C=z@(l;! z`aN}E@;UcRks#+>ul~f)|W_#`S5H`u(Y_s#5 zBq?H8cEaszt(|Ibc%e~iM_SzgTL)6~JES7gR(BoJo9XlM1+nv5S3tQ>Ae}1PEL%DY z3$YVhPc)-!1qhm9sR-w2mhOQQag}&XZ-MQA_+)L^1=te|nhmJ?V+iThYy)i}Ei0%9 zEJ{Ot7^9+xDGe*2A!$UfU~550y-X^?IjO|}rwRjj6nLNrxu$AiC3D!)?IEP}0NXfQ zN=pg=Ce_YQv?Gk}XX`*1-6s{{oYC1k^nA<1077OH%KU~zzRWhomdI=%qUL@o(hs;` z)5h`z_NNJm&q_r&2XT75vu`p;|BS`|DBA$r;y(lTC}9ynOa2k|S4qkLR4T%G$*2(R%(#hD&f4za&Zh!mwFoD=D?EjQWmcVzH#wh6Wj&V->P z-Wnu@|5Em6N#Wlq72&+_SH#Vs*&c?(u*wIt>8bTI?6jDJNY5t`(0kZs+5$Q!X(Szb z`btk9^d!jcWh+9E-6Iv@9NF3X8xX#%Vwnv`ke#{^5D&3G zO+Y*-72zDjoJ5K6O_>&b8p`|E_rl~NJTiEP+)tOb7bAzb}# zH^ZTJ1@6*A3at$g5DLOk55u1uD$^&p`!j|NQ0?b~~5+5yr6H1i~ zEH(sAD^o*A|2oK4j6i;-RD^TL+c1|ijzn;Gu!c9Po5eDu2g2yn*@o$Hybp>a|wJ+ja)zVdZ!iyU1)S$93|`p{^r?#iYl02U}TEMgB}G!g&>$2dN|VaOl?91q#~R{Ijhs@!|a&NpAf~5*@oDn zI2(Kv(-b7MY5X_)%Y?#zNkurPu&aOf#=U#=>ZAz`113taWr^1oA$~G!sZMw!!FcG6 zKy58~eQK?HbOZ*|QeE9joq&|cLG9Yi;lvEdMDEM3akaSFQ3%R@wW5boWjoBRV%t^3 zW!Su(@RjYpwp~A_O!rH5`7>3r!!pgAf{v5Ij*e2StT3%== z9o0V3)UckxR)fI$9jOTCu$Jy>HsRD1BEEUxU7JLc+PlYO)%`I<^+L9Rwy2gBARz^6 z=*JprZWY?Bp2yaLka~_(gmY5o^+TTdj@{mk)p9M}`c?5PfS*at?iD2XcDCWR1kW!7 zHNR7Hzf*ISwoGdtp-4|E|CFr}q4~e0BAnA)+Yia(;p9ctY{(Z9j6pHL7McpdsFvF> zFT%ZT6R7oD$n=wJ^KF^-6#~c*lj!fq`YU&Ky!TM2^cccmhnV}e`)u!U5C3x&hpfeqe{3onEN25e3c-s8r0r5u=z$>s%w z_g1#iw(wTL?q{sE-|&k*YV6k={;1ZNFnlvx7sBw5r6Qa&Jg+Om4LVX+;DxQCNzv{V zv#kLADjMI|gdbb1H>}IC z#mW^KEY^QSi(zjYE%p{^54B~EtCR+#qyQrXHj%C=oC0H-QwI-nIy zKz*Fz(7tpt`}>5;MyUvEF5;W|bCNK$`=N3MnU+F+MI=vU+hdDlZW?-a4D})Hlv^N1@ds+f_l2tm!mlWKCz`aH40}*4NF2rUnb)Zxz_i+}#>1xcI@ELHTy26iAIe zDlOWFPLHF@wWK1_9_CgpqH8P=Y0ikJ9;$FX*w+{iYUSJ1 zDqU4MRgz{U$$bLxex7ZXE#8HNdZL%cto0(jz(Z^W2$~0_BAlZ+zdv>_3I@R|E9e$06(-{3pq;SX0*ZyISSVRcE&4MzhsDF5(63kCRGKkcx1Q|aBwce4w?mTI3BRli)O4fQUzQUvTPr6QbzJ$+ZSrEY>t|BPTh$Tq+h%o%Vu z4mb5_$-kfdRZ{Zrm5Oj)@_pB<1)feCr1yvP-T}s-i*}5H%5Vs0!zLN~*O1)T*#%%r zZe3v*Er`cNv_KDf(bh<80qHEi!q$qA{i0NabFx<+2#+=(06mOyD)i}4xuyR*I3pGz zJ9GmsH3H^%TQDjjFZS3prnA$Mg#1t1?rQ3L6?CbQojS5^WT)~yMLQuifgi+`BeJu* zXX>w{JkuSqUr0qbuM)ebQ6)Bj!y{ChQrHU0*N{C`Od1#?&(w)@T+VnUpy=V z(w(efYfZY7RZ&`XNK!KZF)9g{ED-3JNZgyeW4l38igNn9xCi;~DwyvaZ?2wB1 z|FLdV*@b0WH%=*(OPlB{ag_Z*0(e*|!a3k&`|x&3yuUpbG=eH**Uox!_IM7P?5o)( z+G1H=i0+|)j(V@VLr2n6zk;m>f%P(}2mPK4@br6QbD^&xaY*nmKJDma!3uLx&9@uk42x?SeGNcd59QP>i`2;4>uTl8X_ z(LF!HR*iuEsZ_-OJkYCmxLSLwsnBNH`>tevkl1n#v`5zgTNS_JMrQV|Z}Mo!769D)-G z6CC~tnS5SrK05DA)1~;dr^BKBGd7#f#PJ_H`{LO9_UqCT@ZihZb9nUC;0T3YzbF6k zd6Cy|q@H%KKEoSo*C5$%Hotbq-#cyM_%hknvjqj%jfF%%Wq-4uC==C&bliSOS{CWS z#)DE3k9mbUYp0q5PrpJf)N+E+tH9w~dAeVNUhUW6Kil!2o%qjy{wLy)SD`j9JU^;X zk$Sueg)h0NP-^Os6E6P@sqtwII!!9#F|R>8W~c@|QCb3dHR#RfUl7%xNIhN+!k1jt zpsjRJyH09+T7#~Zig?Ux&}}nRgPtcXfxH@Y^4zuYRTfl_SA)k8uZ;6 zszKkEmOx$&dU*4?s0Kyq@oEshqRv>U4u8Wt$(LGs4cOvW+aI&S9%a*5=EkBAi!%)78>k?M0bP(?27o9c%+^m$Q(t zQ!Qte2BhS#V}F&D{MAws&P#s7!Ldrz_|zT3ohnuI=zZ+EE!!9$RIE$4P2?^Pr? z%q|F9f_|YHTaw&5RB;ZHO)tFz29|WmmuZ-X=2BkJ$~qVdBue>g8vccS&V0vvl*>J5Fc&>1wLb7OgOT9U9Le3o5IwiV&Z zv?6SV%lXPom2{xttK%hQruM@~%$y=N#HZPMk{aRB}c& z#Hz729@I!RWD{*v3w67T*P7W^37 za@&Gm3O9@}Q+q~3x}2@Dl_14GDix9Tb;D8-X^)GQU|K!yfYxHhtIMHjMTXb_5uwIH zNKZ7Ry48w`AEDZkS=HQp0;}ntu-VvF(*x6qBLQKcRIxywh27PR;+gLv(X+01Gzp%Z_I-&n*s2lGr%6Tp&jWoiyC`g%ZkMa0KKp|N z-+HMC=lB@+9*j21cn{m>A$AeiVw=`|i6^nuB5-e#if|71EHzNx7!>P+Wyo7<@H2lx zM90{M*djVx4~nC)CQ%Wly9#agmkEW2RD^R1i+6^N@;EGm$HV4^I6Hy2$>h=PAtdvM zY~yUnEG|Gi-B`Ogk$|6bf&TSu6$ql&N<}zF1gCpCyp*@uq|)(s1o1Jp3AP~Ash`%t z&$+Vq5%yNgfH&)wYM%X<|O_p!^;w&hOOQ~i9lW`yz@sR-vy zSRYgu>neL3T>a5uRgRWhBVOQP<}vh`1czgDGHd@D(%r)@09(3vz8zbD0ala+5Dq%Z zou-{)l?4%&bmh34tra0VAQj=9?0I`LKG51lRQtPn$<+;$s@*F{bc}7dEz$EKZ>H(i zoNA6i9yCK-zfdnFu!4CfG5d4=? zy=vw@883%NO~})dgzS&Ai^-P#mEc#0c1FQKm7VJPUSy~GuaTX8XPy*oCTZWVX6s36 z#4DsCoY#oO`@ug;#lMFw2dEb6rh|6*Hb&xZ41=R8)CH8KET$2 zFuGqV!a1XJ2O_Vc04^U)sEd9F@zx2XscK}-Qm1$piG7W2sx7gVh1dg1>#DBu^-e4L zWwt5=+!v%GoP(RcSLH!4>af|1<~@LjX5Hv&tpW+9RcZoLE7IvbDlOFX=K3R25ze`+ z9%z6oV_0idCe)sI$!iv&xGy=SVZLV$4=p}o2F!@lo>>!kY z);9)8@$F(OL-1{vig1o^&R!TB_6EmbEYtPa#6^BZJQcP%ws;_?JLpplj&;XTW`CUE z7?O%`j^m0$aP==<80>{3)Mk|avgGZ;xSFYRvsxzX(2M1GJ4~e0(`uO;Qwc*W zH{MmkNk|75`3k`gu%;Yn1hpd&{Uz5Aeg@@YWqBXF2yH9N4LP%<*d?v$XNn;HL07CH zT>{ClOuO~>u$3lN=U%A@=T&FuLlwCm)J(y!dj~hvffXuhg|WA@yYB7qQ)rWeeG~(+DKU-l^VXl#i za9&{+4YV78z5yOvwenay_FpshP`f;XI7ir~+2ULb8**AVSle{!Mp|^pR)GK-l!|Z; zX!hYoFgB)IE<|t1<^jn5h)5>c#@Hg6Q#cxF15T;A5&d7n{x)IpBB==HEH2(dB8{j6 z;|-q9YE=x!THXlkjNpD;xzWtb8~Lvz&v&y6#Fpp91<)0C;=ywjPSM~Tr5r!hafJ%q4+#x~9t*5ZOe z2nOLU;Xr@PR)HY;Z>b39i2A@&9A>Go7o(h6D`ByvlC~cjX*ZgsU}A&U-yUv5Jd!P$ zdw%w>A;xp|xLR=ZfwKl$pdDKy3t*;+7WjcSzy|{&DyjF)GPY6#>|&`1=U}%2*knn8 z10m%vw`Fj~a39nDG^&q_dQ7XbYuf+r9WATn>T#d=0Z?}h#(~sE3 z*>YL}X&RJvdP}lXJHqG(Y#j)r|0@;YoYA7~L9<*`8HPvHq!4CR-oYpDH0KIkosVT`Cpf9NpYq#d@t? zoq%f~x8*b|`ZMBr7TX|OJo5@Ldq_0OZ%ntazfOoeO)A1Uk$F2{w-{q+=Js?szax_u zuuZaMGQXg9#4vzz*B*U| zHpUjxoW$uFCV)yC!s2`EZxa^(E*0UN#d#fhgH-cEBpxJI7!2VW&v@8qg(Y+LXZH$n zTX>VJY5Vzwj^sdUL_>T&xXlfQuvZ&tPH4_!YeZX z>J9MZ$2cPD`dk1$u@jK93u3^-mi9UmuTTc^zMNe&w(azi#7iW#%}-3jXy1?=C^ik^ zxPxi5F>hrnNbql#ig1p9c@m##M_uL1g4`r=i#8eedJsWAoo%Eo$Q5anredOH)Osne zr?T}Ryq+u-;hfhc;7`)1cU*Vwzy|&$aD$-{hZ;-V)iaYFnFwV3Tz0|OGTvH%!?M^i zy`$2B8Z3ho@Wisj4L#>}*zIf$3H{roBAnA--Gg@C%*f(-}ew;UhcewzMgC;l^_|A}NdhrYa{ zV3eZ5JbLVXo+GtJpT2zt>qoecOGP;6z7RZQblPd%S*un~4)gOLL3V$_Hq4gYBIOmML#pYH zS+&sIqx?T&Ye49{K`O#Io%!kAK)6bzuD)gN`Q<%;Wd4?Ilr5S09e4KNN|DlvPImr^ z{dt1rqf!wLvGk2@h2_cQ+5NDkGgOAXSBUB3nH^!~H>B}hZOiDqGmXT{lPjM-Sg(|t z6IJ-9gV~ zS(F|gE0QL=0=Rg4q^z;kCcHCP`GQ3i-SFx2MV6Tvha1M4Q z92VgHlNc_xOt|pSuC%g?KGoYN{6~<}oovHwIW5A7CRxo0ofoh*Aaw4Kif~RR)A#LB14zd(XW3=;cnvAu z!!7_@ihY=sFzzz5BcR`-%X}MKDFXJbQW06OoM~O8MGdBhSi0*6)Z{`SBGqE877>hI z1(V?0kN1sU1OLJ%{B`(Gj{^s#MSE~`-Kn6=J5D!d>oBL@jPKvq<%hn}2fF++`k`(= z=&AjI!!T3!wp_YR#g%N8mBTh%!ZVw)a<-?}Szx9M^}DI^C+e{zERNL55V_MFL`E0E z=dp0V%|@JGbyW#Xo(XOVBlSitsD{T!){w5|TkLO<8u<+^qAQBN(QYiHDCX_2sBnbp zYO`9t02Fh1m-9Oo?Bkv^GgD$xu#@u(V@fCO7^8IZK_^nyv)G>}W&NlWSK96#L0mHp zTw=hSyDY#OGP-Z9xLwap#qU#Rl4Qy2ix?NHc&e7#!}%&{d8Ip?FPDmN zSZ#5K^8$5SOV8cZwIDS&-mSdH)yzOmpS8aTBp)%S1GX<=uk-h8<87g?g_G(MoI}I0 zq`EAm#suyAu0wpmZB~6gskA49``@s2B3;qPq#~R%Jr@y%3g7`aT?nFh3>s!8U+omn zBEf%Wn`%pNC2WK3XSLXA|{u0D4E%2tJd`?gesb8x**5sV?e*Mo>`_5oLGE8cO# z6WDqXUZ+b%IOnxupi!@S`}Q1ESB5%{iqsyO*<<#65{YeQn`zs~&Vk${^{QX5Kwxw@ z95N4!Xy3Sztq4K3K`O#IvdnfTLYw&$q9?Npz!qj^yAx^Joe&*lD@DNWmx^!>cA>uE z46~N*xwrBk!Pa*h+b~;Ti||e}1Rd?2Y3nFk145@I72%xD0+o*hE@d?VkoKE`PSflm zbDuyqZ)BTg%Vr@=AY;AIofSGs+9Un}TLFURby5+|(VT@7e|0IcoSEmFKOv02W*cG) zB1{iS|C0S>LgB+w5zZ+%IN<&lwz0OP_y^qohph`?_f4q?=j`%NuZ;Y*acwQ+A=df&H?v@Y^4a; zKB)-jVE0AwKBKVTY7GWSQ6P|V1CGABgx=kdU8Z%oI+*j38JCXLj+_C&IMFD3H(?5`6d$E6~i6It-oumxuXbvSr!#Fu_e zD7jA{myfc|vgNX{FcG$3_h0K3U-PAC{(`LlLGuBr2UPBAip0ttj9?LOEoAL=vYRay9#(qeYW$SZCs3P8&_<4~XL?wh^{Co>0K?J-@L$k^Nm#{x?WPI4^(QH|gY85E`_ZNuQAY z5jiy2#@KSejtg_X=Ci1?zfD+Fq#~TNSQqE9h&?l!^~!jB?FB-(f)i&H?B49i81Es$ z*RqSimf-q$Et>jgpbfgC(>D0A4H21ipZ7IvwFul-Nkuq^yXY`P6!*x|#n^i4@(e=z z5Zg3cXp0N_-uTpOoIhu)Kmff@D#AIS_5J4hW`kF&AH_4Pz#FSqCLp%A&g50jBtGQ4 zh$z3oE(BYY>)}3cU9HmM)sPQH-~m_Qr$)ey-<%u0UuCOB@P0`u!a3e`hF^R(6`OYu zvO$K`L0H~img!vW-$S@3-|T8$zuxq9C&}2Fu?_xZbQbw*DVfxn@t0B&&f#9XJBjw% z(${+6P7utm!{#N7NTMLw#`}4f1MQ?*6c||I0t_Dp|E3JhgXnPZtxMvCJdn$5?2GV?QepYi@^$TBfEfXJMzm5 z5EUX_72<^^mH#`kFmYPQZsgO7a6MZ|QW17aML4er{cxW}2jzi5&r5gAVY3pw3E}~~ z+4ZuZStDjZ9#)MSyU1*-#`YxK57^vsZUY;kXmdQ?ci5as<47yX5w^Odl8i`2IIkpg z`y8)S=cUI9EsV~xP&88nKDGhGe6lKpi;WKt@^IgypS zj*Tg&Z-pdE7pSfv#8Gz5HaXS9NbCJ$$@mauy-TNlFa-BJ+_ z*+mzg3cca!(byzt^#)@6ing0vj+);Y@agG;kZSjKGvrg=1D%WOILy<-(sE5ML5;p0 z?h#;!rtMGlq6J?qJ?R(O6I(n1}iY43elx2Kl)h9#um zIfJbk>32?(if~TZ-(4$(FuN~>kkmt8SX2K^g@1s^ayu2_HV_U=ko%)t%B1&TzKfhM zW*3F+h_V50KP9%{^|jO%WQ?}>UZq+Tz1 zyCBR5-04%3g}%Lec4gpNy@5y%vCXzcx&}69wBCLt(c6b5T%@;Ot>nz{p2Sv%fV@d6 z!a2wV{a!6R3ej*oR_f-oAomFbb&PG6EvSWszz4k`o^8kanzpevTLFTmAr;{q&3e5n zrZd2%VRV|hQ{5g+gw2Pa`+5}-0(P1*IZ*qicyVp=8e;rIb`jWOgfw$%BMh_HCM(^h z?o0=j4eG>68xV0xS5~iQD@D-0Rw}|d+J$?A#;}U#>FrOa4Q8{;e*}SjjBS`LFz`u_ zH0zwu(1!OBwg!aGhomB$(^b18pfSg^N*%hP^?3i>(9! z^$n>A=b+{${otXzesH$_d94@!h*(ZP>}p{!8`5?6?9)zVf11EJSt`OgjKc0XtR}{g zRPhaZ^I6^PjV!VaY@=;k(&{uAC~B=D9ZW%S9a|eh@dBv`=M>M26QBaUo14L~4pWg} zj7RIvJ)6ljU0=ygH1@O2w&l1cNtFux+DdN=kbBwc5Rf-YMK}jJe`j5tqe7VdqDq`q zY*i-A2}a%n*h9A1M%iLoP$(&_dF&vJ+DWXX0`P`wXf3MY|RMiyQCtVlb(}8)zr-9 zM}9?CA7-0l%W7^%Ao@WyPocB=53)Z_aJ*kC!aWXbS*nfY;mH1qIKIg?#~ueZ57kh* z;P^WG;{?Z7q$097IEN;Y7HI%v40unmD3UI zcyHJmsh7+s52J-7(($sV%*?_?6~$DMju*4PMXKHcE#k3^bewS#B$19UJC2R~a<;Mg zjhqy0PNd@;r@yW2&y%v=EESP9u#JdorXw9+oqA@f6F=zlS{R2~^}~=sIvkI)zr)%> z{{rVk;jyq$EJH|ObI6>gEQI}Zc2U{FzNW+TQ$_Srw)#50wd&(zTlGmW*s6c2On?h; zY->a{od-XattzP)PnL>sUNL6Chs#)n&VW3uAkSqNnQaAe;uCf|TU}B~Zj*{|UP-9a zm%*I=j0oStHpmvCjZfH{*k30^-Y6B}oXAveUIw439!6UKz&6&F7T+iA@7TH!c7H7u z;gH>l@Co}*ZMQq0upddwHSr0XcIv;&jKJ9QUw3lkSB9o@);G2_cxL>{{!LnRsbAT@ zNJTiT)#z8YKAmAgj*}jDhBjSdPA54pVo$Z|sg71)lNWZ(9U)$Jk6S}vMbzb_6UB4b zdXZjhnN);xzC7nYWBlR0ii~%#3&OT7PuFkoI<{tn^3_ri&M7l}{|wB`caifjyC`fq zPt$L(#8!-84x}QSW47`FG~imjfk?Xn@Oo0zuu! zHp>>2rQhH?*$NOeZ2<4Stqg1hyEb;Wzkcwo(M`C#52sqs?~;G@4!hBiQbK z$~Mdvn62O7kJuUzIzNz#a89SYL!d#Z`(sFH#nW7^G8le?OW8^gP>ZA@oP!ei4PMJO z$F}iI={I;4`_lx*6;ct-VL0>~EV7NZMJDkZd=^_9Lh%-<2uA_AR zfvo|d^LJ7a>ZhR+hurf3c0SC8L_jW(wjz*&iez{!J>vIf!#R#;<5zvCZ3FueVfI zu`#o~Oz|u>oCQyJHBCRab2N%{^#>DGqe4&TgLB!M5N>BnML6fS46ZtQJ0K2J0|F}S zDOcfAYIOP0WY*(3B2bbh2B2eDT{ygae-Ypg39Lns&Fv%HHL}2`E zXQn&Z9}&k_*v8o6m;=eNP#YD@0kk13zR3PIVevVs2E{wPu9QFW4FoIzN+&a8744ET?Owpi%Prqg^f!LeN3b zQ3y?`W;Hj}8&#Nz>TsmF0cRxwknEaUT&*a!sHM2J%8z%qRA9ZZr1DIFRggqRSv5uQ z*;Q=)2={ZOBAj#Y>$yIJI#4_^+^Dx}C9|d4zlMwl*acwQdi#2=8Uc4=0BO)W*h&$w z*GWY<2kYm7)ln{!)qhvI%y$v-D7z?Z5&LF^hVljg=3kClhqpt^M1D3 zwlE95VWQfk6TXkF4&CdOJS03ZwRhfsu@$-I3wK&(9g0}B0xVa72zD{;{BC+s}*nc-2lP)>%)y86HL0> zLx}7VwsE$|mK4S!?KG;9L_5Ohr)(VvqaR5{IA^r{5VWzua?nf?*?6#vUJC0&LuO0s z^&qlZ`3zS}lNEaN+|bfbv?RP%u=OCkmP$o9=hfHm9StVDRvmH~1|_}P+^*<7IcSsv zwOeo~m!AD=$Z|Wo0BqacI*7av7Wl0?_%Q_~>?b?xUk|d^vb7>)uab&zPIhe^=2i_Q zdiXQJCKcY;1+sn%xel?-x8>TGM959DKHE0fB3mhf^;uF8&ap1P8Irs-^wx?R36FLp zsLXV*Jsw1OFJ&8P3vWdMHZ4*ueWhibWRk8Y?qushc)dU>!a1)q54NjSMJl@k-uVOa zxR-5&EsrM@ATglQB6sKe9`<)h`M*sn!g={$oXNnAnY<1b%SYfGU{4q{YLJ(t38UXw zy;*M68=0un7ft#4TH|FT`4GD}Y)Nh;xwv&cuO`}4QTF&v7zq<=B2=m8#)E9#2<=Zu zML4IuTFqPP?WU&}yk5EH6&v-Ynv7P;B^@!}>?AFoN1{Jrn`}#TO+lr61f6}YGaQ2W zL}vo=hir8S#P3T*IET1wM~0c=IM^tMnI%Mz=MdWRXS!NJEH7jkDQ>7EfwhFK27$Fu zD#9VG$kXEjz0DF&Hesv6BlzGL$TQoW?Muk<8f`uC3_0nD=@bJ0yK^oZ`-2Qf%P!9! zUPc%ZG=VVbEULEQ&*D9 zr6L^GXLKdmrjKc&UBjk2flYSZboPR5(dj>ijYhqZ*%qFTAgmH?b|Kl0Iagwyv)D>? zBAZyLlOklT)PIbuB>h{1ttaW<>QWKT>%&EALksRlr8~)x57evGk75$|Y(be#p8GO# ze?7Y}Y`JgL8(+$rWN#U)fs^>7nBJXOLs-9-ts7ze8mS29tXJMtZ^8W{X!A`-0IQeR z<<>}igpg_9Q$36hRdUj42zyMGYbt;usInS zE~gE9KKt{etmjBYq)qB9En;-0Gcs&T_W0^ zKa(&a3&2OX4E}I>KWBcbYP2

|V#}s;6*y_}Jkq^| zZL%$0(H76s*y<37hovH%L%iY!m_Wm!V>48);riGyJNMK_R!K^-jj*qvLsyt>dKz*N z`W@^dvW32_FapzRIFbSjc|&}`Oe5C3~?HA!XoU8xA?m7&Kz zp3#zfJclsf$~Ms!CTqX%&1^LYtUs2Da0u(f?e~3LTc6$U8@&PMgT^heE*pNIkrrOE z;WzEf3zr+27vB7$lcG(-$g-K*G(>Tng^+E9pYct@zn4NuHx2(rD#Br-VCHn#yvZED ztaCcRi`d7_3S2EU>~lJRGEt9}&N&~I!b$l)A{F7B?}D6Fw+S-$2_$x&Ghz!1m1s8r zPJH9t0E%WcTLCg2t(1yzj%LXYHDxLfm5X}oLoNLVD`EBmXxFC@(G6_#Z2M6NVQlE9 z7Hy~>X+gW#N)Sxjr6QbTTG_cjr8lg0hT#~bzX68@*l0By(^L;5vx^(?8LsR-v# zmL9CbIbajAz!qC@I~Th0v9Qr9XY;;xe+&_QiEW@QqGg39Xb3wFsG%BcVhstY&$G24 zq#lxra87FW!Lq*f6CH+`Z72I9Qu!s@7+WfH3Qes|eCA4LXg_Cvo3QwaRD^RD7Z}%e zsv$&g1b4hP`lN>t($Q0woHOwuY+pil-k_^R(OUCbkJ4T_6ShOWb*HrVQG3$9&SmRF zm@b!!aL#m*@`{KTAKp;AR&2pRq}j~6JcGn`vQ4vXZHu*!L#$hmh&cUh6$qefq#~RH z+P@3$J%TsGkXI=m2`lB1dcBmOYIR0cxe+p$%d2685(Vix){nIA<|` zZ*Z(!ZC5*5w%PaQJ%CK!%{I!G$pSdT)>?J6E;`kD7yJ8!%R8hZoO4;BhQ(qXJP_g` z5qeb>rL7fa2FIRHBB{@@&9o(T4hD||J(J!K`np(8(v&{KR)iq?lvIRsWasQH*OcRw z^7d;fdg|_hr{ZeX$1-<;dOwQLe#SP`7TURmYNBb!VREb~q4s08CWP95OGP-RwyfV% zF=%uQ_@LMV7tOKA8P4nndpw7{&MCTDIV^{Z$vRGsisTMDstE3}js(^+wi*Q1VyOt{ zu+G_a4EjHe(OO4tP!gqb5w6>1<`KOgMP%2p4YhA#VXUcg+|cwoG$quoW@|#IZIg;{ zPHpk-TCvjB)Uc_kbByd(SGR|dREcezEvY4ia;#m{$Rh0sqkydgVe|~C2+N(Rk zJTm4_$m7L1hTJ`C)=9I}e;~B(br@lHJN~m1{~6H#*n&A5Z27a z<9SjM&T%Xl0ADVMrg1PFYlYRpu;FdqVva|-PavFkvdyw(vam3u^@4rjNG~7sB52;u zR)C=SQ>h4tXd<_zix0xlMR7z;^VA(heH;nf8{kFXuE70Ube#A0C+pkHg+>1BNcGdY zM6#|-laGITC8!RTGEuFQzjnI4#n%|WBrV&-t7-Hb;9!Aat)KVHGb4{ARM3SB(Pf2Z zT;zJQRG+DWgEQp>9wT3UW7f?rBSI7hJf0NkLd!y*uNM7z@H_7H-(z!{h& zg+`(soHg`dRAB2sI&e=a!a1Wwhs#X}72Sj#>m4dERm0mEKvsaxo^rCwGf3!0wrRHG z>*B)EST~iu3v}}#)isC< zs<92V#dU6>tu)0wlvGnc(v)<4N7$MWY9mq+&Z(_}pyI_gIMC&w)0Nn0U{gMg?CxTl zYs=0nloEXj!2Cw{O13ft-=tK8b9`6rgFVXzBoz&sZP;AW0dEX{LkNTeYxuCat+Utk zykIyeXLh8gCkny8pIuP4;IAyym8FoN6fITfbg>^2dVWIq9BpZ57wn^*q)ES*ttY7y z@0N;iUMKoHT`f1@rgoIe3J%O#>OeTCO?Z33cLDslJRJi|HUFS8TnBHa)<`Cz>I}%k z+VK^3k=fRce$!zSYKkAH#!@D$6JIbHdU$Pe;>YQCm`v)(7unj9I`TQG2OLr6v6s4sR-v- z7axKXtnk*ho_aO)1$<7l%%UA-7lJL? z^#vWi4z}me3Kdw!8t*V$ErPcs72zE3*+#EwE@d;nVf%Xp+Z0T? z#ZnQ@L9B|rx`#vXa))h&BCL177Y&YRF%7(lX3D1#*8OaAZDDz_-*=)ftXd3xqq0wL zQQpT^hTwarRD^SU1?mUT8Ub(cI;=ue4AcNF#+eAM-aw3BV4H1=@jUPxjrY-ekHzhJ;oQxtjhjL(c#;OPrF_3bq!6)KaMk=cLY1 z(+SAM8C1+h)A4s?v7K##ZEHDGPa{wV(oC*pf0h*fRZDQo)DPKO5K`Zlif~S9A%+RS z8|X>A7vms3{}Cj#eAv|#d{Go00B@rwnngvM?m{eKYe48Ml!|ap=iJQE7e4UBfojwneSX9&=&b*F;wW?n<^Q1l;9P5zfIay*@KTj{~!t%(_2@xCYq< z+TvOUE|li{yL-fkXR@^*q@FGn;ha>TT4cdNNO>F%BFDpcg{3Y=Zmg*5b@A;;lbro) zNb*JO0>ZQ@u zpGa>NjCf>CrxNj%BYeQc-5{05vg8M_rtiQJ&z2(J5~KJ?7qUQFCh3Kgxl$1hYb)Lf zT27|AP+Z=Da%nhoK-%j;tUG(yM%s2GE9i7rL4_MCpe5n8o2>`wT?V8goby^sr$rs< z3*e4neDS}tl}%c|g(Sz==G&6&%b7rRq$WrMLs6_%wo(M^s8ob=tlReEbSfDq)XmX& zjTfJMV;(r&Hal`MnPbUx1R?z6>_W1Ie`O(>rX}4kSV>NjFt?a)+Z|!CXnlA!TTfCS zULh6XygporSDZ)b`;Sq>rVm5BecaZAW z*rwZ3y`WHxb@yZ4qbpKMcR$vh0R1vsB?9ydQW068oVjMCMVb~6^Ti27q*{DWnzb%U z3%KD_m}|e|bYmd^v+2z^Vegh2t#9;!Zm)c(+YdU0$c2~|@QQ6l`ad1M5iT-E{tSD= z)=0f%c1WYwf?TYTi^?-|+@MUKDkM{FGkqc=!JIA?SMF1YhW3K5hyNkuqENpG+j-005;=@{D}TSzt++}iA~6Cw?%2aQj2HfwqKF z|L3VMxV@gO1tIlXsR-w!Ixeyqji%%8*jhfuHo=xf&kJrJVSkns{)eO@oEJXhqM8AR z@gBnaHoFLH;Z5s;+qc+i5xC!wif|5>-e5Br(w`C4=|@~m*KIDioyz_?A#$=*gmWU~ z3Y!6h{E9p_u+6b;Iu;k)*0DcMa9ki2;T*?Qch(F#Q$38Z_Op$(g~h+%wwJ97VRxfc zgmZSu1aEp5+*)h{ZF!{=ys0m^-OAR2kg7>VI46~Vd(CKD`Hx_WdL7#^TSB%M-0o&; zKzT}HMosmmps^VuIHP}WFAIBz}k2Ff+asgowU zGo8*RbAHG6vWIPwEr$7pA*EAC^1Yl8EW6pCCr}2YBAi2^eN}Yp$@F9E{um+}V;g9T zXc_I&Vhy8WP6wYVTMI&JR4T$bsbxFrwbAx)(CP?Al{YKs@f@-`&Nk7O)p8Y+1$9iX z2y~k%yqc{Bf%OWhh~FMqA7Gnk3rh__o2hT;1MCkHEcZ)A{Ptk^8rwt;mYno^UuJ)h zVEKYn#BUFlSyfjvYt>pVp{?anX_=xiT85R@TUF{TnQ=L+_(;dpeO zGid9&k4KR4qvUs35Ve+cF0q=e6=`rQr6Qb@?J-9%RwLv}Z?P2}{0TWN#a#r`0{ zvRx|Tw+BmwZ6XKDr4&n<{Xv3dNGjsD2g|G2CUUS`MzOq{{Xv4|rBV^ju}l$u&FILc zcosXe_pwd2#lsHO_8zt>1l+w+5zfJ-v2CJY?C}kHa~{$CF~s#Hwt=>|IHB4;&(?yF zdPpk5IVt;?Yes9ce+^0gl3f6{B&QRq?dNQ*2-%-VMK~v$7m3YanD+qE@@lRYS$3h? z&Sig}a9J)D;hal08k@l+`y=w$$u`Ee^-LYAt)KmE!r~gK2wM1dY6 z+q;K*!v{F=Gi7hO%72%wh zb>KE*Y`1<32mOC#n{P{U8sXl)%~pzF{gzaObF9;e(q@pJjv$2pgu1I4_{@fTJDsg3 zsSl@0ML4eyte|a11z^32#5b~w!M3?iFWlP(wqAtrI;jZfg!^_^A^4%r#vBL3Gs8Mo zAuU9$)y@Rewto%T9%L7QE!%Yk$mM|+r2ZJuo*Ra2Oe~17q~~Az*;)~@d!-_rlfC$0 zPz@p4b1C!&+byqFKZ5#qN>MK~w!?;8&rngw1!B!n&A~su)C^&Jmju!eRZsxnl`VZJe zVaxiWLOrs@*S4taSIxv03(&7)t42WIEfwJ$^wRA?s|eX1w2K0Swk-RD_y?0|_s0<5 zU$PCf#kZ^wDWqKx3=K&q{9(2hgwzM6BAk<2-J=0|eFv}Kxz0pp@jSBoKWvk2*+EE? z?hVav4wq=J`c1Yn1mV}EBAg>!(F36gujiA9?eSx-RyF7J!bXvu!d8SJJ4q_SIkKfY z>eaC}hM`uem*Sai#u>l+V+iX)wt=>7Y#BIhB^s*KN~wmVf9zvxK}el172%xJ6QB#s zKN&ZEK_2_qX4vvLs{s949Q~a(mObnb69l`ZBAg?br!qIh^-o=x95Z{hoZk^glWmeM zj`=zpL#&g!AUQ^%jIlpYpj4$IoI_b~5OZh7>3P(m$HbER1cLc}wpq4d78aVAIWy8r zFUBaE<7@>8npaCjI7c)0@JLwmN_7Z^4XvdU{)|xmf^Cp3l(~hYppjpyLojT$ zNXls|A7Fo+0C_+v!a0x?2P@^_kyd5GE0u?a!iLIVAB@4C5S$sBY`j%zVld%>e|@HFBflb=$KC2`?mV~9 z0(~F}2h~lxZ({4&9LNMzthB#^E(o$vrV!kGQSX?55S%x=;Y_^_f*)QCs4{#5ze8k-dk@# z>wx6GCY*Sv&h~#6&m*+guuZmwwg#XzLbXR8>m0%B(3!NXSFzP05MM48;T+=pq-Bi- zkPSG5YkX$Y%6kAY{W;qxTTBbmwv}o{xV(@3eZu8EQW4I%oO>{Y>+_|kZN+KPql4+R|ECXlh-fHWep8Pjn^VzQk6Afcv~ugmZAGAJ}`)gEduVb13~Y;`lY& z09zbq6dKj0uQebg|4a5)Ny-0QD#Cfm&+gyZzt^je!4jo>Tecg^{)iL`4Oc6rIfbAU zRQ*&N!op*Jo3J=nD#AI7&Ha_(dIMG#RXlrDD~+bkjMiTYRL`)%gLa}SsXm&8KW6-9 zBm$7>_3T2iZCRTOL1L9YuhmxR>}mj8S>;31Q%31uRRy5)^qp+=2=;!d2Q#uzP)xV` z$~r`YIeX~w91?mZ+eBMJ%L_rQW4hHB=}2Hrveh84ULqCY9M)`17p#gy^&=*s?2m}$ zy=-G_vCN5*{wCTG7Vl<%o3MD7RD^RDeX8Lo3b7j?ta8;UbOrjg7HmEYwQJDF)oYpV z&Hgpy_eFLA*z#Mao0T4q^yZ#k^LAL^rxp;hpJQu9$bLpD!a3R9ddH%pBvO`MyQ#7^ zx8R63tc1#ww;3(E$_+1Q47c%5rE&u zbRy`u45Gzcx#1^e06le72Bh-*jIB1QJU^C-a9(*f4aDs}sw*(Ij)Z!Eh3QVxq`aX< zy{gUz#xj*e@IF?CRZUlml+A@i?TCG+O&t|O*`!Vgz$OCy9JYD{`ZB2q=g`mAJw`GR z8aFpGzagw0Y*TDo?rdzii7o`hb?i?Q5LZh@I0rGOA2!2qK(5s5*`)>f6=4js&9Q|6 z%X%db0+@m1mbSa*A!r#@-aj9L*oHp}cN35S^7lSua zpZ^Gg`zhNnTX2iOks#5`Z`FO&jL`WJTLVJp2T~Ev=`6tk%3SB~+jGzy#=1U*j8?Q< zP0N>N_Fr(GQLp5LqhHEaf?!%C72zBc|7N8zKj*)WV6SBth;8FjA$qQ$L*G^G4-$x1 zNJTh@c*%Bsrxu1faFl}ua}zexf|}k?17`!A(ccsvZPjZJKlk;`+!QLCtwpR&1R%;H zyI5>dZYki+TJR?ZmpN^h4|ai{cXbTx!X{hOcKOY&c~_pr){l_CMJmEM`7OI^#Y$Vx zZhG7d!x|8G#bysIl7QszWEYDq`AZ7r*sfkTZ6m+Rctbzpmbxv!fUO`we}`0rbM*YK zcSd^dd)NhH3;k5+xi?)*yY9EKzep&)RVu@ygqdB0Z-TxI6TLDhAL9R zI<;UKgbi~ubOM~`Ur&y)rY{bg_JiyKv!#5ky0xP$_9KrbZE&(`)qxZud(FTK(eXd6 zAD>|BO6teQr6Qcyj~%fK#}K$kLlJ=I&3Ncl!k|%8OIme50DJcy-M`u4&xk~18I4uVLYE96_G{8DT1it)F7fN zmg1bU>dOQoQZ3HXA_TpR(gONX|5Q-s9jDKlweF7Ns+ZaXJ<-UT(aqQ|-Ph%ZzR?G| z{4)BXZa=7yv6I&yhTyW^B^Pf?V<|<$UbMb%dVS#C-YVDHVQHQA0EHyKjh1&)*lxgK zdM#`ntv8OC4mP8E;hR{ZZ)S7N?^0B;Or9CkiX-(#4K6<%A6Y|sjz4C9i}W0Ss6})w z|Gv>~0HozVZ+|7Ip}VaL^9v-*CZ6*<7VKZKjkPS;$@vAizE*4MDU;I42c1Y+f0X@s zQr3SV6_GZ!4Hpv!;Rdl*Yek&*aw1}5?=qPdlAjx8FC=yWyq#|e%j zQW4H^a0AR4w74%L%)8lzVGDEm(dq7D>qc0=QYykZ>udlzgJt$dWc5L|F}AFxj!yS} z_O}U(_ew=LXOR7oBbm`}?GEt&)mx&Si>-a|WU*o<&-_ z*{0g|gzV^a18h|YxE)dv&cUT&=nO{bpAkouZGbI~UeW1B*h6NTSRc;3NVN?gQ*Xv4uM$ zVe0N@t4G@6eNqw5v1cRE8A!7~BCap9jj_cwb(p#@u)j@Md{!#LIg1|Q=L{@8o!(r?&S7OE(HVrYKO&aZ6Rws^Q-`Tr$^JHBu|g`sISc!Ea|R{* z*O1>Xb^+KntLcQP+s@XCkiAwa!a3O)3@2xxpFz1;H_GfHw5=OX!_*D2)h3mvC>7zn z@(9Ar8I?rvK30a8vx~&GGR#Prx|g!mBhc@Zif|4+6N=6Nn)wZ3y@zdzEvzZS)ZNSe zGy!psRD^R7BoLi}g8YgwKF>DC7RJKDiAVdY*zsRSto`f) zv2AfP5T@=LwsHjcl~NJTf#=7dGoa=_g5W~7VYc9G!_*D3H6V1JDHY+IPS*f*2B5A_ zA)}YD&9i012vheWwh{!>^Q9u3V|t8&9leWPAhuvP6`F7vTBocw!`viE^Rl-#=~do$ zu(cz^|4b^vIq}Cdrrl@Q#bV2SW@6fXime|Z|4&j8&dG}+(iz>gNCI}{KV}z;E%_OW zY4_i31qu59l8SJS{xRz2m;J7*HIIr$x{3DOi`gF}5En>AIEOg>7<5Ksp1wG2*;lg* z%(i9Ed`P=(Y+XtHxJ)X-dHtA?0CYwbnGuOtO9FPW+13(AA?=>QR+v2%ZCxt?jE)hq;b7X zD#9VAxN#YA>x>>XFQnZ=+7gS9cKD!+rezV*?m=mJr!DIfQV|Z3VX?1@iK*O(D(6M7 zU~ZFBK8-`(FWBbVwlpt^K&bRpnJ{WP_#FHb1)qzWOBzJ-XKZCii~F%ugmZlJ`x~wD zP`Oyv@%P#dlHW4#0fe;b*{+r-3knbwFw#o%QCbl$=diy|xGa;3aL#3+*^Io_#8{Y# z1DF2@vf05l%(ek7Dwqw%N6iSG>)09)I#)|YIHz;YKp2)(P{X4^qXcm)yN9ow?ENUx z8fF`6OY7XiP=}^d_jM(wT3(IlwwYex$RTtJpe|I&+0og!4MHde^a_I#vmrs=hpB z-+>L@z5}{;^xw488-`RmnMI$)^GLeLHrbZ+>OvUltSBF=H+=X%jTEq=%A}`$7F!#_ z@D`~E=M2~FtOLKCgehJLQowqHVXFn>?2YxoOux-|51HP{E&^Mo>k1{X!Ouym0!e|A*6N>+c;ZlOA3M3Zt6wH+t@k~ zMsJmhaL#D{-T-FxRTy@Qu&mcZj5&tpJ%DT;WE*A62ExU3XoUkGZ9AV}f1hyqxKzY% zGM68+jk4vU++Q|R5Z`BikbwA}RK#yGh$X-0YT=+jY@r|)vOh>b%#(`vO$Ko#+bB+p zxP*eZoc%!pVyjeyH3)I8s=Oh=*rUpO0LP4HvaRBf*h)z}o&7;V;;CB13Cu;c7{=sA z`ItW*7F&=ev{uJdM&`KO?IA4Z=d#VVEoaza>eLPryhhqZ<(BRO-pd5oseh ziu7hWHPr?Aj6B?(C_-9Sy^~=wvwaB}zJ+bPEyD}CFvOK;syspZCbmih=^LdYoFiS> zpIDwGY|boJ@*hE5|G+lP7T2OekZ6`CTe1*$EQf5mm7sQpMiQfZZ4_yg|Hf92VE-4X2=eU||p9v?Fu@0p0&t`v?6#kh~5!u4$xadV%q$yW%mLm|6 zYJpiG1tL-{Fz=^8M5@K>rCAE2#IF~f*u<~b9M2+)~Z8@D&sGy#HE7H@iqnFJY-I?(_e(`M$Cu}xY!J(P03m&oZImq}JOAac zv%gQcd_^k4IhTCrWP?opBgp2I=g!Pbm<;`sw*Jc}u{9uce)Stmr?*qGL8%V+HTN6TUjZ}p5Hr3lH*`#LSzr2TSs692F|MG6OCWP96RD^SCJ^YdlWIdk4 zRyM{q(Uup>f4Rz5gTNYNwjxTTl%DzaNo`a9(FD{E?07VDUVXKF=9xiU0Cywl<{Q zuat^#&XD1UY_Md!hfHr^7lCarJ{|w%U2Lrg+wD>j&e?WzO*TMwdkCpj*v8pXv-e*v zvvnYhhNL2#Gs<%{Gx+2^fNWmHHp-Tbo&WO7+21EzUMdywo6O~XY@=+sbP3=09`*+b zhYH*r$y`Gl?c*jN<}zFn(v%!0L*^`alM3Xm@O__|K%64 zH6V1JFBRdOj>P@gU?&lPWZ%Uu6kD=0;=lY3wt58npGieH$KK(mY|!lZJ3{&l+XP!k zJ^hzI#r`ZQ{C|>)$QHi9?Kkxt##xR)M5=`&$3}2y3_F9-bVfAk+q-A~I@7yx>c_Fd zob-HGQ_+TT#-ptdfdwUMY6&3>)Qf<(020!C+84;sO1!07AGZ z`pPq3JC{dsin7td@&YZ)j7Y2`yV(V2JDBV$lp@P@tx%Tx9hPGTByg*bV-#u2Edmt{ zur(&NWrtLR^V;%+o#9ZqR#sIbbD_}q1=&^EX4tYj3)rQ4kOn)-{xCr>EEVA#!Ajj= zp>>W!xFK~{P_^6QNKmeMjdsPnMl(6p!wBltY-4Rft-?lz+UiTWst4BE`dVAU?iFlZ z2)ma_ML1`-DrKi4eQ9#_W-Ga*YYwtgK8^GqV4G`8&+DM4qI_v~pl@<@mrkJWXDdVS z-6s{{9N*UM4HziZSXpkt9BMd(0%>gUhRO|KNQTbv*0vr)O{hW{i2BRyqOnE2wJ;dj z=9gPAYeL(6ZJJNU#>6zze80ffknsPkRD?tRQDTavY5Q$@(BVQvx2lfWXEN^o7-D=> zTR1xJ%vrP6-EsW(<9(x>PJ_#dr{4C=(P!*AKDrtH$1TS(u|o8>&K38_8kBPC|Lg8d z;M^##gg+R2#}R5y1fw zNXWGbn{WgONA8Q{+fCRF`z4!XbHNfqvdiXRHwlCg!jkX3dev%Gm!zpGT>SFIzn{CR zN7b+2d;hBH>gqbK)_rZ_u8zTd-CHKW9k=$p!G|_~&tS%N^1hSr+3zG%8OY#0J6Y)L zaFWG5o~ON351-by%Y*d@dxl`L=h~CjWD6ttzM6Y0NZa<+2~#^74b*vsRn4c18>%Ef zk%he*5CK+BmnGapPOgw%GR;ll8{O|sMOe&`lsjfMtB}OJ*gOegI#D|ZsbZSlv^tUL zB(yboBCOL{vNek<%!>~OczD!n&&E<+9W^yE+ple|DzjJ|n$*c$q_)owB#NWKnL4; z`APUi?HfwiK4&VzI<~VKs?ubPZ970cvW;I5Xiaon$Rd?X`abUb)a3o?)rq1C_h;IU zQic1v#tJuB+`M_uAzL6LVyRRI|3q6;DOWscD#CiMm`|OFyz4pDx+A1rLLxf;8r^px zRiX=cS0l886uLjgY3m{J8e=NLIejgB9V7ZFE925 z907U6y`=3jRqh+1x(#fGFK_tykv%Ax&CwO^6KHefeHCn$itwe{>Pnd;Zz{riCV}-J za=4Ha`xaCvI#`pX9N&+nlcl7{zkO0ddz-eQs%RI*Q=}>T4%DD&f@vyIyG2_QiP}x3 zBCJ!JyT6EE?AZ4^2fiMl3*cQn@=>*ADq{5oZSz!F&5OeZM$o&8%XUI)<+f;I?*=;uQRmP>j9S);mL2oW1fjS=jg}?R!c-f922C=QA#H zvIChCjY{atLVXtTf3pO{Vx_iUREx#T_z-EuN(9$RDhtPH-(TXg)KrA^vd}H;Q(S<) z6|v%K@;g!4p>2{Xl^NoW#7rj%%K6&2m!NDl6=59;pEX3oX$!E>H|y()kZF~O@D#L- zQ^ixCTEupAY|u_(G^nkE#K<)jVV%*^O&QPgVRThv*A#2Bd4*DTFngI(6ibrI1;nnV zZL})8cs#|lhIglikvgpQ3$>OwzDrvliQ_v>MOf#!a5v$?*JkL%6M2dR+b1P32Q8Z4bJXd{)N zA8OxQV(~pw5!P7*52DE9N-R6A5)qq@>ufc*=LDO;h)*lIALxHg{Tq%2ddXCTbwsnz zAB3JCHj*Fq4uQ{TgYsSzEz%I6WflQt1Kn@{eO))H3>~Yjf>eeUn~JawD899v%f-At z7dj7Mv)rtcFFENLcm}?iK)gvMr*s9uJ5Sqe)tYZvydU&VMD$KX^p;R=(N;)8xzSXF zb(AZ%98Bh5bZ^ix)R3uReiaN0O&f)g--yV=+NP)ynHoPR=puo5K>OAbi2F=MSO>Ad zPh}6lT!9=85pVk#YnzfF{XpAHRY(itje3sy*!nkZMI>b3HWgtVS)_aj!;d4s5tf&= zO;N>ygBMSgA1{BMw^`dX)si=djjRdaAgdODHfXCL0eZcu2g1rp2PX7~ahgK?^n=3cvmges$Lq$;Wf(CHLv$vOmaoIs-ahj>R@4~bWwsR--5 z76F;Y$r!twauMd%>~cy&Uh#nVo;6BZqE^*5Rh8P}#xcNHAJRxI2uN3{COo9AiUjUj zQxVp|Ex?*^6F%(9K0f>QQLB+nEEKV|O-ax`p>3urw1uozWW&vvo{7d*qufrpS6dMY z+1;ihqR4cnS#mAH#fE6RN&^w07CTHgxZ>NC_Kbt+sCSPS=EA}pS3V22)pCKxYi4ez zZAwpuOet(hD%L2}K4W7lv-widOXJq1*tO%u_QO}J6R%BMe%uss03 zz>MBO3OoufrNC!F^L&b~X}V`=bwbhUcZv?~CQP^d&x+X68~v7)7pmPUZ?FKHH}_(f z!ay-u$Z&~2WfEJGS?RVy<9-rMYM9s@!u(vTAJ%n(q0y~MBb#N)Ka=GX59wO2=xli> z)A~xke*oXm-Mh5!&dXp2Tu36u8j7e+$YuRfFN{VTZN`^?E(pE`A z`tPP9tRrnc3sL~sJPG0Iy5811O8beDA)T?>8c1}GG8JK+&Jmc{D4;w7@`(Eh+AdQq zrblq1WSB`-YO5<{lH*K8SkENwXFm%3+b1QoyR{8fMXNSZGNiUcTN8=e`KBVQQ)@W| zQUKO66|wTQ%~NGH>O{#9Q$bq^3Dcmd2G!*Y&GxOOq2|vbZFmRg7UwAwormuCF10c z$S93gi3raMZU3kin$adohK!bJ>mV^Y)>MS`f}=9;Q7B0&7ZAJc+D5Cg)0rq4ay(C4 zABp1@QxVoVwx9hd5Nw~6*m>H9sc`AX=@@;%bJR?PAxhYQs5N*k;vSvZHy|J zRud&d7KgR(EwQ-4RD^XF!Gq{kOqBezwsER#MwuuXB6?U`1qsmurXs8(YB32?C^aq8 zP~mx8+cb4RZ6`{GfPSE@f&}Q_Ohs4+q%`eOz@>Br!TXc8*{blgCQ61VU)EMgLiq<% z5!O*EPk9t@DqlrN<5gR4U)mETL##1vr6jD2Ohs77dITm)o~vz~YB?NjqGZTuv$hTr zqYb7atTT#C=n@K8_gNgllV3GEw7?!VVmgmw4p&UF;{ z=w3_!zpw2KRe**QCBu^TU2WAQ)c-~^hs5g`QxVpAjWYRBKsHKRqP9ufRMi5e zI8ibLcaF9y61dlyim(o@?es?hTicWbZ9v;hRcJ~RB|~IsZABzxNmCKlk)61)oXw?i zR%>)K23XpirU~LKLAD6McBhz(e6-ZRoZ!Ag+aaoOPm1?(iz1Vj`Bs}a@ewUz>pC1@ z7L{)q({WS>{&Tm%BtADpU(r@mLVt~^2 zh)rv6Qgl==B47*NX{$NEoGr%C$FxtRnD%S~k_0GEd;YX2Z}YTOl90|e6=5CeD%eig zNtDXCA9tj|(SF53oeK%=+1gG}EsH1MCc}Xhkw!+Vl?}rt#aY^VNqkQ?6=9w4l=HIb zw3CnVy+ecwH1Zo!N@<&-N@;35!*rodI_vwGgdpCceQOECC8i>*gIIAqd zLAEMyeP_IwpYh7MbnJXs%*HueZ1^c(MewfEHeVIqiue%fp9uA@@1K_-{S(;)=r6Yz zuh!N{qI#vN2?C;Tb zk}CUC<5{1r6PDvvHqQlQB(2=XOqBD&o!UA|dExI(MOe=Ztf7;3imZGebb?hf>RF?| z4C}&0cTZHkh!}rU+jv#RD_H9&)IL}tqmDe#o&yPM?Z>orl9>LJsR-*#=V6O?@0J~J z2y5&98B39F_lM%P)v<+0{b`0ZIbaLgeKIR%qq<*cfg+%IEQxVoltsM3FI)tmm zMeAMl%ZTLM8*ROxtQ`FbJLEKf#Lm)IN&?$$D#AM06Lxw%&tM&1l&)K22LMiSRm85!MOM+?Xsu(|8x| zF4BAr_NFO_Sg*EOs>Ei+`%o|FA86D|s#X75TLB5pUzv)qj;3pK(JMgS6d!l>zY>D0 zwAEKdFg~8<_m|v$h4xJ)w_k25!n)hL&n+g?xR*<8Q!ZP;t-3`3O@1d7AJaBT6~&A= zEaS*@f=%wZP7;(mv~Mp#`8!h))}bul5Ig7;M`C$+dy5S@eLk#_h|eW)jnByEIMs^? z-#4_4SH-s?o=l+j3DiEpwa2HCxQ=j>UYSR=b&{C=qp1k%Opo6Hi?0?EX>TYWgZ*m! z0&Js{#do(lR=&V;1gpk%MD~BQU7$*K6_5>Vz>Tm18>tF7r`!X_SGWoI0fkZW-Dn&KpV;+=ra%7dRbT>&xN+(yLxCF z?VSR)(MJumEm$SIN$H-ht)i3xrkIL|W`Ju zajvO|`|2V#6PZ@4OB*lzebR1tswRu63|1z|>>#UXV153Wqr{|Ya6P%z)AorX!s^L! zFSIFvHU*u5b(^380r@Pk_7pZ|2l5$57E;e?t0z&<60+B>9JLq{EPOL-k%pKY);3y| z$tc5yL%-jkt%BtD>rF+3rR_RG*Q&IcuI1itG_XLaT|z?ju(pw^s8ogxhrAxp)-|+53b2Dcv?SRM zKO6GN+=!p`*<*KS5}yW6jO|7eeRX#a*FE;EHn*l(Fmvx{PvBo@-$=@1&oB`!{d?rw zG?UM7*dRk_##F_hs5no4m)O!CJp-%wvN|Q+xKD@tl$)S^TgkJXrXs>}b2JmtGLM_q zw%tJn#y)n~&m+2dT$A4k#);Y{DZ!W#58m3ax11E>?hNbGg!a89BCAYASSPY@PZ73f zxwM?ct|zK&a0i2dqF2tR#X{0PDRJ7bZKx8bMRC|(EL4*<5gXK$kX@jyhJLx(l z1Xnjf>Pq~|+NwzWicG|7_;^X|!+s$gu>%;AjZbf{P=cP7%V>xebQ0 z&&2AB+6F1H>W&Xm%dp-e~ov(WkN^CF85Y;JQF9Hat~etKU(wJ z#CnsBJk^=YLc49Cg`2KLJu9Pl=o_MkzERck(9UO${xfsY_*4eqJH?YIWAU?-g|kzH zv$gDOCQsSe_7#$?gR^Ft@k8k4598quJbV-ncjDo0IJC=~KM_6ulfM+tuNT~QY74i0 z635=&e)pH+q|=#`CIsdA zMDdi$cl}o?;Pq21;mr!`3+T`n@$eEJUdF>KaA;Fb-SM!TfZ$^K%m3%~|gp0*XfxU`-H6pm-z!l?swT@kj#75tN`IzLv6vn0PH^ z5SEz7BMB(WPy&ia63}CU612)tb8dzlG!GB+@vsmNi}4V{!%{pf!^3hsti;1AJgmmU z8a$kchm-NJ77y$3a2g)YfJ3`%xkbvB>@Ql`^3Se;GrmytTo_2lpWgfo=`<_Nd(lt( zNAc5c$xrMrw*6$#8gFROvu|bwBEkm!&rHAE(HBwod+i1ywS1#A?pe9yBB+I6^wAly z%{Zbi_3$*84sWJoFcTk;nkrNHoY$wvo+?d(LSXPYu`(H+blB?uW8py zE}8dZ{a%p`4+B18H)!`B>34d$f3LQ&O<(S1$5x^D1@D;vo!C$!7)d1eh2E-td&$=| zQxRbid>7$5(p}R_XsMYE<&rlD**n#k=jB z_$Bu9+R8}yK4U7vI=(d<;k#=Lo@|BW0DUS-=F_pdciPj`y_n!Wt?dj|xIHk@DRm&x zU=90#RJUey)<4$PO=A6osR-+=SM5yV`yD)runMiWxP!`+J-M*S9gB>&t?FDzj5}+V z9%WUSe#ot0m2TaNp!#LR(TYT~(VRzX>m~8+Fco2)?~aR#S=KOtkMyzrY!MbW5?9`1 z4V2Zf7>v1K>9VC5%L+KmclTb#|6&NCB8YxQIk!3&=)E zOVr-2ZK^6Y#RZ4MhVjkXsz~4tn~JawuI)0y0=Bj(3EJnh%~XY^wBT@v?9d11WCoDxpdM4lt zH|m)HJ-NR_WRGhrA|d;MsR--HHf(kdIyny)27vA~)_;cYCTS1j`i%D4M z9lMk8J&TP$_MPZ3@s_EG)i!PORBPdRaTvLtg++|uZ4dQhh?ss-4ScS)5)!7(rXs9k zTC^F4GQlLTL3km?5#-SMhm(L|;3hsw#oBe0w1h0LZK^7=#ZYsy^>LZ5jGUmW1nz*g zDiXMisR--fI(H;Tq|v9r9|^@x+RCe<=!)}ocqO0TsC`e#=T%b?)_p$XA}2eLDe)Og z*(9t~AeNA335dm~w2e|_F*80yTCoz*M_Nf-9@4(Q#N`vFBCK=i-s(7M?86&M7Sk{r z$&X-Z@;g!ak+w;yRA$8c8+3vxN1&4g<@?&Vm!N#tRD^XX!DioszJ6C* zB_cepXd9=BXD)t5C}xKfQSBr~f7I4NV)UY^2=eTe;&Gy6B zX8f8X@DvHQPfF~zY8$Fr?iR&4BG8mA#Vs(DYsgL7nn={nF%@B*+SI+yKsg7KRcMx` z$SL|Gk#V(+Q6)1CW^D=DNF``M``!|Zw5bT|EP@A7One}SOj;!(Ht*CnPL<7^=1(iR zxV%GK1qo5bRD^Xzv(F!d{uDN_4%WYe*4`j)ej^fUk%j<0sBM}$plqNUE?rpHO)5k8 zYpWmu`nahG>ww~0VG+BS*N0M%i=IY zFPDhuorvfyq5O`vLK4bvnToKEa>bT|$sCMV4LXJzGBvI#TJO;laVlR$NMF)6Ulr-f zxWn~NP-jtt{tU4DG+CFV3sG>F5={e-vtF4#B z_pePwSmztr%~?Pg`Hd)Dt8I!Zr4~Cqhaj%fzO@A63R4l*K`8IpEFe<8is0R?ZN4fz z-JPC8svpzVNuqj(sR-*-U(E*10_ayGh}i#MZ6~R+f3-V3hk4-}+B!;k;Zai&*7Jhu zrp*F()r*MnZ?%nAWxPUjr{|FA|7hzZG5wXP27@=PR}8f zuWR34g7OchBCJDE-LzRCrFs$J`)_UIRq^TW^c*t%rM6BI)BiFRVV$YQj?DsAjq8Z) zjQ84l12EX>IfOe+TP+FhWK$8=;TrDJEPytYLD1K0yGFG*zsjAS!whhWwu({)IMGyu z^$f6NA746j_vS5p#RFjpQgOWHsHq9+8@0_ZF8x|vGFocF_qW>Ss^jyxzKu&G<`UsjwGzI! zYAYk*8#WbT9p4Px;|`_;!V-y)ugmiKrOgr$qz`Kwr3z^#>*r)zCF)v9Tt29Me~HWc zOhs7dGHYixA8uyH7u67}!sbbc&DXRIQ)M$dKG>jHu-u0{>hJ$(Yar2i#8iZJIu~#{ zO(!45%0B*mpqNbKe2^GCCU6@@T4^F!gtz@Nvlir2zW9ZV zNpPRgiWY%S8f)a{3ll%1t-h40er77ddZwDcWjKiwht7y?87_Ev$TCX2lwo$5h zaCBmm#q;-R-%tXv$5e!M5YzWLrE(z#yYudHV1we~0kLY6e+IN?TluSifCvwbQ2Pf~stbDdYHm;=r&CNcTz$&6?la3gDK-)xBM)P5! zeuIu|6@@@Y3D)h}YDlndGZkSS*36wAtoF(Fn8p3CVe#|mdQ44I5TLJWo23e9R(ufj zqP=fJy(BbW)>c45^9558*3nF6Xwpt8naxEOV-kNN82_nlh$@UJ1S8NyqVQAgJ4+Ov zG8JK+LSjR#;Q4+Q>aWQBMSSKYBP*x||$XB2_dG8Iue zsBNAqrFktVHNoU-D5vccS8>kBEm{y>gkh)b{3yD zEsDy8Vy)LQ6><8Kwt1?YS{0~+a=rI?Z6zd3pD`6-9n^{!DtMb+6rw=Bx=h{MOdfy zS4fTbS<+4+@X;ui%@@k07+b4+b<8g~sce51mZZy<2XR{%cn8j8(`hG9Dg4#6@-1BF zl}q&tMdTLmL-}Qwwu@Es%f&3ea39gmBH*J0^HGBNC{cG&f?R~J*5o2e;L|F*a20uo z{wim+?b=32S?xSi5!SO>_{DLLS71HGup-_-(Hkmd#JtijA;B(c8>tFA{4`mpD+ynm znUdVs;g~E>TMY?U&QyeTTyx+f3+v2>FD)(m^IIh%Oz+k(EejvUu-Gopj}fReu34U)M!<^gcy$bfUVbzAGT=Rs3numijuqtfYi2ai( ziiVxeOhs6yxvoCwX)PdjXXHkbxqc$jJR0myRg8`suQD$Oxd5!U%H#Y&a8!BcgI3$Gwn7rhjHw9gD39Ib4HjUF4j9AC_8*0h=H)@Bh@Vs=$`Sp(;Ra8wcmNoi6o# zZCxaG-!&Cso!zwkBL(Oy?QcFrQu>wXyrON6DxK-^66k|nmMuF`{-}L(3CD}3BCO+> z#Rn0`ity;p7TKOFk+FBplMtAtAGGzZH#;75It!Xf72OhT4J0}XO+{FzBMy5MI=951 zh{jfJLsW|ic5AJZ8|0g`Zzwtc98(e2oxi01VvTQDX_%V}Q?OdTLXVo75V_jssv=ra ze_6(ccwOCklU$}ZpskBUFKsHqI=xwJkLutnY*4uiMW}fa;`B~!!&EuVrX8t+udab+ zQpNTTZ4D$k6;lz`=^PhnTn8UvY2s(|-ebjUh~I9&LaJ&ncRq*}6~per=T` zpdU9CVIAn{NlWyeUziky#J22mQr5$mZ=Eqd7=BF z%n18x>Lybj>@A)@TYPVB@;kA6N!uh_;MtmH3;kr%>KO{GvS*r@Fu)lz#w}Pp2GtbNmrmOmLE;w6T zM=2MaWh%mYE?~$QzirGtF|>*XSIo%RhS5LcUuunuA_wp)|%A$_DoUvZkQ^wcsHA-PZ6JXIv~ z*yq$xzcy<=-J`99gy~LG5!NxC+4`}TU@g+drcK*#tFKBD;r_O^n^bY1A$)TcpKsXt z)7Zip^-JtGwbhg|#ABu+tY?UIdmY~^7gLUpJ5Xb%m{a7-0tF2opAF!~1qfsH1qg*Y z)=&mzf)})1qnZiU!;%i%Hr$=M(YAVPhlXB{vbf@N+A2yJ;Mb-iq8Y$(&+6>xxV*N~ zecSksj!SCpl@we>!8H_I#{#a!U2sCaF5ir=7X~6iEs9J;(oBnTU%5K1V6i(1gKl>+22Rv)#EEjB)2-FwQ*&gR$;>3_9HfbhZ$KG43J?7Gp5ST|#Fu3?{h8 zVldTRioql|PQNX~V4`~*2A%G5`r`@=wz(@Y*zO*W!O89_4A#3RU~sm(8iR}71O}Vk zH5hDidoWn*J~9@9v6*{8?)Na7ELW$Z<9sJYa|oE@q9%Z^cKqq72@86^7 zIEem{qMZ<3w3dnM#MI^L_*5oYC^^NG_zjPS8$Jv9eEZSthBGIyDBf@#kFvYGF*rdF z+(9R(%GY?5CHg&`pej8RnVhlg@B4!jy!aYAK_%~|C@T3)igrQtd5VsQ=rNO+lnD@h zJw+!%G)2)#5Uo&jGDPpC=oE;4o1#-8`g@8_ySBmfley_*!Su0n;SQiBBt4#@X!T`z}S%jz3To z?O42!B|z0TQ4~}!S7-9v>lI4%1vt6bE)aXxO1P?viA_=z#a_ju%$|qo1n==fisC(9 zp(wg1ems+b?m3U5=pL6xnT*@%1by{I9%X-jIygaJ&0NLgU=BEqqL>3Np(y5nw^I~z zz{eeCz$B5-~{vLZ-Nu7mY2quV6#R^}0MbL9_0o6SU+z6h(bsq$p;`MR6t)Gu=jtLZ%CCIE~vd32e9> zf1ku`c!Z*8!+%f|ZRlFY62Nl-?z}oUL7grLPEe<}(+OJlF^Zx=k5Lpg{S8G?)0xLH zkx)Y6!qb8i6nRN-f+F8ZCty&yIx&?i`|!MikD6Th$)Nn@SQ;jy@}Y63^WUey@6Vuw zDa^RZ%UKkSJBgxb+=UcHt=~#f)cXBA%JlncaDw_hM<-~{>=jHPd!D*m=>(0-@F=_Z zhTsG*elR#eV1@mW-~`($j|L~$R(Uo!fwqb}V=5Ot0Zum22|6=F zQFP`F6h&t~NKtgz_bG~AdYPh_S&yB@#9?OLN>QvK4^R|q$io!H8uF7A#TxQQ6vZ0y zPZWhp(Oov337Zbl^C{X5(L6hq21l=uV~wPilS|A zqA1#SIgc`r-$y5`R8kZT{T+|8B+F+ofoS!4Jj(t)7@Q!i56}tv;}ITZiGD*T=$tt- znH+FVgFQieW;)p8VS?$*o*G5bp3hPg?RlI>ndFXHEcMYWubf0DXz7I%MN8jGQ8eyD z6h-5{%A-umGrY@6Qf|jsEI%cn>HQ9j7;&he`!jIff#ax%U!y zi*j#*7rh)F@_4uw4;4Io2oE2|!yS0|C?4*_!`*oJDjxm;4^QCXNj$uOhZphi5*}X0 z!z*~0b2A*~;bA@=7UE$s9%6V{iic%*SdNF4cvyvp)p%HghZFH|G9K3AVLcvB!^0VP z*o%k#aB%$U^!{wl@q0^NZ_(*1XLD(+TbPkI!b`@zhncB7iU#v2n$4qVJddIacoZGM zqv#GEMW^s6x`s#5K|G3X;!$)KkD|+X6dlK-=sq4rC-Nw|l1I^@Jc@4RQFJbkqKkPH z9nGWYZXQLa^C-HWM-c#zA_g8s7(9wdcof0#DB|H!gv6tWiboL`k0Lf6MR+`l2zeAi z@+jiuQG`m-a&^i;&g%oPEFb%|8*9~W%HU4A@vjKEIx+1HCbRi;vXn&r)uU1@m{jz< zQm;QU*yrV-sEzIDsCMq7vzu$jU&*q{nVlUSyQ-6Mr9OD>Zs_w4I<@e8qm%Q7;Cx&b z)+#7LWD+bfol6$sh1$!*X;<1y<&!WIVV8UB1Qawa>+f|M(;TW!=uKrHV?vKv?UGt` zN^dgn-P4Vy1M#!xK*%lZ;Pg@y#9-!8}hF zLeD$?nImNvS;)mR;;Rt?+ZE>Q3iEY^xw^s}Tw(sLF!xrNcPq@f73SLtb8Urr zw!$1+VScSJw^o=}4>6}!m`^Lrr4{DU3Ug?M`STESXN7t55Od}s=F19mWrcaN!W>y) zeylJzR+twn%!w7|!wPd@C3Ei~=DrfB?bXjVh~^@1_4%L5MbQ}0oGj*VBG}) z)?E-_-30;GT@Ya11p(Gw5MbQ}0oGj*VBG}))?E-_-30;GT@Ya11p(Gw5MbQ}&)voj zWcVvqR}f%z1p!u95MXr$0ajNKV08rnR#y;Ubp-)dR}f%z1p)S0-^iVK?%AJx5B_^E z)Lfm}L16FKs*`v*fW3eq3s2t)?L2(az9FBzbaOUUf~*ct@EdFJ^i1biBe3S4323TQ zHhV+)oR>`F6+R`a&hU!a0qlJ4W#W6w#VoR!fRCS;Tu`8mYG$Z26F-jz5HOZ zc%TuXQT&{rA%)!2W<{0*sPAIRJ$Ah>KBqJr&bY@ zrol95JXESPDQVg(qws7VS~L#aZECpyCOW++-AxWd!f8C(3vC(S2QRrtjRDt9O=o?k zmp_s(K|(hJkgAi)#au5j90`aKzHybKUW^;#f=`|j}tPb z!CdbkEJR&%FGWE!`=L3O_dpX?VZox|&~&Llg;(x_uM;J<=@Y1O5YtYDKlY}b9CUp` z@q)jO;9sZ1O8sfSx8M|eVfUYM$*FCB6xvU7@_pb+_M(%9h?D9qfT^s_I1hee4uw`D z`^7K!_h*N}WNc@?H*?$J>P$$2)B&mAJCsciIN(fR#DqF2rdE(g=qnUf+~WqJTh^(a zyWxl1ryqD?`-*B;u?#z<;GfPJ`~ElHKm5wCtDRtc#!J_#V{tq)WH-N@N;%LxOoRLh zPO<0}dvhM-tvB|(0dkSwGnjE9KREfG{SH(g;Nza1EOd52wFu9NfgY$#dUiltv0QX^ zfhYZ*UiQ}0gTC%5It8y-@_T}g7I=mXKoP?>6E+51C>~7Tkvs2rz&(Ix=WKt|@Ja5t zi`*QXxr2Df!{LzY!Lj-#J8GTC^}_m3(Cbif(wDhjyPeA|l&f5OABsa~gWz3`DG==HwI z8z13%jk&uz@ZCS^;U~@rG>tkR0 z%}lP=H22uE9{Wa=i&eGObG5MfBB*ue()}-!T4(?EnT4Nu|ACIz(p#r;wXiuQs`bDF zX|C3v`u_Ft%Gjt{Kpq=k!bNu--+wp1=npTP|Am)NZ*mbf)x?W_`0VRBm$6gt+P33A zuW0T7$4Y(N_<@o80$Y)ShWEVmH~-Bwj2(OViT7^(bwoq(1-3bbi#~qwt|9J==N`K4 z>rcNu>IFKlFYt^0 z_|QK-@b$-|7uhMR@WzT=QNg1S`zu7XzBTer?tn4(Ji6z}>J_pB@C8A*=o23-Ue7P; zy5!Ph&i!WeB5upYM>Zn}{PA@~Q0jq$>z8w-I={91p7N5YQotWyZp4dza{gLQ<+-I# zO}&403o14&3F=RL)e@9?=-yq6xg`sF*L{8Y_^2fo-5b=N_~Iuh^~tYHd>vP6$q#nD z?)5i663HkQl{$@=d3+5Ol={>K!}oA}uXO+Ol%X}RA->bOQutCVD)r-KyT9o^Qfq^zIKH9_N_}Ns-?JRw=8gAXf7!O-2tFts_(BgC39mv=pZZW&q{jx=<>z>n-4zY+`wC-BVxx=i2(v)~mL-?O2ogT0WKu*ZRY-pNAGOObkg zdh6Y1vm5`K%^!qs0$ve&WvdGsf5EPyG<111{63?Q%tJS8Z_0=N+;fMj3;R6pKrf8% i9(2HieCTh(@7>rZQ^cMkA9^03&!kYx+*R&d^Zx)XHIKpo diff --git a/doc/LectureNotes/_build/.doctrees/exercisesweek43.doctree b/doc/LectureNotes/_build/.doctrees/exercisesweek43.doctree index 19e7549f95db772f878d2420a5d90eb500d6f615..b3dca6c16b79f68ee4aeabe4580a6e3fc29716e6 100644 GIT binary patch literal 816178 zcmeFaTdd=1mL7IGeLZ`6#^{Xa7&8NVvC$QJ%dtVmniY)e_j8&d~2;=fBKt$?eBi{wGYti`VYl{WqbQ4imrRU zZp6>7zoYwFx;4Dy*XG3+`x0*c0xF-_ zZv5m_!PlYm&9l}wumAFo{`lj^rLHgNesPYM*gwzd;1Ri9}77K8SDD01`u$<^tblIcfKamh-yZpqjik!Ht6 zyfchVg?gg#|Kf9qK>_trP9Z(V;YP++!` zXV!O9Rk^-Wk|eU#G=bGZtMheRk6|UQzpc4S3Sq4W>Mx_ z$LV@@{S7o>&#ph*Z{5%1KtZegoggw|Bg%|t>Gii0WsPchW?fx>>r4h?YytOUY->4& z7aJZX7z&Vux5h@ryD>DB$U~oDaj>DGC23^vKJ*!Ter4<+_f+VGYkS7C(ZBjb>m%#y z*4M1Br>gaHM*;*QdQuRP?r%RAdcv^vd8u_?-x6BjxKyD^il>((-x0tsh!f)+6f^>(kL6z8u4c z*WZp|__ps|YzpgJhy))24SqAR6W6%7b^XgP9ol(R50tnaKm!I)duRZt$A1!f`!Qd1 z`y=Z|FykLye+a~;tRp3`E<5!{KK*p8CBAAzC6anfvY(YmoTNVewCK_!>wDI>Zd?8q zv^+&CXg%VsPx+$OZ^cREd+W<8fAO9Q&m+9|-c1YF_uht9SC_56eCg20Wf=MQ&m%8- z3;lfAFwm+FK1fyLrPP3`9A8%XqZ0{FZb+DF0-O81^y#NfL(vhjm+ZJSPd#19OT3>M zTQs?J2^iSc);)V|CAZUi{jKA}&u-`7{0$5{x*WE(ylL^1*KX-N?{DzLZBO3dA?WOH zUUv4?YxL{qH7W*q-x}Q+{i|2#rotCjC|mkzNmIO%g;{C>m&8xblmD}7{$?eu zzXt2`S6_d95W)ZOygsMtyj_6nUp`Mr{J7xJk1Nz;nApda$}*5OoaomfFo@e$@(TN?S4fy#bH#^Iaf9<>-&OG;DKYwvej5E+ZqC#$! z6nhKH2y1j_&7Tu4=cRg!CvRu@@4zho$FIYg$@IjT{}#~wEhG6e0(23&`(kes3s_1) zm56{n&~A>O;M>FpRVyjQi4q}YYX|yNX%_({dTXFl&qyO6NY4NYjW#6>RKY8li^y<| zOhNh>=nADE@*R+5CGtqI!1b?<-;=IfaJ}E724RK%v&($|L;c#-Z8w0FUM%pd4^7z3 z>R&%t?D=YMchmFg$64T1ZfFGc_mWQJ^k4blgJv3`6+Ut*0^Uoy9cwA*i8@evWT4Nc zX(08ol;nX?Y=Jchs`xXs6Ru+aG1Akav^<^_UzNtQg2ADEQsbMYqVSVasppmaNCy!H zl%^Y*;ram(RzXRKcy7oM}q7$BOFGgE^P(B7SW_8FRA^q?Ob#c)oILAi^8 zl$#sf90xRYyIO_ZRzI=G~WgJ zUku{i)b|D>IV-Nfzgq8P7hVkJ9aZ>tqiMbiZg4S}cT?ZnjivULnbO5T-a%z=H;VSV zVT>0;c~>>Q-FSc^zB-4#7|pw>@9oCYcn5;wVkqyVy0;ri^IeFmi=n)m`rd9Vzwn&Y zywwq(zw>EOE{|@l? zhhX0aJc{iURKPPEegM(_B~YXaR1PWpfY_Bf2+BK4oR{3a>811UBMJ18^INazD8e3* z=dk|QkNC9n?-mbSK-9l-?nj{$0(_+#Cg4oK7jHWAP?6gn{r0g(e+Ru?coZL0HVQ{v z^RjO*$gk`7^6O{EDBg%az1C)YEk^O~n|-amoeDk3C{7V6-;>|d<=-?}qPHIP*x9g1);@Mc&_2Hq2pV@Q4>`EeFsuP%7g zTjw7f<;H*i#&To!pxk(G_xud^=Y5>?53YiFA2)hI!7Kt9zxUqmd2ja=AjntS4X>rn zycSvB@Zmyg{FAqr8p2(vaf?}9{}M=uBAN&+oyU7WdW5EM8D zD!dplbT(pM$GrNLnNbABdWG*CH2`6GN@;E+w`R=)MQ*0W`4>m=^v_>0GiO6<_FtR~ zt$$WLaA9cusc{;CaTNou25}D%7raNo0%vPWJ%&0ISa2y*+!W$Fo&)8dl;$=H@Hq=! z6XLufFb!e_5V&^&JU@er=bMQDZaa<|A^5}__u~Sfe2a%cnfN-`aF;gW3()XG==FD> zd-y?v@{C>!=VdrI{VMeOT<#nQ`$88VLa%@A-F5NDUvZUh2>1G{)^yLh-EQia#W>x} zJ0ky+{`leb6>?ZSRb5}(T)HjttKU$4SC8{8y#1#9(=UEQHP*KGo9c0U{1o7^KLLNg z@f%lXto6Bfbe}-?Km71?hd4iR=Nl+vc=}DfpPh}k>z`o{ZWgLwyq^OFJq$Q`{thC& zpZ&$_Z+R(-KYqraV%eQ4qP|Z@>hD}|o)=X2zrBM@kfXAmL1Z8>S%`r3VVnZk@2=SC z779}@cpZvLhj{u^Qq^m&(T(sr)^@XGKhr+kF4#XgF4+I{#tU}1U9kV*%@*w9$=6-5 zP0xcg9|*lU95wZwfpQCvsSBzN*#O7Oz=$B0Zwou|{>%tSy+&!s7Xk`Wjcf?&LGtD- zo6b`G_q5I11^H*k1^GYUctQTn+XeZjZ?+&8PrmMg3@>)joew#Ix_8JCt_iZIIo6j1|5)-QiZRvYb_;7092fG^)b(|<7?$IlP<{pxnH z&ON{U>bBpP-$Ir4JL~n=o?LVpKHSsaSHlGtQ__30-E{Hf?QVLoLFeB?;{1+vasdb2 zLKNc`q=M&=(g`Lw>@l$Cj~T25T!Hc{k9n#(aJ2}KPRK-s)O}!y4s%%8|Zd zcJI92n?-j1GMc-OoWJx&i;JLUd{|Me* zp?{#5#{QqJ-hiclqj=;3@L5U-=qW&xWAe+3UNOX}5m982K;x&7wp*muoN%7_hD>gg zt_!#24Y~X-ws1Qm|LJi?{uA`}Mk?K(yE`{Wcfj?}Zy`zhsi&ULfBH_ta9tiY#S7Tk zBj@i!o7X>&3iMDC_r0ay44R*J0egc3310B-$p7$LAAIoZ;K>PGKXGjpb|Fd#ySn=L z<(@x1S%{xN+sCJ#B0I5o==+yY z%1JSNp=PD1`8+6S=ab^uQw0xq^Ab`xb<@AoO{g5XqfyTPWk*lnTy!+{&19?WPi4=& z-vdI5mn`HVgaZOJ>o`kCI2PR_itP(*Tvb#X$k09>iBJ@UTzF&cM|n}#-6CJytl{CQ ze;n><5$}|{0@?yk`%ynDDR5YTq1#2$dOz^x&`YFcrwh-qdO0MR#IRVz94|oz7KY245xM#6H)-m5o{qi zqwVM_1k@l1(Cz_A2^%D_x5gDzdMxuK1`>UQ7qv7mqZ6*=<6QNz{PpZKyvos4LB_`_OFt<=l|%`gFHrF( zFbY)sDhc9!cokX>cG8&Wm>UjEgJp>2U{sR`Q;jhJsE& zi=jICNo*+rOxDxW=0cAF5DK?Q`0_+#i0+PGTs%si=%+a00*RS3mIJ5fY>W6wa5J0^ zhdU>4!fFNid0Eivc*jcafRX?=@|9^H-$jq&bqKDj!5MqBbY ziw6VFjev)qD+p``e}WSab?XjSxV!m}RX^9QyDgy3-A?N#R~NkEZpSVP-E`{C_JHEg z@2LO|SV`_~BA|?`+ntRDf4foP#a{fE?Rv5150}t-PaMxEF7??-p3!sRL zGh0z5{|$Qj)Baz1dSmDR*QfeY^=O~|0_m9;fASOjNfl>EnxR?HqbR0A;vB<%c?CN46AmXiwo)O`4V++c_&eUH za#fPzNOXg&(hS2g-02Alo+n5K-Jm%VXF2N2FRy-rgV6;4zPx&t{uGW1ehSK_zw?aU zv%e6-k;ET9g#+Z^>^BG?y#6*waRuOMRBCG^3bJ&cIsY8y7~%lnENKl65>Wy;e-5G! zzXM88k-`1!FF>`<{|AMjzH=nbOAlMU{_bgtG(Ux7kq2Kx>-tY$Sl8dVS=Z<2-Q0i=bh4`=SVfN&g7e7y1GA}`Nl(0OkTzf)W=dF{m7J|Dt#16uul z?D`E`y8ivxdmzt0_KhbUvmOm|yD?X!|u>tXlfJFl9 zi9LWT-=jkRGNM8tXP-iT&k1L7{dIAU|D(q=09Bur*iWw9t*Sp<;``uXM#ofdVe3If zDE0)!Q$(;0jjJZl16d&N@g-pL$Thr2=cYgTtb{(^H1r94afI)D6&)M=$(0fKnuWSZ z;P}-QYQX-i1dk)^=_V@ow!Wk3kBT`^HT3^(x!Z=01(E%ydmdDOhvXlfprGQA)u%B8 zLB(IZ2tfhtc@rV{#SdZr07kR5AAVLKrl{uoUWyx7$`_~~Xz0hEJ9vtI%K}tSJNW`e z_8H`4!Qs|0i(ecEe?*2+Wzf|pa0n|x-4TR&d*gPhe`0_66X#195R|>?$WbN#xL}6} zcSP-#pv=d`RNhu|E~h~El;eHW(-#WVPP_hmNV!)!yYW6pb)s$-{NSde&({D30Wbyt ze3M6?TtNz6^7PC|pjEI&kD%WxNad3wIiM8=ByVlpEq?NF6r^ys$So0^%ABSantpyB zZ)ULQBLd{05E|YEHg{g-JHxnHhV!_N4Du0LHi*$iBSuxgJec+x;pb2XKOzuvjDsHsO&J_m1rCbf(Vfu=#G{V|WY0@m^ZpDroPe)q81GNd5QH>LlY{A+2tVy#ihwy~3bF z@S^iSgHh)EFYw<5q}ac)rtgOoo&OcezYI$Jd;j>xJnWq60Vwf*zp(v|nJ>=&ar2e) zf59dE0?G|8=KKrz;s)$<{-4vQ0_t=AU-%^d&d-1F!3$bni7+1H^wsdJ<()pCm4W+| zIso?QtE*Sn1TI;C3$NZ)Rqw2(cU955sfT!izmq8k8i^W?yKtUXZ*QNy{n4eO+8aC~yxjwzJp4aTrE9-fkfqjM5zZ}+ASo}NH zyw2LcWLTH=yxz*cW<{@1cINHZ{BlTdz2vC*H^W zoah(2^p5IzC)K?5!rvX$Ypy&BvpB~?ywXTCqUhPtNc_J){NRJ1hrZFT)jfr5am@(OZ~8*A z!{-b~ehxlc4FU=Eh`6$SjQW^&kA`UQk^m%CnG3HyyQ7Do;(9g@o z2pPvefrtl)$Om8^rD~vvE&uq;@!$ri$NM4tXyBg` zD84v;hN64zEd*acTXB4=@?L-Axv*h~EZHX*jKcPwU4Q>a zZF`L}6N|74&>ZnS`tO)7NtSARBmVK7VaWgJFMaTVE!M}g9X{x+{TjUZ`NC=~)^L>< zAJs-}2^S5QMp}HG#y(h^dxZ*7MZ?c?r{0XB6wOT!z;cjax z&MMxR(sgRT&~>$2HMnViJqo71`E)*Bx0bn3G!Dzf zqO%*?>p>$V`uJulxstuM*|4%;=2oN8B9u`JUpMA0Zfj_h{xEaub!*K=r*s|wHi(wZ`YbN{;j_2HR>s^ zMKC+*z}@KZzGRH8=W$BD(&98-kowq@@q=KR@?^Z9WE8&G<7KmLO(qzHuT)*ny7u1l zvUDuVA<^2H=A>EYXH~Vsr0mm{zp$pjlt<4ETNZOi~h(NtVk=m#GMSoT;dj@x;XT%?!(QmYY`%nJ1WJ z)^Fvj(W0~32BC1EmSrf*g{0btpgtwu&U*8fO*2tL9Kvt%?MCeeMRf;5Gc#bMUVmfD zgS?s?NRpj+4zBPWd#Xk(y^6$)A{b}p6Z7S^Z&!`f69Q@;SF7caNU}_nXSm*G%HvKq zktSUy9m?B-7zL;pn^tK|2yjk{C3RxccooA`f#J&KtZGcUgM7K2d01t)=N5~0V~sQV zL@5tj5Vs0lPSP~pY!iu6#dzFpQYM?KY_+<{bQ8lk2&BpbiD6k`#e2?vWymf)_MDyH z_X&krwe7t^tNpU(4R)#;Iaa*o_qARlU+;RYT9| z=Ej5J5Y8qUZYs_Cj$W7^Q;wrS&hhnTlZ5%*5KJ}Rc)T>}G$$TgCbOyEYBA=-*|klo zO0s%Jux)35m~mxq%6AX6)}AL4F$UUV#eD@|a%E#KY#oA4{3YLER{Zv$2G&eB20Wcr zv_ZS$0BLoYN@c3@+h)7D-f0uU@3k9;nYCNb+OyW&Uumf%MQz*C(!Ch&m%XLg^o18vBHst7(j`LLrJ7b$dpXMWMa^U)lt>uS(x>8wt3B_{e1Uu}2 zC}A&l-JI5cR* zGP4PMK0x*F$8&b*=9nzYrXDDP7*f90-8E|o*Q(c+O_Ln%>6i-%z-?fzJB{_aC${TT zAI3I||tuoze+94C^{ZzWPD6IH%*SS@B7 zr89DRxz6jlPI?g$;;FZc^)aRRTG<@$HL2Sliax#=0v{gpY7_%iUcJ6Hs2^q-*zR=78aGIF|T^f$d<#L4uhK**$=X!HI6Y^jYCGyanN2a{?$4wvvXq?JKakdC*i(z}~bey^i^^%mR=;N+H(R6=Y zv@;Q+F#}SHGdK(*GP-QKAn*Jf1r6@;>o6gn?QaCkawLm-K|yH^|ivtO}4Vm zuqu5h51ih9vFy~>_S|4tpu_nN(Ph}P`*j>3NCBfI(Us-Zc&KL-!+4$-3@|eyaArK2 zgwYgl*ZX*amAS~YH{34UPcXH^Pv&?uqga9|_B58UWhNon1o(u+0B4}|=&e^_;!?_aGbmdbj!+>lE`qi?^gQ$f4BKC#DVQEt;LbVVNArwe_;!=kLqelG9LWyG z@B%3U@vjI6ni|J4iy5>LEX$ag5hRRLS(+fjXJ|i;y{>IdRFJb+)o^LU+bE;Xpgoyn zZVULxc-98Kvx!Gz%1pD)t_*`!0%c(Ld|Vr=gG#xvj)#q%G0Q|-tBVH#78>KRlMz0 z%n8GSE&@A`DFcavf^!f-Mp{6#lDs$cWzxY+d7H_wiK2)tr$EuHu+5~1@2V6`U~e9#I>&JVl8@zR8B1gNurT0zd^4W|+Zpsom1E+FWtq8$m8*1B?Cz@>Bk$w@ ziFeE2FMR>T-qvZ%Mq6bJa=?r#l?p}>Zjyx(EOab63Vr0?#h6u7)BLQliw7y)ttz!v zZ8fd68nt0{)|qVs=YW-^rlJZ+k4j`9w6O@vT&Qz2J)_`R;Gc}r>2{MrMKdNitD2?~ z+tZ#LS=P*4q}{f2SiwG~7m-LWH_h3uvKV63svm=rIh(Qi_OLH6mUDU;FElhqWU5aj zjO{8Q&!TAPQ5XhQCS=+4!-389fTy+i_H40Gcqv@S-eEse#gJG;pbwSH=(*au*WkNY z*=&j3SvhlE0+VEn&D&)egqRPin$@jNJ@)`Frvq|EKI&^d+!%{}kdH#nRHP1K()ey2 zX9{nm@-pNdT>@HSLPT>}=A_k`*@^2&7w8na8X3`Cx&xg!+|gQj>uDinl?M)d^Ty|^Inm^%SZ&L(U9kser#FaAx^aoA`o2)+CLy|7M3&VCw z3N;`}zR{>pGo0*O7xFyh*%C05PhP696Iv%rG}hb2j*0T=@{X*rz^k!`f@ zsAF&7ffAIAG0f>sa)v=`vpUQI+y;FNWXUEJOyCNXkt(Yd0lJDSO`Iy%1pOQIQfxRyFKZmhjlFcy*(%rxnBg@g<{-KG_o znx4R%>LCLbwiLN}u=jCweh4tzT*1Cx1>D$~brZ5BGQDOEnRfk|iu5rNt+gqvR&+T) zvc~21WEoRIF9Xizb@#m$bWp+gm7SLR!`NebsN-PVhI6bO_~Vx!p3Y=tUh^|fo-_kEPy$K>gvyj zVJ90b)WIRf)2cNLL8IVujT&)gz~v$`>EX4~NOx=<3?!i3z9G}BVr=PbD5}T%MqBrl zfd%}$uMycWuLg6;P1SwFSkI5PY;(O)`t!2KZ9(L3oz-9tx@t@gyLK`s)MR7Nr3frK zv&$|{8aN|zw7SNoHW6pUxYlVrJbHXK3euo z;XJlc4R<6|tXJzEhKE2V+)jNrg)bU4WsV>Xc=hehkrtt@3K(Pwo6c!?t$h>iQ#2;Nw_g{})hoW<95m=Dfum{=)?lr{7KGQjvsvzn^0n%sGb3u9 zMXP)2QV>FsQ@b-jD$uLBpXEJ#kollUqR+RJSs(3o>tdQJU?TOSMs>Ze9I1onPpAnL zpYz2!t!qZ5rL-x$2Ko`amUSOVUU)UOXFgJGH7vEQbQcYETAQM~^)=vG#~}<>R=pO( zcg@|j-lBThbbzo3^b%U5(o~?ulQvvAl02lfTbXji5m|^29v0XtPV4uTN5F{ zHRp}#L?is_#uL@do>i3&@UUKNc6t%k=~dw!{T;8jh~B78tG@JGlB4x-U0P?RDm&}W zs+_o;WSa=HYBy%X-jENHZIsYTMc~FvGN1Khi7SUu-dLwY!W-s|R-|QY)dn5K&Z?Td zM}Nob_1>&6+IDTxp*X@Q@A)}r=2c=f*a&jB3tB$#XtEMlsBOfh7B$&75{gu;rRmcR zEFitsZfERw=B!8amP+%p3cRDgtRO4+V$8+mo*$g2Ti&a12GVVK6= zA{lMwrr1=r&LKb>VWC@BS1mk%PFf)2#bnOZe za%Qvx+b^{NQ()&v4~Zhc?ly6uJ0={^FWcCShE%2ECz6%A;)>-D{e@RG4;p^5;F&p-Q;{yEVAj#IO1>q{awJA!*YMg~23ys0 z@o+G9IIMZI=ZWG49o?m=KBB3$-)OkOV5Vt73ib-UYWij~=-DHe(5GRW?6$la8|KRt z0z#Y~J)gPCn48fPjazSnZrJp&#NsJs6g07}3LsiAh9QRXkTP9>{${3^Vo zzvH!3orEDl?A!BQ#_)gv(eSdie7EV&k&U$=tmPKrK3E~Q0prU7uhqjmmnFpD6001k zF6i~W7UNN1>2@{1veYkJ z2<$0%O~#EOkKvJHoCM;fkK%yzdMMPj*Z9b#IF7Eh*Qm0W=met~h#tEBP?=p1?`6x; zgL+e1?^rrigZft+D4@lh6i z(?W{@{pO@F!1$~dQW$Ex8s9d%X4ZbN%(yKCnb=!R`}fWDNm+sUUmcDLNo~@e0H`Ax z(;50=(9j099|CRzJ^+wHxk0GBJFo4uF);+Y8*CzMxe@w@*(R?y2vtv{E`Z|rVAkKz zbKR4P_MU-?P+g-i*b2O-q}_%Ec&@VQNdPr&wp9{1tF@%T0gy@r;9L6@XMoS3>;;S& zt=BsYXF=0e;<7QB`DJsm7P~7j7SSY30Do5bMkw#KNX@I05xE-S8sI1UDFD8DyS`b4 ziYo-U4;1bK@IezK#R4cI7yckXC#!%0BvNPro~ z!Q@n)c*Kwf+iyVlgW7tw5Zel1+N#8=-GiIYdVtA@{hiir?j;v^TqjzDgAU?tjM?6g zr)v#5U9U<*u$Jd6U5)~R!2?aegTcm|m+gsVf|tiaIHC@!1z2y&d_(Y})VBONz$y)^ zpT~!h*bSI;1Clls_t{y|1=2-qknPWm0T-jyW<{?7zM0!w60kS4=VukuMSdH24SHJYv>A{|bHDJl88KXL z0dw5N+Nzq$YUEEajCP2=us|?m!$$rFz@Z2c;2tcin%&jOMn}3ePAtPNam4mPzpj%} z-<@M^1!3KlbZEEhBcZ~ooMYiEF#w-H8SEM`)FUy-$Mu7ff_ZlccC?RtVY=*8xZcrD z8TnSqk*Ns?r=o?6!4!aH7c5C{fg5Ij17Kn&+<;zW`|*%Ro*-igA`NhMQ`#*@T~70( zsO-#UdrY)vBM+doSZY!@-WrDzYovQX3XlAwIS5xRXU2qUztsd>fDnWYGe#J{&usxZ zPtqiht=^&wwzw>WfLen$3;YZiGVW!gT;>8oH%(Cnf8cncBy+&!HPCY`@NqGmznv&Z zcHv9|%>#DqNQlATb?@ZY(=6`H;KxkJK0wbBcjOxX1lQDdUyPyy`oy(V&ftE zP#kAbM%ANUVISRZL$z$#BzO#~oA>db8(u%Ei}5gT4#7Bu*KJk&Xt!Q3;43ix`ppdd z-Hiv!fP=@G+T42ju+7#8R$%s^dTX`&?ZYWuHdv!mT_1(dy|$k=*e{XHXgw@5YN7P7 z%;0wI`Qc$(wAM-2=|W%C3mNwkdtDkWyBiP(h}pi4jS2QSyt*lLn15JSF2=%U;5x>% zrWJeoe)%*$%BR_M-HtXy7%?46PwGu=+;HV3DOED?e5e|)L!5v|Hc3aq^--^uV91s- zMWa0E);DUHzSO2{flVob5fcf-05C;f8rSHECKn2*d42G`V2NMzLAWU3NQ~^shKh)w zx7n*K9hyDRwIf->dV_hAm$SyCySE3}-bU}Y*VXo7(W^rUNLOds1=l0Y$wAztb3R_^ z3uZBB3&Q%~C`v{$T`dDk!dwMyi?KIsd81U#dVM%)atjX(O=m+;XG8ORz1Qkm%yv4{ zgJg( z4n@6ra6wCFY<-H)#UZz;M@lv>S4fKHcVrgK`Cf3CWe2|>iA}w`irRZFbKG%!VAY@p z{t1U~aQplF-x)HaT0GmVMY-Bn`B0|^h~vXuy^4$kgBvP06>VZX6eFc zteOyxA>x%9y985U<~KVBkx0yOt!&kIs*UXwXTMX?-|>16>ak<>l=8aP?5qwZL^KSV zf@BP%zD&_tqvDD9#E`?jlPiX3HdewW5)PG?=eGB=&=^$5Tkvv*l?p(A%W&1_0AeEA zrVnQS@$Yz@0?0h(N4m3QMS8elsV27yhhbE$9yDsGbFs${IYBCqC+#c;r_vDf?8Y?c zMftX+beZ9e&G5Ya02Y54{8@XJR`(*-nSliBckB3Uo%IBfuP?=RXeDz>k~lS_4hM=G zOvVx^V3fko1R)uKfdl&_HMt-W{1Dt2<}k+(d$wLNXRQ}?f51kP&C)_xS|g6x-VpgK zKtIvb?E=Joi2e)os#_E3`chW(xm8cV?y5vXV}cg@;WDrV^Fq zadpBU!cFZ!?UXRtI#Qkx6;mJTk~!4n;Vf-4iz>HtW=UBF-=$>^D6%d4;J)$}7B3RP zHu09)oNtiWT*K21=Z(!>$dJG?WN@RqwFxy-l7wD?ZO^aREhSaKQ-8KgFKyHv#A$dC z_T>$UO}yze>!FL{f0WTy8Z0&4M{;s$fPYCv81T-TNZbq}<_NdnFAD)yEmIjUv%0YH zX0UG^ql=NXy;rWx0@y;}yQm9J+({0Hc0x&U)DA@`KHY{)+shA&YD}_GH{a)ucr$O8 zbGRLh^=d^~$%|eaOiNiNlV;d%skn&&d_0Xdb}(2pj#$jz@FJIFJDxJaK{ZFOT^(=d zeek$XhpnpBi5uXUk3tI2nndkRPXIeDDMzff<{y@!=DKApT(2yaBY^V(XdQI@a1J(45+YyM*i&P&B~b!S@Pq*-3nxKrNlGZ3J~lCLDAVBD=+55A zeuB6JE`*35w{I`Qp?jdoD5ZujI6k6z4EqtF(B%=sZ-7P>YVAejR!G=qh8Q3nxPwA4 zhM>wS!(QI9cyLyUx#sny2tqpmPwC7yD>8zykbP&lN5+rj1275xJj)@Ygo>&VYhz6I z+8k6{c&)oVf8x*vU1jtImXYi-gZPX=qg`K!0mOwRk(;m(P!cc@0|THZX#ZfB?H8-9 zvPE%7{uE-GLipKa$v3*RApp*fFoK*J4d@Qpww7}?y0w=w<51-$Ll?uocgy4Q8 z^j6UrDklK01>3<67S&;%O{YiN1{%ZVwG@GUmb%oQqtt-tD>MK|`f!s1K2=Q_KuJtI znFtU^NR0yul!-FthhvAA90=)HNbPMD5`&F0@$w3mc@s1D*S%50F&gJN81^awQRDWfuKFxK!68W)e@M;1Cbr(BWsFcEK$rLHC#>_yG)3|ukAwjB{r8} zk`k*og~(LSq{I(g&&v!MIMZLY{4< zwHXdyZYx<8su@igYc`6RtiuzHw$W;?k2u$5Os!jP6})WHt}7}o_{gVFyzb{Owbm=` zfOZGjN%ytYBT)NjUq`J*fBCRas#ceGW^eo;AK%tmIhZBKQQdEot?R8@UiT6lYleJi zy9ezt4g6d5tN6S-jJ?LY_8IPEC77xqH z{j@(|Ug`I&jAtFIP1o;lFCS9%05tVU$|{Y{Qfm*!G~hi(LMdfNQD>%}ZMsRv^_k_e zsg{Gz2J{TBx)?Qkn5cuIxukjh?07q0YqKSihsd}0`_~QwJ7%Ea^^q94^O=roErrf> zi^wIDV+g!UkIVT$bqC&l0zOIIoMZlMF~WzqVStltEXX$wv(t5FLwk&TsC2-W-Cw7f z1kgCdmgAt;k8&*R6U|wFk&)9*5>{E(QOyn2RLX7-w>`dtjn`Xn0pa>Kmb+wmykHKK zB;Bkb^bXpjI`_6Y1t;AhucZZFWGa4~xqZfn5Iz{X5aLovBU0b4(x`~-LHLp4c3PAr zf(S3q-Tqdf*#X3iCI>7JNbtQjYD^lg91$C@h_N810?wxm9std_rSRYz z(3V|x1MV-i3ohj@xWVA>bUl*u!q0$kH*Rb@4iiAICtz*?1+nJi386xWHcRdIR+^K* zj`yHvT#}-89ID54kLvTJuSJs=sd{7On zj#akzx!O47$^qV+x7W=!#HCC-ImB+3L4eB<=FmkvFp7mE$|#;{P6Eb0TpmW_8vKwq zzPzSp#WxyHc$q)`*?ga@&g#^P`R6r={gq&;Qv`kg&kPEQe_uDITwq*F341bl= zUvbS^dA>`g5Kv$9AbfnB^%n~}xYO`nk0K-#@CeaHwjV64PC96c;2cxPS(XW` z4>oi~4LOBhN1zr&K%+n~5HmTX=h%*+f$y~#@Cc;IXdknJJ@q>jE07lMRq4FkmL*&f z1PE@Z`ZIET>)U67vlvw5!<6ZeWg!?H8&ASP~@rkF)k5Q31k7J}ZQGOS11h*R};Hr$87>L6D8q2Vgk5dq=3X=Pva0q&SO z`|1(`GnVN6d>z>b4}z7_1u<`HB7`OH-B_RcZaM23kp0lsT8ntNsiosC#42|jF&s2& zJA6zMDE5yTq!1c6T<@0StSs0rxGcdIYSdD$udVsKvh;`GcbfSsQ|*hszMIW+tO@%9 zDWfbi$av|n#2Z<=Uf7$>NRoX>lL8f{*93NXGWs9~2viWEUG*QfIkRSai!tKNdngX+ zP;2yGCD)r&&zwH27rlmDZxOprp1(qO8YCb)wHIv3JlqyJ1%Uh``-@n_05=KZuF|TZ zIQ@9vfy5CSV#i}raZLz>30!Z|tZdIQZ#Bg@=uIZwYmiLD!gGs0zjbDP8~j|GnAk4J zeH=}|@1EpjSFmvzo+JvImaF-Q9TN#svo#Jg1;O_75jU|bNBgs08_%X@m*Eaz z8y0yCdkMuwbimyh&66#q4xyn;>+L+f@dpfNMqNoR;}ikq)gY;4 zJKw<`llfJ1x)}hguqwG}R;!w3B1hcVgSwVRxEOZ_h7}ya1+Xax&6t(w{wCoPoye#v z)(1})mGw=-GT835y2KLG7w60&nk??i5Yx^OXR;nwHi=vx{35D7mc3I|pX z<&~s^=+?dx!KpczHfrku*jK4ki6rph9ol;hj6qx7`mifOZZvt0uK1NfV;!<#dXAwR zOH)dsA+v_%_>Mei*B}=V1zZTBGU;yf>4t9-3WRCw!LCgq&PX4@mfzzYy#xMFPR1d> zD8jsxcE}hK4W^i)h#$=9d+S zX%H*Z8{dmoJK7kPo|}&j`exXCD3*}k$ua*LeyKL{OEn&}x7hW-^~?uj`|548US0dA z@Y?!l!Bm(YZ*t~pf_P-W%ws32G1j4xEEif9wnia7kBB+4F%RR>0laO#xI0F2Y7+_U zlO=V=$!?ux7qN@AE%FzM=XJU_zGBqsx$eXLw)#j{@|$ND^S!>ZgH40IBtL8~O&#f_ zwh0md&033tkj%!zJaac%y>dPJd*{wvzldWtP|#*e-n5RcOo%zTje}Uuis0{2O?VAF zu+f?WlYc0NwB{mv{XzPHBo#6Q#I*GwHsI9uuC&W~y&HPJC$87)i~#q)h@q`lr<;*% zka)nE#>OFhKz6(!w1ya4c4taC$#RGnyp^aN~HZl3zeLa4(p9(C~z6X_LUa+vNG307NiYsKuH^%^QGbLqGjV3G-etPsHvwo}Hkg9(m>;m#Ka5S%^06EL_;U)oI;6`a$#NoUg+ z!X3M6K#UW!nN^n<_@tS{6t;eQI}gUbMSyUST!?p%F(FH<<8+*xni0kjGz-p_PStQo z4mbT-w4kaBbu^A34572eaegr94q`Z9Nx(P~0#uy2$MR-_mF6@=kY_mCqo|xM&%J}P z^Odp((8aLVv@(Z18d0px{a@_Ekurk15wcywZnujpkQco@B8RBjWtTzraqb1M{8w>zx1_dMn&JvWKHWE?bRVQqt%cF-rY!*D7} zxu`eHjwjF7;Yf8sIWL2PGc?N@EZrnkcAPZfBz}rag^o%QBKV*@dAo)ru+^~aLX7EL zaD#nTT~D^cjxtDMlD9>`kkui?qPDyG$c2z6yjNpM(kVk^^58IsUuR?VmC>`tSTIPt zQ%yM37>WQMt=91JjgF1gMUk40=ba!7?bT>IsCT;*v4E^@!W}~%E@MJas1}V6nHo;4 zs=O81zA9DN1>~&{Rj}G9b-zkPUTqAvo-xq*teX*mXhK3pVn%6P##3gu>6*cEV+o7F zW3c4Yt}}<@&3?} z*eQj9?zZX29n0Q06FR}t3DKb!zNpK5D+N_X*DMz^61@(m4aAL;}#<<8;I-10KEmuIpbMQhmWq;qH=V2`C1Jr2ml zD&9@R5yWlHAnB?i4#ojZDb4rx7@R1U8c>j`C+mt@cS(qs z_Ettji90el$PzEc{1)%Y5*EZOEEK^amdqC9(KH}RLCEBu+g()Y3fnJ3>?*%;r&!Qi zk}O1)CoU#b+dc#S#Q`MCRm0ATm{L=6Kp0^9u|hPelA+S@b6~pjd{N$U>RKaradjJ4 zwe5~CuuxH7tj7l>StP}I1rUM-xv?&&r4WWk8JU?uJ{Si2a0P=zYEpG=LhWz1kb?_; z4$u+c_r#-qGv%m4fIK`!U+_d!*OO7 z`Ix-Nr_=x&5iDQBM~lkZnU7*2Nw?u`RF@rj z;pLr3>w4!nkj{{WU;Fc?lS36l{=v3ThGa_#TwoCMbyy{&HO~S?auw5rwAc`0z&ID& zPLO3eg2d8BZQ=5QZc+q6X7ix60snfw+{Ke7p<4ST1>vx|4smVs01i=D`Xe|Bg5dh$ zK`KJ zB9gBN#x`sAyGUc#xvD|S#D0${k||hbE@9nhHZ%W!_TDsBl5|ZE>U-}jQ1Tef;JMhc z7}DKi`*dejWk&AVxUMJnJh|^%-=0!rMnvurnX%+{X$cHSV^qJaMgk-xG?E3#;2(y+ z2xK-1BtXa#NJxN2gJpy;!eTc9p7)D2^W-_Fs?NDH60UP~yUxk{;)`$p-sO3px8&as z!ZX<5=$^?a(cNSq>zh-kvdYiK${x}3MV?mPsn?0hCI2>?%++uQ_cgsfF6PIhz;R#T zbPkd3ZkeC8RB;=rA#P;5y#>B|(cDIRchBM# zJBu3_%NCr1VW~9cHv>R$q4(%&sFI$o!lA$}5Z1?tnP2E**dTQ-kqE*zzGy0A6{zoB z&@YNo3^9MdO$;xiO5R<#zv2XNu z#YF8CkTdhRkRB_^WM-uM#a=VfUB?5k*68U*J`m2thee5>jKZ}OH_9pXWGKqVdm-_3 zs!P4FQH;fVy8(hymeKe^Za6keDUdco*`z$Lw>P(o{d&pgVzb8i-CxP)<;uA2mr{ow z*G?r7liw%BO(@TrQBiCK#$9g9jgymRr*oVhtE*C@A@#f9+BpFf43}wnyIaAOH&c$I z+Zo~^7BggD9YsVbdu&50t#!Cg?-Uq@12ex=h|D>Eez=5Y-P)R%}_Zl;pSgaDa5 zB1Av}(+VCsqyAXt^}u12t1T*8_=#|kp ziwLCv*jE6ZsU^AKGJ)`0ad+^C2U;kf13yQ*U0R0t4V{<%T|UnxG)co1SWqz!6sud9 z8?v;M=Dpc!p;QK|*qlpF{HlL4SO~x=3JE2qkJh4**&(thyE!Ex8^y%!bky%kAqA`} ziF#h%>_TmLCbWVmr?rYdED6hnB&nrRE#5i>y1fH}cGCSmj)@5vHIg0JRwJ=xv<$zU z9^Uo~75`4{_#1&vbe;_HwF$y@lDT6{iOzr?DD;DcnBGG;eQ&g%#<*=h+Q3AFg32k$ zM-lm*$p+?-0SoEOd{#bnD(mXD)5O&fpX>)m@e~#XVG`LLlf%R!cIqof5%V+>Hz$5s zs7X`9*Mn1iz>-sOg@@WE)h_!y(FluffVln%C#=Wx{<^X{v$xSWI(w} z;ZUs$9|oXYI?(ulazTD>>xFP2GYlI+Zdu=92q6scGPoVMTs_YK&Jt?$UYEIrAP;Z7>EY+38Zl`p52H> zAkisBceRad6vEqr*!0Jn$sw0r4T@W}5|2jrqhzfS>F7~yyq@Qiqe*8~J5_GS?R;yl zgq6)s_3NWHzl`M@i%_6XdJwRf`t-0vKpuZs!zVSAxoAT5OQ(3gm5goFcuVIHWdZ&% z>9(}dV_e8UT+?8@?Z$h<@<1N>*D7cPnqou*bBK13^UHEiZy%$T>FPlrg(N4!vwch5 z3B^V%d%$%AO>x(dPm}(`J_*jW&|8WV?(vmyX_rY+ha7;|SR7M3epba#J2| zac(9N2-H7n)6^y#+iT70wi4X&4Lx2d9H-?ao!i+uY{9vVA(s=q+x#Sm)f(+_wL}{( z&Ia_2dUiHMfJd4;OqsJGk|EqR7%oO3U_i*Yn;lG@xa4)B4z4Bobd~Rh7#8B8c;d`t z2wcWJF~BC)OeS2$W4?v7))J?8eG5)}GVEKO)sA9CvI>059k>8GBW#Oa1@6lrH>syn z#6J)(S8!;8wJH(}hgTVF`EZx`(8yoeAv_oO0*73gx<}-D-BSr9K!fb8iF34;TO-ag z)IRk`opAxcPsHfA^@D$}G=V2OM6@1m?{-)3W5tqBs7HQ@YD{e4Os;zHW8md$O#I_& za5#m5xxH#11Yng$TlncV6u8Fe0C&M^(g=ftB@KYt_5e&3tQ$!#v_60%hW-W|SWtC= z&Vz(x`yeu@QuMe=77M+I(O3`hwqtpK|{s0Fr==PAac(O<%B0r45JKvg{k0=L`TtO_jI zFd**QxG!-2z#s2lBEX44Q^Bi%xAr!0Y=ee~Vo5^vJZ!~OIrt=2B>>a9q@O|m4`XID z@WBiQ{6Cb`+hW05a7@W*LuW#B^*I{0F0D|dEt#sH#X@Dr{lV_2?1Uhijm?07hjMsrHhAH z*XEwc=7SKBSEV+5FdgvibPF?etIHht8m5q))n#=ZUrn;Jt{#dCC71)m;$dQP0%QOg z+*TL)7Q+8CAkJ8|cO@&7C%XWiuN@h;65#KuBUZYSBpkt^uSF4#5SxhQTuc{t@j(7i zm{>7{`Fyz*&wvA+GkTy|3UpelM-Mz}qZ)Cs^~%@{oxQ&@GhInaY0uXOz_Wp? zPze_ohwTb$Dz@!c3iA17CH4MGigBg5&Wvn&9=W=RNy?wmJy25)rl`6cqHdRmp*Hp zPMOp(xs38rIx7#|Ls{>TU!j!}rSdo!E$^2OFGSnWds=Z{GqGfs90VV5{vby2y)e1g zFv1=#3WrO=^Vv3JwS)YykN6Z){FOhTaO5Ln#?zQq%tgaDMkBc?A z-wI|XId0yY9=STWEvD73#Wj(huH{P4jFHM9(iT*s5Bn70TwXNm58CW&)8$eCsxLe}s>5+;h#}=I(KR(Rtn;ZgmR+V^drbG*pw$>m}kXte99xJ|O<5OI#g%alXqc%B>3W*+nCnUQF|oEbPgPT+hD%wN}fSG z2A2#1DG}QbJ98eCi*S6EmdD|+*c;Avn<>`=FhgIB)xAH~KN?`|G{7NL34-DDuvSNj z-Jo*Hkguq$xB8WI9SWFQ>D0#ceFO&Uoj-R_g-yIVkv7n->g!;A(c5jouslzW#_f2Z z2hD+qG{Asz(N?3Nj;pbDM~&^Xu`nJwdx?Sd%F_VzA74AG6dUJSsjE8 z9h9ZvQ9oCUg|`(9siu^q(4?`G!^!A2Fy4ZfPvmdW{D6O2sKJ(6Yv_pyn7GT6+LSZu zAW7eHt08!hqg#KDD>ik1ftOe7@MP%kH@YwhA6f{-_XCF)g;uoOZ3B^3tr(B5dNp0y z#;Tijc&{H$xz3DJgsEa2{Y3+jO9jN78kIVr)wXu(_ z7=ubug11cLD6Rs*FFCQ!CEFZ$qE`Fb;HamjwZwJ|Ua)DcEZ5SLsoLecCplS>7XDAkCZ%^g1fw2 z*a$<|_V37YDPB4S(0{t~nMhpP{1b478=o!R|-6x$Ayn^#gQq~1k(jnbTD)@XuezjIh!dBT# z)U&&BWNm?0C>H6xbjjdu5>23u5z<3&N2=qCH9dYJvL1YX1 zaTPH5G@Ttm#7BjK>SRQGZ+#VhM{rDyCKg{sCWQdv81WU9fxO233Y-;xEY5CW1&2;h zk@OCjDAXP(Cc1;MzUDwa8cA~FJoJ;G)L0#g;KPh6M(t=~l0fGiM_gHWT;c%W?sL*y zq`;hcJ1UDiFfWU8ve63a{$Qhs2ip7w_^T3#g*eW{rhz+IQWv0qR2au-7SzX}phl1u z1(Bze^Z^_RM^FtWDifpFFnxgtEatc10QLJN&^04w3OrMrUYU!+V8w;GN>A+_IRsR- z;RE1@Er;g-1Qp%wZYuW=Sxs6E((`0{3Ai5k1Cv8_(B(>P;_K*(w;(Ci6YYG3xYv8d zSH7PqzUQ{P&=4=K(Gte-xy?(#v&;yT^>~Iv+cGB{%jC{@4IC% zc}}`8qJfK1?9q7@isz?7qd03e0`Um6U~s+`r;$Q78EGa12?y(F+Zl2-VvXLy9_3#z zFq}o`d*ZIV;x&+t*gOv)5Y7STIqnjtacLBkLSV7l?~_Eb8fCmF`)VNz#@=B$<@X!Y z#VTC8ttf)Y-vS)tmdq|QQvXljJeC*9)g~fV7NI!8-!yrg&2|JO3GQGn+^Txwe@rY? z1I%*5DVPl;p>om^xXulji?FzlJJ?lk9Av0;B0ho#v16T6CLL|{uFK9ApWhH95s%ut z-b3G15tI5bPvI#IeDEVUw#Vb9F70!jvAmt;JD}VIrm>phcqy4I#`J8tR%Lco(kY>9 zCMK&sE$&n*FIKi8#6ulTj=|J5E<}LFs!HS07~9_Xk=U#Eus0UfRIlIS(xGnZiFi3+ z*rt#1KxT5w!}8HMuRpN4lvBs4zgv4)*EYFJ9>Rz|j!6WOB!M~~wjXp_lgs$y+I+eD zdEoAXDU%CuEImnowYe6ILZzHbBZTP?YmCD!I9K(KbZBY&n9<`kKHFiq!R@ik!(kN$ z&9hM}OB$D`=%dP73#|hk4PLU!E?Smqh{|7Pn)%QkngAe!8?aS(7yfl|05t797&ykk za}#gQSgeD8q&}BEY;y?oBdHR6PT-@+r^ltnSZJpf-B!&X$hX^iV?CJ0Hp^`cu3m9F zPj{gZRwS6Mlga)LP<;R;Cfq8nHDLLjrJLJvHGt}nWluET4QbfPs~^@BaGvyCjJ7^n$^6(9ob;ts(5Rh=-2hW`*Bgqqc0 z3E0Hd?1XfbVfdm$`CzBH@1*5uNF2n9p}56sa>V@)`+uuA^RLH5V8W^4iLj~!5OY3V z3te>rPLfDPL?6YL$bUuL9o&E|F~j6k@e;XBOP@ zf-qkMd%<3`aBA0)GNo=D!;6k0Zh&`4B2z&t+F$!MNG9MaorX5xTUDz+i z$wYEi0A_TzndCqcF=zoNIITOYoHJMH-Xt#9vQ_yM>Lz1JNe-+A+IXks z(%h(b>cgYG*b30$wCSPJ7?o$b7FPI4POS1eNMbAV=r$5;gm1;>FjQ|1{Por_Fg>>S zMl%{s1_t1w5cD3$aR71(l%JqBABGU~4ZMsXBGJ(RexrPG7gmFu;0MwMF&QCk(^R9I zn!c+AjNBqWsJ9bBW|bU-r{I^)0!EYtMU6BVz+2m|tn=y4W?x$s+Q~*}qy&^rm0L=B z+CK-0iBvAEUdyW()L z+ZB_*{pEUXLkxt*^Fgj?Ah;yZkechUB(J)Sd4%4pMS&gwjasQxHy*WWQC& zD*CXaR}&_;u746;%L)HxmjFmJaop}s@y4lGY>54+Um1@J#bdzVN_6wFz+{4C2l-iT z61-itJ+XihJtDWs-qk4gy0X$r#D(P%j*Q;1KiKW}%}FnR5M&VQ4l47as;6MeA}|f` ze97jnAtg3dL!1+sCe6=A!QB{PvcO{N!*n^TbDd~t$R$$%)5I8<2DZQQ+KL}eWOz`& z&8HfiKg}5838B&RQ3qH2B6 z?`>20%A_GB`_pE#wi=CPKTI>^|0-vT?Ld39-hl*X8*B*jV!KgexA2)Ixy+a=6(n_x zECI=hQ1dG>xw~q2{NSw^hx&4~rA$TzpdbB<&K49clac{I%UniWN+Z9A@G9`(thsu0;fvBv2Q7;`d zUW+AW9?b9xqIxz0u6vFL&ElyCTnbRNC$S&y#|KgL48T?7&Vmk{U&i5w>>h5Hpalmi z_QAz9?sdUKi7Ib;&(ths7qyIf7Th4NUa)eEcQOs|Ir z!&4d%M#GGQmePJL1YG28c&8@2`7od8g+=(=yQ77lLsx=Pe%A|OjY@k#Sad<8%a^!f z8-UaiJi@sg_#*?&Z6hv}##sqaN&S-U59V2&1NE@k4J9Um`Xhi`4QWMi)(8`>!wR(HXgVALW*7*A(#)Z+-TII z38}m1_MvP)5=AJ&sR>Y#AUH^apD=EfB z=WDeYpU&aBo|Y!S3vv=N4`8o=5HXIV0-I%6XsLZ;wL#`D#A&MWX74tYZWdRC)F8W( zkO!d5;b>VZ+e$VF9;oec#6=V^y@NWiq(nf>zrYRH%l856D#+kaS;KZW(zZk70zy8I zswA9h!QGK?ms<|{G5BxWmH8Z$voYH*SnpGghIKx35VpZ>3%G)ovh44{`38QPXn(K* z)-%wB@4CE(Em;t`PHw{t8x-%CN$fh|#`;t%+~(SiF6?SR@xiQM0Q=pABVHeacShS8 zt0X=yLYGDop^!h3;45SBf|_BB;J;rdYq%nlAg+n{LDW^3dkt`yA}b2T-ckSf9&D2% z0oW5@2Dky`PbyG4yL?yRl9ft=aUNzOH8QY{cgq+-fdQ0gwB=2p!Oi#Qv5dpW0?P@O zB{{n~>2NO(=UsUK5ZKW6E7p5WLFPlH>dMf8fAI(8Xt@K~aU9tr9C73~bSZ$~^}w#b z<8^qtdpKn+K8(oia=wLT8Jcus#gep`Accb5N#N`$OQkkK8#w_snHJesfICK>q%y#L zGV(z2S|ypEm?25PDF}sPuslb0FA2Gj+B%4PVCU(#mYW*TZ^&J;6yT2!!!DI+Z?sCf ziM(2;Q7|Boyu^I$r(moyHLL5UqUYQ+?P!W}Smo1`0iwc_esBl{lE^3)UnT;6)u3r1$k1?L`DL1S0)Ts0_TAyb**X$3f~HEGfSM>?M=6x;&PO zTkwH4C{M?R`3g2bVk7)!V1y{=3SmH)O)thx3>c_!=SSs!Ut3j-oW3<+1XOaVa&NdF zZup)8&e-}uJgoqJPsL{dssjE0?T$;P% z1SWUIWB>8w8ZgHSdOwuS$6^TIBR(>8$oG~)v!J5wC?8CVvrne!LxIit__f?Kl*xoXa+1~ce$Luw!+$}c~ zn^sKpRUXhZyie1|=0B5K@DvZ2cB3TERtglNgVv4dFUi6gKn)-+8_4)lfNzGx5-jCstn8Epmw-7 zy<8oqY@REm`sH+9Ii+hwVN)6SgW%*{BLPrbErAm`P>a;J>&ywn6kD}DFoN-xQGvJ+ zFBwvK>z^vcX|fdaPY?C*{e1huE^?6+pUu`mzFphyQJFA1U1pg~*PefRDVzCN$Y z&l<}Gu)tMb&)M96+NH8lBruiq!T`)L$jMYd%tjS3xe!QKi{Sao&6-5XjR^i}vpUEf z^3w^@N9B6ELZ?(fJ}(&4MuBiFT=AE~;P?a&;dZ-{YY6O@yGck>z3hD5JaXgSsFCu= zZo6>(r$A^T#0Q6|q%{#&X2+LNjG6s=i*T)b{WdegrOAQGP*joIP3rX<(s(!wr~~9) zT@5Go0+Q~@Cj&mQAti*JPXiDo`2_qXEMKhAQwH1GsXvSd;IWWy)4;kvAMekeGr%o@ zta=HEmXf;JB-GnuEel_vUnA(`mSl-}&)9{eMsbN8vH3OREI(92zZ6#&i!8GHso`V~ z(ry#n-N9t~*erAq%GoFuLH3RK&i%9v%q1V?K_lm#BHLqDa`8I z(^bCEY#}ic;md>GJSpeaozZql*nwl8Kb1SfP)|lE7hTN9DfQ<)9naw(@~0R7q_8C?PSM2i%lDuQx}gE49yV*MH{k?Uc` zmBDv|%tv!gh=7hOH|j5TLlIVyaVge{O-u3k@FZ|Z=CkjQ6N}Au3FvH{i-+e&rBeha ztDQ@vbe30S9GR1k5qa;VE+7bTaCjh3OPWD{L#J`Lz-|VK7jz)HUN-50? zz}t#yQ<)$I0JzA&TSm4uE?jIhU{&0-J3#j9;C-Alg2@_q6v1BHJLFn9#OEMKN$|AT z?bv#aPmY~(AU;H9fm2Hz^ z`oTZkKWX(+VKENOs(cuHGsR*Iuq=RjvI+)$UK}gCKCop0PC$y((?}IP=dkxoo**UE zSck1yLT)=zFAs9ba((4jW{T|=N3c_;cvu=ppa|b`%mBSoYy-Zo=o+bXqiG>uu5G1G zNN+@YF~m9|FDCLIF+%V>U`?T%%GmVuyq_Q8*|6l{XjGX1V9ukXUq@*5JR* zC_&_y8AFfcI_IGx1 zf3meJ4JpY>g4O}c5uCjRxj&1i2FDBlcZh?c6flE@Uf|nEV~?N6Z6p(|Zgmh1$lKir z1ht@{CZ9E>JIv)^IH^Sf?PS0|+_AmMCwc7{j~3g@ZJE-AD=RAx!9bMY_veW4DSv7q zult;AERbzUpoMG;+9+|;$73b<-j$vj1N1$ExIw+7`xCetSiXZiBI%l&!Bi_{dIf|C z^t*EX6s>pLeOYPNslEQxQB}iZ@mKP&^t{W#97#A9M{+XX8QvT%k|;5G)0 zsz0$20|-4o?V`dF>9!L_6@0Zk_-a~uT*~iF8jx~oqUk%Gu;g+K0nac|0iduU9$WbM z!99i?(<}#9F|!8?{$@Memi$tpG}^?$AHCWGj>B^CPA83`-hnY(gOb;})d4Y&C>x`& zjM%(N9W#e!!Y_4NMmUS4zQ{XEkQ1(s+`gfHI27#<*X23#73)M~+CyF-V$V^ONW$M; zK`oY4K*o171O~IXHVt@ZO`zC)GozjSK0szc6zw$5sRd)dli-=w<^|)00pYqk{U%`c$Pytwy!I}L#d7Y z;F%+M_o^T(i|N?QAan=rMqk67hNQBi$(G_;g5Z5XA|Pbw)Qhd)K-IK~5RBDQvu&cf zT}J5gtthd=R7ZXqIF7RA6@aIm7+gT1k+BHkEEYOA%D3GpaC$Ki{{gDXl86(5F#~aq zZ)2rgs-5o6H&xgjI~g1c`3wwB;Wmtxl@VNR`Ls6P#*xRU415ULCP#)$xl4h+D8Tw3 zOBNQ$ds{__RHIgl_ac-?NUYau2taAISdR39+C+k&*)$?-XK0@R4g|R5B3i!^9i$?) z0+^%Vu(}EH-Xt& zu&PO9+$44q(y?u;m}bgr#d7XW6}oeP{X=@eeGIuoFs#!ya_Fov5YaKn+`=rMEBGQL zIf(p8@M9*UF;Eg2Vc>ia43=*fmhA^Ig2!W3EntSh!$J9YHyUVCf_u0_`Cxsshp8Q6 ztW0rXLJ&XUJRd*|^Dru7^=)7&F68AA70Hef2fu-Cb31RA8sX#d=x26Dlgq7D%0-Mt z`DEsRV0dDbif z&Ue*TwnXb*#D$;O0(aP9Iq7TBc>ELuNdl1d6sVl_Voy!7evXLlp;SY8WSx z)QxCx5h7GCzQO+XcMIVBm-76qsr0xCxK83=L>kYIv5NWO~%B$%vFj~U`S(Yo{H^6rYN-U)F?b}o( zgL|ixy*+j*ZW0`=qwem|2Mxmvxy2&0W+#W_b)(y?%(zxc0)jY~;5It$!!q)*kA=Xf zp5+Ph5vwA=GTe?XmmH=lK1XgcmhU}7#{iQvq3ChK78zbvhh`G$72IuX&2Z`z0Dp>6 z&9{Ou#f$<<7VAz<&y9_c1Eom`j4x6naN19i-X4Y@*94Gz-j;uPc#&YX$ zKrYWZxNwv4EkZIY+f`;Z)uY&49Mj9#-pBeuIt9v?fxA%L_5lTAciwbAt}PGnsWmsd zO>!7XAXg|7LI}W6bBXvin97b=?l!;0Wm#%AQj9-&;6`VfaOqyQvhl;O8-0lg33L?(4WELf_VErKLF zq(cvHDZnX@ZUIz)jmBSwpqkwmQ}F3E<_d)jgM*ELLh_^yr%-WTC!elV>tO99c5T97 z$0v~-;^`Z?3F%9IzFIG2B~@+&{2SZ?+j2W%oQw?=%Iv;i);pv%2j)>t^CSLa1YEZf zA`(;BL6Fx-+_JJ@Pog#qY0Yl26`CdN_g)Ff>6^=giVjy|h+{@ustcSIJC69MV|C=< z;YJkpe@IQrB}$$#2;w|IyKa##z6V^a%&DW*^^p7y2!e|Jcw9FeCf6vD=|N-}aH z4S@yAi{1BI#CYo)}$_Dng+Uknr(9veU!GA|o?ZTS0If zUdDmXeLF(XA*jtjOcnI6g8f<0%*ECyU-dUQv5O|N>Y3W$%~|pB<+8QFzP{<^67hVk za$Ca~LGLWJy3rg68K%?en>R1MH~!iG|{7L-( zAIAUx5&Zv8ef#~pKcav_#L(X&4VJ8bU;dFX`?HJx5tYuqD*g4p@q^E1H?uEiKVI;t zclLwXkBl*YR@LHH@dfX#ke>fr^!$$(1?wSJ$5-XgjIntB@E^Z?_}$+>5m&3X`f($E z|LzwiiXeVZ_5J&1ebEQ%d-o^xnfQvHcx7mFdHM?Bdds=~Y9;cj{5@}Xn-%j>F&``D zyC`Oj3SK(<8YA%6{&jl}QNoajCUm>gLb1=ip(uZb^!Yo&4`KEtnj zUKK9-_R`0%6!dvN*Jmgxh-*dGbd}fVitJM)-%Q!R&=m}~=$q@WeQ6QZux3m}-8Yx< z6=n{P>HK`9(F647`S86&t6%KrtCdfhtD5e#UsKkobiG-LYqXlZk=3x{)wyD5nB19& zI2%#bUZO*q{z5Y33AIb}@v`9K@jDX^EiMx`KwzMAhsdetU7= zxYul6Z)U&xF7h!0{Jk^XANf2M$iLxijN0t0nlVOOe(=Jr7)QX>GTG;tTlY2Zo~OR+ zZGE6WIH1_!f?j8yVWD|C^eojqsXx!K=)L`Uj_RJ$pPakTp0EKuJ$j}JpVFs);PNp0f`#`&@S_&xON6}t539>OUs`qntU6hX7EpL@P_TD|yR%vGeSkyy;<~wVh|@KYp{sVPBOSikh81b(XWg7b^}O{?0*)u3$H;f`W!&js+>ms+h}ShvdrA%&W#;fQB9mvsec zGhW4c&yVT$!d=+5Zx0_Uk9$rQUa&&!ih^#5(S19a@$yu>`I5bq?o}PXTSJbU5nZN< zU?;77w63=o?!|=bg>D*6+N(NL2}@Z#n-|C4|7 zw^wf${BQqk^?Sebm$>iVE`Re&HYPq*gj*DMDz(-e4&Qz@pUhZ0SqlwhGQ^OI!V5`N z)~w)OoKF!r@!Ci0!yY&Lc<|{+nxpw-#cd9*a5^$rN$mx_N)WXdn`Rqg*Yxg`$bdmp55GkwO=Wdb36Wo{o?J> z^Hli3J@Q=csVDDVPk)}FvZwSV_blg#r$5hB;ZypQd4^NX)1zmp?kW8Ve&`A7Y5a#j z`;?ZxdD7ADY4#HYe+@mT<0o<48A57b;#Hs^>P1 z3mI%t$6FzW{k|*b*at4tv_c<#3wnC`F;8C^nrj-L-AdQ|f>QbCxqv-Ac&-|s(yQF_ z$OFzQdG|~eUg^{0^1f%Gkw9(A`-}hJNAB7;ZF-CU`0hvlndhUyul&kqpFyxzR9Jcp zm@y#Ay_Svj=14N6ym|40$+fPW`}GSSem?*FbM|k_mV?bwB*8iovF4OyzX+n_d;1nr zs{Z!vjV7+7mp+(tzBKEjI_b05_{jH$zIeeN`hrveVn zH%{-Zl8^V=*of-Qm#>|np+Pa5MbEx(2bpy34&hfmdlXnFKA7X4Wz{x?oR-)}j;zV5gULPKz-;AFu5e&geO0pE?Ya;Pe^gMMm^wpH~T{ENw= zX3(#~oS!N(zhdXnYt)5n+WFmS+DjkzC7MUo(U1F^cS+E}S>ufEms$cXUxn= zw9Z^>&3xdFbhqM1uOhRbe*k;))AD=D@?-1f{A9EKvd%U8EcIPI*)GZC3Y@ z%NLfmw`6I1&ol3(Pn{_rwq)@DHa-69>`gW#nmAEl1;Se5F}hhNW|SQjGq8 zp%^)yFXkUT!aw>D;CS|@XMbk#-@w(h_;2waLTLY|_!rKuo#R-waU18Z)y40l+#R_1 ze?$*|Rr))(4vbY#h;sX)mw*Sm^fx7OucfZcC;Q#`?BADDO8z$#s#hn7@I6B_O z&f6$)4+4&G*N+4A{9O%DE*qZ3gAGFT*^M#Z`q-WRG|tv%I z0OEGQe5Mm~uG>yWSGm;O{XHB7s-N}2T2=fvBWXQ=Ii`(mFr1aWwt<>BekbJh5iUPV4?wK@mE zyN`SRN{ihS)DEigo`(cj{)O{H zJfOd4PrwkdzHv)KW}$+notu73Ccm_g*+0lvI+MdL-T(TLBl_M;_rG#By}b!O;L`oI zf6h7Z|4XZ$r(U{ranPK*m#%w>yxXxD89JPO+8XDtPdxAh++YZ49P9MCI3=t%U5{sh zT6QeY3xuixHnLKb3Ds#}905Sq7 zgz(ESY-t-{=Jgxtb1THmSqNYMRQ{Ru(3|f*2N=QiB?Vc08-mDW$X$fvH@~vfN84a$ zz6u2dW&N7|!3%w1)05)ZBF;~p*XO<|yC(A)w+HrbuPop^Q?)K?GJyqXw%xy<$|;Gk z|Mzv!c5{3hEG&jc2g}(I>=gdvzx0u+&#&Xb^Hc8wPT|nsbT-JZS@mFp{P)m{Y`Cih z`TN_>M~nX%zkd6@8vy*j zVa`(km%CF5_bpoZy(cJ||9J;d|A16tD~Q@NwJ)8iy;vF#1yS4U!M#n-&)W}GiR}aU zT7B>QOv!nrNUxxBy<&=~8A0u6$Yrh#M4VZ#`E06Y0G=uTr4&4k{`|Vne9WwHKZsEz*xo2RzAC zP5{-8Um4JCS!fqp^qYs@G<9s&KB&QK{`f-VwK-IF;BSSwgw!Gsy5>;c1y@>1J-N3Y zVd)tv!z9kEP4tk8d!-CiTyH@B>yH?9PgkC!wh!)$E!{)KfIc_e>mbm$=0mPC8?Yt$ct3Kf31^_dC+M>0fb zW~_9`VUq8t7>IG#W)#G)i;x3R%bFRY;4i?Js*n5>jA-aZ3K3WZAY1+{#5DZ62Jg&7 zI}^MRmElTW+2?4r=WcwS`f#QFhtAyJZ>zde=C__YfS$fQy{-@LhrP}r7Tnk~`FsEP zKmYJtI=k)NpRu2LZ1(St@8crF_#0_t!tmdy2j!|X@!!>ipZ5{v(WD^URXB| zgBdv%gO|P#Y++Eb5xPV1eYmCU?;}4<2-0zqquiX_2w@C!uJ|K@HeZls z%7S#59FxwF!}`Jl?_tl4O}A&Ax;9r5iEHu;%kTx;7epp?e(()UoQBnqbIX-)Hzx){ zc7uSE$rY#4PahSJ0P-BQVa9)A?V*QESy#$n?5^+@e(3agy7NpGesGWMgB(It?pYSg zS)ZO`^$`onl^M80M(CFD^y$shmacO^ynA9rSNd>%>|V1&{Zr?s%*WfI{wiEg580uv z%A2Ce=n36Qd~3>{WGtHFaM9=b(XmNchK_+{Ow#7lHDcVIuXXk4MzC9DP16-@IxKEn zJZx@W4Xglg=NOl0c z%!tLz8&*H@JarECH!JiG<`3tydn?7Luqy4=wQ`lN(=@l{2Ro1R885ot+savm-quGh z8vocU%xAxXfzcXB=hUZL#j;sKMW??U!QS`gjqh`6!slO`mNK#fUA1)57uWh5gntyS zMZABTK=?i5rKH7as4 z)e;psVZ$9U+TjH^*+{LcgsjCD<)mBGRazKO9OhwDxB*G+3mnRD_4BKV0p>u<+fUYD z(Cb@E1E{UF&*F9+^OGfUXz)`;LH?RJtV9r-LQiwHt~|A-r}X02uWu*klzn$kfh+HPT;uv( z0QjtP(?0J$(v1HWC*ld$5ah(Grg+;dek;?-gah%)@kVCv69dcQOWSO3DOk+TZ-0Dq za_#ItmFwnd$CSFC*+m@r`@8$z#Gk#%W5q`=oWszr?n{sLpSo#(?s?2>{Qs$(Jv0Bm zXR|y8+S9oYfQH4Ekv|Rf&wr?$?Z$+fe;1d=r99y^VB9Oz{5#HVW1qVpAk_S|-}nW4 zbN*XaJf8bPm@xr^=tgU%`4 zMSsPkp?Ek!m7Z^w2dX{WAnX-LbQy{SL)I&}WIV(rL(H84Z$>hf2*)Dyia#_cu4fYe z3uh897QsXA3w!3Txf>`J>gi&wdrQ3gV>s5V>@-)M7@qH4QSh!S!{aS@KUc=DbzsP^ znPAD9nK8h2WL*2o*_?}C{`;64;}`MIL;KT?H2v#2XGi^zJ>n7R|2JUQY7CSCVHggI z84po>st`Ra@EcP_5qyS>dx3I8uzX9Fm=00glL`pJ`wKfm5S-YM&>=X(pDn|Rh-?C= zmwX76X#kbl?hkx&k(=Vhomx@+fqY1&RO&5of%s*q7RKZ=acU-Mo%9wnN|n6Of-j%1 z)zC_oNC6FfL8=BqZy7?@EUk)DfKfCk1f&yCP789$sJJmVqAXB<0Yf3b%w(p_C#1|U zKfAMB%$Cx7*hsKZ=D`aJj^Ht>!Jy8Wgdihb76#1p?jY|3d3WG6qI6Fv&95nQ7?rl% zKUQ&O(Lej%Qia&}FV-T@vRVL(Ow#}!S!gzE-x}DOxj77Wk0wk%qAu@|9E|=Q!^Nc@ zO%?}q*)G74&}>ME;1tRal0vMJ6(Y4l0u*Bkm<}0jS!6Kgo0^RAKqfFN9o9=gtKnp# z#1p0q$_D`G(N!1)pDPYhz6p#D^f`&2m`So&{m=1?%n2Gt~B!-sGR>uJ`olxoUh$ zuhPsOOr$FxEqZu*^c=N4r8mE1NkNWQ@y`C_O0BN4bRQALzjv-S|{4vuoH|SDqiod!DDfvUw}7?77xy zY8Z};?Gt4*ntJ2ptfd5SQ(tzYoDhcUB7JALn8%S_- zbZtjDa%!{^>z!fSSWT8X!!9z43IHSy8oRhU(%lT|i8XYK6;o~?JFp-E+Z#xGcC0{u zvNSkSSEy|lC#0>xytFhr>b#}VS??x)J&o{d6MB%+fsh*;2t{~c$ZydKz(_=y(m-ek zilSBV4aWJ~FTeJse5*NpOBj-kqCwe&-c2(wg~n&=qSoL+yTMR8qeNYE^+u-R;Ynyv z!1oVN&RMNz19fe1sMX#@^xAp+ z7L#PY-ZZ`6*n1XJ)S&^oyIz^jN;P_$ZRY8rxw%D^=DR+;MsFM4CiZ+T?%wBZU>$KU zXR@mE3?5;Jm+uCXg08eh#L-x1935&P@?q+?9b%)3*aCtvp$yfm5;|PiF9h0g(&{+% z6Z50PTi{vbU;Ere?tbqX;IExS5&i_r=IIvnjN4hk6~7(}yzlU}@8A}up0go7E1JQl z2()yIQFp(ly@eN2W)SlmPpl;)I`!;RI6|CFd)DFCo_?S*&tK=oJiS0M&tK=ooc5!T z^ZR)bYCFDV*AT5O`eDtr*-YNBQ{=`=HBTIzc0N_@tyvIt&}s8Px$zw4lIx}Tw+s&q zF1dROoE|H1aoT#*>^MEbN)&agx!Pqz-_m#IwV((aD+VeH96;Cqa)r8 z_hbF~$IifE$Jk@&J~ZY*fP@p@T1=e#jmc%>d=U(~Ut#H5Ean(J&*y`;0AYJufv?@= zNyDN)Si-Y_Z9#w@x+4tGhaP$0l`~HC1-m`%tIf6ynrFY043|#23!}vtjDn^WkuFLq zKt@>HwJd2p-LDsri?f&VtEqwvWHV%^1ww>n$Te>p(*{n)M>AoqIlnQoFV0|v zBrJ)C>Dec4Nqoc-aFa_=?LC?ei#Cc~UT1HBfC&mwCQdPo4jyL{>s>(CUJ-ONRhTcq zTd*^IH!SfQtq%x@028V9%*^4E~D1jqG_FrVnuxfHH6CcY9GD3XFuc&)v4t)0xv z@LPbHRi$8AOO9l6wJR&p$k9)SP6S6Zq{+6QGyNfy-kME_GkzN5CBIBq zBxCoy?5uD{Z)kMQE|oPFW4(Xi{s^meehu}93AU$%c(>!U~SSkVcDK9cc(C` z2Sw0cHe${fH|)4MYqmul>|6`x!eknxB`=y0U`}i45}D)twy677qHJy~>!$wFBaG0j zU!StqfJwqziYR07bU5#}LPF><`ni0RsGuNBl`iQi!`yc zRQnpoGAr(+X|%-xr>pjJ^e-00oFXl(Hz1gWJ6|2%!e97qP3r)?2u}D7^F6_yNn4AZ z%1p~p{P+OGDOE$p`*Ir+wFs(W&KN69Si6{8UYWeyi6 z$NmLN*0Ztg=f9v63-_C|89e)&-6u%TiL5W)?_Jt(9B9OUe79A!Y@8Zt7hG;t^DwwR zHO_;SI8-D>^v)nXT0b2HA6+}{VjxmrdWFJrMdG>B8Xy&f^JAGlfe?ittviK1mp6`I z=j3&d_8YglD?Rr-u6-kZiz+;y+f59--@o$q{$D zgm26aJ^rlKAE&On(~j=2g>mmJ9!Ae)=uKB3$rPOlJ6%Al8slhW=)Sf#H`U0~E6^gB36{H~mB;g!W@05cj z&w=J33pm0OO(F71K~(n^m-!S1a!YKWWTWh995JeERI!JT{a`~6dO>&nTY;%%@iwe!Rb!4n&)Xj~>^(3DWCe9b*JBrh zv<3$&x``YDbk`YX0s-DTSg`8A@oJ48lnJ;J$jak5Hrd_o><2RB`K^yCOeCqN zKX(jY5A^}np3V$wWcu>Vs>Ks=gJJyAROiTRioZynB^J4}QNP<_W-qrYfuQV+7y67n z;rf{0FvAj@Y!>vE#b{mh)w~K^zo9iK*j)s@wizuX9|wa1Eb2kiEetTM`x>AK$enF^ zacNly;EJJnGOcr-U3+F(vj)Vu^3RkK&sl{oJ$iCj`xy2rGf>{H`zP+;*n#|Z2k$Cy z_8Dt#Kle1i5P5t;)Rud;{D*lxT2!qTXyH~SlsCn2nhVx4XRyVf0`<=BR=R!Ja<;tc zY~Ap%u(QjSfX|-I?>&d?;d`>Zl1+l$wmUvL(wjWi2FEtzIx)W_!+>YxXd=w&;81{D z3=6@vnv(HUzAN~#Hn>%OGyj%UX+p?A?)H98AD?Ud?p=HN;%`8y@HJh2m#@EGD=F?E z@3PX8+sny2I<}?A+dFGPGe5R>rPFg4SBz(jyc79hs|x@E7M5(SDGz`E8-M93>rNG4(5*8d$Hc+_K*qi`OmGLqSU>|o%&Eoa=MxEej8^IweAd_@y84n|66t!bM$pN;pNnU|u>p@2I_|U*7h+JB9AMI;^|q z(yWhlGxz;Dwsu$x>|)pL&MaWq_gm%-VHL%-;k^8j&LG&?E@A&m!^B?fLEcbMwEeyP z?-%CE!Lp+@3DyUalE9bexF5+k?V|{#JC9zjEZ$l6S67z(MvIR1e1-8?VRixg-^b^c zO5T-_=+is?2>OtIX!TYuRxhJOHbcZs{QsS%(39^wM^x4seGj1N+UQf+_vX?xCwAK=1$jtO`1i;Ge$vl71ny?N8-m zz3=PPec4>PTkz#tt$GWPGe9~)lSZzTJ)+*BBQhH5^OTxrCUXlMGP#zG(@wwlk_8yf z#L1G5c2=W#1~JWxa2<4u!$6N0etxw>XQvwTPulb;SR~F9mc-4wvNlXOE=!8Y?5Q{; zv8rAY_~BV3BS+7sbJqJhHk0=0^xAie8v#XB-yRnOj%wBmGij{T0h%`qgICgWkTj5N z2n|DTG1tEDLe@H~#azy2Nzk=H{#q+LnokoKPEaJekjMiDH0Z=Y+$1~8se0#?461ro zEq(31K5$7}zBY@K(`p(nSqsi=7Pl6qRZrGO5S(LlwJ_B52Hv*9MmhjVK-T z@b;(*z*Q*c?VIn0@bIr38c!3Tf;Fy+*g+8K2<`EQE5x}sB6XBmBrdf14mxGQV@wVC zie<$7Uc0R9me#Rl*a(M!iM>GlIA9fqAg3wc7-ZaG18Ln~bR^i~FH#AsI44MicLj;} z7d~qW8UPE9Y#LQO!n0TPzyx~8HgNyp#GzPqbA!J29L4TkW8IEcNdlH%KIXYUJ;%jk z(g0oaFMY(1`07%d`~vM-;ZB9Qd~G@#&6b_*2qr#2)^s$~hvkPan4ra?lwUE^$%V1# ztZrH_sQ<3sN?)-1#WPe6B7m_JTI_OnPgBpCN43~Ltfwa8^9-riY6rNJ*9t?#S`>NPgL_X$ffzGLh;dycf|Ayoi%0QsjcUkI77`o>)-j3$658pf?->ynnx%kfyeQ$ zzx0^Wy~uS)Xbddv{mgTCdhfH3Hl^7OA;S}+EBCa8nQ2)I+{N+17ATLGz>6IJ+GB|~ zi_CQj<}$An$m2SM)aBXm($cwctoB}!;oJjY3Y!oL9ecgEtZU^zKfRe$#5#K+8o3?= z9Vk>&s(|gTPc(-l3)<#uC@qkVkCdE;k~>@d_AI3Lmtj(f5Hu;AEpNAl3Z`fx*w{_1 z0=*mFQ^L0MQ)V~>I2lGq9c{1&1WL_Z#@+-5*(0}k7Y-;_M5IS?X9;1F1mOf$h7AV$ z)0qZKvcirBpN)#wI*HQofLn)kF*4IIc^d5InBj`-7=M;^oP}EkRxgrJ7zYfDt8nT7 zXyr1=+%T$XpE9Kb6N5)wGdIkObaA9Ge;nJv_S05yrA2m0J`Inb-aCfZp1Oj8KEEf; zhwMI7qgwzCXZd;SXSN3yWD{`%5wKa_vLFaT zSi@2aOqJ7Yh!x%k-6Mb=A{06;V?1M53>tH%Hm4bI?!dDNBJQ7jPD{@%0WS3*Gco~j z@012wgvx%yKp}4k6msKvf;>nNj?5~78hJ$p?8e~lZ{3P$vjav%=ocGQ1l0o9@I?nX zgh@f7U>-~DP1Nlpj2oo0NT2(BKSQg&^Zm@N^1DCnvjP)ofso3w6cLy$`^-r`xBpP5 zF;+MR=9G^v8|z>r70P^uRc-pV%rQ210PD+HgWdjmSLcVV{ycjH za;crWnb|bhi}wtY=6w|=!yI8OKDRM!;4#_kD`%V-v%6XP&s{5xJd#*`m(N_{f_JFb z4K9-DFDzj!#Mx`yTZ($aensL*E_k!^C`q(zd_N(j*<71aMWu2~Y}z4jMZrTj#AV6l3* z%DQKO&&UZr5gynC*N$r7-1$snU|1;Od*RTp-+SdxV&)rxwbf3BcBKl$R_cL@Bj*|4C_7| z4=$?F5%}DwSgao=2{~VVB0Mmij5eV24pV}2jWhG=4a`f9dlDvgCUt%yJg}}SoJO~w z2oDI*@QLu?6X5~#z<4O0oRh@fE#wvbM0oIt@PJ7$5bn-hH1;Z?e=QNmzP()z2DXIo zE$|?p2oC^8zs@#5L+Hd=e}dK#cwmo&ODwuzFVTK-g5YDG>au;K3#s^3UDT!e<2!C?JIsKAYV*k)%fXPPkes zoyOW%pjEyLyW=Nzqn{N#*w)D2*3{etYg5i)dzANC!2^*h`K;hUM!Uqm-?M@Tcb*kI zptaFw1rHWSrA)-asbHE(JS%u0EAC`OM1K0L;6Xkja>TMbH>5UjGBrE0UoXFUcZf)R z^|OKp&k7zqD|qm%;KA37cx z9$cM?$_*5tY)yhvcyrO*x%IPx2hR!~sHQ>x&m>NZSDzI;kg<^pl%7pem-aj>cp!tr zS1``h4t-YeU=yoN8K`Fk4=$b+JSb$tr8imqDSh2M`&Qzc ze^-3-D_{D<^A`@}H@>|3jqUpsAyz;ALgD+Le*9!{etv&VSHj*tec^=4WZsIm{O*S5 zBPE{YFWuSxrcb~A4;Hjty`a*b^1}6qYH`!I(+Np>LDpscm7BAZcPUrm(c(hfY)kpq z>gHVWB`0*b1Ko3bD7L&sMPE_#gUYn*YD0-SG~x;ZQB8;nI=y#67jaNQT3KA;X!+99 z*R1^f+w{@ddP91S|9Kj>x0bKGb@PB|pF7Q+Q?MnxOuSp9cnJBUC=N0vE$p-@0DNrgUm~Bf0q72wJ|QK@Rg|DDoW+`sOHWS zO0A*O6;BRjo!9GkWzFH9Y*=(b=sA_v5(Ra)-?%y9M#ab1_vJ0jhlk=|z}McTGZ^nK zUcb4JUwrh9yV3hw#oQfmxuW7(=SO{!Lh#Br=+EIR@6(_0E8lqKl_7nS&?n-B(JSxM z3p5WFZ@jr$^#0rO9q&dL+c%}9DzVx2jZM+OJ5+!uQ*mA_#>i74;>UesR|hA(m_oe% z{&u4M7JadNtIgMm`%Xpeq@xQWk(mziv*8`O_Kg0Z`S@GuO~n+N&F$D!F6aT>{V7*` zw#DH$h2-C&V#id)MgBwKm|ajcS=K?!|{9%7vzp`2za#w>P;5RC4;hXshA~xoo-e z6MBKZzu1!Hb-Z$7ct;h}dDdZe9qCzziO48rh2>`*MoNFS!w6IS&Ia_^9G}`zy5Dh!~Cu7`xGH;j>_JCNWb=5R2olS%SFSiB^jL@Ux|w$ zL}D`)>&v$-3mz~xHVnIB)@A;*Yk?9?DW?&`ji;yc0u`17Yi!LN)z7xD@*b`r0Vi#4>xbSyQe8Sk^|6fb@TaSDq^-iq*8{PiuIc^ zLR0~rZgrCt3T1^=`fWsf7^H?sAPwSOnoVQB#V^M)-k^XnMDmC5h%x}6@8`E_i) zqsede^M)NX^XnMDmC5h%FC(GY&C=jMgP*s5BKDC#Nqxm=BKGt@mAXiUS49xD{e!{i>9isB|vA@ML*; zcCy$wDM_^T_e~$p>K8;@US9ot8s?27@@sTz!Q)@;r?IWDbF_l;@FA^?$QWLvCT>Q*UHwS>?UA_KOEiU7qt~b{&;jT^t*X2+fBfK-{&x5Y zx-TMIFs$nHV{u_=zyI0j*S52hi^bV9WrFrX2xHH~_O=a8L6Y z97j_Qz^oVO1I##p*z6H#5*$YZA%#E*M~1yXA3#VU0x;|a`T#--0YGBd3-0L=&?691 zhyYA`fi{4ULIhyi3-m%j5fD;{0E~NqRtN|{NFf3+?ghF4LJARpaWBw%1{47yg#aKn z?*%#`AOInS2*A7-=!D=n8Zt^4Tj&KEAs_%o31hPn5&ib!WACtp02n2VE%X8n0s>%^ zFdmq?p;ib8fKkGs*}Ophbn(ZYhd=;~5)Q5O0v!NG35R1Vk3b^=j1ms5^n$(5fF1#( zghLBvBpX6?BOm}q35Rxi!M+gC)QnNWp$#+I9|8hklyG3fjI;n4B^+4lhI^g?MSxMl zffX~_8v+7glyG3H8&-#a02n14*fFDhAs_%o2?y4?VWk`s0HcI`OJ=ku1O&h+Vc%Le ztZW1Xz$jtgk{QVe@RoEOC5#gG?RCSd5D);Pgne6PRNV*&fKkG}#co&;0s>%^uy4(b zDnmd3Pzi^0ec0*PTDFRRl3BYPMWJ5pzPzedZYB#I` zfJ#UJcDo@*K#SE-2?@ZW8`4j&0Dww3>`g6qL#7#01fUWUfaPw;gn$5`5)y#rZpZ^L zN;tLM4KV>lfKkG!#X%|kZ219ZX#~J1;naFJgw2ou7$uxq?}ikFatH{3QNpQRJLaAN z0WeB9vEL0*2#%vMql6QCbHmMVFaIn(0|H=_aAIEvm-&;h|vARqun2`6oILkPeqq2URNO~ApQGrxE&oRhJXMVB^0pd^u^avOwv~Y|k{e8hF z830BJlNNPA0Bs2<0*n$St;`E{vDg7HN|>}MM7ansN|>}MM7w7|kAP9aq`mRL<~eMh z0Rb>dn6#<`X$X#^8KZhHk%$U~fB+aJv~!Y*3I6uw4FIErajOH84Z#M0Q9?^cx%P#C9s#3- zmX30105D1z8wt_2rkUaYOma-BfAjQTzd$D{`=rIC6P3eWAp(ol-%z&8>VOI?t)3Hq zq&Ydy)8D?mdV&7@Fq0G`OGQzk9Jb=l)1TaCOrD4Y_S-K%6m^;Yf_?^7;mPC*JxX(h z3b{rv(GM(@iuyD0{V%Ung3+$dR6gOQ7`T6DCjg(8!Q?$E1Omp6}=6pBNUkT23qKX;ub7-q{7h<_HDYj+}% zVk*l7Ek)(1OR6z&`9%DEetwu%E4bcdD^gjXoB25<&|N*ck@a(A(Sd03jrrpz=L;&( zLT^fWt~clNtFvE~^#=}@R4VH#eIJQWr3B6w57*JzqYFx^qx+$@rRpe=b#c0>CLl`< zP%SL=OB~7ySr6Wih+s|y5@ZboQBjAQTeNs`d9u9j(G6vkA1HsqVt#!_-%UU0WGSlQ z(7TGJ1Ir(rxYEMVyqn2y^SYfrk@<~my`#x*^_rC~n)#(Hy`jnP z^e+_!Bh7q$TKXsObMh{c&52d%(*NM!O|w`H)209Wa$<73>C#Q}p{cIg{ISTYPVR1% z`yPpSKTVSk{})LciA<0FE{S-f^yuGC)n6%LVaQTd-SVsdByCu~wSAu!(xcBS)1xW1 zray3=BmJd%Inw=}XpN--EM;jop2*fF7%~KnSF~yq#0){>C9T>72}96$O{+G+h#_b^ zm8(rK#stkbnQ9YE7=rHl!jvKCt}o0O0<%?>Oj&};PiaOibQB1Z;Wkg@PtE+J03b<3 z0F8S>?Yb4DhycKFmnHK{R(>iXK!S(>8ux?R5gk)jSZo8 z1V{`KKzF@>v=9IoF7a13{meg#UO-Za0J`c0Vvhp?bkz%nj1n3y@n@o3`6*>-_OKEf zuCQ1B)XYB$0IYi}RSG)$JR z1Avv#Fj=||09Hc7WNCc>vDu20&@frL4gek#8YWBE0l-RVm@Hif04t$kvUD8)tb~Ti z(scl^5*j8;*8#vvXqYTr2LLOfVX|}`0IYv#0LIN;6g{c_=0f3ayJXyL108&EpWa%0J zND0l8rE36SB{WTzt^t6R&@@@P1^`w<(`4xy09Xl4lcj3_U?nt7maYMSmC!UeXbJ^&sQ8YfHZ0*K5Yq=bg2X!IN5l$jkHCrj%`04t$!va~(`RzkyLJarxcRzl-s zY5fS`F`;p?v_1evw909Xl)lcn_muo4<4OX~uN6h)+j#>vw90C-Gj zoGh&mfR)hjB$d7p&EP2-I$L9QlBx~>Rzl-sY5hllmC*1cRhgC0~u!vl@AdI40zL1#)Rl1#uOFg#INBLYkzEyEL)wE&x-Dz<5xq{|JB*5TTbt3>v ziwCtZeAz6Zz z(DZ0`9RM&Uq({)16em5Xgr;Z9>qG#K2~E$IYmQ1uh+vIldIaWDtfR#e04m|cd{nFr z0LO$~0>Ck$>FN49Z2*o5O;6X?0f0(qdb++202~ue%tyuAjSwoK>GA$L5r9hAB>+@H z)BFPc2*6_Nw0>(oEZ1xUV>~9Dm=DXf0k9Hw<^^LsCNxcOsM7|Z5_SmymC!W9qD};$ z5}IaM)B%7>I5wXbX!ioBgr+GTbs_+jusZ;F>jQ12nJ>|3K7t8WLem@*{YNmtvt!d7 zlR5x!OxPs=RzeGAq|pdyULcZ8zzT_JmW_A>x&TlKjk9cO06-<|5&$Zpahgw!2tXw? zPV>Vk_qSqT>`){p>d*9jYj~L&^Xbl1^`q-<3y(#08k0L1i(sY zVP>S;3$PM)W=2!IPB^kKGt!L!R>IBz;5}G$z|6ujon8cHSP6}D&9uAW437!B1b|9t zoa|O30#FH!lig|nKqc%F04kwzwq1<~KqWNJwyOaE$ApRbmW}4He1`XqtpMy-A}SXQ zb4*AHZMdN(02~t<=NpPPpa}rSgk1t)CA8s&nh}6XXq@m^;}Jk5>=FPfp>f7#jR-&` zG|srJ0RWY-O8__~G*0={jsVOtp{xfByJmVqBrY-mv*RuSpb{Db48c zi%dWSx&(kqXrB129|5R@hPQY~A=Z5aPzmh->}>?H4Zty>;WZ-L2><|Ddp?UoQ*%SATNXU$0ykpWO08~Qr0tmVhU~){%3n1tNz%gN$ z0B}rbUV%YB0#FIN1b|9tUIIct0#FIN1b|9tc&C;8_2~}{AxdzzU6%lGOgQLlK$76u zu_b_g&w#vu$uTj!R!p@4EdZ>9b_OI`09Xk-1i(sYXF#GA0jz`_0zf4+uS2qFhkKMr z_5!GcT>`){p?M(`{RluM>=FQu3C%09=th9aG3gQjDxu-+el?_cjAzGP0zf4+yk4+Y z1fUXj34oQ*!ts6)hW$!7#(Bs64gs(d+8L5*MF1;dhX7a!?JQDhM1aXLu~3glcE$aT zkjXKzP>)C(0FDW}1i(tzcu4l8Pejo>^0ya%=sW_TgncTA)c8=q44NNwuTOwAvH2F<-iedIi zp9%*yUOK2x05x&iykJ&+0;q}8=H;5|6F^OzHoptFJ^|FkskPC%MoWa6IJGuf*C2qJ zIBi~_p#D?9n%F!$y*>ff#OA5V^$D;hHqXkeO91mwNE4f<Jwm1 zY`)Q3mjGs@P+#bGHco^oDgEBW+Uow^z5wq%5d@9%0qQ>msEL#2wchI!z;WWFd8P3p zLFHqh84JAngq}k4GSl@5pe9bN?JrbscF7n(O`J3@v0Fa|P!lK3>#No$fSNdIUR<*- z0nAOImS}Izw68C~YnjHL-a~vHAp96Gyi8+BBX594Ah! z?XhSOU`@2P$D%=iHL-aak^1cbYhv>f4)qDJCfb{|?NcO}r9ygOZ`QV-0M4B!%@b$q zJ_UFe3dNv#(qerAtcgQgCm{CrMtBC4ibZZhkdM{k{M-acpn5 zZ+|<0nmE?Gmf<^tgXa#!$LfdA9~?Y=@p^rFd9%J<{Yd<+ZZKd93yEX%+X3nmU~wGV zo4)O7k}!#dVqkCMabJUgH>C&yYfGE^39vYh>@8*NeF|6{o7W_+-x9Gn+S~fv{}iw| z+S~fvPk_bI+EK~91BEflZ>GM`ybxmDb^w!E1c9~9mVHkFX0r$adlSe#y%AoSLIf74 z@p}pIfU$Y;qx$UtYofjF-^$KFLsllCW!${(N;w7ACtqdo!FM2iavRozj> z0BfSfg@nBXc))0H1A1ReWD;7&){e{)Ky^!mcc+jdHP5iC+Y+ZJ*}2~v%^F|xT%Q1H z;>hMw#=fTjHF0EfDPtc294C%!E@kW^fSNe6xsg~?<$a38B(#jIr5WzkM0kq|DU!uw0DIa2yhcS3Se(6A_k|g{Wt0e-U$R-ZCC<>* z^Mb(Q?0sJhuqHOYVzGVXyhPw2W-7WbGrsnrL+;t5Or` z_Js0{1~f*px{|er0BfSfBQbk=Ba_fFvX@Fh0DEG9HL-c^&bqx3Uavy!z*_RR2*I8h zU`@2TmbQlgYhv@7arK`9*2L!Zy6O@z2`wX=$AYTc0h7>@SY6GlYzIt2OJXmfWnW(y z;<H&*DV`V0xC9#-NQ}q}m0UReL)5iCbquy8@1E`6K)%8Ta zJIWY9O-!aX*OB%RKut`nt|wL!FbOS*&BIw0=15P0NoYyzm12KI^6w0SSfP6tE^XzZ0mgCXVr0oWx?v?VjE^rp=7f-QCmIN_*O5s zPc%hl5rxJFOdd;YcYmRp0FD!5yZZ~(1W*%W%liwJPXTITJhgQ#iqxa(7{GC2Z1ub{ z-xOs_gqj#z-r?YaAPJx*#+G+DDhZ$_##T>E?|BMX6K$rS%f^T$Nj?Rvi4&U{6qPYx z@>pWadn^_0fXQQtE$^{Z5@1cVdTM;nQ^1;N_0;$t0<4LacX=wG0@g&!yF8TySQ9Pp z@>CLFO|)5kpjwfp=wkbRFSfkTR2c)TiI(@7DhQZ7me}$>QzZc&C)%vQP~8rgJeGK5 z_Y6j546r8JD?TqHP)UF_(eh4LB>~n%%R60_1XvU8<}c8bV8=)^bi+L=V6lgAP#7HdFk`Xg)zk^pO>#e$kuf*=X-IMHqnhk)Q?fHl$b zZeJw<)(Gs|JFu;2(@z7?bt!#=s0oFv@JDycBz?x`#$Fqt6YvR!ES>4KZfHl!> zHc@p;#F}V(&$a3)U`@2W=UPR8HF3~kZ^W8twKhw7vIUMF2H%Xz#kL%_FEHfaAoW?cM(>0;q{Y+q?f&1W*%)mh&6MqhR|2)Wo6n z^9L0KSQDq#N2**5m^_xD_45a83=%wd9@;E_FB$=TFztZ3m}O`=$Fq_EYohfN5EU`N znrJ!8v@!-*6Rn?ssE7g9M5}f4LZi{1XvR-US=tO|Ed^ZO|*UzrXmJd6RlRU+(rSn1167UX#Fe>8v`bf zWoS9)TSkG40oFw8XK^ZGfHl!_)_G+NuqIkR4O9^Wtcli7162@UO|*U*sDc1%;>d2k zb7ecgnrQtzQbi1~CR#s_#1b%hEJM2$UFAby+?lzLWoZ3GR7DK1CfYv{#f?xVxK`NE z{)s4_0BfS<`UhM?pphzbAIs4GnJm~4Bmve$%M}@iD;TMEmE`cmk}6vGub! zJOLgj+CLe`6JSlWTVtAjy7*vPBGyFvXY+Uhtcmu|=J5nr6Kz)`5f1@B1tyPWX#aE| zPk`4G?Vk?h39u#(t)E-x39u&GKcC1GU`@1tK9MKDnrQ!gB2R!d(f;{Fo&am2-FoZv z)5Ql=Efd#%d#b6 zO>E($EJMKLu?$-{Da#UIO|)GjN<0Jn6qx&1hAo`cWeKn*ws2OLCBT|!^+s9o0OSYi z3jpF~FMGMh*udfYExwXkr^V92^0oiLI=ymx4eu7AB8n&_)&sXb6%3&z;AX zYfOuuE~pNHZp0r7+_6oBa?m9KWD{`&j3##G3uAoe{h*C}CN2hyCblzY0)2tGk7dwC zJ`)!MtcliZ3yU95A7wol<9quCT@qkTY$KC$^DQ#t~pm?2-VF6GwLMxE8_Qv^CXZ#%Ms^`bfHkp=>_UzJYhsrKSQ8Wb z6`EuS%Dr)l&*BW)$gt#|0@lPX39u%%k>kn5fYHRxym8uNG_f-RCXZ#%N|vd33?+A- z;aXvx5-^(BnLE#LzVo1!JXhu^U`_0j0MDIU$+Tr+fHkp|Ok0KkYhsrKSQG8vK_LP_ zA3zVVCbp7oTt+yKCQKg7pi2V0p4dvhGZO=>iCq%labhbO*Gvo;O>E1Z^PNGqL`D-k zBw#eLrIqc1AjlXnn%E%$qls;e4?sJ>n%GL#IqVBe9?PIh0<4LxCtS2aExi$I?nA4u$}a6T2k9n%GJ$5GDqAoY*A+*2H$Ik;ouq z?U^(&X7*URB*2>3PCXPH14a{D8zU7pk;`Lgry>iE0i%g+RH=f!k;`LgrzQ-F0hh

|&}osE$aW{;(vx;XeLFq+ue7%Aa2u|oo^iS5+I!A}8eVwVJXoY+of9vlO#i7gUj zje*>m%VTM$Hjs=#i2#oiyClGx*iLmK90NQ~?2-U$VmtMba18L=xk~~@6Wbf5mHGms zi5(I!n%LebtrP=B6FVc|@>trbQib{gb05o~O9Dm{+Z!hq+QFC^C$>|m3qJ)$6FZCn zqlt~jiC_Li6uqmxAg*!*6O`Us3VHa`|pAAwQF=DYFr5g2uBz5!St0S+Dev*x=V^${3#Y+iu8J_4hT z%~uubBQWaNd?HgH0juM*d9~ZR2uyxUf7-mvX?+B&j??B9HtQo`b(}UYtymuctK+nJ zRloWOSRJR$%emD@!0I?{UdO9G0#?UqoAZeL*m2gw>Nst49#KTV>NxFg9x=nofBk9m zS{)i~VHbwuXv$=|5JHR7+RQ;piNL61^LuaWM}bkt<|)bb5g2uBe&1+)1V$a3C*ajb zVAQeIsZ60qFzVR+lEeB@VAQesDgXKij5;D3UQ+)-V0D}{zc`~l z0#?UK^E(^rBVcu$w7Dx&lqRf>ljfD`>qddee(6t|mng4~fX9xL=C!HoBjB;)q}2&s zP8XO2nEs@BP2l=b!0I?@UJOe##hWqkxj9b4U-+G&$~ z5R5vux;IroVAQdBt+Bcfg2{vFPuiVRW_tv4p$j3jI(Ez>FzVRq_E@eh#P~Q*f6~07 zN&U9KsAJsWgJ8yv&GYx`M}bktR(I$MZGln8cBi%Z9>J(%^CZFg4}ww0cBi%3C@>i@ z{Ymq*pt@0DQep_9)%AsZ6c}}EegwUK6!6S?()@1L`Us3VHous(J_1(9ajW~3IcZ|< zcj=GYomuCbBUZ<8yEE%N0#?Uy^Q!>sw*{<@<5ssy=}heQ{40&1ncSHExcL=qT2aU$ z;FE+G( zcJ(9ixB88Ok;&$DjO!yXGTH9_dA4_QNi*Yi_s{bPj7+w?){$$Mj7+w?){#SCWU}S8 zjtl~qG&62qp{;I@U~YivkDHg~s*k|PWUB|FbFMvM79hvX3(?e%0;7&CFSjURpg9ef zG&62_xh03d3?f@zZpk4q>e%i& zich93Fn7W9M=h`TNuK?quZMnhp$-#Ja!zl zdz>R51+0#vR?p`b9t2j$QJZm^zDLYBb!>axE883yb!>axD~rIWW6S4ia&3W8 z$L5zw*6$IFIyS#au|5K$j%_c!ZJ)$(G~<$HMr|*>WfAc9%&7VGZJG~a(iBPkjVN9ot^?%eDnZ9a}9yu(L|p78rGG zH*ZHU$h~8Uz^G&Miy`W^1uki3)bbgtOcc1JnNho`L)izxCC!Z5UU%HJg#okfIBNNr zSMEVD>ey;62=N@!9x=cbZ~LR>Wq<4U2u2;-O`yt0flFoTmp(HHj5@Y_ z*e%l>xuls<%ZJ@^2zcz6w3|kjZH~hp9y=y&7WWeXJ6+(CW|G!dU(@C|WMEmm2~w*@X~CTV>QI@1>L*fD8+ z4LXB>XVyupm2wJgfludIlWXo zimfzpNi)f4((+bm27wtnwtWIM8wI@Xn6$nUpNRsaj;*i6XAl^5Y=0$w*BlvjOge0i zj5;QrnRU`*)UnkvxH*ANm{Mj*`J<`~bOPWdA-wfCxFf;4+Hv@JEj5@Y`0(ff@ z@e%)<=xlRj)UoYz&{+g# z?AZR6hb!`1WdZsxt>e&1mzWU9PQOEW-hIVa%QOEW-h7TK_Xyv zj9V?6ziEvr0#?Vk_2dMBv5f*&$GG+6gbV^!$GGK+7@J2Sqrm0L#I5H?q*35C( zNtm_;MjboYBuo()b)2+YS#Q%Gr8;uCGI84lS|r030goNy4)!Ux4`RltV+Z?`DFUO8 z9qd!42#h+mU8W}67VykE9(ULy7C(Rhl9&>ezbHQtA=h1v7CWX=!m( zvocF$>7(83+D)f8js|_o*!gVqYti~@es*zxadmZh^=d?~mEy4a8>&6CI(UKpcuxG0 z)~k7*{`T$F3-srQnS|iwN0%=yKX!b({HYIakCvaLPd-KeeVYFJ8T#*Mk8hv;BvrI| za@D*|7YU+Utayz_M7B;yz=FPn+J>hH~)0;o1cFCWO06efBpWG#qHAJSV zclD2dMuzCy;(rv^<P9dVNy*_(9=LZNz2wW1iZ1Kg?S3`%q_=9g%+Pk8U2)F1Xtlzhf`P{qFft%j*FU*hJh{3&p{{*)@ko8sn`akq&cE@slleJ)`QdwK*C&@3^zYF< z@ODRc4&SDKNWVxD9IoeAkEmm1U*Ej6`{J%|QP)S0;*#DHiu4L@LE57-aFJ1j#sR#Yn+xIC# ztc<4Ssg!|h;4{rlkX@ci=8+4cJD)byd9%Aw_FM0ye|>m!adPka?9t=Pv(vlL$t87L`O+8Zvo|gueRc8Zt{9b^ z-W&FZvFcFXW9Hk~_nNk`KQd`!|K8twQ4K!-m)6=?X56%(fzW$r=jYJ{jc^{%-`xz0 zE+5i^zlul=&&Y^G;}CunJ$OHQB8E}IVb;;v1r4yomyrNR;_=HboQo0VyNmbVySzG$ zNWpI&FKC3l9anbr)6xgI`mu=N%d7u4eI&Z$&HwNh(&w-nZ-TygwAb2SAZrKRO&I24 zegD11*`ww9`shyd85)t(E7A6q==w$sVa2eXy#4EEmo&J&y1BTH3UA^{G?;!s-0+(PBNnH&}c=z8hUFFYonxGx^C-d^Vd2C#5-q zkPZZz@z;!Vr$6HEcCK-crgQzR!{1ANo|@1-Y4S=1-hLL3Z9LLeDlP5rL=7$N6ZDOn zxl{v7`^{zA%n!HkbMs*J=j3;4hPfTU{$={o>aXb2W2zOKPQv#Vjs2u(gRe%fQ6m&J zItF*6H|CEYoYLPKE;P_kKQrC0LGtULh@y8WxlHThSgb|#%PSOvVQ-eMTFg&Q#F|A+ zI}E=j1XC?z&=;v!)R#0*AN*!rY|$4>D=PtT4+G_n1LaNv<)*akAlvsiQ0_^f+|xk0 zXMS+kv`bN9#)ocM8=LIX1GlV=O>P+?HkoCJ*yNQVVv|*dh)qrzA~qRih}h(lA!3tF zhKDUm4F!oEq)UpDMnOh9NS73)le~$xsEwfWaU6+qOF?3LtK82 zlKR-9+W_LAqodrc1`XAYC%<1?iG86}<^k0E2W%QF<)E zXp3@XL1G8#k_iH<8x?~cjOD18uWD=%JiqddFc1e$1Qq+sl`8bY52|910T?gAE zm#l;BkxSOW_Q)mcV0+|}b+A2Jajk>x(Oj|)wnuZxI@lh$WF71vT~d@H4A3P-`NANv zgLFwzCNaop2kDYypXQSK0yy?*E?EaVNS7S@G?%Os?I2xJl%xz$04GK+Io;;As7#jT z)!pP7SN%pJN?$gQwnJ1Dbu1{ z%_c5Yv$2k?CncgxFxg}|%`*UOQ2l*C2_mIvk5#3hZ3$#5)Z;SR;HJtDutAmi5U@dI z`Vg=|HG9GaN+OzjzAl!_whb!ahky;L=7)d{D(&O8E$XTH(@4PGCH`ZJ;ycJCf!+8N z?Ex*h28pfhl72;7+a>+N)^*qwzf<9g{|$9eqn37WEa?4>pQf(BZ}{M)Ft(?wO!J$XluKqU)b6%=@+(FE~(qL zMe&^gyQC<-gRqC?6<6_6+Y1i*(Z(+6JvMep@3FBL3JIHP{us1s; z;ulGyJ%~*1G}+uOyT2R)MOzf#2@)H-r1#OrF6lisc1iECu}gZ7ja^a;TX<4dNt)kj zURSq8@twv>;u0IXB#5?xR0lKSo_a;;c9+q{b4gd&I_^$(BZ}{!Mlvdydon4Qdn?h_ z#>OrwRu}R^sYLuH*)fS*Z0wTWV`G;TM@90{j*H7XZljG|(tB*|lHOxumju|w}E7EUX{`uZ;#9&o9VvR$^5*xYXsJxpnoRqtyOKjwl z0bnDS3;-LsB*Ydwtp2oZXPo-_5iN9j(VlNo8h>;PNGIBs!I-MU3JL;oJ)>+ zVg`_(CXC9HGMCucB{i@&TgAdRRkR1A?xKxd(tB*|lHOx$yQCUjs})zbjYQie{leCE zNuRKB?H%Zneqm#m6pVS@PLxXf(6)z+OL~uu=aSxIW0x$iZzn}_PvpQQ>ymVK!@@LS z@AQVI3Apyos0Xl%>m+Wmu}gZ7ja^a;TZ{m5jl?`*TqkKEGYQjqfIHSCh*wq01>8BRqe$ag++@Z5p;_~3T+ zUg`ab>t&bMxlRzILmp1yd!zFN#5->!bR{oCo~&H8rrBk{Miynv?f#4shq zguf$fWS5lSSC*9Gwn9?8_hA$EjO3K7S0*=PM z0!a!j)-;W_TWmC`3?SObE)n)n$+a2^j*5j!hIGkHN0Z6~9(L8lR$;?8(bjcI&#-k} z(lcxWmlSJQ*`X8_bFyJKT5TIoD#7xUg4~(AvU}x{v7HrTEo|hHBRO#?ESUI(ja)JS zY~+#wU?Z3G9-I6S%x(g}MlKluHgd@Tu#rm!fQ?)-0Br1%VChv2Q+;sBF|+jQxw+#a zJOMP4AYF0{6DPfoHZH;w0CtcrIe{y#n$cDxa5YWnZgw+aHYl|O&?UBkOSXl*XI4hb zJGcms<3^%`Z7`Q~8Eu2Pq)TiAmvo73Fqd?Pjf?Pj-zBH;a*zP94d#+A8;QYO(j|6~ zE{Tiq1kkpFbjc}mddKMqaQ~QO+6&SpaSr&7!=`gi;Z2<@v7ARXk(Z39vi!)_tctt$-GRC`qg~2+ zF^Q$C#y4YDJJr5edBv2)|$o{=jJr3Ua$ z5KZjD5wEyE=nfmXWB}O6B{i|diktAwZ6k^MmhP9-X(WwZGU>U*ZtRk7v5`v#&`6L= zYGSL|rE1#)OIN<`Z`-)`P5{^jF6lDb1}^Cm8_gvHXe0(M*>1Gikt>Z!aP1v0qFs%R zTrvP`s-5PoU);Tzkh4C8@;5bIEeFXUbeUn*vv2W0x!+@}H?)NI$T#OL~uu=aOQl zG`D#j_r*4Rrz611MuJ_^du;5IrSscjuhge#W0&+E8@r?ic3eCL6AvvG`VgCZU-&%y zkamMz(sOKFduOvRomY}UQAu1z8`s_m02{kxDa$Dys419oNw?9)E-4rbjYOT*@dF#X zr1#j^CB4VSF6lisc1iECu}g|ML7__)SEXXPP?+5*i^o=X$|_uP3~yoHtV()}jce~9 zY}$0pj{sdpdjc!e1%QoRvfQ>ki#B%2(n08WCT0I-ou27ry` zk{gjIbV;$nkROw{?2^bO1Hi^ESzg~x{E9YqNiA$O-%+|fwwhDMF1gYOa0=&=aj(4M zO7~0U+xD=uP&~1ku}gXqZMeQe3l6yUjyKWfu?<|ZeY@eYy>>|+ z8@r?@=FVedm-HMP*WS?_0lI73F*BF+KHAtN0k&8>&K}I@VhxaM+cD#k-eY5z1lZ-> z1ea}FdoJl0wzf<9g{|$9eqn37q+i(DF6k3CuDt_Y(l2a0mlWDoSSKl-Orwd>)_}I_ zBuU?Lx)8IUO4EddS#k9q8?U%}kBwc@du;5I-eY5z6ta=)k_pwjFOC3Rc1i4#0J|)J zF0rvomJVhl1HYn;U9yx4mryD5Vk1!#2c_Es+v!4BxJkEh?VX`4K9_IX09&oWD(s={ zbfF4t?2=m1c8QJWlHOxumju|wET^G72bM`;PP%N{$R!8m&FdsC52ai-66BH)yR6$T zv5`v#fQ?)dV*AxdkV|S|4~i)j$ZPNp}z4_pF_2cIc4nDkou=+mz|IW8=k5)gRPoBPby}nw^ zAK$Kixc%Gd<<0tb^&|1OU;jiDy+d+W{s2|#Xi|o2@6gSBI?;BAjce}&fQ?EG6HL*LH3p3c*F3WpQAlfSa zO29{>7P=&ZjVF~_*lI08VUMksJc7$=vTb9#^d1|#r1#j^B}=Pnqkegv$7LhIE~$aN z882oR11a6vzDqJ)61$}L*w`gK$Hql?`sJn9QC|!Svo7hfk>Dac0bpa7EG=}8`o)_F z`lW#@m0;Q-Va8*uW)c zy=keM&1fhFh54aWapq3Xs3UV9_JB+JgZj^#miA57Ekh8;*cBG;h{Y#VJ`*l@^sQEH*`vQA6%ZhbRCOW zXWl-7?%Oxjlt)(CIX8ct8|w)y#WU;4+YSryR?fKXm*h;U#j9}BceUV^NWJOC7#MEB z=ruN&QBF63%wrcT;8@gmtc1gP0AveQuj165fE-%j0-8Md9Lzk3S(B~S- znAQ{=VHXG7wCn&&@le`DDca+HVUef1Mgp;+OG?Ikv*4$(Rb(6dH+BY_RSc0ycC>t!St5Pa8=qM~_N5eX>hJm-HVSx}*j+-PEhJ zMMZmTzlNkZ=>@wabV>iQp-XCEr^yQ{+O#IonE(QpoNS(dLATW!)K<4?P_C3*VbcVt zBWzfTM-!WlTITJBhUA@L1DBkD{jxC?(aYHl%_Ur71D6Z|8@Qw5Z( zu%Sz8MLR9?rG`?ob~gCHczc3YTs5QZ6dSsvR~3WQSO_=GC1EKZ&1k2G zNVkndtN?X}4P8Olv|%Zp2{@yIulkusOGOFG4dE-9}u$zzWT`;s)hSKA^kq77Vw&dxlq(d zw4&`48@OZ$(FSwLF*v?Bo)nJe(#%cSeJX$*HWJ{HAz%ZSBy6B0rP+Jc7{@*ZDW_zu^YJtC`1^+t4Ltet1Di6lAI-PO+g&`i>1N@Qi!@ zV?&qp9~-)4BDM|+ZCkDQ`Ovn9==9EblT(<-rW#CzeaSQvM=f2F{&X}cgB5uE!_G}6 z$=qQDo)EC1OUlI4>PE6%yUz}#XbG;RMpBM8bV+$lcLBSwFXd4&V9&}0nv7t*2#GIhewo79YhtY<$cSa!1b21S7BAKPj zanC6>a7n^0cgaEFV1{FC;F6=BO!Lh*64`G2i8gS_5U_zuhJX!Ra@3oYlCvg5zq%xt zOOATu(rNigu?Vf>E(u&R1Z?1vqu!|8NaWdQf0P8cq$W0%|JxXl8k0~lq_)N+*%b#` z-hs7uLcoSDN&5oDF-crnaFFAz?D7uPaOy1D&?U=<{3o&oaIS4T#fC2FKQ?qp|FNM< z$~y=0Ln&GP&7VdBT~ZFN3)rQBYkCjPRsbjc*3L@hw)ms~LYE|fqLQRlTemZJ8kDPF zL}63Krp}ZEx}^Wu&?SAxhP8LdIz4YBV^mduuuJCvCnGfi@u6+g0#x}tNeI}$B@>XG zH5sc6vNYOh9bKg)R1B#jC852%al-Ya_s7w4qD-kKNoQ9Y!10-qGxmPO+Q2 zq*H9{lBL@6lj1c!qn=Z2IF~G+mY>MYv&V6zeVeK6{_*yzEHI_jQKa!JbI?=0HTCHtjwfYZKOUroEDQ*7vx z{zn_Sr2p8^CFRM`oNiCj@m|_U(z9x+ZBqhkXKfq0r2p8^CH=>SF6loubV=W_VeK8d zEV!J&Qtp!JrBrE`Y;mV7vsXsuK0v2;LcoSD>3_7LOZtxuUDAK-<}T^9OEz~&r`XM1 z(kXUxmy|~{Gn29@jnX?BN)1r8b4}fLhz)D+gn$j_k|3#eCQj?-roc|4ja{<5;_4YT zc1iECu}gZ0ov!cD2oToZp)Tn?Hg-wxv9U{fkBwc@du%+H)WPm}Op@)Au=b8-mvoBV z+$Ei2H+M;=*v(ziDRy(0bc&7VlHMyxkS-bbf^uI?H$c%cRVS}ntQ^m zxaug0Q*7vxF~BaARiWpkCdJ$J?UvU`^3jGa=|47fN&m5-OZtx;q)XBn9F$b+`^-H- z73xCJ?dC4owE!vwq~#qtsTxcp$zeC2OFE4iQp-cLY4P8>}{I=7!4PDZIZ0wRcr{$eS8@OcLqZ*-wRJdusG)-`b4Qubv zqIVg4P{^00>3y+e(5%%nuIVXPngUPIifahiz$HV#1}+%_HgHMWhXQR|W&Wlq6`i;3 z?GRA5ZQzn2U;~%*wUK0_4P272%XTv;C1*KpB)}y@z=kgAd$eKg9si>}Wn9wpwmn64 zTs5QJ`8vr?Nv7z2$q=xiOKNpVr_shPS*qkeP3sz^=I#_5y5z)rZ0M5yV?&qp9~-)) z@7S>RjyU&KngV;(C1=SE~$l`*3nIeQf-!>rIFNjEG4@nbV>iQp-cLY z4PDZIZ0wRcy6v=WH+M;g*s%7FrrkKjZtjv!v75W3Q|#t0=@dIimmKthbjbk?tv{QN ztSF6louoJ;zS4QucC-z8(b zFX?}@;at*xY&e(nA3I2wq~3=nW&TGyNSB1QcR~=rAYGDn7ej2@lw%ksHk?cPt|TIR z2CPc?j~%2-CcPkClJ2bwvylYplCbs;EvA75hte?^x^i!GFsAzj2UvS21Z?P%-bP!j z@6hrNti9uLv{P*8lKw{POEX96bH?Pejo>o8`Vef2!63?Xo-m zrr6Lf{l|uO=|48KOD$}=qC4+9ahrF)Zri+S+i>aCe{49Z^dB4ArPh4GVIzS>cr;fY zoMJ<}^gr6rF8#-bF6loubV>iQp-Ya+=NMy^+?4LCI_;9sCH=>SF6loubV>iQu}ga1 zwwWS4zDJuW!s9@?bN zE-4uc*lMBD?Oakd66lgc5!yUCkRwIC0WSv=>LK@6$PeJKwrJTKzyA z2zc>&eYKcBzFqxr`?u4}oAqtoUH6So&J29gK{hjO21|RN;p48u^3YWd!gGTu%h-{_ zk9MoR$({Ev97lsbl@9{vMy*79vHBZo#jArC=#S^bA8A{Ep8odj)eH3Jhc_SGu6|5k z_Tlw|)SW~ z+4DEc&#nG~zI*w~mwt2k;=%H0d1v|Z>R*fKmFJev-#nP--fQ&|{lt0p9mV(mnfU&f zSBKkglJD`#mk(|pEb`y{)5ULo`tg&+`T70z`%f0PPhU8>JYC$1_xtYV{XX&&8;ITe zEq{qRy7<*T`tXYC)DrPi)bEQEN-sm=k&kzdzV-5(m$@3 z(J)$`ot`c(qVxIti>vF+i}RE9+1Kamv&)O<;mrm8Rs#r?x=t5R<>I6OQ( zdo14YDD(bzx6fevZu!3s??%}-xpR29d5rhfW4sr={`y;Q9f|i%zf(N5dtZI+jenGW zvwY?H?9t=Pv(vlL$>sI>zI^G6^w}GikG{HibT_(QEKctY`@{H-de;AfM3-xc5d%9noo zze-#5Kij@f5n^SmAE1XE?d>A}Prf1ct`^se_5Jr2XOEWa>!Ul-XCnCu>5zOSy1qGC zM(gE#9X+{PeEsb5<~q8%xwwulujmWqXQ!7JpIb-shYuGgYx+vkug$j}9$ud;7pFJp zi!16nzi>K#e6(24?+q58Pwqxn%gcNH-b{Wn6raszcj)Uc>4(!77Z@L&t&g^S`EIn{ zbZTn&>fP@~izk;S%j>zHy`R z4LZjk{!!XF{`U5LNbdifdQL&^|1y1P^;h)iF^!7TA;aF`@ux(Kdo_BEnw%(!*dN@D z-k3jra7uqYG#N~NUi0HPl0UXIm>LXvr3QAPEQ=R?`fdiGlpBsckIPmX0zz~jws1kUVG5BONZEGmyKQCAvU>XV{Fw;Q`0fK znXgVGA+rn-o4gWXcRZx3-6hE?^{_{U!`xO!g0->9DG|1o;W%vDWRxLdlTRXSp>4V2 z4v9Q(l3Ag5+epYJ!^0LO8JlA}vzwuqRO&@LE|lA&M&b~gamjMq_6wVFNpVUl-z8&l zPB7mk9Y&jR$dm1-g&CGj1baY@i6m2T{!tvacSHXSAH zD%$!kS+tu$&mlH+Nm_>}we6v5$zDXexl1~YHsg}Mw`~)bblA2Tm(+^3YVAr%I@E2( zC4JXz#wEeByjp|WDT(E1)8TThkK;&`WP~oMg{|yfH4-{8V`4XTuo;)s!gd&K#wE3| zEh|Z#XhWBzJIzWiSvuojeY{-qus8iStJ}lI z$D!p;Ssm==E=e~(Zab-JBm=VzzB<^9OA1NOFI|=n`_s*j1?;}rCP*D@#wA4{^Vp-J z0MdSa9y^|y?I!4Bi%N{JZEImWi?*o52(blGA=)aoyDq6-*|zO2qYYgWCg3Q@9kyD6 zNU_Zpit98I=#rY)>K93|yKCEwOM*tCTJkR1>J=q`rb?n2?&C;QV)UnN*T806Qat~B zmrPVk-bLGXBdLMSxTIDiafof=k`A#Mmvmz8+Koh1VuW3?j9of*Zr|K%U^6aR#s)(v zXN^QuVuaE5yGu^-ToSsZG8Yd7aLS$DDK`?o+BV~ozGE{ksfDeYP3L2hDb<*QUDC-k zp@sl5E~$krz9>6$H=P34z-C-h3tKH_szzeE;Gm5yDls;1Bo46|m(+;%pl5qksz$UK zm-HQ*nM; z5U_zuhJX!RG6Zbkl2q%zEP%ypYpFt+%eD<%a@HFIY_-9(vm2M#z$N|1rsHMEC1v&2 z+^WSE-ABB3eheq zNgL7Dn!3}>T@>E|ZQFlr=#sLCR3X~MX@c8mLzmRUR=KV31iGaE z*w7_uHLoOq%3O8==q}o#_zvijgVH9*Xk0EDSzH608J^$PZzQ7l4#4gUwaa%&Il9VD zfvs1ltI@XUro%9?flG?3981xjlAUT&DQ!bECZ5z6z|JcwaonhCFJPg4~V(Y0IIg+qB_eIwsMMHgHM8F6}0a zWxL5m+bK41$q=xCONM|ATrvb~;F2L=1D6Z|8@Qwos@}u+=7zO zMpZ}A7R7g(V$%WQya3YnPG{KACFOlndAlhVL!d?Q;uM(nNjk%ZE~$l`9*y31$#K84 znfrvw3V=p35YIm!?X*dxZMzk0jTHwPZ;RqP0K2^BJ}zdbPJ07&=qru3g=vB=Hgri1 zY#NjorU_$uM#gPh7aO=FiMi-)`9?BUklRM$7#q0cxHm0rUXP{UXIyf!NnpsB`BhNDl7LR+Q22LOlo<{NhUt!l*DNx0WLZ2B>=lH-X?!ltzEffmt7LLWC+;MCF63m zXKDoEN85%jSw5ICo~cQJAK1_(hvmhzbl~IzwkW;>T+)AR=#pC4a-N(WO3^I2qoEWn zKsJuHQ*7vxTG39ovz2a>Np%)&=#sLKd~TXB>6Zl1DK>OT4Qv|Ss!@uHHtlA27H#N~ za_PDdZDr+K0d$NFT~Z4>on5BU?ri2xr$UgDXkpWSUT!gMOb1LlYb4Mm9b)gFmC?oM zu=WmJxl!8SoAgU{FM7wRc86$(R>FnL(6`wnMua zpcPk5?DVGK)Fmw(%+NUGMPm}G)=?e-5_Y+f6fbHV_ncxwmmHS%ZYFXYKG#T`Vndgd zC;IbkJ3aN6&TgDyLzmRT?yJGowrx+0uQCw_O0;x)Kv!p#R;B0&eQBp`QjWG$Z0M4- zdtMv?7VmPRgO4tw4PDZIY~YefZ&q$3#q@lq(T25mw6JM(tL$ENNz=>hWRKM9lCbtp z(wm6+R$c(*OBvmEj162e0ULaiVxGHWY~Yf~W_Fv8_Eb%Hw|3(g8@Qy~Xzy*@G?aq1 zcQm7&UT&hgqiQ zp-YyxQztTEHK!y_qYdVgNzZ?5=#u5V8@kP6D|hKo%4xKrOUnJF+z46m+rGC`=aO=<52MB5=Yti2QWrlq}`X?n?Xre3vX%6>uDF;F5%0S}2~% zN-O?E8@Qw}z$FR0+$D=e+8rwim`ldJq_mwnl|%4Olw@C@q%H|-?@+nX z(z5(i{w6u>wz{MiHkeClVy6lFN&qdC=+tp{8Exp2gL1TGbI(QFDK>OTEo`Ta1iGXa zw%kq=@!vL*DGhgRjJLJgHgri1Y#OPHmXyV&@9GR2x}+9%y1$^JO$T~A!-g*DKQ?qp z|FNM<`i>22?`YYL(=JJ;aM5^M!`vNXLzna)8@ipR@}sSg4}q!vw`abopB8T8@S|flTuTN zwp#J?qmclYbd9}dGD!;#u=b87wk-6JZQGRNVr5dMgAH9$F0bYr39SMbT+%5vbV<3G zUBE7!Oru3`^@^GTcNuNylKx{ummHKg_=-2M(6Ve{J9SDqE*-UPSbK*~km_KkOUJ5_ zP~v-M*w7`lu;mwJl_arIGHCzq4GG{ByQCJj+~Lk*(@3VXXhWCOz#h_WePK*OWz{;v zhAufMZ(bJ*eK^Jjb4faj4!WdxNi>P=n8YzQbjk9;jG0VV@CO^Zr2o-|F6loubV=W_ zVeK8QE=i|j)!_l;XaOH zScHeLONXXrvcOGdDA;Br*T4po$`G)DU20;tHy753Hn7VOuz_8MfDP<21Z-fJAz%Z$ z)WmMjZZx_im{f*XNVsPYBr1C1t^he6-UdFg^^W z22>`fR9}UPu9VK`&OF10E-7ok6rx?)S9K_W1C$a%FO~|G%!(EE9Cu0RlKx{umy{{^ zg+`(dHu%vcp-cLY4PDZAY+Cn20_ZiQp-cLYja{;o$ucY3jl(Vpi||l&ZXN8jGObb) zy40~FC4ohFLcnhBl1`)D+$Ei2H+M;=*g?7^6?X~I+^Gt5nAkzOB$fB`GTK$MG8(wT zB0RKNS$0Xe2%DQrwrTErvEf|Oe{ATI{$oRz)WUAlZuT}3=#u_pLzna)8@iE8j^%Futf<8(?FP7Hzc-~Kr-l0}X2rW$D8F2lrBJgnx>mK}tgJ3K ztilrnH}J_m)eb1tbC{)Bz}szi$MFV683Z?Q${@IbRT6jk+Ok=C*MlGJ1bAf-+`ue@ z;0A6P1UInDAh@AldfzW$J)S<55h@>LOfU5GK~E+qi82Uo=$8S+8~Wu~o|DS&Wf#k2 zIUS!&deARD;I5bx)A$<}<)QZNKHmGdpa`Go_ zMHcFSv^p=Y?w3>SmjQ4?zf7j(b%?aiUN_^Dees5V8G{3Y^4gZ%dcD(j0{t?8c*FT+ z0P%)?89=+8&{++@6T7HV956EtzYhG-v)l^G~V9&<(_yO_@&c$8~CMDZUet`$PLT& z==!BoZUet`${nU(!iqgXw39IX64vYqBHm&8C6)RrXEg*7Zv($B8^TODr$zjPXJ1HWu}zEd4<1HW_{Z|s*z>7wM>RNYgVo_ll{Z&=JH0KbIQ ze2Clsc!%ki2{XU+Ki&p@>2O??pt^TKv~TQ}TJ6MXys=+uaXZy-?3Y^HPUG#dUvdK! zTK9oveRTU}+wrdC#_O?K?WFDYUC9moasV!Gn~4M8^znn7jOaJ5T zhhKiHRBv6DUB^Y&X*@W^^UMBhQaeQ{X3rfcxQ?^#cwa zGlYQqVVU&<4!1D74|siW=$V?}7B?O0gTqOtCb&fruMZAgQxn{2#Njkk6TJP1;|auZ zG-B%fXo9yN@d|J_(bNQY8gb~Gn&3_&?ul_Ss#4KZpmBx}alf6jBI15KX9c+5&RGHO zw{up22kM+m#UKAwWq?yMHNhP^CtYfdY5{11J9JK_=#M72(})M^oJ`rD5F#F^b25d0 zLWp>v&dHSi@jv2B?H^5WhdRy_|Iq|@sN+K;=X44l=$w--8#5TIbP#bkAg2W(rT~yX zZJY-;aZaZZ_k7ODN4&Xn4ti<1fHaw4)-;)bTM**GJ)d)O;7k=D|2rpB1}FsZ=5tP` zZ9K+_Cm}>UQ0I*C(V!3_-rPAIxA8!oGwucIoUt#*gX&s7Qx8b1b2@F~OhF(maGGeV zT$*%{)i`6be#DzQr(=bYT=FbQ?e$rJ_BYU7SOXQ0lR;A6ERM7+6kI#!kDbIxws zIFc1w5Mn9=X*HE@BF=(0KOy8e;=Vg48}a7O={VxP&pFwMH$NfdIO5Hn)3K^FpL05n zxbM!%w(&rnlc^EpzjKZaP6#<|<4l#H5F#F^bB?{Ab26&J6bjO6DvsNDpw7vZ3JM|O zfjTEsEXe(lDhYOGugq%j4PWd#hui_Xy&^f0`4I#%74|L9HQbVY-h?fTBG+8#OA>u55OUf%O=<`^1`lA)iJM9Q&WXVTm~&$A09I=;c%aT1 z2e8js-jbj}mj5+`#7$$xi^e3liE~bp=+`1~>6of$GZYQdZgq%h^&^c#fP<@Zq*6lgxH}S2a!hYzZ;Q3_vObsEO z%Q?H7xj}AEjI(~gp>YNfaFZD)ZsFhg%)xU9;^Twc)sLS)IQa1T!Rq_;|2yBhJzD*M zK6(1$_4;Zte|)?8;r4H*mpAL%)sMvA>PH?LXaJEnnR(*KcNB2wp8*8iWXaZPz@dEx z5O7cCopmLJsUzflz_~I)$#hI}`1RHN>>{1T&!*dH{o?BC^6J&d>2QT9BNRZuv3mv( z@Gwo2D+&y5jU$G z#si&mhEX{P zj8zh&yTzQg@j&OCiP70wrx6cj&Y6`J8jmxTgZw+Mk}G>8!2?;XErW+L=PWgqP@J;_ z9*T38z(bjHmcT=qbC$qEan2HWD09vdc%aV7R1NaqIk~by{>?cHO@%2N6hg!UbIgPC)dA|9x7j)R$VmLeXgb26oa{MT`=c95QPj%M34L#nd=Fm9!?zF5gB zG?hs(tF$S=PZDSvs#-252l7t(K*d(2su=hK|rgug{Bgya}ENUa~2{VsB;d&IU$rE9h%h; za;hqUI;U9;A%_tUriM__Ifq91oK7Pi=$vzCR0+Xp!~>dhrq)Tbe6t!t9Y;J59?+aK z4<68*GY=k+bLPPVnsa8s!>J*ZwN6qMvl>DURV5B-&Y5p20nIt{;DI`49MC@JZtf;K zXQ0k$Rzt|Css!qsW;KKyMm(GvLIvkEt0Ckx;sMP$vj&ueH0R8N2kM+=HH4hD@j#t3 z3Fw4SZmbec4WW{bhcxF@vO=T7fNBV3LN37rIw6!catR)ibLN^#NOR5{cu3Bf0}p7Q zGvCHTa?V`DLt3rPfrm8b%z+2$oB`Dk$~&i74WX{bk zsv)#%eS_h=(=j%tYK|wbp6G!*b3{#7$Of9Y#E;8bVnEGOHovG~$6e=fG&6(`m#5 zbdD+<^x+=TzWf)eutFNvdL2L&%}3gjGW*7xBPWYj_1;2kM+=HH4f-JW%H}t0Ckt;$hVg%ILUR4I!ry4{Xk<49Kj8kkg0<>YQdZ zgq%h^Q0FwOA>=gTfjVbmbjz5FhzmWWsas$*gtpcx!2>%XB+m#*@X(wyZ7QM7IaBb^ zoHGRv?1a#+jfdu(X~aWYtxds0bIuezwAI=zcwjYzcFt*5L&)J+C9oPo*@y?~oPpI4 z%0@g;=M1cdP&VR$I%i-tgt8G2)HwsIA+(FQSq&kF&N&I{t`rgQ?I6pnhLF>U2RG-W zkkj&nSq&j45m(^B%{di#aL%c~gPU_I@Zg+t10Grpp^cD}s+iRfa;PfP@SIaMmEh)_ z3OrEfoQ9T_B1c)Wa|Y_1W;KMIs!E{FX;wqXVZ=kLA(T4j%;;uorx6cspL1hCv(WN6 zm5zs2Lnzb6gIldtO(jt0G^-)xR8`t^&c)H{`_CU7-1*k+(dq~E$thN$2@ZSaeMQ@?dr!A#1F3@v=i}rUpS5i zeX4)-+344z_0|0B;{M|5>hkKA#<$|9P2 z3BB^%^7)$w^W1x_UZS5k&%UGh{y!7n|MKc@Z@)>t$17hxxOuS1fAdclzxnCMPZsCr z_t)<~S=>H-;pFmkaVy^MyPNm>$WLq_(EC08yX)oR^B0SotNA(oZ~flo)w{QI_3O%i zjW+*E|5N|E4Fdg$<*W4j{`PAxsNeTDiEQ)xF8_7vnj(7JP#!J+4fVp)Pri9`zCJrS zpI=``^3St}XD9RZ+2zHpjQUGeU-28a+xK1l(|=Qj>(A(a#rPH?yZm{={F4_xrZE3^ z`7O&|N{Rl9*Uv8I=jZR=jow>C@132WN2iO&mlq@{^YtR45JflFi|Axde_TF{9&`AI zH`iwukD|+)tLXLD-+GJQX}y%+{c!&H^5!~v^R0jQwSPN0ov-PQ*7UQMXD7?(i%0Tj_oMY?H0#Mg9W7sa`nnzR+cd1! z-jQ1J|1F*nHUH(&TgzA8x_Lmn&mHc56m>HAHLqC-7?we*IVw&FJ;4Uqkpe(%rd zJXG-zzVmkuo;wg9vh(PD9{|fsMzKG9h5Eyv=KI5@+pd0xG(&ZZjR+pCey{Y}>JKt6 zz5PFZ7oHSM&Gpym~0?Zu9TaJ@GHUy12T$KH7e5@A~Xl7k8u0H})RSzj1UY z`uow~&YjG+y+hwLmmMbiO?T9H9n;$m9x3jxV0Gd zjf1{Gd@SDMDD#$gqukr&|2n)&VkC`9z6-%*wCkP}sUz{8>32Q6xj4D^##di^;~%Bp zDPOw2e7L4)-zBxWUf-85eUU!02-7>*&eV;_GKZ9j|UKNdB(q3*~30mlvN~NArgd7bk0}f!l9AJiI3UG7grRDUpSpVK3c5j_Xdm4CwHT(<>fsZBFImM; z`ePFR)%WNRG06OV`ak*4-=lBbSiLg6!ie`z>FY`(-rp79{K}X9`tPShv!B|&&&`9? zpVL3)t!VX^=}W7>qEC-$@|OwOa+p{71U%{qXpDd?j1sIGQ4Zc??GNYFL)ygMe+bMKf)&b?zIHTRB*#2hgV ziz~C!VR!9`v>Y*kfmC-)B<0>Qk&=7IL_&_39JVJ>3DZ9&M#r7TiP3SVOpJ~@Wny&P zI@9K^nfg?52&^Vd_f9>o9et<8_$2((yV>UFow+TN@W87yV=EO2_Lw zyRLM+4wHX6F3KDF*Pa+1cj$MbD4~CGVszYTocz;qQ6Y+$j^I<4&0v9e2va=(u$zI#I3laU6-7b-Maw z*6->t>FaoRO!_+B9h1I}cgNI~j@M~VjE;*#$(!@c+hfTFoBGmQ>M$`n?v#nqalkZe zy8T)^PK=H_Wny&PA(N<}26Y@Tb)^NOIGTSU}oJEIu4lnW^KF%6Qko!nHU{+%EainLncvOO1F)7)t*G*DF2uk z9e4Wd7#(-Y#OU~>teM@lCw(37j>$hA7p0Z_>v#U?xG0DOYasY3q1rOd_FEvyFGigmt`ybvo_#6r;;;Xzc5j3G299CamLb znXrzRnTDqOoHg1L)^WE?SjXKmVI6N_FTcjK!#eJgNhEY49e4TcL_(*3On5x*_Ss<_ zcguuz+$|H3G7dtGLwytmAH(u#UIFq%)bKd5cKsM4H)38`oySI_{RKLmk(S zQ-?aP&4hK_Z5zir?v|-T9oK$#9gfGfnL5;QZ6^P8TqJZN9WS?W<8wW9=axpj0P+@* z(CHr&)^WFS!aDAjNms|aY)@Fn+c^KE-^Q_yyJf;U?v@GbxLYQy<1U#*LMPHpw@g^a z-7;Yvcguuz+$|H<@phOr1_m@P5DA^#wQ*ghE_Ga&sY@N#W$IGLb(y-v))Eqy}7#(lv+3g>!&|N8A=5x{lxh7Mm<8e(UtmAHWu`O(r}Zcc}$k=5y-mc$fK{`b_@mc#V8c^Rxe&9$X`zvqL6r z9q-Ir22{9Ka~|9wleUg`$fT{~9WrU_cxOyC@;N)}cSB}f#iid3nLHr3O#Y3>hx&Q> zR@&3v0Tj(SYvglw$fT{~9WrU_c!x~dI^H3ZwvKnk#N~6gv=+U8a!&nDT+oTeDsGwZ zc)ZMHWv@&#PFTm?GU0WVcFz85OcG>!!sBtbOjyU=GGQGDOr~|(#WYy6jbj~m%Y=2@ zB@>s=>6QuWxLYQymQ&j`61U8YG_s3b zEuVRfCViQrMiwYgv_b>VkfT&%H5C41S%D zTTRSyTTRSyTTRSy&{X^X?pu4IKvUv^Mj#%y)x;dP)x;bJO==u(1ol_4)pTKwEBZKd zyyBg0QBl(rs^_%T#2mNP#2mNP#2g1rbuErJ0~{|-(}qA(?k%BuPFqdPaa&CskC%Nu z<>XHnX*=e)ttRHUrKV6lr>!RDxUDAUxUDAUxUDA6tL*qJXykKm+024gpf2B56LZ{F z6LZ{F6LZ{F6LZ{BQ>dQPRugmFRugj^G&QyO6sqU6)%5&vJi0i?72EE@99Puz{Bb-` z&)JOpxIocP$nhdItq)fAO4UF;r?DpFIBCjdoxRKbuHA_-vlDWhH09+_7tn<9xUnYW zxUnY8kCP@ve?pEo{d$Coq9)|Hu_lbijWsdHE!!?o&uMC>Ks~3iCg!+p+cC#&H8ICQ zQ$95k7q|zPIUXl}Qq;s8hqeETnl8+7MNJpxxS}TJxMkY~>N%UXnm8W!*C1E(S*v{k z76j@!jqSu7x3v>i8*eoi8*eoi8*eoi8*emDNxU8%JIPY zoK3$Tp_)@2(1w6q?sqlbU&UAxbKKTW%yC;y%yC;y%yECMb~UH<;}`L9=D4jU=D4jU z=6Io+)(tv^Pl0;QrmZH9$3at0>+ClSTrxXxJZ`IrIqt7Pt}5DzISzKpk53zYoH=f* zi8)^Ay=9}F3^=|~6LZ|wPRwyjO@Vq&Q;rAD=QP&D9Jg&d=D4jU=D4jU=D4k<=a1uo zdd_0UoEtda;BzF5H9dbE57cv-+NsI=9U5zT{y5&`eX@-0WWn(@Fp#lSpq{f}J8ja$ z94~f^ut^igD>q(^%8<$MHZt zr?H(l9=E*T1?oAC?ezR{Ji0i?6xAiCHc)^;&!S7zF7OLm8)x`05!S}ljc4Cg( zYBGt(H`s|e?(g|h&1N$-yA;*n1A;$~X6b#5^%o(WXG}eUixUnYWc*EaQp_<#CFKcgjS=%AU zjWr?1Lz=#O>C)v(?$0NS;jgb;y7cL6fA|ae_nq%7?hSt_Kcv@Z$u#a9E{4B4{;fBe zCyU`1?zazbmr5UGRyy+#+6_t!7AWitiBrJi}u(M&Si8<~s z{H-b42@@<0(3D@X>BhF>z}!#X*Ycd8+Tc&jaa&Eyaa&EyanO|K0-p_S#~k+)b~Qy! z%yH0^>%_}?W-`b9WJWF5gk7-lBpweGcGmr5hNdRuxUnYWIBCi?>9fA=kmGfK+)`82 zgd8{4gd8VL`6doRFv$8Ha=h-3TWX4$kmIB&-!bP}J0ZvGFh)?+gd7J=^?b)tYwQ## z?5z9oxTYrNIB3c@9$#xG=D4jU=D0sbsOLLISZgQdxW5oeQxkLCRugj^H03*%THAKa zaes_ZSJcED2Tl2o5!Tv?Ic}*bP}o`b$1Qa=I|T|mjWsdH{jrqX0vGfA<`LHTQ=qU@ zZn%G4N~WE`xZUY?-z)8Gw=^{&$7}xhPQsU5?G!MS#J+*TP8psT+*DJbu+vx*#^c7CkmJUhFdjG7#2oj>EsdPVoZ)^KDD0FZ z?$OPD#n_S^rkLXKDb9EO~kn=>=R{=^)&)D)=aG__Ne zHzFrZx#yokZ5OELtoZpSIgee*p91xq#+oo5Cr!EM>B4P?@p#40(=`<}F~@yPt=#i; zVLLI${alZxCg!-UCg!-Mra(Ps#m|Yga?jI+{3&oyXT{HnwQ|qXg*9weru?1(}H)H?>os zp3_(pa@@4-8och%SQB&H&(pQ?&m9JQyutbLvaKfOxUDAUxSywM<)5buwjFcaRugj^ z@=y8a#DaEWj$3L9)N_{oTu+pLo-SagKs~3iCXUB#?Zh0n)x`0*pQnrR&(qPsMaC_G zdd{+~Cg!-UCg!-GJJf7D=D4k$nB!ol{PVs69}m=Xmi?Sqlz)yjsEOloTTRIE9Y3!U z<)5bu+6g&MnhMDEz)e_~891oZSQEzM#+s1h#+s1h#+s1hJAPgzQuJ};xT&TtTn_}lnVp#9-uO;c6LTCi z6_LXT_!D#7RugmF8wW=_igsd-gQg*U^J4Fe#Z6taNvM$mg)qDzx z-hu>&rYIzOOBUE!HXjmQQPiqa$zT+VKINDhSyHZKDHMe#YBfpo~9@!IwZ|BMKRIkJPxn-6_YdrBwz{X@-RA2 zR5AG}6vae`q?y$877-4kC?>jpl3%1LiivJ4iir;CMNLaF(fxy|BB`fW@+m9?mEKo_ zC_&B9u@cmY@{{|TmSUpU;NGX$d`xs>Q5>WDr3t-M ziSE}}M6$h{nkXi^tc+N_A!~|aqC+N6HV0I*6cW7&E6wyoVM*xDb~EzfSt%xyx0+0l z-q)hNZ=ERUeTt%x=uO$S(R1{IatS^XTAW93!U$P*dR20CEDM$9gVBu4A*qSN7`-Vc z9(v8EC<=+*tozH~WaDQwOCiylb+DA8C?t9l7E5Saiiz$YZXL-!@Jh{x#i7#s{8KC= zIqX196lPtTuvkLVQcQIJj6YRNVT|5{ai6B8Fh*}ejIQZZOmrBGYFdhkZtPP`bmQh@ zqDz>$dPA1OkkmNEMEAGrjtUcXKFZrGHL*-oi0!K-&i7o}JUh^qhiis}O z#&)8xV034@0gJk-MdhbFpTZMBohY~=D~dv*Hy{wYnhrYI(Q-Jivhk-S>-VT|5@oM&;O&Vfn>qk)>y2BfSt zMKRIq5P25Xe7>ca=#U+*7L^@7Ke?7Q9}^vtW}2dy=%%6qHKPsxWbUY1R36=HK0Fmv zf;>nsYKmf_LncoqAqs-$YVQlwj9NDz6CILfnwH`i-9I)l(iFu+_xGxfWc8AoPchLU zlcy<)i4K*JnxdHKkTla16{s0)K+;Us4l4Onpk}n;Z^W$V=ruZ!NNzK*3#6u{I7Wv| zo~9@!I;=F)6vae0wiFV*4$I#(Ermp{LwTlbp`eBYBzhgzou@caoOROdtYOliEivuOmqpzy(po$l(lCmCOS+QY4$!Q zy0N90=yiXqCp}9AYDVj@_*4pRmF|6kno(OMG&$>1mnGF+?<;P`VWsyq14K7&K9134 z4T+|u&X`IDqk)>yx-7u66vafB74ep$nCP&hpxmPiL&9qFG0|lYo>fc9ZUt(hnCP&e zSx;1;X0#5=bY%w&B})ZrM(Z$Pq$!GHbYn|#)&-LLnwDas8(WHFbpK#Hw?DF)qchQA z!bnpT61@h=eOZ&EW+^5*?0l+eDI~hBr2;jhbyFnZiK06)Z1(Gr^?WMg7`+B7_ccW! z(XB-x(Q7R~@|4PQB_u?gb*aI6bWKr6^crm5CrdxoEX72JT`Dz2A<=8Fa$i#v6CIX* z%W~r4n(xVQX0Ox=)Qr}koS;xkt%$;z(HhJ+Xj%$mboJi1Vkss%OoM1ziizIv>t-}X zVT@jb?69Ok)p{Qjz2O%fYFdhk4$~mAm|x9OOmt&MXQE5e+)D+iSt?L7T7%@io}&k9 zMr)=%RSv}Ha-;K_PYnryb4F{%KE*_rbxEG36dj$3ZY+w44s$ay0j~tl@-`D4ra|O( zs3wYuF57Z>KBZ_WCOYivqSt(Zn$eoo`!@e$>qLAp-$dA$G zluxDR3)GC(Of40t8Lh(HjHacS=%$Vys2Qz7If167km%LOkEb+6VT@jdBhqC-qgwAn zqGR(ZibA4WTMCI@g=!GZ=3}CpiVD<>R$;2%Ixo zg=r8?QA~6=7fVwV6CJjC(iFu+7X{u3xzMS#voU&&vo6*?#YBfmNX_PBqD!2j+P%~PE155NAJy0`Rm0i^=n~#YOwOA7ODRHVH z+X8*<)F|V|>h(JIu`X^P@ton|8yEyck)EafQLt56r)|vAYZ)+ zHVa*#AboS${W422+F=jPq8wQS{3hYg%Cn``pT7h|6O;JpAs1(x_g$eZvZ0xD$=n-%5Qh`M;nxc^C z)|O(Tn{q1R^ow=x3lQB;Drok;=aA^pHWS@~Q_IkEuM`D}M@@X{jHm$7A@VHxhI~d8 z6J6#Ryb*G-i(XEK$XWAoj1Dv0&0<$goD;=Fhea>4VyM`7>P+)7(cyqBO;H@98;fG1 zLz%6nPchMD(VN%%6dj$3E?dlaq6%I$ahx?1Bm{~_D=4V|3UKK(qOn=*FU$=*FU$=x~gt%u6Z}y&A})!~W5Fq5{RE71)zp zQxxaXVO5Z(C?+~=)vPIsi4MCWYl;dG-H#G9MIq74uqvok^jeqYXjBFcHJ%x@7R5w| zMO~Vf3J~2-S!;^o7~RHFZZs-B6(}Ap!}i|_mO2#`AiAFlQb59~C?t9rwk^@LRDkFv zj(%z>BzhT^mB_9WMaNU8q5?$scb(B}K8(?=Ermq4MgkJuS`-q!39HYw$uGKkYDSJ?gJOc-gT3d>V4%HwU%_l*+ z3`PS7j#^pjL{xz2FvL>usS{Dp712*bG0|nt!=m?{hA>Avo2+0QA~7LkKQVLJ$klIUWne}N$F}%|w@7r#zoh<5b|l(K76ctVi@f&1e~lc_f-CeB5_}1SYyM5&}erMC^H=itpvV z1C>MxZgN}Vgh173Id`U)3j0&MSAFA~d!_P@)Uv|vbQiExJp7Gp4mP}WRUR(8htmzk zuE=kn4X?`Mr}Ix1!(YqGKAr9Nul29@U))>t-~428um6_(@MZb?w*38F`TNzqMS4rN z96OpP?e1hgP8Q$(>6Ll^>%;$)clY1@f$z z`Nq!KPjv79iF^MW!#9uLlzqm#?_Zkl$LHVt+pBL*Z+7F+sGWR#6fe@N-AONAxX=5S z<>&qTx0WL4^U}8t=c8oM9d%~2t?Y4dFz9xY!DPJXoLu$U7nQsh9h*eHu>YQ1{g1Dn zUj6q(=kn^GTtNCe`}4u5HyA(I>THeU`Lr{Vf09R&>BFr|_>*rvePyXrTE0^L$zEAH ze&xzn|LYf*j}71dk@vmj$w%?DGwt@XuO1xEwk8K#Nk86-AIH<~U>47|9>wv)*;cK( z)fxA;YPF>S?)87r|L52>ReJU#N*(!#(&V5dA5l8}h*I_uC8_0-k0@myabDxMEAypm z^slTcJhAqvk6oWl=F@Jx=)dD^dpW(+olmFnIB6e0znk7Vd1f>i$BW(c#w<<}xxU#V zz1y2~=gD9++di01#z{QxEz;|M))~#?+2U^(vYDRq>_6O1Z$5~}VwYqxmG|H5b&`0N zbPkW?mzS4c)0WSED8IgR{Of!=lHYD8lWu#z(|zdvSHA9==$d}KNMAdcOp@^=iO>A! z`|}|e<6LT-x;0$dM&*hKOTs!l1?(8oxJE;daW1l&mYL= z-FeiRj>T5;iflJQx%y<<>BjD&7N4ef24mO1SF zWw!g$=A(Ejc6L&`$s&E_m=aGuKi7ZvSI+;(%A3CBT!`^i)33j=Yg+r9bWQTx>K#IV^D1M#`(xHEE1_e%DR zSa&>g&Hv=7qgg!fP1=tSolCtMKR%kw;`Z5hW?s@w+8+&OgQbhU((Vmro&Ax!kYklE zo^*)*JLxUCn3;5eCBejNj$hV37>wlNq!ZscijUfIO|f*P?$VLmGy5I+YUkT&sh=cA zv-j@bfAr|l_R+^le=^>lOds6u#UI_5SI+J)(%0QP+$Xwsw3GNytel8dZ^-joU)!mP zS?){^x+`Dfo_X>$zjyLA(&swP^B%_2?LnLzEWd2hz28p`NAhJilg_?$hF;QNyniEo zTU_g~ecH=TFQh#?at-}i`bMT}FrLLzM{)6BXRV&N^vl!Eqtjod3%)x0c${<|xBG(! z{gM0?hrK$QIA6atJM2i$`m4EgN20d8 z`{DdZ#M}`IC4)o^we0wxiMvd?gYkhh`UweMb8MK+_s_rXR(!Z0_u7L)@!6St(yPng zXUWI%-TgRDN^x}h=qh+Z|t1h9Ng{w z19_XfnaCyGeIo5}FrK?s8-6JNea!i5>E*_W0Qu?sw;zVS9X>Sh{qyv-b9NYa4n+al zZ1|V*b*OjbbhySjIC*<|-LXdu{mCMI(LK5R`Ck8r{qGOI_(0;g|8WmLyDSg?;U2yx z0nhMr_fV10V|d>^eC{6p!9D!9d+~p{hrhoj4}a$#{`9&${E2&b_eFX5x_kJId-z}X z@Z)dE!@s$QpSrjGL>}hpO{c_#TGkXT%Pz`A zTg!|3nfocbsDE_Vm|fJLyKBrYYRg?&c2O_fke}Q|4PA&hPj8>aN@n%j-GRW#^#W;$ z_NLd)eZJh!r-=(7 zUSIvJC5gMb*4gg@yA(45|Q@W>7D4@(=VSsosr?Cp1V07-$z`mmcDv$ O*gos#&K~pq?f(O?C@#|g delta 351 zcmdn=!tncIMz#jlsc!-qHnQol@QZ0_`6rj;C#4oCSn3)YPj+E(b`wGt(NQomFfyK! z!5%v$L$C*%RO^(+DYa8HGFVY%H(y}c?7aP4CeKbLrVGs5J9BtWF)K2g7+J#10<+kdP46k-k!Rv!nZCAwM^=lQg@Hj6W(A`WOgoT;s#ylAnX8aT5u{nS zkjF%t6R5dIuspvgB{{z|uS7RDGq1EHwRlRFG|TjwLLOcARm=&eeBPiwcQ>!p%LRR70%1fsgSpLqFHD_;pd*CtWmb&+xJeK>fpJBDSm=~ z5+7ffvKQOx<$W~U@}c1}uW`xq-i*HTzC zE-yA<%dIq%NNb$f&DH0mggqh4@zpM#M(DM~Vo?>q_1^c-c`!o-^MKQD~>!ZJ~ zDAp?qM>;6hSQL$(qIe~p&D1|t6#JD{O*}|@EUgAN1Cw+cv4^(uw6YlsVvj|K20M>7 zWAz#T5&qAqK-F46_v_BOEm)Ete_+c?4Jk=)X0QhQ9~+&n?H@;fXMoKE@VugxVh>bL zKA>i;*+|^&Yt0(5l9bz(Ri@MldSOav!|Dj^d0Bd>{wAxo0D*s>=L{KJ1iKb0JOg=i}4^9>&BV~ z?iALu{(k){weDY~^@!d%jp(IrtR}lIXkyD)&S~j!j*DPK@BYOovOB9nq1{<6AFjbP ztvhST)_#a`gzvpS!|m2V6}Ppzp&ZcgOz_4;qN^l zKmK0`hxKITJ@Vn9U^>;4b@Mc3_G06CTgf58;jOwRqAvnYj>~4rqHkpK$jxR?7|WsD zK1fA5^ll&aJkQZ(5b?1(4gC#Wm!r!7d%G{YBK{T$XhT1Qzv$n;SqOd6kA2M->J)WZ zPjhtg^n@jYv=>=F{+=%L)AAR+2oJo7klSeyX8RDzz?s&cwc+fbQtlxAnZveQcl@Bz z>BoV{lM2DrwC^Rhv_R9sm!E2SX%G^>FJbM$EJ835_RScq)J%)v^_^!2vl|)@Fx2GZ zFy!Q8Z=2{IkA^dK6w_JpHJB4}V(?$(+yy!7a2>ZGX9I1iS?GECcr*)Po2X^C!j+wW zjb?*GX@90Io%YU$oN~rfGZQlw=CMd?UP7#A=CS*FZ$r)~y$q3}?7h3WoH=!82AS(N!THtb`4GPtTD^w#60?6>uA5K$ z^tP8zg%MeKtTg$rW5@J5ru1x*DU<&{>%cbAX{=|PSYQ(YdPe?fO=&wk$$82;cV{%A z)c0A+v*_l%&uX*Y|DDd*$m%?cuER#qz53tjzSziGqO6JEj$W;`iG{N_1a6|;TPf#) zO)QE5>zb3rJG>x?rW(Y?7L2u3rX0kyWD9)ng6!SGs`G6MVt?IZXd>-9j(Ia{D=Wg- z0UNF01x**Wu}%t-%)WIsZraYexX{b*0Qy}QBzFgE$q$$^oDR_49hhPy z+cH#dCo97pc9E77X!cHY&jEUSC(BUqFrIUtp6u02^GGigaPpaNaVw@qUc;^;6M{q( zmUObiU<0=#V=fdHQH>AT$-q|jr}{l;7fa(Eq=>4)*2FX0ejQ#A zmnTbq#5VB3cI9LJW6Q^4imd!Gd&EK}JS7v8UuDYP&5BdTZcL4@`wAzI@CkOA-Z`$) z%EgwI6YSE;p?labZrElwjIz6E!E}Ew>&_-n<~~eXpW12v93zqT>|+Mnj_zY^{;OL1 zSt)9^pVj2&lv=I{(_1atv!5kEvh36e6mo#|`EUGA9bi$k!fEsXuD{Ci(8N#(!FKA~5? zWPgdj#i)7P!^S23`d2JUFJ44CDX567BI=(5=YS&8Hv3W!iGwDdL#+o&Sw9><$MQIj zEh2+2mL^|dmjh!3Bj0>J>>{hdQ;PT$eak&eW1T--M8Wwi%Bq(@+3vqn((+5}T_`|X zkFj{Whowuwg_n_Z^}))vmz8a0u6lW`!Btj?voSR97ewCV?^q(A0%m>nM7s4I2Iv_2 z<2yFc1)q4Gg>mwQU%t+=0>?aUbL#gfG}rrT{*Fh%G4#pzES`@kBF9O@4@xCb?KvC% zz+Pnhvmz>s-Tcu4i7aOSi7jO8OQCHzTSWVRW~KRMDIMwvIn%FP8iego5>k8oDe1)Fyh=6+d3 z=0;XWv{oj$;`)-d{stC(Z?U6pct%0^B7meL#@_Zgf|lQA+3ZDPcTls4SQSy;=MI~| z_{gF%;zp9~9!hiEA+qh8J>GqTR@`InX-kUAn0{NZh@iRMHQjvZ9@pf|z0VFYzE<&C z>wM_}D<*G6=Gy!_6rrLj%uoK#LOI{35cfIFM{E|uEwS->nAHvJjIb%uvBo0+2!Fm} zL<&Ti*V_Jtjgar3g*NvX3S+PrR(LTW3iz9iWq%9x8`8)?KJiuHdA1woifA8@q!k~EBPW!f5I*>dww=g7PjX8$dh+| z!@u_9=>e(~Zwv|82XbsHQ^>V6P76?V9}=|K(E*vP^4{|2d-$LLB+rU8p)fbtK<68U zc^SsXNhQPSu#K1E(*h`JKlHn*0b?AM)p#2>!dwjqi+mBVD#&&t4Ag<}z88Xk>~P45tv@Om?Ux> zZ{l_@;4;qNE6Qs#7DGcza8zH`P){tT3bc%3+ytykF`kag%3@x89~9$xyp`fh#{-p` zQkffp{BzdbmtjA}u;giv0^NnWNZ(?0|7IKwUBZjg++ZF?LxOn<=pilM;f3!qs8Dgf zj*qhh-zlyH%jq>Bgm2N`R$h3km|Otd4uJvr&c8zV2*%zMIt}BSl`i%#UvfL+Jt|j{ zcj509lcW7TT2+#Fz@6&il7(v&{@?huaa6SW7PoPxP zPL(3~7~CmE%LFP#aUWG5Oj08G8Ud6^p->c$<~0IUzjlv;+W?XI0L(-p`Uq{1BE?^h z;yZZ@utB8RuXy~F?}QTb8Se@{t9cr;1a=LSCYj~o82l}=%QY_|#q)4^KA4YFJZV$~ zw@I|90w2w11&VUO{$l~MFZmKni=VwA(iN{);x9A)z9Rh98!T;TQ3ck2Y*F9z0y|S< zcsGNe4pgb<3phxmp6~M9;cz@q>_o?km1q^`h+2Ft6HC#?CG*EV$DR}au!-k|{sX*G za6cL>P}aKlqw^6vVvSm<4nLz850V2lC`g8A<+^Z1fU{;@IFCmKsjjRNB)bx2bYy+L zH!w<2_?9|%>+>4CL6A?W^Pi90CPY!+2D}~k$v}ysOAYwD&tj980yf?Lg-zj99&fP` z7ZJKcQqhmkQ0Yl3&)~293$Iyee1b4BZJ`!VDGiaDk<41~VCvD3&j_6Vw2_Y*^2U6z zFULn7Bj?ljMttM527rN$MX3>B32z<90P(>s;$?A@8U;;RMz~*3_roR?#T zD82(vbiw;K$H@LgDrkS=C14F4#&~$JB1~-w!U~G;lh$AyPVctlH3b}_KAax4*LAx{R<=4W34K8I3l{BPnJ<| zXFf{MMFkjDXjf;9s32d2m@a&~5F!$BKvyJZ1e%=F;=1y0wK~OR!bqZdeYq?zHLBkY zj1!&ByYW(fAx#9_Cq2mBhD|+qXEkBO13fYM z20qP@g0c}-1OJ83jBL!HO^U1hHKDl5Uri{xKgRdy-n_biA=t~%(cYMe@|68{A5~)e zz)es^3`#FRVsSMn|LVi@+55r?860i0*tp-9|IR-tt}0LM1s=%{TAqFW1$gKa8t?*7 z3H;jV+iS59U=MNF|Y`Ly$!J3w|k( zx^f5~=>{bY1!#;5G=C`XWT_`EV#Jgk#zQUaFzPgnM=+Auq76?mN@!(;$3k)}HP*S* zkio=IxFsls@r?Ib~h&|;}9;Gx#N)=O%$KtA515v@C9CN zr#E6da`99?*J@)kD03RG88}0T^+{Dk)36}g8!9Uq*T4wY{ax$88I~n8q$Lh7$ZIfO ztWoDp=YI#Df12^~*HHvqQ;c0Znx#FA&r|6cydOI+_$G5O!=^}a=a(~hE6)BBZb30) zNtpa5$HocWU4mGfHj7u}!6jsVw?}!{ne^K%{xUa9$hey|8x9vdMQ+$Qn=j(1Cr>Zn z(YOqp$Cq1oJhp`NXruYO6Pl!e59jkHyqOX}V-}!KVyQtMPbfgLK9ARPk@zjZKW}G{^uF;gG@EveP zws^Euu%l~RuzCtx#Y(4y8?fV!rl ze!RkqI(#L+!JCv+MNEZN7`Cl(z5q`{LSsElnh5UJ+L+>3^OjU;HBu|c9>Y=&=xC_Mbv8zPqsYc+_8o`7+WKav)A%yeaacIjyGi7X<0X9J&)o0ly!7!J;XWb z(t5rh2r{=g>A(hl+>O5Bebfb)e9?<;M3wAD&&FM#)AEhiF@hBvc}M<-q;!X0ZI50~ zO4`H+KsY>^6z+HWa+0Yy7o2dqso$xYg%aTF({JyoJSgpEG=U+k}jXe!aTCH z(y{jiWYDHA73@A_2QKiWXNfZ}@|x&-q4qPy!Ew9YxC?t7YsnQjm2;%3j@BtQ5L-vjryzW)ZJHtq- z0ER+^RvuT(b>6wki!go^qVTM$?Yr)HIpnPI9kk}>m6y&tM}E(bGu-AgJ>K-joA@Jd zAI5(#tu|Zk!;jc(p%#9ACcjhKXNUJtX%*TZ`T6~>M}*1H4iA%|eWj3}$x1nI6!Kfb zc}$opjT7mv!_RU?4De8xL}-4a0%HWJZw#;3{2H)k0^i*QuiSSV6GN4CzZf^)?oaV` z-qih2I6|;oRR8cuD_&SG^M(l2M29!8Fcptb=yZBKMcVxgUMftjUmDu|7V+1^RP|ZL z0S^EoE0_ijzft@xi~Tu=Un#aya8AL|jrbyd9Rx@&&xg^a7qrrBhYQGx`jxln!l-dk zzk2MD3$(AOUqv^|!U14;!3D|=@Jj$l^tNNP#|=2$DJMN~qr@Jvm% z@n+#Fhh>GU9M%jt=;Ugp{k{<}`LLl4g)6HUfLg?9W;yiIJfMi|J+XsdaNg~?0hH0* zznt@*a(=Ums$}j&GVjj36MMt}|KfS4D1cUE`In_RgZ+c(QZ2vX9+a(gv#Eat8au>4 zkgmq~#nROl{sv_x`XzgCy6O27|D!e>DZYwdO-jv?T#M$#Eeu}R+^-0IG!*33t2~>0 zE}c~PMJPPRFX~xZxKZp>E!l6KNAz5mEIZAr@3+wcY|ZvtVEwr{&F?Mi&(kgZPSCyt zzo5LhMHQgd!vBp8_XN?3A^yc^d6s`P^=jld<9`zg5sK(`Q#kd15*6#^cP;Pg+YZ_^ z#J}ACM0dgr^65i(FNgv%{66|u)hsFH{{M#O4PIO{ufd`c|33-@-RXZ-K)PQz6nul| zPE-G=|7k0Ex@_>`K$<=L|3d>qZ&T?QzyIA`PM|J!x$=L-jBv)Sw?pBKsjNQl9p?mnF~s6ItLDx;??a=zl*x*o)pB z<`<-n54Ljp5BFPm;J+geci|1GRjBqu9u-T~Y9q@@2gx(>2R?A;}qv?lP!1NtnNRL@vRY_lhPkX$dl6cFE6{rZKdEE zIKB@ou@$wIhScz1?753e@Ly-$;X{5k1p_eydI6S4 zsOk9iB>&%dc%<6{I8_f;Rq517o4@@Vj~DQ)yN>@%fhoKYPP^;)lXWL9VzQc5*Nxz6 z%BtsINBj-p^hrH`lS8bWf(j@5hx_xMkt#g9N2>5#lm?V8kup4;m?hF!fr)5*Bmbc> z{LM{y^WKW0+4V6%M_2O;q!xqyJBvvtmgbJaL;9_GTNjm6)6tkA{G}=A=B+>H& zRYpEd-3MYf2Wc;!b`ABA)BkB7#{g_^ulEC=!KKy zNH71Y|2F+#lpN`wMv0ML^j?gc(LMk?ujD7Y=Z5%siPr=xuA+83ql+L>hw zVoT|0mMzLPIE%EkjnJ!?m8Qm)6{gw)N4u4;;@s2L){OIdWo7i$qnHl1ht{3Ai0JFq z(RLPpQ`&SMZ+ejud%+guoY2X3gYoW)zWbUvU2H5ATPxj#L{&fMKW{zoq+%(oB=p+X z)rM#D3%l8pd6lwiS0<~Q?VSFG((-ksW!aT(EvGtrcenLpe4&!EkZwM2+hE;^i_r2^ z58F)fw-^w!dfH4pBZ7Xx&W$~7RXKMmN+KiHo4T*xRcI&SP^TUfAd zTwm`tN!qHPZKObhPhairVbXb^Eln^H-a0EU48Qcsi0)L#s-z3pj}l-~`tCDHkzw#K4e z2yQ*hB{+y)9%h@OPmPvgIyqWyrBoSiGx=1+T?|jA;lmN86m1pO(Q*_zY8-Kg$h>Ix za-yhn^eeWKj8=}YwPhP<;%Hk5pSQe#>Xj1^C!=1qUFK(_Wu_iF(pH0CidJ(~!`p8D zXX)BVTOP0|e!LM)i(a!07bL=r2BVaoIFMA2rj4?_#!)HC7t?q-l`YzaXs#snMCqf> zBPrQo^!;et2rastG#&|N3=604U}X~8<$1Ol1bGRN88 z)O#pi-OI@$#vBhncX5V}x8aaZ4rNZTWwYTzjP*LwwF$OPJf|Fm<=Dai?=%rTj9dBW z=uL$u4#&whF*qjV+U5c;YpM-L$7i}t>jH&@3ua8RrSkVJmDgD+r%Z;*@A;|>0{MR3 z=E?Bvk#cJHq1O~!20QJg-Q_8^%IpZ)rrMh00-?zqg!{#w{i>;O&dqYN<1(fJ?SY_+ zrO3~;JEqyv*iEIf7XXY_iZiw8(`~1Dsq)fWsjtIZq15Vi z<7;hEHh$2eI-scdXKt#!K2*YR8DM9&V2XPxhDag0}}pkA1)W4JsU?OghU zZ5`(|E66NWlLr2b*+AWii^x)KezC3bG^vM6alhIYc-kb|<6n`vd@0Y~uwC&qsoCJ> zO=Nzci8P<+t;oJxwg!w(tRTZ9?luBv9G$*zi?JtruttlPiWK*?R*04Xg-2JA(d*oE z+t!!y#mb7slztbvR^8#EvS_t?$f9TyY39#+U>{8oS&|~|+g{c`t005(fRt`;=#jWr zNUX&_fh+Kgu5WMis}higMUyBu?~`Zhy0z|BiG*~ z`TfMSZ+u(+;##_I%NRfHf^W;LLfTQ@p`viHqeU-wkU^%jb*;a4OkbvKT_SC@x1H|B zTIAeVShI7sUh1@-zSXqN?i;DpAzjP!ZJBRqi+x*OFtx>eeMPbBY4_r-tX|X3u5or* z3b;(K6@dWPjTF$Us5a8KB_KeX?%Q%IKpWuQ5|sCSU;w{dQ6|nM#k7&USS2;%b@j-< zOj&_Ag9|L-8ZW>it2;go)Nt6WN+mf8t5BQb+GgucT*N3$3ehSSXrd4;OEif$X#GMp zJh)PlX+@}J;^oZuL$!Dhi5dl=CA7CaZIbhf_Q*K5OK1xUw0}}ku@?g-rIcoJC@cEW z*|QWvQlDE%2JLL9hdQ|TCU-~9bnY&#ZDD+gvSta*4~I4CPF#dFqswTs3N)ogXd}=> z*?-_ch!;1yTTu&k+9Gi}ogb>ChF(Bf?HWI+_@AVZXl=Q;JDpxhy%YRHwAK_GuT{%w z2_O+Z6_m@n;DyS?<+RRTZL&a(Ew3%~YLlzu$K~NC53PKne!2pDd47)S~%0kRF)k%sUI&M| zU#+atR7@T1F=wAEH9n_|WVq3NC)KE4A8L3vm84D$w1(8I0UYGrzS-w4nAW9ea|$#K zO)bDHm>Q*_OT5_xQ_+T6KL1=fb?jH}uy?8adqeFC=h0PU*hN>N!GZP=TJVZifnIN_ zg;BevT6+&v2GP}~+EP!GnkJp;h)FjSi8ig7H=1nf-dxKofK{o5wx~eUpDmsuJk=6I z1MEfIPV=&X(pqWv^yyV(L` z)*Ve$Y?3XWaxyi8O(NDw3v#}msnz3rha%lUKeyF3Sa-On>~x|XMxDYC7m+EDofZ{n z8rA{!_+mBdsErX#!k*W?^@ZdijNeg0@6f`|+Pj`R=sQ&0fyyz*iweq%m#-^y)rQf^ zuG*;J{9@L!TOJ>mPnvKBy}K4ck#|_MV}7*hDySw^QFGn&ZrXQRwHWEgssgnJtL%KI zJ0hRgjgeU%Wo{2`wRI;h!rJ7X$hmc6)RU48J+)}wAx6HGWVUdNs7pnAXMkM^l`CoV!J?+a3e;A)!G7an#usZ;iS`f26) z@)-4CXLmnjiIH?vw2h4Mdd*~;FT$V~v^E04>tPu`=!;VO#izu7_@Xw)BVH;wvA;H4 zG>Hyg=kY~lXZ!#>f7AX}p8ivKx+0Cqfp!mRdX9EmH>%1$(5lM1a`QmA=3$H~8cz-c zsa`@Mgh&L(2SeR{w$P~2%UTUyuBx17=e`Wj$5d4xswh1O%*s`jAF2>ntc2xjla3F4 zncT9K5LITF(>X{>VtPv@u(=ZWkq5UaSm6^Q)ME(vHmWKs&e=n>)p~D5(M#EoGZf(G z6|UnG4|yYK@X%Jp?#1yT!9BtB$58FEK3y@H3cfiN&9~fUPI3ke*RYt)!+H;MRUWF0zchHNYQAnygzC)2N8iR@3 zw`uoSZB~J%$>X$Z1)7$Q*M2I{w0i=|EASQL^@x`RRn?fAHc?xs7mk(vT_{%0W-W7} zEQ@t^&eb9~-j0Zx3KIiq$z*LZE|F8T+Pqw>3h7x>5Hx|bXbLJmg~$WJ1lD(%s_hnk z3$b7Bbvq7crS^-JbN^}DO&mdxteeuP=~^0Z8Y?5dPz5MMsZ+EPyt5^x^6QY&lxn`N zJ+Wv6vMetK%|Ln4REat7BPQ()?OlDEGHi-8%>LbvZas3HQ8Tr}jLlan%qPbzxLn=w z`O1X&*%+wvA?S<|Z}%d#OjtWx8>sJ80=CD>kT@=}ykzI0udVdD2~idp^?7F&T@z!&Sp3at^Eimim!IO&O3 zdeu;;$t$&%`kZPq7H3rx9(5F{X?M*MZ&Xtwy}>GYZ#s0x+H%k;ZIu3=qIgGAP~>WW zS1MdbfQQ_on7&%;qVHA|A1jKI?||Y%i+iTHnO;q11#js>Q3S4Y%{y90#=esNYJ+yzPR)*=*tIN)w zT3sfdB2L8pBxfn7R*NHf-BgF?RhJJI=)`W6(37gG^mKE#c38itlsjKtj_sR!(1`->4%gVd+CzS`x}4)u z_GuaXeswj+?b!!AZaRcoxT(&#&$V`bK%?wSSUh?l^#$Kr+)}LcDeVN~If~f}XS6C5dq(TWhguxVdFXPS zr_N}Dd0E$s+R% z>6fthR(Ike=Ciw(v~2OW)X<|e9jL%Xi+SD?K@ zYBJvxuSV~%o7zVA1+IYO4Xa7)8*E~t;83?g3*XTViu_Hh!+(v>OY2fc zZ*&@w5t0M2{J_BW-?S*kAH}QJ=$Z(i`huTJT+$sam+LiDLBH`K-eC`{K~bad)son| zBJQa6U6=<1d6aAOT`iWE_eBW5hc<-}P6O^~rFd;$gwO6lUmp=Iy$}RMo*%_^>nIc} ze|YOCXPt-lwYr@3pDTiS5zqNJ+sV@6cg+9ilqr|wVW<1s^ODZqj{_xSQ z-apvzfj06ep6ow+f{$+!pJ+`AaNYJq%fS0`x(qszWAd}~&-8i;GE(a#$PCjv!r=;) zT9k=BBbHA44ZJ9s8K{@%nF*AYg;V?PHxuo*G&l) zE0S*hy20^IlhkfTF=)3Ufzlj$1GN2O)3aP4srYs`Xpg2h;glc;F;OL5$Egm*BQ6*` zPP!3q>H1&~Vy>a5D8$-}8P1UADF@gkD% zM28+z0Qq}|-rR*ORD=60YIxdK?jx~2d1{FnLxQ&C(!E~&sp01Gbk%3&w`ok>E z`nmAm4AA=&z^_zHZ{%VwyvioJkZ*fIq}V(cQwq&I?f6JOR_7>qOJI}-(=W9G}AV1%#5m$J0t`VgjFNR%=A zwV%l!0aRnHGV6&Ix>2jV5km zC0I|FCPO3i>IFzHL?F~GwW~%#-_b7Q_ahObU@V-y(90e8{Hqv&U8D5-Jg=r2d~?gX zJP}M=%Ia^i)xr_bI)^sTLQuUgm?qNm<$<=EK8@D9D2#BDA1|4`Mz18^5ca~^Qckbu z!r8k5mY(*2`RbY!xl*s7;FA|z+E^6qMSv4Y+K zoMaUKRssIMl_+OZ?q5r!CGCJ-MBv||eHGz|VA-gDYBee+IEPo#_c9(`OM1b6Pyp3b zddrEZD9Lz2Ej1_HqEoZ<(kz+o)_@=Ms_;Vs6|buI1BOgD3ADT_22=tC)YKF37HER_ zHbp0aZpBIUSUnuzj99&%o2%vBmwdSTRnyZ1hMb(G>&AQF0w8BrTuw7A9&vm6V?Z%wu67&8i7`n`u!^eVyPUwkpg{ZXK67C)U!}GtQEP zG+ZdNw*H&A6}eQvib~hhojf7QYhp}Jk`tr-KjYmp z5~yvm-btc~4HsRnb%=$~Ti}K5$uut2gRpRv5y6*x!3Cx4 z%gNGwN8pL41RP1zr*dbKsAIzErG^-h`;uf8^I<~-o0Go9MZo1rG%s>x?l;mXdeR8< zvt_KDpPM#z&CmF&4F6T3EpLqZ8J5ZHu&1$pfj?4~)5Rv}7t3bnpH1|ojO(@CIu+M* zjwH#D3#65qu3&(Ir6{}^2!SfoqE1`0^mrO8+Q3X^@g>dl!+M?Ck~*oj%-jtd7InEf zk(M>rbG38@$E$dmm=GdQ@WOU4oZ4#8x2r8n<+cMr9g>qMTZ5=UOFe`4R-krnkhJiJ zmWZXHSdxg({#korE2gl)2J z0!ijYR9H58y^CHA&oA6YxY#}HqPG#4vYNNbB76qWWvdJASXVu#NdASQ>Rk{-jY|Vr zxrmQ9Th5ULf}!Ymw+g&F68h!>Sge_|S9g7cFj-E#^Zf%{(F~W!n6KDF4`Mf{UJu=U zBz0mBy{7)9>a{bn*X*mRx(QD@@AS}%aDLUYJuF)viBFxl)pNY#!3B;?DOc;r1dH2@ z9E67;U5}55jp(f>H^*FqgQr=YV}1Y;*pr5y3-fa zDX8Qp0{ZvUYqR<;(6xR@r4TJj4lkunB3MLK|N0C1TE;q3e1E+wiW>04wU|WrB5fI{C$QNbFqqJtJ{TubPB;yG zNgs#zzP!mRzl=-`SwhV<9^XMtIsVtatUuO1sVm3OM}kmQq4ez_3?!E={|wSI7>?h; zmT(fO9|ew-aeN32IznF$L3%k-S7phKL$R#!~DpX{54WM)BVx^&R@~deTWl>mkup zq^qxC&KpEGUekAJxe78tsAakD@+goGs;7MXc$9vV&#LEk4v z&*r-<`G1O4KR$G5$t?$XzX^Jh8;mTXcl+U&#%fcYAft!A#^TZ7OWzP2`s{rcqCMu)D$+9wf_f5SF)*_$1 zso%l{o^yNVlI5Am+3?*SsyZ9B6*y#<)1sZ{X6p{-x?>QCPvM5m)kB#t5B40T#JckW&s@P z!d|=pkfi!*lIxz2<$9`;xMCq@jU>97kK_xuoZ76&Zs&usV|i$g_1p6KTTpF>!K zC)Jk$ag{uxKX^+IU~D`UTjWvH*>91KQ~R@&rjCZ&Jw0Gqm%Ui;%$HjFSX1qLN?zm= zJxGA$e1xmq2)yXcLH6`}OY{}`vHEg!9H}pRx;G1SMan^E?o!>K@pG0--dTnv$Q31^ z*9y4g9KIrfO&`F$XZw3T7^jwFGIL?5H5V_`fKD&Ne$qL5Wd&vf7k{zd;vsHW#7fk2 zfNlL0lV`t`dM#er4ZE~bPY66G6!(q&s8!f1N^T&=sr$1DeLWVPBU*(_CIsS)9F<;; zSUCs@B0G0%AhYwZO0Yj9N41LW;6}WkgwXhRketyjqR6@Q9lZ(TuQX7JV}u}5%aeo7 z`1kZ0j8AEx;>f*5=d&7!U9?2ny%wo@3O!t-w{v4j(^q&Q2#DNcokDlkVwJYt3kKqd z_4)~*$UrKy0fA)cMQIzb{Q6v}Mc)8|-w}X9!SvS#eHOn2r9>&xra$8B2kE8+`eq~O z0TJT7F?2D#+i3Jgy(<613zuD@pEe?EUXtP+tCo6fSI(iuoAiggSc>w^J6>?Qwps74 zc8=!j)ly{KRZWqV@{=vlwX)OPst;h;1>V08Q{&9vbq6iqrf0H7bY~kT-?|jHU9XJG zwY^9!)(XC(3-;x9td1<0H9Y&fU^jPQF;X{$;!k5+{N3=@Nl(i;B%@4hH!IXUGOS|-z%t99z z@!;srM_7bdG(A5?;r*#E%{L!oxo9CQ+>OHEoEIES)PM#vG0~mcjgG6FqLTKV-THa$ zFXhrlbZQS`@OSdtt6%1}R5d)U58(yS-TiusXzjia>jzwAQUC2eY}l4{!?O45acGIM`BVKg z!!IJ_9z@TeQ6{A82le&ZI3Xe=XN&+@--i3-5M25i9XX_b$7lH3Ghc{Gq>@K~F@wq< z(MJjlvG+kIk6?VimMY{GciuUozv;);3#JWe@8{425GnM^=lUnwVI}mSm(XJ;!14f{ zJAr6EYq=@;EJE^+FZ8w;1yb&WlR!F4Gf!gKBamFf3qSqf4S)5Nz6)q^r?GuAN%az^ ztzWr{Ekt3MAeVK_S>-MB40Jq@s%Em7GuSZo*BA6$KF6}`)r;8O zd`sXb+RJ%x=TN{mFcMhaMs9cp-kxvtbl^#&ycobJsdd*&`a$-o&^p8I+DVu7Y5c6E zfJ`|(zSTpi#kY7Ea7l@%;!))+efBL@ZfB(k>T<<$36@xEMqSZ4e~>2A!vk7&P2X(Y ziHjKh)4oFveqeP*jqB(Pd}{eRI`IK*y{?D5(5_#{#OFe*{5{Yry3p2skDQ@IxUj>1 z&=-lnMK@OU=n0Eua9@20Tgv>XuhTm=l)cfup?ZbovAZX-oct%u?7VkFEi+&s!LJ@nSH}~9M_47!C4OPjt9ucaxKp zQSq_%eU+Z4u;wWfe)$KIW;-AJgMA6MJU`xu#{V6R)qHs) z(Z5uM8GuV6&gRUhjxS_E#{i=n-)H%)wLdVN6yj$jF{fnUq+xzWKR4nfFGSHOzxR%- zoQ-xA0_JTm46y3zZ=?ZH%0B__e75qD^Nzn!k#ViDa#B~DN3~Hl!;fJBkQ zA;xsB;d`p?ITK$8FJYvJHd%~%!Muu5e7Znj;j>xUC5$>imW)3y;S~|LOBh8tw#K3c z8rA{x@7B9J9AP6zZgy$oBdu!_IdVHIRQ$|=MlHe&)2~C5=j3~W&N*R5ohbH_fY;^& zpse_YPJ;#z_CgcycPe>@CgP36Fz4n52m>u&@y+w%TR9b`&vn*J74X#xzEYS{mEs!V zi-R8_-1uCWE{?=rNHZ>LTNTn~g(N=SNw*t9GLXdY4LEBzGJdXz=}hXjPwD0;n;zoI z0=s=R1ethe(pmT=qo4S-6X_jcvc1M2H_cDZ1HR`!Z@T3`UNK!BETP4d z3*gNvce`^h_DLIN9hUTIFha$P}=Eh^a;}W!}Q!zHaGq z7i*XiD*9eRM)Dlls1LUq(^Z!TPJ=2Da7aT)rC(Trd40ts5VeS)ie6DMOP#wWzeW1Ieu>WIH(M^MI_ z7~hYaUEVZ$Gj24KE;Q)sEMpYzC_5aVA9-^&SUj?9-Y^@XP!BVfxxGi9#Pi8pSh=D0HRV4I6igL%dh-X0L~+4V>BjB@<>X3_=rrJda_ zY)?Jr8@~uNSwXAiF(0B39o~q|l-2E<$>{TfJfg@2#`F4&W-|JwH4h>5(c6jpq6`#c@kB8PBUGxRu`M+_car&h&i>VUH9^e-n(~ z2+c(bZ1R@Trvg9IOnu_uB)lo|bD6zB`5Y*ocishs$bK|?uko$^m*V(Hh^$CU_93!= zr#1VGPj$VyG|$#tn)lfWw=%ysQ%UO6{YELqi#L~!EaW~Y!pk&Qao6fogh6qdaM(xy zmV9)0xt3Xp$N9qR9x*DrxZts*I6lN1d7%iH{4I;(&1KN*2VoL)kik&(pfQqnZLWsX zk*9Q|!iS6}Jg2z`t#B%L*eJz^Tdb=cfp$4cyBxQ6HadS8bM!P{B&i~}h=`#rMeJdG zkuSoxM~oPVk^0p;>e0{H<0!@y->MX(W5*Ooj`UxT8I$;ashWyy5zlLRAqa>#StG7;xjpx^(SSEE zfFV)}WW}Aq*tSB7a?fDYXVd;OMpK?+;U}MkPTAD#EJ~d07Q)4jA4`{Tzb;|q7sKl38GVXi@8F}>gS19`OqzpUH@$jJR zbH-%8vxUg=6!EoT!x%x6bTkzORkKR-6`hUjEu>&-q!U zpS}1zFWwU`qPD)SY`&@Vag_bgjc^_8#1T`85l-8`FBY0>_nVdsu`nSd+G)7%fv@)YCzG56Mf?bkp_fR{g z4m3*g^p@5KUaq*+YuwT&x1c*@W!3Dq(VAgbMAFJ)a?c&Ocn}@CW6b3fTY4RynE?)B zn)>1{5GK;ayGV)?g(mTi#)V6|`gu@GRcoyhEYrBU#jEW1QA2JOZFOn)eUw%J$i#5z zzOk9@6M(3^$bM1u#eXn90F=S-+kcF%{FJ4{25v_33zia}Jb)6X=*R=3jX;p2sOIlR zb$-(eK|rLlPboEfxA#_4O2F5d{VD9BF^m^#VWxrQ zT`}DZrEF&Q#JghPn!$UvQl5_H<^aCR;w3%3p%o1+hXcN$rCeRRitK*o3}DHzz0Csv z6Y)R-p9%&~tG+(a0CXWaf`3KqiS8<7*1>L~8&0wQrp={LD}Qq(G7NwXDXy?-y0ywI zY&!Wpm>>#{@;0+M{|g#TuO#H%=he zG}hMF;^12GLN9%xdkOwcHwS77iaK6UC%bgrX_(DXF}vv;{2R9_FjlS8O!KDJT~T*c zsB&nHwVS42rwnVIw%=|>l*32^tJ-{Eh8nSDE0=b;yMKnyi0y>m(G%6cp?LFGjTCeI z9+l8vGQUy-oj#v#)G%*o?<(+WX*U&3ln_?m45sRd<~(h?0&i8|M*#Er8EQC&)ie*Y zy&m)IwKLrc%_qsCX)W_Lelo*dC*b4#a1h>=?X6MWB#1gmO_R(lpr{97A0(NzaDt^E zPHb&-=gABi{K*A{IFHme@qDomWu=+cUanDBsVN_Q1+~VDOj=!SB$Nxuf%0g@vx>T4 zS+=!&D%Qvi5^2VnSI>-KJifJ@ckE3BP}TF&sIxq+wFY=q38B=lnVCi%nwjlIi|74?;%z9ZJ2rC5G)L09 zOO>0ONw~n&WD%z_0IIc-y}T+rtUv%5G^qvpuD*h=cEe>9lx}J6XS@~Ii(`Bd86LY* zGR%#0lINih#pr+H%8D=yt`7_Lo)*VmJ zlsge)-Y}OIXv&&tRuo|2<@GZmyH=)J1|6Ge`ioL$-YheWZoX;O<)fjMsA!(d0@~0_ zby8CzxE|H=SzaihHD{w+hf3xSy;ZoYs~|#7fbR+$)C5Sq=9qYaMFP}2TGQrW3f$qr z(1V79K}Zg85S+!GCFYtRa_o(PMTSdhyf$I}2lFO$4)mH z%sPz;WH*@~YZbC&mzAT5Z<#e%lym!ACf+ftkwsgJ;^Tgg7NNet`$#MC-2TBD%o~|y&s0TWH2+F?V*Gm0OaYpBiEYVhjNdUdX}Q_K1@E;MaPox@Ut#v-W3ptm zHijOqz$`Dhb>-WA5ihMYUsNEx@L=sq9P&Z|6SWYKVk@ZDW9*O=J~-jzGrTH&ie+FHbyBrQYI!bo5E z<+Wxv7weAe%mkj`3qQ8b%y-dC4>t9J^SfDerx;E!dkg5|g#f_C4G7%3vR|po`>Jzf zS{e1exmKUhR>sV@wj!-i=0=z^+Sz@hd7ZJDl=T5d_)O}%+1y~=@tHuxUSqQ@7~u-R z)l_Dy8H>Mt_JuaLRl9~CZ$)pCrxojN*vB*U?`-u zQxlf|Czx4Uv{T{m{%*K7jhvsD1992%DQ4H_eL)}Y#$*Rtu}Nt6Vu}`#h<5EUS8==w z3&{;>*?t%q*G?I^XTKTF__TJ)_2cNz1K0zaV=*@mLGCo__^H_i7b$n8FR009X1t)5 z<@|!ru$I{2g&-iZrgC9yDvy&3TMn8P_+c+J@D4qM-c?xPH2siSieL0XC^}8J&Q*or z!!7YuQ5(K-z$`(f4B@_jGwhU^XoZy2KaK7ZhUQ))_+h6URN&d@wHUY%QJT^$_wWeWz+&}{QP;| zY=CbbswZ~I`$TA@3N3(TNrbCBb?AXu@|{gDny)Zkwu77<%F>l@%v+wj zyO+$ra3`PcM|_K^5>#>=r+jOk)iXQDKxo}TR#Uy#xTUsqW?V6cao$~V?M~lc6D6qY z4qWlZ=67ZunmqfNczI{1{0Eg@Vy4m|%Ktcmofj?%Lc z9i?X{J#bTnIpcpfXE7ezQTA6XU4Lk{!SRN9k4*QQl{}@R93hS=9=h0$YT{Oy@}V8i zQfPK>G-~t6OjG<)d7oz?1pbK%M~TNpeRc%j-hbQECg--+f0>;GT;^eq9%0Z!JYstI z7xKYeW##OSa(OVr2TRsOAN_5<$d`0f3)`7qa2oR1d?J3T^AWPbtbfe%e5cZtK7WF- z^FH1G$9x`_tS4que#94a{t1d42`ZD{!(NGh;{(n=Z2w9z_LM-sd13JPJE{@&en(k` z58!r_yR4eQ?c?!Sc%?tyP?A~|>7?eZ34Xxx??i9<+2e4Pl)s5KP)bXS6|#TDD|S+u zv$DSz&*uL2PB`uio^5%m#qLI7AS88CT`FPWRBxQUK5th5L5}?-C9km&Q2kBXH*}=QJ?qpvvu41Y~Cttta+N23yDh1gR>t6UpfQ2Ag6>ka|K)7eeI_H2s@>#Rz?;`Z2rtT6Hw z`kmtTaJ^1v*(qQsl9776{(=i*UWh$XFvK+HSn{+5exdg6jF0oxbebSeq#-5ITL4LQ z|F5re531_8<2d*Dzza*&iQLcF34fn>H1r*hDk2YPI;t6dR+X)rpg8n^-g2m|FY&{`Lae%!EHa{Pyhb zIeYeg_j}Jhk3GR6wz*q73t*1o$^j}F<-}g9++zb&Q!vGUJZgP&pxX9-i zJ)!P%vsJ%_6nt2jJ{f`$`%Q;Du;#Z@)H@z$oKHGsoLe(g{W_S!Kl|Rh!c=vP%lOH( zJY3nTeZ>6-qsiGN9iq4T^4adH zoTDZ=Z9b9xx4w+}GTMY6*y>;1A8#L1ZSJ@Nm5bWaArED=ul#m_n&!P{oAqz|Sp*94 zSv1LK;npos-sZOoRg%Z)o^Ac#N$*&DlN(p0KF6c`d8KgLv|_akkA1yfiZK`Iepaj| zx97y33s1z4@?cKOTq%G$!Mj$*x93!pwCBXQC5v!oPz#vR!r z;hZw;dZRn1Oci?HwmEyVMZn&2$?+^v!TUT8W%H=B$CGcMHzG}=D>n31a4y&yj}d#D;~edEo(J;wY^TsYURTV#m~Ht zJ(cT7VQXyend?3JG^egnxbHRZskgNBNQMMT?HB ze|nslTx?~8TlXhe;Q;r!lPY;rTy|HrzjG^*T-s6V=OxeSiEcuxddz9@%W3uItX4Iq3+@MAeO9gXG&Dz?Q#ZRfXLI3E zk#6rc=>4>t(WYYYOz@O8HN^Rw&8crw@yPjIoBD3o)?9cd7W8q<71uehhIXHiC8pSY z^1S-t;MsVWlX;oALR=#55qF8pp})Q1hA6W+!LrL3VH$g#74}X zV%8H8j{#vsMqePEScunrn=;}QUIcAU5bFj4HN*!|!23kMXrK>~83Sa*1i&W-0YiY= zh>F7Ug?Yt=OY;^KmX>VR=1@Gc4iMFNv5yH5FX2@zW*X5a5$H|CB>^$SckpHb6HYV` zn~2pZz-vS~W;r+WhyZ4{HkCu?f=QS**d!2N61Ru|=E*gc#D9seiREd)GU5_(fr!Gy zo2EYz7zR`lf55bS<{yT$-b#1T9%Xx;;A)!fpu{J2^93-St!%h6T0@kEaKf>?;hfJ_v2>0un$;3LMhPXytA;O*qLWw)XZ2|5>GhYxzSwI2de-ZEz z(w;}`D`-6Pl*vzfZ;^!R3M62g!95?0g;CDc4jCMm=07DFW~fv8BYwr z4`CBY%$otsCA#9+$asif5j%+OI5aR@iMkvhb1hlr2bL1=68nfbxxg%7VXe0$Z*KmA zCG+yjH)FPMGvB>;K@AIVSZNtjT85LBp`^{%sG|*sl9pklWe8~*K3ay3mSKZ37%f_c ziL5`q3gFE#kpGK{HxJqeU=U#G*wgT128nAX>zsMHgB$p+ygRVZi_@pcuR4CSFn# z0%EHdx_iAEDNWk<1t=ZyDL_xDnNJ1oL+dCPNnC&)3 zVzz7Py_Iy_3VN@2Z8ekPwL?;wONYJ7NW8Y1N%2}w8Y1!9R~hvW&}^?T6tj(GQp~m* z>a}KjcsQcrblg1|!1YXEB$Hyg|6o!~w~-z!rW+4YThq;?^PU(5bR)!mTN#P{mW-x- z(SObEF+jpIz=uqV^A2IMjDCBEkvQ*SCdGM=FcRaPiVsQaWc#!Em_<+jFv2JT+K+_IE&^iZX8W>7B?=Rfk@mq ql$I=R+{8%CxRK^OmKI!3Zx&mg$fVdZjytU_n-)aP*RH6iJpTiKvjLp| delta 42315 zcma%kcVJG}`*_cJz21B7ecx;e*~2Cx1PLJ$dn6Kj6H190qiV+9d*rEEw5V09?M3ZY zRc)m;imEQuuBuwU=bUrj_r7oF=lk=An|q!;&U3~+_r50&S6=pY^5BF2ZB;ItUK}AQxZ}hERrF)e@jb0Uo)RNR+KT?}CBBVO_rjcaw3Nq5j zTGEW)#oKF`*i9j-E-43{>YyTxAgdlJ4zuczW=e0V=R1<1rb+NNC#dSg9aWdKQ^rc% zF#;F7>LIIY`YcbSmSf6xPK9OXbBv~DkY`xS!q=Bh_ zlLlmla##|4DRuI0h~NVP)lttRZe)Y4C+)E?7Qqz##)GG?Y)EPn`iBURJ1cPUBX)I7A$nvr4%Dw0VuX?+CkBIW(-DwsKC z8`m{8dID=R$uUEslXOECIqc-x-IJ@W1sRT@aVYxnlc5MY(3&LEUu|$^H}Thf+n^alhpcua1}{U~kpWa!ApRB! zg+@hbD|*!6F|$2N*5Up3q@00{c*6SU?MW3sotsN~S$dVu=v6jjXt$htFli&HLVxvi zM-$T>I_&B|`V`>RsUxZLCSKb+k{XmU57&C|s?dqFD!^+`C(`Uqyuvz@L>lowc;$B{ zCEi4MqBAN{`F{{L>Ox8sP-0yd(!p$kd86&&P`@kbLR&H!QSMjn@u*8Qf_s#g2RF+w zPNF=t%_gr1?aM^A_JvX1NhiF6+~%Y<9fKOs&vZ-!R*6bxIMe20wMVe81M5=TI z&g76C#vNW{8Qj+g%b>*IZN9CP0C>MISyr&Ee?Rv&VMU$(WPyn$n!E>)2y%oQ77twq zNKLXv+CpHKk0n~)Fo4`vsGqtZwOzOzV!Tx`#DF#&aqX&Wj0uI@;bcpZ^;q$9%He-y z#x2a*h}Y2zb2h{EJZmSIKY|1n+KNpJ?yoDUpB+I41ifJ>YEDb4uMa>d$bA6fj>h|7 zNLWBFu(wq)o^(@zEN7)4c_C3r7ih4MykdhSXrL-W0eOp1=`N~>K76o4s>lGfM**?%9{wAZo>NV_WvL}yon^e ziO^>=62A982&Zi(O=trRa(gPF@NhE;r86~=26lJF^k$!sD1wus+$|W5s^}(O0S<4$ z-ujUyDu83MX@?U&Vk?QGpGr9VxfPQSA)@ryw-GNwztVu%X&5AJC&BcD6bltU#q9eE z7H%hPIKqQ}Nf@X*aQ5|+CqnNXq@9by^&QCJktag(r)b$%n#jbjVAH3hoQvPzpCUhR zyG(aOV5`qaI!EA+AdlhTXE>5ayP*hT9IpiqFOdm$Q6f>-1D})2ctPL9!wKCq6Yl8b zlwXGZwLCbvlcbV1;IoUwItTUHru#A=a~FxH8Fo>)-2hI%e!q)sq`7wCcl%tEu&RD~ zH*rwEaj#3fw};dv(}lzUV;TV_;W)b-EAT3+|8i*>9cLFsviv@B6aSX5ZJw~r`*GAj zmg{xI`DDB_0fhA0(BzK73|14$d4T z-T#Z-j6);}`Wzy4FpAv6|7|Za^7)d~a%E-rFUdASy&TfeAcq_Ry&T*L`liE#ai9pw zGShd?l(roqUlAH_5LY*d;{`EvKT0}bavVI0GpG!Q%)46OVy479<~I#ea}E^}bp)x& z6~tTqEm2*)Z2z~UAMJ^dXqE;8k4cE=MRSgkT*BUS2-Mz}DchcJ(#(W|r%5(DCwZPVl^haox`Jhw-3XA= z`!`6IpOemQLjLRq&R;i4{hb}{BhzwZnYD{lMAjlmmwu5-^3g+o@e6r}(67DZ@Uhk; za@u+1HQNF%OdLt(KqB*sA zo79}_r@^!=zmi2-7&va@SQ+SsfmD-k;~-K%g)*KfP5(p}a1=f$)bN%?<9jbrIV0|n zqb^u8PuSSIxOhiAK09CUVZ9h!+uy@Ua&K=ry?%MmExO_NNgkoYy+u+EheHoY2Y$zU zL9>SvPjvnP56OJC!drBMW!_@9q2eR#C5!dsN91clHz0GS#OS3S6JLHOIOP0|92R@a z^q>AW38M6nlype{`X4fj;H^hM&Uwq}!n!A}x^f6k{)^LvLva6JOxxcig2Nrb+r8=` zf3ExfXHv4T{^w`7gm`IKKmECc@QMQ)o|C84%ZD!~%fQJOq%;XaGiU;odx^GrLA94; zh5-+SpI)LKWj)|&ugFD&bCHYEsj$`enwtDsKK;Q$8~K=1{rWy)s_)nyUdXutP{&8k z59K}(caxY3Hn-CKbf6DnI_4~^rqy1RBdg}(BU-SS91m+=S}0l46xBbl$SNGoq& zIq1yva$~T?i#DTSzLLSQ*BI#8-ZYWWSYMAcs_HA!DCmTVAIoK6p%rDSwl6ITAC#oH zVDY8FNG)<^mam)Kt-f>t%`oJiGWj?aU+YJY)6Sk^-;rYNXH4|YaL1pHMnoZDS%8~_ z{Q-16&65&fV-X1veeGBgx|J=HPFdnB`r3v-su9pX52Qm0{n*!S|6`jk9Q0BXw7xFi zehk-&(sqa?`t--psTgjPAdRRgCwyg1!F#dRZxu}6p+CNX$BSTG@4I-UhS1CWj`yvM zP_7G%i=si08%ne3OKF7tqNxMuQDJmBPI3H%5?*j4oQ}jhnRk(}DuUMLK%R7eN6?KN zBo>bcB55>9fNf=H`31GRDUQn~PcJ|BY(oN4!y4~qw@~RgX$sd%(KMJFEwn^60`#rX zbPS;#4e33k^o~;c*TvBR_&2w#O9|7m@g?X0>|vaj{TEXS0L~HCm!vT;tR!ti=5Sr( z^GlhOF{S8UvVv2lqnm^RbxPBI1Un(3COchcElbyty;9kGWikBV3+B2ssT>Vc$#)zq zH>AmFm|KN5peOwJK7m+^meng(r5}?h&rN9DB}l-XfvJPLEh2A`xA;HEOeFDQefskP zSDO6p_xk!2nR~2HQ6*87&Lz_Clpuf6O^d+6`l!=S)rn$%xZB0fPyaayJxOD5g9isM zQXbCK6tyJ?n?#(iC)167F`S9#gl9!fT8Y%==&l9KUnbue@U2B#aJKOclo*&+i>`SS zliDfBq?2IcoI1EO@#j;ABG7m^)8JeR^>OkeQnj$!bo86JZmNwj9P!_(RZpdPBnIX+ zqVaG$6=UeY3o8LSBGwX6Wy&kvL3bs)#Qofe{z)SOB+Z@1NK=~Aq~LRy=1pi74id}3wM}pstKkIUmU9CR za$8`N3@7l*rnHU#@;vOyTlp9lgiRt3SESQM94z*btr;|q3=x#}hyb@S;$Q|%gq<0* zE=P4v>FiLd87)tyI3+D?Mr(4mSUeo$3$riy%PCJxCRR4OGCz zjBMwO65wPD^dADU8fpG8rWq-P4;NfoBRQ{+JvKmE1tw<^&Mz34#G5l5azuVJbOJD;I@~8k};ohM$4T03o zv>M6eB3z}Q(9bTnHh^87={(w?i123veLxq~)bDkEaG)!#Li+tTo2uD3J~k*K3)MJ| zCldrYbH9}8M&meGr18*hn39V)P8B%S4d-JG;8Hhq4dSBdb~p8^!o2Qu6aA!!oMw-G z8=X=WZ}>!W<=gacy03@~{ii)>6z&rv%LGt+qHFd+U{9Ljx9>I2z&ky$0A2F1L^U0< z4<7fVi#T6Va_^d!?30#6_o5dOEP@oM%tsaKArJ5R^b6nwCIBzQwNu3J*T&ORw?2`38#uPx{dwey_`d{{3kxP5VDYAid83 zRHd~`0*q^K3xEv+aJ7ZvMR9mE0H<*|fpYQSp=HKEI?RRk%RodM{U)@OT-wG^m|u7n zoXVv^oKkEWS_k1~-C{}Ua2F8BH@k`|#knT~a|~TKx^xws!Uv=NPEKP7Bd7gu(&5@* zT8^WMVpC=aO{8bvgtmGJPUlcZ-to!|d5>Tu&_Xsh=eMK=)sgn0~|O4|mBN1aE< z&>Y$;n35TgI+4cU<-758 zy?M840{y__E&zs4q>BnPHJC)_6=?FEOr!i}aCshO4eCzDLF!GizL`pU&`ZKM&}AA1 z1UatyTnp64PoqsJeS!S>Gd7=@5+sCGoJoJBj-s+U4b#+81QU1>R;M|$&}|M_I*ay0 zxJbF`vn8P@BkgC?#ki$aRE#QdMIogYQpU~0h{-k*2P7Y-%lGGD_d>WBa(m3D^+;nb zAO+#K=i|8LiQQ%a+UUgIx`5UpJq5NsuBh~}Sj1&7q{X1^LRz8#_2&z*E;*?mEyPiF zyi-=zB09qZyNjQbrQ0^tpnTc_=kKVWYY>VtJsgLJI%qu)E&(tR=$rygP2b0EigxiF zbtC7|;Ac7>y-zo=AGke%Ip>Rt96i1moqblnu$X>C=#8SXrvJ(H5Tg^hA$=LJj85ZV zv1jqkGFqCxRSe=UvjnZ8E46Mw{Bo>0H>CLDCg5yQxh_AtoNlAVipgBqy8=Us5RnU4 zR?yL`Trr_onPPIkv&`!ZKK}q2R5KWCSn0;#+m-Y-ZGbBANA%yV!YNN?FnO*Rc6 zZ#CV_(fG(kyB8C~2ac^+B2SO?D(WNFtF6D`M;3xb5-*Yp@%1VsAH^8W*Bc(CHwpbPSaz{Z+!1mD z_+hY!z|mv$C92~WsyF?`+Sbq>w>8lIe`xg16GxXIt4CMrZ- z#PZGI93akad>t$jp)YTnA1v}1YA@Fc>2uG~tJE(#7kANkdMWLZTu2BCYl&0UIvjJiWtz3yA-TMk0CYC0s8W zD(mwv(dCp536ZfI&532~un7-o1i&{}=u}+MWnHE9$vgpu%+FY1IC7OHVEgl{w6_F@ ziDOh`tsBn8Yq+B`1cclnTyDIhscA8)AZquAKhb~bu@GLg?akM?(&HQb%yk+`=_Tor zOM2ih^cca}yWrE(4KW1xF0tP6HyRX5{|Pa-i64i^4s(-QH2M&I$xja&8^qrr6+frZ z)?#_WqC!P(M}&%zV@x57Mnd)Jg)GY`jm6_5yrxzSl~eLq#KEev&t@6!7t6^!Gq;gq zsYM$juG^uoA&*=}#lkm=rJRdtXAh?O3}(SOCrT8vaCoW|DJ-@I2Ekm1B>}o>Xa+(> z{-GXc8pOkX&7#uKP&o`;*DQM;fOEOIgbF1@x!z{0?ba9yJlYFGa zv$BrWy<9$75N1^S5|$J=nPx4i&n<45<^5XC_ik$~vf%Xljs+Fw;aZ@s)eH7ivrKvo zZEQ<{W{0@G){@Y^s%7$PCf7VX5yl?z@CDn2Q=9IJqz^VS$ z%J4x$%hdmcuOt3)^1m>^#c@HG#lGOv*0SOMMjz1C5`gGF5MCCQ9^2e9?f<5UYw`wn zU}F?)X=>T@f71(@c}u+DL^(^$|1C4DjpZKv*dIgvfB8sypmu4C|AM$>zVNcRrTG8J zUPt!--+ryQ%m>2CTB83?u2K^;G#d5|w*G$@DPo8CC;xBv@tj#uahVq!FDLDbfF?(1 z(Ki(vc+uSwL^r>o#9){7C^6WnMTz)-XT zT(r@K5oU+47a=?Rq0e0%J}p9a_<=Pop)j?-CFOOi+&aaZ|HP@_g#SMF*cnO=vJ`P1 zdu*gn9c0Nr^uN&ORVn0#{-{c!#3%Io^8fqbzQfI=juEfdX*AQriRdHY#1<8-O-N_B zzlFuXp$gVM^rHwdKRA2E<)Kx2cARw{p*teX6W_Zd#EI|W@m6m&XAf;r%MsbZU+KZw@7^S|@RB`I_TORjWo*IER8YFa9RR>9&2d-_}3F0d?)guVl;N$@h>QkAx~a-=|K zJ&xidQAxAh4j*X!fVM3xaq^bLKxVFW7)%&qjfPI;v2QmVWc7yuf>Aa{Dh{ItS?9x= z0akx30J0S6GX`6SkT-SyVo5`LmCA|1$A9S6pYi1o<0X!vk*{Ym+Uk+X=qHiM4~JTJ zu)R^D9DETalK5dc7pI;2Pw!g86nZMkbm8$RQ4Q?0g$wN{}^C>;8@pzY%_ZO!S8sMn1=8s%x^PH`U$L$YiE@cAL9M8{0;V$<*(7OEAX_v>OS zPw5t^))v^8ZTrx;;}>q$l5V!e1)BPHw?ToX9&-*08p)>Y)O=+#E29~0oLEP*|@_CaNbURfG3)ZFPA&7wt93DcT=m2iYdF(J>-BN5;r4 z`dbp7Inox&UonV+%7ZaQ=fs#jb0$8U<`eTu-?(yR8qQ3N^8?;`^&z%mZ!9Ey$pTA; z+BEuM%TjE`2rVZ5KkR;?j1Lt*DS>v~8BsTC#1)iREbs z*gG2Im8BmYZNno;-HOXswIcE`pnZyqR9}#1Yr_FQ_O^wRZotOc=I~pwT%TB6uHU*9 z7s*g@oNXS$cpf+=&TwgzRh$oI$&frAJIzN@@l}T6^S8UuR(L9oR3bjv6VUAk48R@0w_9gmBSeS6_5-%YxdIY#-5Iii^O$nq(_O?-UpFme!MP z-sBhPIT`y4f_c(joQz3>0>w_r)5*3o1kaSrH(X@j{uXn_%o|=#!SKYC5aEd`0r7qC zA;{*bHkEppkQ*eAr`kdoslw?KX{8c!lsQz&#Uc*wud@|3Hb{uKerdk#r47%*3;dQ6 zA2OEmsCZ%mV%F1tUuv6RCBr59y8=B~8|vad_)Rp!SKA&J!lQ9Q#QTOy50|-!7QKmR z^vAX+8`&#~b{jk2eoziGqACr%oHwdIy=xku9@kGlX^{wIzg zNW)V;!A%2vU1*h3RG)FjR)UcCVB1|B7l)RV$F7UrL&FD^6lcks-m`hrkdk7$sSmto zdz;V&LIb=&l%E|3gaE-CStA zBh6GwH{^fv2uVIgui+!ltB-8w=@}&FZ)l$R%T@-r{*bPW+Aw0uwE)lQ^wvAB(Kz(le$!rs7F)wfoM!4Ab?&`_`1`jkP zK)?S2Cs`z2ib-Gej`GyFq3Ke}Vxn9&n_yLUoST0_mHK9zkP>TAE*5A?DWn|bTzC|! zTNRDsyJy1a_EzOvmM@K7D2%o@pW;$%p5CRfVy9%a)M+)$Rg^8p9bGMzdXM32vMz** zstW-d@vaCI)08C~8D-mBy7T5nQ#}4E++Rd$WjAsz6htKqZTVxy;W3l|H0Cmzj)Mol&%jEEkkVgOnv^o8Y;usIs^~Q~zR0 z7B(FyrXx>b@(~7KEv|ssB>l3b1o}l1InlO4SUj_G-SpF=DqKTl8=7ici+StC=a zPU$8|x(SvvS2h}Vc#*v>uLYK8iNP_}^+BYu)WO8o;GwpG>`cl^R7lx&9zi+me>DKYUP-w-I$Ln*<}targl(SRPvb^wgzO#`@Ewa5k!NMui? znS_MW9OK#CUJs00J(UJ-BE+J(&pXO&vrSlDsh2XCH}MdzZ>%||qfzC=yg+}_OR*95 zm-Onxa&ptULXM)6dytf)+*4?I;qbShVjmpn?r~29=;Qj}qeA8*L0;wMg7EWP7k7bH zpN8VA2RKru^+OlOlotz~qx}?bY=@uH@pU%5;+(mXW2YNsIWcS0d-qqW5mrY^NR<-c z;s8vCTIJ=8)n_2y)F>}zjI{?UAF}omxvha5nv3vO64}1Tlu!e@N#y#i8m4p{#(JfEQ>*_cqg5vpxRdcX6sE{#1nLyQ8`TY6*1O5dRSM;VW&k_78raCi=;^e)LKbFSngiqycl%4v30^7#>EqQ?i!LmMyZ zBj;h}(_83bKE3*Qff7d_#o}&8tX_DbvV)LYuzQhG4H1ONe>v>Vu6i+6cGWuhN(DlT zRS--U12PTN*8pY~EnPvRXKDCy369~eyLn4-V0PVQEyFRvbr-c93zX{)F#|wbfun(| z2@#6G)fG6#xtavljt_8f^lZvosnp?3=u~^5DlWYP^H(Wjl_?cOj3&XV)wnCMYZdxx zdNL#ReMt&_ql6P-&-pCee0Cmd7}FtHgEqnd0** z$hBY6M+gtBAV;irA1SQ~Jt6#s7nrA@mABTQ;j)dK0Ab~xwMq;8+h-l>fwZDiXRlN8 zE%dJR^<4sV-i^^|4#f^{ytt z%d+(~UT3#rh+SBM*V=9FO@i0R?e4q;R^|?OEYVc_Q)Na0UVnV5Bw-UAY;TLVo32HV z@MPBqf2M>JmKP@?JUUJ!=7G;KF-PdfKgSwNXT%wGv(zqSvvG$P`F$9#-Kdqs;1@nj z-`I_=@od`sg)*f;Q@=ep@AbqgwHNy}XUxz4=IzBjIPK;Eg4`4sA9zdgS$BE&p?*Rq(<@8YpaCOL$c-`o92&u2fi5#|v zcXZ|ZRej|l!-`WFk*kvH$y3U4+)|ZX zi=M@;k!xp^9<;Z~y12=@n?C-mGJyJZtB3*ie0*RzuT-IjDl-Y@fu~Q<3MM zJ$iyG7`ybiOMEu{ZAFoR-@+G{l`X~{zwm7P@JA(^|1ETMBdsVir}Y(FQrwoVYIs$t z4zI2#ljuX?Dqp@6U)rR(T~W?x@G53BZlGO~ogRNpnN09i=xu*0#!lA1C+xv6{~A__ z!0Sp74z3lhz6&#|FSu8ZUfg?+qc&PzixdyP| z20F_r``a5zCczgvP1%iqRZ{U>;mlu^nzW&i2+w{sDInxGtbFfCS%-g9qG920N-O-{ zpAZ=II|_Wq5QtY{a>dsa*7JYI4I4T+UW8yW6u*gsCf@Pv-*Qt56NBcdo47FA7%zgo zK3aaV~V^g+B_e;mDsS|X`9Nq6&}GL8_) zeS&L<&QH`R44CgToXcOmkE#;5bzf=c1ZO``V(}vn?%-3rNl=GF$U`L>mT9D56^xIwaDMNjq*09Ou?of{>IHF0ZGK~a_~ml zp^`Yf=fscu2l1yn@vTpBsel+bK?#G?AuLcCB2PyyhgC0>CP+m7RiY3>#Ipl5_*a=D zIpG?m67+kHi-O%wW?9daTmzL~cz=8L3d3ly$%cHe-)zxCEfu8PaM4;`!4f?7KKXEAuW zq_9+poQB(g!m9?G4;UL@;L$mi5_(8TWx_k~)aR4FgyN zf&|TCY~o2E_GESiuw0^?Nf3#Aiqptf6CAVpnc0l?@^@z@1hSUSQyb3$Sxx1ZB>Mwu z2eC@zR~Q_`&MW`O#=qToEnMj0^=pDmzEwrpW z1-}(XHNwN$bQj$z_~eipLfg2}AuJ{WeeWU@c{d}1RgqL3=^#(+&XKGg$L1s0%}7)g ztrs2D9>pG!8TrvHoi~Z#b&F>2?)LjZ`c9>s^B~g1-F{FOUy!eo6*shl- z&Gr)-QWaKNwKO}2$q(Kdj?f#FWmZDVRh8Z9S6DTHh0p|i*^+>7kg2?hd^3M{SNDM|lC9ooFCaJs-#Wt%d(j~SE^Ru6==#o|rUX^DxTw)A|zwIgJ zvsjkOQN&s8J;hl#eb)_vLqr;ttIECNaN~})h*{@v6*r%Ep`y5t|AX5$LMW1V!!aC5A zhE`ptsIhdS)C!*0M(2-&xY`myB*4-POaO30;G{eO5K(B{K2>Tgc#lYBlgO6*G*+GN ztR_-0CykXLTVSrda0*Aj33r|3JXD$!{g;QOI0I-zf0m#a7f4t-ur9kuA4nr%W<65{ zeN#P#pMoKYJP|6XIR~nVG*lCv+62R?28fObqJEM@(YY%$lq@i!xQEz~ea+$%1z}vG zh-+G!x6_a1A+r%1$5JG`W};kosg03A`9vAGCW#_&&3hwJV2*6XZ(cXX%GX|ilokdE z#x`LmY41cCtya8MMhl6AN4GU)edzE+nL{F4;}d07xSN3z5z@Z{)W-i+nYgNF1HnJkumn+W5cs0sGDE=>_E z1US(yWU?~!%A3$c-9R+{SXDC_l!ujB>^P%I!r^ZviM7qr=BUPtMEJNl`vVt*^IEVp z8k8g~4;rkygnMx!Ty~2SyyIH3cJN+HoDq2?30u5dNhTs?Dz!pD#Uwc=yktPcobcaP zY&5}-!l00F;Byq(NJ@fxZLmkwhG%VXcoFbuSV?fy?dS>L-IjHb@Gz*{j#Z%pJmKrx zv1Sr(j?LqfaMvS}E$ZfDyfd=RVexkg9NeDe6vEUobb9GPofdlX?AL*namxI(0}G?; zJm9)tM}}W-sx2L{s}tJsg8MlDE_P!6IP<*IiMdXrR_e^Eu;bGI-wOZRSC{v3rs5HO zb!X;9@f(-hy0V4zx*=yoHaho0k{k^#B=KnozkSu4B_k^OG7L&~V>RjX0{9nlaBKH| zH`D}olSBAlK~DS<-OOC1gsmiDhQAN~}@MEA_84q(In*=!3 z7rm9CkLiU`MFcUy%7B->(HMyy2JLgu%E9jF@IwykZop%qcOM)BCwsuZ?}O%Kwo zdLWu{0HzIOI$lz9S#|OwhZs968*?!M4#0_A*2P8Mco3_GXSUqQ4-LY6cCs%r7)w~8 z8nOU!{v0BDzZ2t+!Dvj78wQGKJ%r^VqA>935UIN;`xR@5I=Q_C=2~D521d-Kt_@`k zXo>{waDhZ0#3kkW$(RR|fZlz` z5m6}Fb)r;~=L9}m2uc9r%qG=9um<;dxb zsP7ck*>7aB93R}ixG-)CYfUF6i)~rwhcal8uakUavaDz$rEWP>rEX$kFk>oa(FV>k zFz4fBF){F~<)U1p=S^e%DE&NH#!;JzaonFQvZu{VjN|9ZUhTT)=kYC$P3H!SD3OE<}T!Wa$gphxply2MbwOf-@?>x*P}d7h&}k zjX0Xg7?UPWV9$KkN&>^+Vm>Q{djkepDzFHIWCKff^4GTm^C9G2H@y;On*RKJF~b8~ zlek{#P7?56%G#1eTqW07ir>#b83}M{DXPAxCdBV$kz7u^qxmJ1Te4iww_V0oDu-%{ z7#`rPjjzjfBYw^l*sE7wj>|D}l1mAL)+=x$rj2LtM>v z5^$*a5pK*Ol$Q#<*+*zR?ORLMilLlT_B=%3$)-P9gUL=u)#AmXj99N@5a+E&+eX3q zbyy$}AJHZhP$vQXInF*`#xI?2wgXD1Lvl#A0FqyeICJ=%b)$FHO=Fl(cP zh?L*Fk7TGC zl%+`fKU(f?zZi?wZD9@NmeG7xGDT!s@f2}tMElBx9HsBw%5dkuQVK-Q8js9^sGYb)I1B3SWOeAQ z6gfPs-HAE-0o>n%5uc@p?_y1efr%($`)KuU96+7uzF*+1?+YjTtS^|2a2QU@!tm>8 zIL|sMV4{sLJZEvGlCe{aJB*Xa)qB|m_DFj90dmJL*>2c}J4binvwiFeePuYs_%6PJ zGiuyYaeQ^#6$r%eI>6rMnBx8Qxd(9g34SA<|3OyKg_nI0@nYYI_sc<+;gY;me*U@k z8!Pv|U~iTdq>uWR zeMBJgHh#ilObe|jzu!*iYN>|fVON(LoQiLc&O6Tbu>De*y|u;CZPW=Av>T?LU{COU zo3SU^D0h z>^&o-lJ7AmuAIT0#sD~TmW{%l^xPkq_`EArJclR&F#9{)ToO<$-qK0qa~?A}%@c(Nq{@jxKq~j8z3^0*Z+7db#Q;LubBbiTySAKS9sU8=6TKno0#4X> zgHUwB1-4lknJPj#oMXpB?~A4#(=M`c`29z;BMeGk!cljwO9y-L?_Khyz@bZMl0Y;~ z`tUz+2VTbM^%S8r+`Nnl;MC9lBRh=!5cNy5mo&K>swP}vlQDEcmzsYw2L%6!6XIuA za8+^6B?)q_iU7ZR71u(?qzvtv(;$Dn>@`Lxy^|`YICmiPI@@C2jk|%NOZ=J5B6p;i z8$aW?prpxanDGm$dM8!B&U6P5xrP(((hbCmaKl4D`(JQ!>k=ebpZtX_=1qK^wfI+Q zxX9sMzp?{LMw*C1QyBLfZtFMFKm83yecB$QZhoGcc6SQ-18r&#?f<~7I46qH-G+Li zl)cH0A!h0mETai8Tp??eCUfFMV~y!8Zn2%bLZW2+meCSc9Gd-!b2r2h>h=E<)!QJ| z`Q`k{o14Uy#!adJ-nfXKhu2>QTadFpRu`3FpYj7L%pP@y_9HU{YO z-?%~j2bYF3JVSZ(Z4j(~!WOf#b%cXU*O7;M4+J#H*)Kk`v)t3l$C4zmjJBM-q;_|IIV)F-nTc5d+o_@x*v9~2@H-q=?=WYm>o-<&B zB*H)gVZ#fFApHOB3$~igkOp z#p;UC7CSqkh%-(;buoa(UfWDO8ER9@!$_u9r#^MLEQcE^S}qdFrmD>epG9!K;#+?; z;DDFP&lF$N)X}t3U14-37-v_TIPq@T)m69^!|@P77FidfucStX{mCGMSH8EJZL&g) z09fL!R&(;>9w)Os_#tSnk6OzaA^nDr+Lho@3ZZ8Jf4ZooMbs$HmB-C1(2NdL z2vjH2x9XY0CBDYv6NExmwk$w9`ue$PWtkMw%tT|XV)^=lu6M<)bW{BC7-J@J|(+^>mfo$GnL zz=~9O<|SC~QcF!I$}Guyh8yq8DX7#`{r40MJzFZ_i|fhW-zSyBAZifCaz?6pMOiQ5 z>tJA-noOr6Z~jrMTWRVarEttLHQFgPazr->bmr}6o_cXwu9x0N?McYbl6K{9jA{K{ zB-iw;e(GR6<5ExL=L5LeU(MxrJT@~2pt0BL$psXvFBVW~i;y-jN46RZs8Itk07V5H z?hjOLoJOo!@G;Gov{ZdLwX4S|<@)KGj`o%(_zBebA!;b(3|6CYhxhtWjC3_PF<9*` zAxWf#Xr$HZi(25szc~c!Ob;i1+o5U$CuGl1wK%@aXmE;pSDk{i!ZPIhu3E*37cmU+ z7CP}J4pZAWAqP@e1$=sDaCqlEHP#7PoPq0v-A;(#aJ3odjefE>-(yODcntd4g|Kyu`k3GG>e9-MTRon%;yI0yKUUqTs0~EoDzI&$ zk+}A5H(bK4@Mx_1D-CQQ3vi#o*v%puh{qU^K3-MvE23@3t3x@0IGXY2cr}<-azo${ z@$4e7fpA(N%$$J12!#6+Fc+;2L?&QRPkqa`h|-O>RcC|MAf6qFDdPXtB=tJU z<)Ekqkv*auLpfNc0HTP+t1<=a>NrDV@z`fN-Y6`=9`C|Mu+VB;1Cf@IQ!y=_^tGp| z)9Gr1{*S3@EZx{Zj@2utBN{@)D1z5jL(ygLPg5i5J~s?}U-9WQwG2lj8}NtDQm3nB z=@~Z!4iVBz^P3Sdap*jgCeW+JDw^%rC@FKOI^RUT}i_}KS2Fd1Qj%I9B zt;UZH8`-i(@0za`A#A6_`dkWwPXOJ#27IomHT5T;b}vc3mGq)!A3-1DXBy!2KJ>*` z4Lxf1nuek_Ldt&in(|0;ePGIl^aIHGF0?zKe#uB9Vc{z&)c(~8ms)rA?1NZ}@T|s} z6Dlr9ElBos3ssF(uNkEl`jYmo+6C?>$6aJr~H3_ts5K<0j196W=)a+hTIoHyN-x`!TDf5q3m1zE%i z%$OUJY~V?Z=p~esp_P^J96UiLIJ$wt)SSmMbciZ`mgUe%v|oX7XVCsj5PnL{b8`RU zlp2B0&>X}^yA9>wzPYg&-2LVuNnnm_^@ls(tBvR$ z0aE-85THJR`kWusmXsbdlq$kuvaB1{*1x1Sr%!A9)3DG+XGVT7O`U&;M4S4>_OxzVUk`#r^D{2NlNd4dn4r|^`M4k19q^s&; ze#d=T+>MQng`$u*O>2V28b21B(nQvX>31=slACzc2y}y(KRvyRKL$;EHxYY21Mg$F zdcvst>RkF>6B$l%;$<9i;%At~K0t)`VCDn09!EHcUnH;>F6Q)4&nD90OSle6aN;4( zmSmeh+{)L(%i5NXs{-w63-xz9iq*@d`W2n*p zF{<$mjChRG6eq&(k8%9?#SMW&M2-JOI1ASQ?Z*4)-&j|kyP1ezG>)=q368g0y39fF z!6#}aN8@K5>?Q;?6uS5PN1aB(;r>5Z{IN|emYP3RBPgxVRD`Pn8_<*N&)P>dtvRA zurstvU?0_{(ItW_47W(O{81m>)07{gtFF{SGD~t0Ynx0L;dEGD32~N7oTV_gvX)Gzr^}vmy|OlsZIqz((lXeX zfR;~(>@+P1P9|ta@E5$fM;wW6JPq=Hs%Y<#BamBFt4~j(&b;UUSry5Tz&};BEC~vO zcdBXC=nYT!wQ5=;dL&(pz0v6m-;c$9-Y#M3W(Z7m#6(YZJv z(>}GePMm?5cN(*v*&Y~mQneV4A*%hvRP1sqIovqYaV{0DOM<^rwKzl)mA?53(?lIz zFoMu8r1cP9*K{+~s;hNSPGpEKag4J}cEpZKf@o$yC^ruGJx(@-r}~EunUXR?Y>PmVuCg9KxH#IPN5B z-b`ypCKyD2Hq&wuLuB}zOgA@f$<%hyWhjS#lWJ*}rb^ET>U*-ZnHIWHY6vr0xzTKF zrR||#2;IuS{MK4&`jz3ed#w=-Az}pkLW)aoBS}Re>eoj5mfdV7BK> za;6XxpDE@DW2ay^E9f()X!zr(DVaPG@Xe40)6mKC4lnYp#|qOm{Dz&t;1|9zV40zn z;(ucjK*t%J5uBN?1?Zz@X!xYQcm5)+H64^G^Tsg?RqmZBADrS<^d{rM=_EHCd>FHL zmevkYIa>#78s^Nc3Yl^~vYcC*#QX*$Brr#|irt+$bdv=6yFg-J{n#8$r}T?VIV~;1 zfwH_*&{185&|`)=#!35gnQ;9QPIqT6(o_y>|DhHRU0Y)bJG~HV&iaK~YjR8&_nR9g zK8JxtT1^)-`Cbuy>WR`UUps*)!etqNE?)fD^MdfpjvE(iUGO(ZA8f#%m@U0Ti=fE};3a+362vYGQ}*Ay(1yGEH#d< z>=QtwmX%%5g+Z~kSou#o>Dqm$ZRGrUnl$$gcLo&=5$d-7NLxd&QVCCSO8U_7)WG%V zshhBOt(Gm};lMSb*5=Za27LEAElI-L)1scBIUj2soUE1gT4h?!6FzFaw#dnvdy3Zb zgm2z})k&ztRdrcCNcY;T-5_*A zbK&m^5V!@sBk%AcyYRCu*o9qfq6?qis>O1++olR#*Ie$y_1lJ3ZvwoxP0Mnj7+qwS zCraJzSO}1d7yzej$64O7=Hj97#qC-sviN&DmS#`E?RRMP5VCRydS_5`k)ry89a>HN zDyT34FZ?C55T!mX;K4s?n%2qm4s6?{ea>QA z2=A4{UBSm%DQ%()UK&>K#ETF7kZyce@233~6*`nVACzQob5l_x^Z zUaXl(Ekws_v=0MUx`lkK*LR<`iqifqWS7c3C_&;-&cK6O7@=cYNcZQ#rbAi?J~BT2 z751tzpnQpS5P{+Z1Q&^CR1MIRFSU3VsQy>lH2ju^0rEMF&T&%VYc&q&#^1Bq?}Q&c zjNwGM*j7#YS_>v;ouGwZYl9IaOh`K7W5i3MtB&tJgheJ zTP#(^H?WHz)1u+gw^$ggaORwIVmi2iT)E`(1J7tjlsqYYw3|`(vuM-^ zD0)^~LT9v;hyGbVJKwfP#tBgNJ5&(?FDKwp6}*b0fJ?r^(PczSF{a^raj0>17Oh3{ zF-^AmL*6-@p6}tHRE{a?bL}B^KRA6}8wvV(Z8d-R?{w6%?@;GKTh7cOuO4K3z`Jc<$9pjE)__RU)QTv_$&8H2guSl`NzxS_b=UBs5A}i{*k|l1P zOF$j{)m3c}rh;VM67sL}si3&y7tVUr&)Nc<3i{m8lIVa|vW%_#4fSr>N*q$)SMlS4 zdv9oE`HkD8o=$QjKqlRO(FSn7d~R&8SAW$On@zZKSMXfRuUb>i34h=z3>yBXMbq`3 zd^Y}u>jxJfzPlIZdKvJ5C+hm&wJJ{a&w7H|{ekrd#fZHNH>b3clfaalS`U@pZ{?Z< z(mSo>c2V$O=;2#P==Mu8b&!fbZkzTOE=`nTt%b+&*Eb$(l}Lbo6A5 zOfwK(%VMvHc)~v`Es}vS{Ywi9k7y$Yo6CjVSU)RdZ-ZxjiE0mp0aklenkYHL^1_G} zhZ|9R5p5v+Im%v(HYtF>wMK*}AA3AJ<3#9B(Q!j;_Qz~s8<9r+QFag>hpDaDRnkXq zqS$eJY*ZUj4n_emdvBaKq7q^FjuU@Tna(z(3{a8dC_@d20tZl8y0QR*P-B!-V}NGY z@G-%vKzo2bN3#znRBr>sqQ*e1!#)&uMcgGFm5dw^8s)57h%L;Ph*I8ViDq|4gZ*Ci z8cyE0Q>1W?;-0=&qT7~`X zHSuqc9u^6a0rnK$DtZ`RMGvbanvqS{0DE=;Hvb0LV+*oLcV`o#=ES!ZK|*%C4#|fl zon1I0Em0{xv07$2sgI8S9Z2X<4;AScWFoeai(=pqCKSahSCr0m1CpUop_siC;s_rM zg%QQ<>x?^o;XY^|Y+qcUseA~!9Qlct==gX__qs9V5TP$J;3G-RP}HIie)^fOi6@8J za|_eUZC&M%T!8o(djopDt$QKF{5%+AcMw*nop8(lYwO&Dt19j|o_kQ>h7FGb0TLb| zN{Bo{FiOS1NJK*wSW0yYNp6Pl2q6o3G|43)K(8ehNC*TPCR?D>R2<55bgBY!k?K%G zk)RAX*fFJOkwzUWh%H(>v10oD{x;l1?LVLU+q=8x?Ai0(@7;UuxqG}UcPG);cdBTw zb8$F&oT~TvzvnUsVw%8<0dFQrrn93@lT?8}!4(*d+Pq7uVLV#Wi5+1^Vh@eSd76~v ztmv4D2oL!(1zek~p7MD!vZQCQtoHykOaCK@w znu2v|E*y&#Z?;SG)qMY9cjzy;Ly!4$j{?{pJ0N7cXz;JEGa;9pCO({_G zz4KX4_3q)*-e1rzO6p^lJ8!=zP`P;Fp{pCc6K@ULX1i;ZD(HK|?faiig*evcuH9jN zm+g)RMF&kQ$?!WtK^jxfQ?+&*36(HI^Q;t#jCzqcV$>*sKqwlBq z@L5ceul>4rIXp>6tp3RZ(+FlJ*ve({OgU&~3dU*K*k)74rU0d)O zd9p?g@x0SH-BTOyP1o9(wcUl0KX!mW5#?kvJ#uR8A2+K_xOTzLPFOd$pciX%oEs!;#W#vR0XIE)c`FalHSC?OShK_%7H|z4TBjcK5|F^%HTKta zm`UJ<)jE}r0;2O-+uSy#|MIq}$PF52wyD|v%z&JYhXV3F-_EE<{R}&&UTyb3?y`P_ zELwHUc5Ejj;M$hDU2XUBT-%y;&*N2aAMQY0P$1>di*x@R)cyj)!P~9 z_SfwJ=db&ZL{2~*_R?btjt$5Zyx>)p;p_X7YgX7k-=gmBcLXUst|_lqRFr+7xbKAU zu#-5=-uZx>=YmserT0dFE8aIIWZz~xPNAu-*m@=||E0c$#Hj$6CJg7jrs{m&4Oc6! zRh4?zBei0VUW&BrYFFJ)TD$9xI-{=pyrH?+W15}yhFb3%WHZjGiRxH)z5aY>yxrN- z_clBFY*c+ki_VR;C*M|M5?XU{dhw+*xU7CqWl7nJZKKh zCB?h7d2uYV4iVLOqK>H~G#+1K<`QZg;3tMB0Yi!29mpg0&j6Z<<1>LU zP_K$g%JLId$TvLv&x{5!wn2(4e{DH<8B1{}1GI7VhnN92ukqdZ^XnO0?9<|LSQgaf@{TQ4KWVaJxwA}i7P^;f|!NNEM_J#2w$d6e`3`lAfNbZ zG0;K$3X?3ehiJrn!R#b9=K%NAkih^@M!Z1$o>-C#1b|?@zj$d;e#N>{j7uz%Z3^wP zm(-LH$Cj3HrDaTM8Bf}LhB|I2X&FXZhLD!wqh;u588#?`(V}IzXc;P6hKZITqGfn! z85&wfg*KndmN^WxsSYLbh5FZ`eJ#4zqIoTP*P?YTI>&CHZY}cGB5k|_9cz)a7CCE? zvKAR57wXj_UoFzrB3o_#EsbcL7GgFvt3|I`w5mm?S~RLfpV)y^pdz)XQHv6_s1PNg zJuTwXB0Mdk(;_%6V$&itEh2-mp)KrXE|jB1Sz1)3MNwMBgqA`>XdLvTML=4_gJXhb zw1`HFV6=z@rw))v%Sbr%r=%uG23dW*O~20sfd#4xWAnW zT)qcLVNy)@1180Eo9Mw}x+5TJXS$Q_L)0=IxXDQD_cW7Yzbn&eU-VydUj#f?|foW+eh7b6lkZl*bl88^|K e(`muA^k%W;3?{{vs~FLi4d<8PrYq_`-~Rx5a6-EP diff --git a/doc/LectureNotes/_build/html/_images/exercisesweek43_11_2.png b/doc/LectureNotes/_build/html/_images/exercisesweek43_11_2.png new file mode 100644 index 0000000000000000000000000000000000000000..d6998a4a8e78b01b0e69265ca07e9815cf4b4ce9 GIT binary patch literal 27610 zcmd441zc6>_CAh@qQV#$NEjd`U=VVUP^6_x+M>IWHc=4JLn$HMag^?(B7z{&AT3?e z9BKHi7xd1IBXjSa@BM#1|M}o>ihcHe_q*5otYfM48JLRYNhO?9knuUTjlNnW!uGcvU@(!YMhM%%(t-_+zRD+lZ8 zlSlNdtjsJiY;4B=`T(n`g)ZCYYm)`Ak?m%pDwae=DA)y$ zwAnf;ST~eRjLDqX#3*p@iRi%Q>%Mz-3h5sU8+Pv^;VX0B;c+SO<((az`(%uExNp3Z zC};I_OSCG(vC))$gA5n9NvfWbJhJ^L@AG~#+Pv<~2d|D6Jnxxu)||3`*3rr{)ARK= zZp%*vjeS;_kd3f2M0*upV$g4*Ug9m=(C=CqSM=-DuK)C@>+S4DW+I{#CKW0oqGyAH zv7rsA+U2Y{k|7xD=?bn6^{H2UOVjdHe2!P7`In}(vo!MUUcGP_<+dKG6Qgk)f5Sm@ zn8>xJtgmO7o2a*RqPxU;etNL0|E%sO1$FgcosZ9C^L4UX$jQmAD@t;gzO~e68mkq2 zYc>pM%QWpMEc^JeE?m%Ux?Wi;-lQ$J(b18JNc=eF2vM1zJz*$bv%tQ%^6uTc+F332 z35v|+*D)474{b(U<7e6(q;I@`TumS97y6G32Y~&JQw!nE^(suaDzcx zZpH&Lnv}itQrSjR-Y$!R_=UEyy8K&~Xz%x)xGbZi6B9Mn=Iui-ZP1jeZP1YPe9xXe ztoBKC68;RQPRV4oT6j3m#6``J#nj2k6hU5!B;hB1S+v3dFZ(}T73Nh)bw{VO z7%b)!Cxl&Qi)a*NWWs7=r475@JsN7xNHobEJdt7CqEzHYX1kD6xHu`%=CZN`yBKYf zH^M3T;=IbOTemQF<6(iYbs>-aIYyzu!AXZrvO806m=n3C-rcyF$ho`p>2dpka5t-= zIz}|&_H(@f)?M$m6GmE;VRx}s%QVe6{Bka}^X#>X7rbilWsUCS%b|_Wn_=E9%sbcP6Ugh3`C!-K7|9^c!TSd^8QM)d-`=O- zwNHlw-dgeOwBTK0vW7cbcCcT2yIJVcr8wHe_a+hqnPF`BS+@B>uKGqA3i(;J21>=@X zMVNioeIE~r$tfuKeznQFbN4PAcROJutAmM-PN=|P#-BFBpk7=ukiD9JWlnl&c?Qqc zZqoPhd4f`MApAPc&(AL=r>7V9!mexkNC#eve{uY-RPed*-tqwEGiT(m`}XdQTo}!h zZpk#3?|$#eyF9mpgoNF^>ry>VORHv%RmhJ?5$ziz%ol83iUtoIEv+650yZil;+SM8 zp9Zh}bX7SUUVTwBCnrZW)9Cr+r6ZhHYDPf?}dQB@NN* ztm+LLTsuDJ-%4xFFrFuPk@%Z5qqz zrzVVbthjq+-2AWy?b@!xoC?Ci56+x9V+GsRA8try4e_Ajv5B+n|5RM;Mw_8meX+xF z$`eg!}ZF$zSQPShPK9w`2^Q1 zVa#Pk4R+I@Hpa7M7%l;Hb*oXkLPsw_BH+mufx#SrnKgl*Y38vtT=fdIx7rkB|#(ao3?k_^DvBK4>S0B;mjx}dUY}l~D z{o%tWR?ERYD}H`{)=lTKOgmCyU)YN;%@b-Pz4;QVs$|4!I+nj>b@{Ziy<2HHSX)z* zZab!lruXvl@=#k|mOqPH44ekTia-wgo~I(L4vs_uO>ejDCt4JS>1#bub+pZ_XqQ2I zeoi2lX-beuuGmyxMJ>!RIx*?<6ZfcH7R|-_clhUx=1LSj*d>4MTDY8?9IY5Rllr{! z*P3Vv6zK^A)q*e~EN@LiOc@*;RLwB(i<;`UOwz))_YPfIm>Fxl;msRE z6ra3x7sWo)z5Dh>WoMr=Zp&5V=H_NC`CQS%u=4l?1}50H-x9HHHFu*O40ofh$u{qvhKOlU`sAp6=luh9+2%JYo}U%* zV^;R3-9>p$2ERDzLG3gxJJOU^(tA+C|D-G&nnsEh0S^%uE;d%Dm8F^HEYr}4h=^&l zmUnzu7Zrr$$-DTNPNJM0~H$baFYkBfOZ(rXK&C0CE#P;6G z^HYya@Jlvm4LvU6r2ujDd~WBpJe!f}w>#MM8dEgfJw59aafJzR@(O21Cl0)Si53F1 zfHoI8wh#2_MCF?Z)h8Ue0 z*r)nVBBIOh#RiCoQ4_;Q@7nyj@X1ir>`2Um5MOn(@nae@et79?-ss| zz^bBTK5;Yze+yTk!(2$4M?c^SpC;lXwK>+ur_JPu zVOEP`fxR`|i4*qI)NSbrwl7D#1{1iSPXsr{re`i z5A0b5#$TRB$j!Ux03PwgVzE|VKfmhAU{T8y#j0kRj7%)7foL=ND_7#`>J)l=df<&r zqxgnoHN(0%*=D$4(FFwXZ5URm$kkE#(oB2eL;}ox)f|gx+7CKu`Y1S)ktwe%FA?7D zl|~C<;HhhG$qR55gI1Vb53>}yn6AK1Myu%;k|>#6Kb|Pa@Ko!ww33^d(AvoT3&fkz z{01LWO~6>3(nja@&Ko z)AyQv-x2iYWzbkvvwc%*gEwu6(%2&!ii7cE$4cHG!@oaX zf__#X^ual8zp&x@?fsr_*{${1oHDvyb(}M0lLPCj#~pa$?o`AyC1&|&OV{RR(2Bh> zbxz2?bEk_CoPTFe7TZ|qt5>DCiPBf_v-;q)Bl(txTefzzX)f%QBP{0EW1}R^OBCWS zZrPQc=Glj932$AznB^3B-)*3WZLrz=)SItnPJ6gH_s?-qb92Ja>VpTkF3R706jKyr zxkT;_2WhyeH{jc?WtK_vB7*7|&G9;&8R`5->mUE-^y4r7^{1J_;YQJuorVLh&ras+ za5OP1*G%}HWgVuMtECkq2pZ^36?U5}aO}cG9~X;dH~o0mK#A*;Zkh#QuJ2sMypa!y zyZgs&ZMsix+<2tUZ`LQ@-N~piL)2y)p`_&dYPUy}iBh;(kmdyLKsFzWmsJ zdLUff?<85R;l{*SG3*)3N%e*_XQxrE;?YcLv#W~rNquawwekApoD36}A2f3&#%{2E z7iZ&1<`7nw#-x`ma+(E*TuS{H_ znV~3xl{!qGT6y&6Dbc`SG2fmouYYrp`v~Nr3U+qc4LB_vfX{*Cto9lN5whCtCD3A> z)#04@^5v<5*)9*I2ZM^bX_jDwA&oGR$jooj8ze(v=$@Q}4jOETp^~yia+8<7z#EvInVMn5)qSP&d zLS2?sNZpE}9zG6GmWk7F+hgUBc!G7fE%LbUQ@_Xp5ues?+vBOj`jO`AnhS9zle!|1*^xk2=AT0(LHx19X zcdU)c{{e?|5QTq*!cy{4GIVE4B1?)%oO4IyqS?VutH+CT|ee8X-JmWpk^)lXFs!lSIBqGEzuSXdbDbfZ~?8H#acBNc%Sg0Y%Y z4t5fa{+=9B{VWMuc@N}jDhGXBTyS&4HsV+luWgMBku+7aWQ_w;73SC|A~%h@4($;w zs+>v{2Fv22l8tvvZ48>;^C~SLjHdYWMAlUKIPpm(GKsV^!iE~BYrT!mK%;UATOR#9 zdQ0gR$XC!zhUx7W62bx*9iVw3Vc{|pTm0kJdM3%$wXfB$Z{y9DiLDSDBRC0Os#I^u z8Ogam$EoL}s;28*vp$HT@lKt=RU|=F79a;{BD^Bbv;IQy#e-{!+4HAW>(res@Mm^m zRUd3;+6DHbZTw|{d1pJLdEu9Dz4qKzaCiNP|3nBjM-=n(5(4vP-6f4v;x(?$V>Z^z1iFe?xo^6~?M6O3cSMB*aOmBx-eiEQ<%YX8@^w zAiF+xKZ`1DP({q=&sQK^<`_essDelrNRU>^i_yF>14K~qInI((`K&JH;{s39F2*~m zC+Fv%M`-)F@MD<(R*ijt*W=}5nYg)CAW^YyaR&AaadE(uM8cQE0XGteu}k6F~x-uXH00h^Eq|c;VvCWzxnvH=k=gEUqpsE{?S-d^oFh^ypE@nyp$2m6BD(B_$Oh7i3aO zVi1E}QLwkq1$L>|Jb!J7$@V3z9>)%P@0Jmp0Bc}W0M_RkyUeuNGV}6k;PNNkKZWqb zK7PE@lZIcDGbs6;r7-J*)hYC)h_#_Jo6@c5=-^_`kps&o#USP<$VI!id?O4uHUcq6 z0PsHm3A%q#XVr1<^ARX(g=CqUCSY|G8QfSOYeKk-LxkioBO@cE)hEqESv7J8fba2^ zlb44m%K#S~%H&aUR#Kw93f;#A!fTb7Xp|Aj1KVp()s~o01;V7Os|zTf?#v}GDxNx= z7C&13U<@qIQ6l{PDVRGFwp8EUU9)=al^xA%O99$IA3`1pDX9{0v+TDfZ{C0KAVI{N z8qspFaCz`hc^>9!fQ*z-#*7;PDy1IHESs-ac!7IMP|HdwDT)3*rJf!aNeBxQfQ&$1 zO3DkUp2(&&-ExyG=A%b108p<*`Om@_UaLM)xzS;)AXZt+NpYst(i@#sH)?xPK{wKZ zh#Soi3~R$eW9#&JtrF^w!dd>Z$L14-w)M6Hgw6|NT zy)Ok9<hwAtGBkOAbkEa z78m$6ltlrT`U}FNzYMT4Jw5QAz&Z&7ihKKx?9bsyD16Y?a$#4|9X}gRHIK%zhE|Ri z)?BB%%^c}gZ;7%90Q~A5y4)7MTNhq1UGKFiaIQ%>!$3}?Xlx{m zgfmD7*RI;dCpp}Jr7bR;i=QMRac{JoBoS{d%>RL>{{^ha6=814_O({uW zIg6>}qe;lwzkK2h#GANTOzmjFb*DmZsWiTps5=qI z&R(23^kX-E?9ai%#~a_>ysfxMEB2iG7VEGIo^J+s-L{4P+{*+5rKy10!Mb$q!@hPW z1dW60Yh8J+E942gzOT?QcKpJ3?=QG1@?qyuTo}>m=M~?EzlPPSbPdxv&6%;%D+{)3 zM%?%i>*shv9-BV(MXdM0J_9=(X<>q8DulC)3SPK`&1sXHO9?^t1Y)vz(#(vJEGX zGPY;TY)L0#2v>R5(xUC#hYGg3hS~07{7Kd;`2L5qjK}h0c8AZO{3~A4xkU`zAoZLn zxyvCMr|G9}st>Xq<&fNRUnt?QT$^@*N%B;si}?B8OzEX&j(xT1DN3dujX5j&85pL} zl~6X8vn4O>oOb^i{7`de3Lk~Ulcb#I2;!hJjay>mW2NF@nFw(7-EwQo{bp;13t3qP zU8(K7n2U#0xSJi=KNyET8QNe!>fKhyi+QWPzsYwOZ5cE zka&aogg{Q?z-6HFna`hZ9eT2J=1oF!AV+GJCXH2=l4F)K%i;Tj(!AH%jpyup`wozjI=m%BXR}q}R`< zut>Qn_>)I)!Oc`4UE-ns6?jJ5{aT40MAvI$PSLrUMoC9`O=V%ge6h|_p^FO+6;Mg?WYX|UrXnk~L%*en#xn|_MCrhR*c6RC3Y*6@3a$`RUQ=x;^_$Ar_-=A{ z(hh^hlw=@w)u>RJm1vV+;M!_g;U4U-g^#~{!~?zj7lL3Pq~2Tql6tSkD+Y`8$%9o$ z`0L32@bGT?E&nyG@OQuuA_en0fL0VD@upvY+3%6vS011dnm`!qp(tR?4S+Dj*nIsg zlqD@GSwB!6Sr0{=48uk#m$`B+UteFVe~)^K zz_V3K$CcPUm|VQK+W^3XK0pY>=H^-rMwFI{LN!r$0O!orf`N}uv;R|wJWzWcjd$+c*$1D6N?4BZSbu*k zkbMSolf4M0K?N16Y~es{#{qQ>fXSx{&ZMiwz}uX|*REY-9sYsw+AAxiftF51bZzmw zccnUM2=N5+yA(1hjOXJntg=XUVdPlcC?<+^FUrlXoTc#~0q#5sm zkBE%q(5pH^zJI^LP+dGg-t6VMN*AUhM_xzTeLsZKPBT%A3v20pehE1flavI7_^!;Q z04?WulzeNg%qyF}ngGb000>w$_2wfe$&OX89X=6_%`4K9UiE_o;$mX51@;8@MtM0o z0L_DIi0$Py!2l@{;6Ur(5f!g}U3a&|9#o0{a{E{lIt7q*!LA6XWg0PRmY0^wKq(x` z#I2cRJ9g9p>h}!_Qp@)b2}!YdY`nJDC3=%*tN^{0eY62n3zBe z_eDX$`bZHnI94VO4pcS3MxkOMb{dF9I8TLk4uB5

 @@ -493,6 +540,53 @@ const thebe_selector_output = ".output, .cell_output" Representing the Data Sets +
  • + + Setting up the Neural Network + +
    • +
  • + + The Code using Scikit-Learn + +
    • +
  • + + Building a neural network code + + +
    • @@ -508,7 +602,7 @@ const thebe_selector_output = ".output, .cell_output" doconce format html exercisesweek43.do.txt -->

    Exercises weeks 43 and 44¶

    -

    October 9-13, 2023

    +

    October 23-27, 2023

    Date: Deadline is Sunday November 5 at midnight

    You can hand in the exercises from week 43 and week 44 as one exercise and get a total score of two additional points.

    @@ -589,6 +683,13781 @@ inputs \(x_1\) and

    Everything you develop here can be used directly into the code for the project.

    +
    +

    Setting up the Neural Network¶

    +

    We define first our design matrix and the various output vectors for the different gates.

    +
    +
    +
    %matplotlib inline
+
+"""
+Simple code that tests XOR, OR and AND gates with linear regression
+"""
+
+# import necessary packages
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn import datasets
+
+def sigmoid(x):
+    return 1/(1 + np.exp(-x))
+
+def feed_forward(X):
+    # weighted sum of inputs to the hidden layer
+    z_h = np.matmul(X, hidden_weights) + hidden_bias
+    # activation in the hidden layer
+    a_h = sigmoid(z_h)
+    
+    # weighted sum of inputs to the output layer
+    z_o = np.matmul(a_h, output_weights) + output_bias
+    # softmax output
+    # axis 0 holds each input and axis 1 the probabilities of each category
+    probabilities = sigmoid(z_o)
+    return probabilities
+
+# we obtain a prediction by taking the class with the highest likelihood
+def predict(X):
+    probabilities = feed_forward(X)
+    return np.argmax(probabilities, axis=1)
+
+# ensure the same random numbers appear every time
+np.random.seed(0)
+
+# Design matrix
+X = np.array([ [0, 0], [0, 1], [1, 0],[1, 1]],dtype=np.float64)
+
+# The XOR gate
+yXOR = np.array( [ 0, 1 ,1, 0])
+# The OR gate
+yOR = np.array( [ 0, 1 ,1, 1])
+# The AND gate
+yAND = np.array( [ 0, 0 ,0, 1])
+
+# Defining the neural network
+n_inputs, n_features = X.shape
+n_hidden_neurons = 2
+n_categories = 2
+n_features = 2
+
+# we make the weights normally distributed using numpy.random.randn
+
+# weights and bias in the hidden layer
+hidden_weights = np.random.randn(n_features, n_hidden_neurons)
+hidden_bias = np.zeros(n_hidden_neurons) + 0.01
+
+# weights and bias in the output layer
+output_weights = np.random.randn(n_hidden_neurons, n_categories)
+output_bias = np.zeros(n_categories) + 0.01
+
+probabilities = feed_forward(X)
+print(probabilities)
+
+
+predictions = predict(X)
+print(predictions)
+
    +
    +
    +
    +
    [[0.80625657 0.36420967]
+ [0.90297441 0.30170017]
+ [0.89823921 0.28566769]
+ [0.93420126 0.25920793]]
+[0 0 0 0]
+
    +
    +
    +
    +

    Not an impressive result, but this was our first forward pass with randomly assigned weights. Let us now add the full network with the back-propagation algorithm discussed above.

    +
    +
    +

    The Code using Scikit-Learn¶

    +
    +
    +
    # import necessary packages
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.neural_network import MLPClassifier
+from sklearn.metrics import accuracy_score
+import seaborn as sns
+
+# ensure the same random numbers appear every time
+np.random.seed(0)
+
+# Design matrix
+X = np.array([ [0, 0], [0, 1], [1, 0],[1, 1]],dtype=np.float64)
+
+# The XOR gate
+yXOR = np.array( [ 0, 1 ,1, 0])
+# The OR gate
+yOR = np.array( [ 0, 1 ,1, 1])
+# The AND gate
+yAND = np.array( [ 0, 0 ,0, 1])
+
+# Defining the neural network
+n_inputs, n_features = X.shape
+n_hidden_neurons = 2
+n_categories = 2
+n_features = 2
+
+eta_vals = np.logspace(-5, 1, 7)
+lmbd_vals = np.logspace(-5, 1, 7)
+# store models for later use
+DNN_scikit = np.zeros((len(eta_vals), len(lmbd_vals)), dtype=object)
+epochs = 100
+
+for i, eta in enumerate(eta_vals):
+    for j, lmbd in enumerate(lmbd_vals):
+        dnn = MLPClassifier(hidden_layer_sizes=(n_hidden_neurons), activation='logistic',
+                            alpha=lmbd, learning_rate_init=eta, max_iter=epochs)
+        dnn.fit(X, yXOR)
+        DNN_scikit[i][j] = dnn
+        print("Learning rate  = ", eta)
+        print("Lambda = ", lmbd)
+        print("Accuracy score on data set: ", dnn.score(X, yXOR))
+        print()
+
+sns.set()
+test_accuracy = np.zeros((len(eta_vals), len(lmbd_vals)))
+for i in range(len(eta_vals)):
+    for j in range(len(lmbd_vals)):
+        dnn = DNN_scikit[i][j]
+        test_pred = dnn.predict(X)
+        test_accuracy[i][j] = accuracy_score(yXOR, test_pred)
+
+fig, ax = plt.subplots(figsize = (10, 10))
+sns.heatmap(test_accuracy, annot=True, ax=ax, cmap="viridis")
+ax.set_title("Test Accuracy")
+ax.set_ylabel("$\eta$")
+ax.set_xlabel("$\lambda$")
+plt.show()
+
    +
    +
    +
    +
    Learning rate  =  1e-05
+Lambda =  1e-05
+Accuracy score on data set:  0.5
+
+Learning rate  =  1e-05
+Lambda =  0.0001
+Accuracy score on data set:  0.5
+
+Learning rate  =  1e-05
+Lambda =  0.001
+Accuracy score on data set:  0.5
+
+Learning rate  =  1e-05
+Lambda =  0.01
+Accuracy score on data set:  0.5
+
+Learning rate  =  1e-05
+Lambda =  0.1
+Accuracy score on data set:  0.5
+
+Learning rate  =  1e-05
+Lambda =  1.0
+Accuracy score on data set:  0.5
+
+Learning rate  =  1e-05
+Lambda =  10.0
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.0001
+Lambda =  1e-05
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.0001
+Lambda =  0.0001
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.0001
+Lambda =  0.001
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.0001
+Lambda =  0.01
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.0001
+Lambda =  0.1
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.0001
+Lambda =  1.0
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.0001
+Lambda =  10.0
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.001
+Lambda =  1e-05
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.001
+Lambda =  0.0001
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.001
+Lambda =  0.001
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.001
+Lambda =  0.01
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.001
+Lambda =  0.1
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.001
+Lambda =  1.0
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.001
+Lambda =  10.0
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.01
+Lambda =  1e-05
+Accuracy score on data set:  0.25
+
+Learning rate  =  0.01
+Lambda =  0.0001
+Accuracy score on data set:  0.75
+
+Learning rate  =  0.01
+Lambda =  0.001
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.01
+Lambda =  0.01
+Accuracy score on data set:  0.75
+
+Learning rate  =  0.01
+Lambda =  0.1
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.01
+Lambda =  1.0
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.01
+Lambda =  10.0
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.1
+Lambda =  1e-05
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.1
+Lambda =  0.0001
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.1
+Lambda =  0.001
+Accuracy score on data set:  1.0
+
+Learning rate  =  0.1
+Lambda =  0.01
+Accuracy score on data set:  1.0
+
+Learning rate  =  0.1
+Lambda =  0.1
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.1
+Lambda =  1.0
+Accuracy score on data set:  0.5
+
+Learning rate  =  0.1
+Lambda =  10.0
+Accuracy score on data set:  0.5
+
+Learning rate  =  1.0
+Lambda =  1e-05
+Accuracy score on data set:  0.75
+
+Learning rate  =  1.0
+Lambda =  0.0001
+Accuracy score on data set:  0.75
+
+Learning rate  =  1.0
+Lambda =  0.001
+Accuracy score on data set:  0.75
+
+Learning rate  =  1.0
+Lambda =  0.01
+Accuracy score on data set:  0.5
+
+Learning rate  =  1.0
+Lambda =  0.1
+Accuracy score on data set:  0.5
+
+Learning rate  =  1.0
+Lambda =  1.0
+Accuracy score on data set:  0.5
+
+Learning rate  =  1.0
+Lambda =  10.0
+Accuracy score on data set:  0.5
+
+Learning rate  =  10.0
+Lambda =  1e-05
+Accuracy score on data set:  0.5
+
+Learning rate  =  10.0
+Lambda =  0.0001
+Accuracy score on data set:  0.5
+
+Learning rate  =  10.0
+Lambda =  0.001
+Accuracy score on data set:  0.5
+
+Learning rate  =  10.0
+Lambda =  0.01
+Accuracy score on data set:  0.5
+
+Learning rate  =  10.0
+Lambda =  0.1
+Accuracy score on data set:  0.5
+
+Learning rate  =  10.0
+Lambda =  1.0
+Accuracy score on data set:  0.5
+
+Learning rate  =  10.0
+Lambda =  10.0
+Accuracy score on data set:  0.5
+
    +
    +
    /Users/mhjensen/miniforge3/envs/myenv/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:692: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.
+  warnings.warn(
+/Users/mhjensen/miniforge3/envs/myenv/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:692: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.
+  warnings.warn(
+/Users/mhjensen/miniforge3/envs/myenv/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:692: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.
+  warnings.warn(
+/Users/mhjensen/miniforge3/envs/myenv/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:692: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.
+  warnings.warn(
+/Users/mhjensen/miniforge3/envs/myenv/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:692: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.
+  warnings.warn(
+/Users/mhjensen/miniforge3/envs/myenv/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:692: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.
+  warnings.warn(
+/Users/mhjensen/miniforge3/envs/myenv/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:692: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.
+  warnings.warn(
+/Users/mhjensen/miniforge3/envs/myenv/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:692: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.
+  warnings.warn(
+/Users/mhjensen/miniforge3/envs/myenv/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:692: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.
+  warnings.warn(
+/Users/mhjensen/miniforge3/envs/myenv/lib/python3.9/site-packages/sklearn/neural_network/_multilayer_perceptron.py:692: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.
+  warnings.warn(
+
    +
    +_images/exercisesweek43_11_2.png +
    +
    +
    +
    +

    Building a neural network code¶

    +

    Here we present a flexible object oriented codebase +for a feed forward neural network, along with a demonstration of how +to use it. Before we get into the details of the neural network, we +will first present some implementations of various schedulers, cost +functions and activation functions that can be used together with the +neural network.

    +
    +

    Learning rate methods¶

    +

    The code below shows object oriented implementations of the Constant, +Momentum, Adagrad, AdagradMomentum, RMS prop and Adam schedulers. All +of the classes belong to the shared abstract Scheduler class, and +share the update_change() and reset() methods allowing for any of the +schedulers to be seamlessly used during the training stage, as will +later be shown in the fit() method of the neural +network. Update_change() only has one parameter, the gradient +(\(δ^l_ja^{l−1}_k\)), and returns the change which will be subtracted +from the weights. The reset() function takes no parameters, and resets +the desired variables. For Constant and Momentum, reset does nothing.

    +
    +
    +
    import autograd.numpy as np
+
+class Scheduler:
+    """
+    Abstract class for Schedulers
+    """
+
+    def __init__(self, eta):
+        self.eta = eta
+
+    # should be overwritten
+    def update_change(self, gradient):
+        raise NotImplementedError
+
+    # overwritten if needed
+    def reset(self):
+        pass
+
+
+class Constant(Scheduler):
+    def __init__(self, eta):
+        super().__init__(eta)
+
+    def update_change(self, gradient):
+        return self.eta * gradient
+    
+    def reset(self):
+        pass
+
+
+class Momentum(Scheduler):
+    def __init__(self, eta: float, momentum: float):
+        super().__init__(eta)
+        self.momentum = momentum
+        self.change = 0
+
+    def update_change(self, gradient):
+        self.change = self.momentum * self.change + self.eta * gradient
+        return self.change
+
+    def reset(self):
+        pass
+
+
+class Adagrad(Scheduler):
+    def __init__(self, eta):
+        super().__init__(eta)
+        self.G_t = None
+
+    def update_change(self, gradient):
+        delta = 1e-8  # avoid division ny zero
+
+        if self.G_t is None:
+            self.G_t = np.zeros((gradient.shape[0], gradient.shape[0]))
+
+        self.G_t += gradient @ gradient.T
+
+        G_t_inverse = 1 / (
+            delta + np.sqrt(np.reshape(np.diagonal(self.G_t), (self.G_t.shape[0], 1)))
+        )
+        return self.eta * gradient * G_t_inverse
+
+    def reset(self):
+        self.G_t = None
+
+
+class AdagradMomentum(Scheduler):
+    def __init__(self, eta, momentum):
+        super().__init__(eta)
+        self.G_t = None
+        self.momentum = momentum
+        self.change = 0
+
+    def update_change(self, gradient):
+        delta = 1e-8  # avoid division ny zero
+
+        if self.G_t is None:
+            self.G_t = np.zeros((gradient.shape[0], gradient.shape[0]))
+
+        self.G_t += gradient @ gradient.T
+
+        G_t_inverse = 1 / (
+            delta + np.sqrt(np.reshape(np.diagonal(self.G_t), (self.G_t.shape[0], 1)))
+        )
+        self.change = self.change * self.momentum + self.eta * gradient * G_t_inverse
+        return self.change
+
+    def reset(self):
+        self.G_t = None
+
+
+class RMS_prop(Scheduler):
+    def __init__(self, eta, rho):
+        super().__init__(eta)
+        self.rho = rho
+        self.second = 0.0
+
+    def update_change(self, gradient):
+        delta = 1e-8  # avoid division ny zero
+        self.second = self.rho * self.second + (1 - self.rho) * gradient * gradient
+        return self.eta * gradient / (np.sqrt(self.second + delta))
+
+    def reset(self):
+        self.second = 0.0
+
+
+class Adam(Scheduler):
+    def __init__(self, eta, rho, rho2):
+        super().__init__(eta)
+        self.rho = rho
+        self.rho2 = rho2
+        self.moment = 0
+        self.second = 0
+        self.n_epochs = 1
+
+    def update_change(self, gradient):
+        delta = 1e-8  # avoid division ny zero
+
+        self.moment = self.rho * self.moment + (1 - self.rho) * gradient
+        self.second = self.rho2 * self.second + (1 - self.rho2) * gradient * gradient
+
+        moment_corrected = self.moment / (1 - self.rho**self.n_epochs)
+        second_corrected = self.second / (1 - self.rho2**self.n_epochs)
+
+        return self.eta * moment_corrected / (np.sqrt(second_corrected + delta))
+
+    def reset(self):
+        self.n_epochs += 1
+        self.moment = 0
+        self.second = 0
+
    +
    +
    +
    +
    +
    +

    Usage of the above learning rate schedulers¶

    +

    To initalize a scheduler, simply create the object and pass in the +necessary parameters such as the learning rate and the momentum as +shown below. As the Scheduler class is an abstract class it should not +called directly, and will raise an error upon usage.

    +
    +
    +
    momentum_scheduler = Momentum(eta=1e-3, momentum=0.9)
+adam_scheduler = Adam(eta=1e-3, rho=0.9, rho2=0.999)
+
    +
    +
    +
    +

    Here is a small example for how a segment of code using schedulers +could look. Switching out the schedulers is simple.

    +
    +
    +
    weights = np.ones((3,3))
+print(f"Before scheduler:\n{weights=}")
+
+epochs = 10
+for e in range(epochs):
+    gradient = np.random.rand(3, 3)
+    change = adam_scheduler.update_change(gradient)
+    weights = weights - change
+    adam_scheduler.reset()
+
+print(f"\nAfter scheduler:\n{weights=}")
+
    +
    +
    +
    +
    Before scheduler:
+weights=array([[1., 1., 1.],
+       [1., 1., 1.],
+       [1., 1., 1.]])
+
+After scheduler:
+weights=array([[0.993993  , 0.993993  , 0.99399301],
+       [0.99399308, 0.99399315, 0.99399301],
+       [0.99399301, 0.99399309, 0.99399301]])
+
    +
    +
    +
    +
    +
    +

    Cost functions¶

    +

    Here we discuss cost functions that can be used when creating the +neural network. Every cost function takes the target vector as its +parameter, and returns a function valued only at \(x\) such that it may +easily be differentiated.

    +
    +
    +
    import autograd.numpy as np
+
+def CostOLS(target):
+    
+    def func(X):
+        return (1.0 / target.shape[0]) * np.sum((target - X) ** 2)
+
+    return func
+
+
+def CostLogReg(target):
+
+    def func(X):
+        
+        return -(1.0 / target.shape[0]) * np.sum(
+            (target * np.log(X + 10e-10)) + ((1 - target) * np.log(1 - X + 10e-10))
+        )
+
+    return func
+
+
+def CostCrossEntropy(target):
+    
+    def func(X):
+        return -(1.0 / target.size) * np.sum(target * np.log(X + 10e-10))
+
+    return func
+
    +
    +
    +
    +

    Below we give a short example of how these cost function may be used +to obtain results if you wish to test them out on your own using +AutoGrad’s automatics differentiation.

    +
    +
    +
    from autograd import grad
+
+target = np.array([[1, 2, 3]]).T
+a = np.array([[4, 5, 6]]).T
+
+cost_func = CostCrossEntropy
+cost_func_derivative = grad(cost_func(target))
+
+valued_at_a = cost_func_derivative(a)
+print(f"Derivative of cost function {cost_func.__name__} valued at a:\n{valued_at_a}")
+
    +
    +
    +
    +
    Derivative of cost function CostCrossEntropy valued at a:
+[[-0.08333333]
+ [-0.13333333]
+ [-0.16666667]]
+
    +
    +
    +
    +
    +
    +

    Activation functions¶

    +

    Finally, before we look at the neural network, we will look at the +activation functions which can be specified between the hidden layers +and as the output function. Each function can be valued for any given +vector or matrix X, and can be differentiated via derivate().

    +
    +
    +
    import autograd.numpy as np
+from autograd import elementwise_grad
+
+def identity(X):
+    return X
+
+
+def sigmoid(X):
+    try:
+        return 1.0 / (1 + np.exp(-X))
+    except FloatingPointError:
+        return np.where(X > np.zeros(X.shape), np.ones(X.shape), np.zeros(X.shape))
+
+
+def softmax(X):
+    X = X - np.max(X, axis=-1, keepdims=True)
+    delta = 10e-10
+    return np.exp(X) / (np.sum(np.exp(X), axis=-1, keepdims=True) + delta)
+
+
+def RELU(X):
+    return np.where(X > np.zeros(X.shape), X, np.zeros(X.shape))
+
+
+def LRELU(X):
+    delta = 10e-4
+    return np.where(X > np.zeros(X.shape), X, delta * X)
+
+
+def derivate(func):
+    if func.__name__ == "RELU":
+
+        def func(X):
+            return np.where(X > 0, 1, 0)
+
+        return func
+
+    elif func.__name__ == "LRELU":
+
+        def func(X):
+            delta = 10e-4
+            return np.where(X > 0, 1, delta)
+
+        return func
+
+    else:
+        return elementwise_grad(func)
+
    +
    +
    +
    +

    Below follows a short demonstration of how to use an activation +function. The derivative of the activation function will be important +when calculating the output delta term during backpropagation. Note +that derivate() can also be used for cost functions for a more +generalized approach.

    +
    +
    +
    z = np.array([[4, 5, 6]]).T
+print(f"Input to activation function:\n{z}")
+
+act_func = sigmoid
+a = act_func(z)
+print(f"\nOutput from {act_func.__name__} activation function:\n{a}")
+
+act_func_derivative = derivate(act_func)
+valued_at_z = act_func_derivative(a)
+print(f"\nDerivative of {act_func.__name__} activation function valued at z:\n{valued_at_z}")
+
    +
    +
    +
    +
    Input to activation function:
+[[4]
+ [5]
+ [6]]
+
+Output from sigmoid activation function:
+[[0.98201379]
+ [0.99330715]
+ [0.99752738]]
+
+Derivative of sigmoid activation function valued at z:
+[[0.19824029]
+ [0.19721923]
+ [0.19683648]]
+
    +
    +
    +
    +
    +
    +

    The Neural Network¶

    +

    Now that we have gotten a good understanding of the implementation of +some important components, we can take a look at an object oriented +implementation of a feed forward neural network. The feed forward +neural network has been implemented as a class named FFNN, which can +be initiated as a regressor or classifier dependant on the choice of +cost function. The FFNN can have any number of input nodes, hidden +layers with any amount of hidden nodes, and any amount of output nodes +meaning it can perform multiclass classification as well as binary +classification and regression problems. Although there is a lot of +code present, it makes for an easy to use and generalizeable interface +for creating many types of neural networks as will be demonstrated +below.

    +
    +
    +
    import math
+import autograd.numpy as np
+import sys
+import warnings
+from autograd import grad, elementwise_grad
+from random import random, seed
+from copy import deepcopy, copy
+from typing import Tuple, Callable
+from sklearn.utils import resample
+
+warnings.simplefilter("error")
+
+
+class FFNN:
+    """
+    Description:
+    ------------
+        Feed Forward Neural Network with interface enabling flexible design of a
+        nerual networks architecture and the specification of activation function
+        in the hidden layers and output layer respectively. This model can be used
+        for both regression and classification problems, depending on the output function.
+
+    Attributes:
+    ------------
+        I   dimensions (tuple[int]): A list of positive integers, which specifies the
+            number of nodes in each of the networks layers. The first integer in the array
+            defines the number of nodes in the input layer, the second integer defines number
+            of nodes in the first hidden layer and so on until the last number, which
+            specifies the number of nodes in the output layer.
+        II  hidden_func (Callable): The activation function for the hidden layers
+        III output_func (Callable): The activation function for the output layer
+        IV  cost_func (Callable): Our cost function
+        V   seed (int): Sets random seed, makes results reproducible
+    """
+
+    def __init__(
+        self,
+        dimensions: tuple[int],
+        hidden_func: Callable = sigmoid,
+        output_func: Callable = lambda x: x,
+        cost_func: Callable = CostOLS,
+        seed: int = None,
+    ):
+        self.dimensions = dimensions
+        self.hidden_func = hidden_func
+        self.output_func = output_func
+        self.cost_func = cost_func
+        self.seed = seed
+        self.weights = list()
+        self.schedulers_weight = list()
+        self.schedulers_bias = list()
+        self.a_matrices = list()
+        self.z_matrices = list()
+        self.classification = None
+
+        self.reset_weights()
+        self._set_classification()
+
+    def fit(
+        self,
+        X: np.ndarray,
+        t: np.ndarray,
+        scheduler: Scheduler,
+        batches: int = 1,
+        epochs: int = 100,
+        lam: float = 0,
+        X_val: np.ndarray = None,
+        t_val: np.ndarray = None,
+    ):
+        """
+        Description:
+        ------------
+            This function performs the training the neural network by performing the feedforward and backpropagation
+            algorithm to update the networks weights.
+
+        Parameters:
+        ------------
+            I    X (np.ndarray) : training data
+            II   t (np.ndarray) : target data
+            III  scheduler (Scheduler) : specified scheduler (algorithm for optimization of gradient descent)
+            IV   scheduler_args (list[int]) : list of all arguments necessary for scheduler
+
+        Optional Parameters:
+        ------------
+            V    batches (int) : number of batches the datasets are split into, default equal to 1
+            VI   epochs (int) : number of iterations used to train the network, default equal to 100
+            VII  lam (float) : regularization hyperparameter lambda
+            VIII X_val (np.ndarray) : validation set
+            IX   t_val (np.ndarray) : validation target set
+
+        Returns:
+        ------------
+            I   scores (dict) : A dictionary containing the performance metrics of the model.
+                The number of the metrics depends on the parameters passed to the fit-function.
+
+        """
+
+        # setup 
+        if self.seed is not None:
+            np.random.seed(self.seed)
+
+        val_set = False
+        if X_val is not None and t_val is not None:
+            val_set = True
+
+        # creating arrays for score metrics
+        train_errors = np.empty(epochs)
+        train_errors.fill(np.nan)
+        val_errors = np.empty(epochs)
+        val_errors.fill(np.nan)
+
+        train_accs = np.empty(epochs)
+        train_accs.fill(np.nan)
+        val_accs = np.empty(epochs)
+        val_accs.fill(np.nan)
+
+        self.schedulers_weight = list()
+        self.schedulers_bias = list()
+
+        batch_size = X.shape[0] // batches
+
+        X, t = resample(X, t)
+
+        # this function returns a function valued only at X
+        cost_function_train = self.cost_func(t)
+        if val_set:
+            cost_function_val = self.cost_func(t_val)
+
+        # create schedulers for each weight matrix
+        for i in range(len(self.weights)):
+            self.schedulers_weight.append(copy(scheduler))
+            self.schedulers_bias.append(copy(scheduler))
+
+        print(f"{scheduler.__class__.__name__}: Eta={scheduler.eta}, Lambda={lam}")
+
+        try:
+            for e in range(epochs):
+                for i in range(batches):
+                    # allows for minibatch gradient descent
+                    if i == batches - 1:
+                        # If the for loop has reached the last batch, take all thats left
+                        X_batch = X[i * batch_size :, :]
+                        t_batch = t[i * batch_size :, :]
+                    else:
+                        X_batch = X[i * batch_size : (i + 1) * batch_size, :]
+                        t_batch = t[i * batch_size : (i + 1) * batch_size, :]
+
+                    self._feedforward(X_batch)
+                    self._backpropagate(X_batch, t_batch, lam)
+
+                # reset schedulers for each epoch (some schedulers pass in this call)
+                for scheduler in self.schedulers_weight:
+                    scheduler.reset()
+
+                for scheduler in self.schedulers_bias:
+                    scheduler.reset()
+
+                # computing performance metrics
+                pred_train = self.predict(X)
+                train_error = cost_function_train(pred_train)
+
+                train_errors[e] = train_error
+                if val_set:
+                    
+                    pred_val = self.predict(X_val)
+                    val_error = cost_function_val(pred_val)
+                    val_errors[e] = val_error
+
+                if self.classification:
+                    train_acc = self._accuracy(self.predict(X), t)
+                    train_accs[e] = train_acc
+                    if val_set:
+                        val_acc = self._accuracy(pred_val, t_val)
+                        val_accs[e] = val_acc
+
+                # printing progress bar
+                progression = e / epochs
+                print_length = self._progress_bar(
+                    progression,
+                    train_error=train_errors[e],
+                    train_acc=train_accs[e],
+                    val_error=val_errors[e],
+                    val_acc=val_accs[e],
+                )
+        except KeyboardInterrupt:
+            # allows for stopping training at any point and seeing the result
+            pass
+
+        # visualization of training progression (similiar to tensorflow progression bar)
+        sys.stdout.write("\r" + " " * print_length)
+        sys.stdout.flush()
+        self._progress_bar(
+            1,
+            train_error=train_errors[e],
+            train_acc=train_accs[e],
+            val_error=val_errors[e],
+            val_acc=val_accs[e],
+        )
+        sys.stdout.write("")
+
+        # return performance metrics for the entire run
+        scores = dict()
+
+        scores["train_errors"] = train_errors
+
+        if val_set:
+            scores["val_errors"] = val_errors
+
+        if self.classification:
+            scores["train_accs"] = train_accs
+
+            if val_set:
+                scores["val_accs"] = val_accs
+
+        return scores
+
+    def predict(self, X: np.ndarray, *, threshold=0.5):
+        """
+         Description:
+         ------------
+             Performs prediction after training of the network has been finished.
+
+         Parameters:
+        ------------
+             I   X (np.ndarray): The design matrix, with n rows of p features each
+
+         Optional Parameters:
+         ------------
+             II  threshold (float) : sets minimal value for a prediction to be predicted as the positive class
+                 in classification problems
+
+         Returns:
+         ------------
+             I   z (np.ndarray): A prediction vector (row) for each row in our design matrix
+                 This vector is thresholded if regression=False, meaning that classification results
+                 in a vector of 1s and 0s, while regressions in an array of decimal numbers
+
+        """
+
+        predict = self._feedforward(X)
+
+        if self.classification:
+            return np.where(predict > threshold, 1, 0)
+        else:
+            return predict
+
+    def reset_weights(self):
+        """
+        Description:
+        ------------
+            Resets/Reinitializes the weights in order to train the network for a new problem.
+
+        """
+        if self.seed is not None:
+            np.random.seed(self.seed)
+
+        self.weights = list()
+        for i in range(len(self.dimensions) - 1):
+            weight_array = np.random.randn(
+                self.dimensions[i] + 1, self.dimensions[i + 1]
+            )
+            weight_array[0, :] = np.random.randn(self.dimensions[i + 1]) * 0.01
+
+            self.weights.append(weight_array)
+
+    def _feedforward(self, X: np.ndarray):
+        """
+        Description:
+        ------------
+            Calculates the activation of each layer starting at the input and ending at the output.
+            Each following activation is calculated from a weighted sum of each of the preceeding
+            activations (except in the case of the input layer).
+
+        Parameters:
+        ------------
+            I   X (np.ndarray): The design matrix, with n rows of p features each
+
+        Returns:
+        ------------
+            I   z (np.ndarray): A prediction vector (row) for each row in our design matrix
+        """
+
+        # reset matrices
+        self.a_matrices = list()
+        self.z_matrices = list()
+
+        # if X is just a vector, make it into a matrix
+        if len(X.shape) == 1:
+            X = X.reshape((1, X.shape[0]))
+
+        # Add a coloumn of zeros as the first coloumn of the design matrix, in order
+        # to add bias to our data
+        bias = np.ones((X.shape[0], 1)) * 0.01
+        X = np.hstack([bias, X])
+
+        # a^0, the nodes in the input layer (one a^0 for each row in X - where the
+        # exponent indicates layer number).
+        a = X
+        self.a_matrices.append(a)
+        self.z_matrices.append(a)
+
+        # The feed forward algorithm
+        for i in range(len(self.weights)):
+            if i < len(self.weights) - 1:
+                z = a @ self.weights[i]
+                self.z_matrices.append(z)
+                a = self.hidden_func(z)
+                # bias column again added to the data here
+                bias = np.ones((a.shape[0], 1)) * 0.01
+                a = np.hstack([bias, a])
+                self.a_matrices.append(a)
+            else:
+                try:
+                    # a^L, the nodes in our output layers
+                    z = a @ self.weights[i]
+                    a = self.output_func(z)
+                    self.a_matrices.append(a)
+                    self.z_matrices.append(z)
+                except Exception as OverflowError:
+                    print(
+                        "OverflowError in fit() in FFNN\nHOW TO DEBUG ERROR: Consider lowering your learning rate or scheduler specific parameters such as momentum, or check if your input values need scaling"
+                    )
+
+        # this will be a^L
+        return a
+
+    def _backpropagate(self, X, t, lam):
+        """
+        Description:
+        ------------
+            Performs the backpropagation algorithm. In other words, this method
+            calculates the gradient of all the layers starting at the
+            output layer, and moving from right to left accumulates the gradient until
+            the input layer is reached. Each layers respective weights are updated while
+            the algorithm propagates backwards from the output layer (auto-differentation in reverse mode).
+
+        Parameters:
+        ------------
+            I   X (np.ndarray): The design matrix, with n rows of p features each.
+            II  t (np.ndarray): The target vector, with n rows of p targets.
+            III lam (float32): regularization parameter used to punish the weights in case of overfitting
+
+        Returns:
+        ------------
+            No return value.
+
+        """
+        out_derivative = derivate(self.output_func)
+        hidden_derivative = derivate(self.hidden_func)
+
+        for i in range(len(self.weights) - 1, -1, -1):
+            # delta terms for output
+            if i == len(self.weights) - 1:
+                # for multi-class classification
+                if (
+                    self.output_func.__name__ == "softmax"
+                ):
+                    delta_matrix = self.a_matrices[i + 1] - t
+                # for single class classification
+                else:
+                    cost_func_derivative = grad(self.cost_func(t))
+                    delta_matrix = out_derivative(
+                        self.z_matrices[i + 1]
+                    ) * cost_func_derivative(self.a_matrices[i + 1])
+
+            # delta terms for hidden layer
+            else:
+                delta_matrix = (
+                    self.weights[i + 1][1:, :] @ delta_matrix.T
+                ).T * hidden_derivative(self.z_matrices[i + 1])
+
+            # calculate gradient
+            gradient_weights = self.a_matrices[i][:, 1:].T @ delta_matrix
+            gradient_bias = np.sum(delta_matrix, axis=0).reshape(
+                1, delta_matrix.shape[1]
+            )
+
+            # regularization term
+            gradient_weights += self.weights[i][1:, :] * lam
+
+            # use scheduler
+            update_matrix = np.vstack(
+                [
+                    self.schedulers_bias[i].update_change(gradient_bias),
+                    self.schedulers_weight[i].update_change(gradient_weights),
+                ]
+            )
+
+            # update weights and bias
+            self.weights[i] -= update_matrix
+
+    def _accuracy(self, prediction: np.ndarray, target: np.ndarray):
+        """
+        Description:
+        ------------
+            Calculates accuracy of given prediction to target
+
+        Parameters:
+        ------------
+            I   prediction (np.ndarray): vector of predicitons output network
+                (1s and 0s in case of classification, and real numbers in case of regression)
+            II  target (np.ndarray): vector of true values (What the network ideally should predict)
+
+        Returns:
+        ------------
+            A floating point number representing the percentage of correctly classified instances.
+        """
+        assert prediction.size == target.size
+        return np.average((target == prediction))
+    def _set_classification(self):
+        """
+        Description:
+        ------------
+            Decides if FFNN acts as classifier (True) og regressor (False),
+            sets self.classification during init()
+        """
+        self.classification = False
+        if (
+            self.cost_func.__name__ == "CostLogReg"
+            or self.cost_func.__name__ == "CostCrossEntropy"
+        ):
+            self.classification = True
+
+    def _progress_bar(self, progression, **kwargs):
+        """
+        Description:
+        ------------
+            Displays progress of training
+        """
+        print_length = 40
+        num_equals = int(progression * print_length)
+        num_not = print_length - num_equals
+        arrow = ">" if num_equals > 0 else ""
+        bar = "[" + "=" * (num_equals - 1) + arrow + "-" * num_not + "]"
+        perc_print = self._format(progression * 100, decimals=5)
+        line = f"  {bar} {perc_print}% "
+
+        for key in kwargs:
+            if not np.isnan(kwargs[key]):
+                value = self._format(kwargs[key], decimals=4)
+                line += f"| {key}: {value} "
+        sys.stdout.write("\r" + line)
+        sys.stdout.flush()
+        return len(line)
+
+    def _format(self, value, decimals=4):
+        """
+        Description:
+        ------------
+            Formats decimal numbers for progress bar
+        """
+        if value > 0:
+            v = value
+        elif value < 0:
+            v = -10 * value
+        else:
+            v = 1
+        n = 1 + math.floor(math.log10(v))
+        if n >= decimals - 1:
+            return str(round(value))
+        return f"{value:.{decimals-n-1}f}"
+
    +
    +
    +
    +

    Before we make a model, we will quickly generate a dataset we can use +for our linear regression problem as shown below

    +
    +
    +
    import autograd.numpy as np
+from sklearn.model_selection import train_test_split
+
+def SkrankeFunction(x, y):
+    return np.ravel(0 + 1*x + 2*y + 3*x**2 + 4*x*y + 5*y**2)
+
+def create_X(x, y, n):
+    if len(x.shape) > 1:
+        x = np.ravel(x)
+        y = np.ravel(y)
+
+    N = len(x)
+    l = int((n + 1) * (n + 2) / 2)  # Number of elements in beta
+    X = np.ones((N, l))
+
+    for i in range(1, n + 1):
+        q = int((i) * (i + 1) / 2)
+        for k in range(i + 1):
+            X[:, q + k] = (x ** (i - k)) * (y**k)
+
+    return X
+
+step=0.5
+x = np.arange(0, 1, step)
+y = np.arange(0, 1, step)
+x, y = np.meshgrid(x, y)
+target = SkrankeFunction(x, y)
+target = target.reshape(target.shape[0], 1)
+
+poly_degree=3
+X = create_X(x, y, poly_degree)
+
+X_train, X_test, t_train, t_test = train_test_split(X, target)
+
    +
    +
    +
    +

    Now that we have our dataset ready for the regression, we can create +our regressor. Note that with the seed parameter, we can make sure our +results stay the same every time we run the neural network. For +inititialization, we simply specify the dimensions (we wish the amount +of input nodes to be equal to the datapoints, and the output to +predict one value).

    +
    +
    +
    input_nodes = X_train.shape[1]
+output_nodes = 1
+
+linear_regression = FFNN((input_nodes, output_nodes), output_func=identity, cost_func=CostOLS, seed=2023)
+
    +
    +
    +
    +

    We then fit our model with our training data using the scheduler of our choice.

    +
    +
    +
    linear_regression.reset_weights() # reset weights such that previous runs or reruns don't affect the weights
+
+scheduler = Constant(eta=1e-3)
+scores = linear_regression.fit(X_train, t_train, scheduler)
+
    +
    +
    +
    +
    Constant: Eta=0.001, Lambda=0
+
+  [----------------------------------------] 0.000% | train_error: 3.69 
+
    +
    +
      [----------------------------------------] 1.000% | train_error: 3.67 
+
    +
    +
      [----------------------------------------] 2.000% | train_error: 3.65 
+
    +
    +
      [>---------------------------------------] 3.000% | train_error: 3.64 
+
    +
    +
      [>---------------------------------------] 4.000% | train_error: 3.62 
+
    +
    +
      [=>--------------------------------------] 5.000% | train_error: 3.60 
+
    +
    +
      [=>--------------------------------------] 6.000% | train_error: 3.58 
+
    +
    +
      [=>--------------------------------------] 7.000% | train_error: 3.57 
+
    +
    +
      [==>-------------------------------------] 8.000% | train_error: 3.55 
+
    +
    +
      [==>-------------------------------------] 9.000% | train_error: 3.53 
+
    +
    +
      [===>------------------------------------] 10.00% | train_error: 3.52 
+
    +
    +
      [===>------------------------------------] 11.00% | train_error: 3.50 
+
    +
    +
      [===>------------------------------------] 12.00% | train_error: 3.48 
+
    +
    +
      [====>-----------------------------------] 13.00% | train_error: 3.47 
+
    +
    +
      [====>-----------------------------------] 14.00% | train_error: 3.45 
+
    +
    +
      [=====>----------------------------------] 15.00% | train_error: 3.43 
+
    +
    +
      [=====>----------------------------------] 16.00% | train_error: 3.42 
+
    +
    +
      [=====>----------------------------------] 17.00% | train_error: 3.40 
+
    +
    +
      [======>---------------------------------] 18.00% | train_error: 3.38 
+
    +
    +
      [======>---------------------------------] 19.00% | train_error: 3.37 
+
    +
    +
      [=======>--------------------------------] 20.00% | train_error: 3.35 
+
    +
    +
      [=======>--------------------------------] 21.00% | train_error: 3.34 
+
    +
    +
      [=======>--------------------------------] 22.00% | train_error: 3.32 
+
    +
    +
      [========>-------------------------------] 23.00% | train_error: 3.31 
+
    +
    +
      [========>-------------------------------] 24.00% | train_error: 3.29 
+
    +
    +
      [=========>------------------------------] 25.00% | train_error: 3.27 
+
    +
    +
      [=========>------------------------------] 26.00% | train_error: 3.26 
+
    +
    +
      [=========>------------------------------] 27.00% | train_error: 3.24 
+
    +
    +
      [==========>-----------------------------] 28.00% | train_error: 3.23 
+
    +
    +
      [==========>-----------------------------] 29.00% | train_error: 3.21 
+
    +
    +
      [===========>----------------------------] 30.00% | train_error: 3.20 
+
    +
    +
      [===========>----------------------------] 31.00% | train_error: 3.18 
+
    +
    +
      [===========>----------------------------] 32.00% | train_error: 3.17 
+
    +
    +
      [============>---------------------------] 33.00% | train_error: 3.15 
+
    +
    +
      [============>---------------------------] 34.00% | train_error: 3.14 
+
    +
    +
      [=============>--------------------------] 35.00% | train_error: 3.12 
+
    +
    +
      [=============>--------------------------] 36.00% | train_error: 3.11 
+
    +
    +
      [=============>--------------------------] 37.00% | train_error: 3.09 
+
    +
    +
      [==============>-------------------------] 38.00% | train_error: 3.08 
+
    +
    +
      [==============>-------------------------] 39.00% | train_error: 3.06 
+
    +
    +
      [===============>------------------------] 40.00% | train_error: 3.05 
+
    +
    +
      [===============>------------------------] 41.00% | train_error: 3.03 
+
    +
    +
      [===============>------------------------] 42.00% | train_error: 3.02 
+
    +
    +
      [================>-----------------------] 43.00% | train_error: 3.00 
+
    +
    +
      [================>-----------------------] 44.00% | train_error: 2.99 
+
    +
    +
      [=================>----------------------] 45.00% | train_error: 2.98 
+
    +
    +
      [=================>----------------------] 46.00% | train_error: 2.96 
+
    +
    +
      [=================>----------------------] 47.00% | train_error: 2.95 
+
    +
    +
      [==================>---------------------] 48.00% | train_error: 2.93 
+
    +
    +
      [==================>---------------------] 49.00% | train_error: 2.92 
+
    +
    +
      [===================>--------------------] 50.00% | train_error: 2.91 
+
    +
    +
      [===================>--------------------] 51.00% | train_error: 2.89 
+
    +
    +
      [===================>--------------------] 52.00% | train_error: 2.88 
+
    +
    +
      [====================>-------------------] 53.00% | train_error: 2.86 
+
    +
    +
      [====================>-------------------] 54.00% | train_error: 2.85 
+
    +
    +
      [=====================>------------------] 55.00% | train_error: 2.84 
+
    +
    +
      [=====================>------------------] 56.00% | train_error: 2.82 
+
    +
    +
      [=====================>------------------] 57.00% | train_error: 2.81 
+
    +
    +
      [======================>-----------------] 58.00% | train_error: 2.80 
+
    +
    +
      [======================>-----------------] 59.00% | train_error: 2.78 
+
    +
    +
      [=======================>----------------] 60.00% | train_error: 2.77 
+
    +
    +
      [=======================>----------------] 61.00% | train_error: 2.76 
+
    +
    +
      [=======================>----------------] 62.00% | train_error: 2.74 
+
    +
    +
      [========================>---------------] 63.00% | train_error: 2.73 
+
    +
    +
      [========================>---------------] 64.00% | train_error: 2.72 
+
    +
    +
      [=========================>--------------] 65.00% | train_error: 2.70 
+
    +
    +
      [=========================>--------------] 66.00% | train_error: 2.69 
+
    +
    +
      [=========================>--------------] 67.00% | train_error: 2.68 
+
    +
    +
      [==========================>-------------] 68.00% | train_error: 2.67 
+
    +
    +
      [==========================>-------------] 69.00% | train_error: 2.65 
+
    +
    +
      [===========================>------------] 70.00% | train_error: 2.64 
+
    +
    +
      [===========================>------------] 71.00% | train_error: 2.63 
+
    +
    +
      [===========================>------------] 72.00% | train_error: 2.62 
+
    +
    +
      [============================>-----------] 73.00% | train_error: 2.60 
+
    +
    +
      [============================>-----------] 74.00% | train_error: 2.59 
+
    +
    +
      [=============================>----------] 75.00% | train_error: 2.58 
+
    +
    +
      [=============================>----------] 76.00% | train_error: 2.57 
+
    +
    +
      [=============================>----------] 77.00% | train_error: 2.55 
+
    +
    +
      [==============================>---------] 78.00% | train_error: 2.54 
+
    +
    +
      [==============================>---------] 79.00% | train_error: 2.53 
+
    +
    +
      [===============================>--------] 80.00% | train_error: 2.52 
+
    +
    +
      [===============================>--------] 81.00% | train_error: 2.51 
+
    +
    +
      [===============================>--------] 82.00% | train_error: 2.49 
+
    +
    +
      [================================>-------] 83.00% | train_error: 2.48 
+
    +
    +
      [================================>-------] 84.00% | train_error: 2.47 
+
    +
    +
      [=================================>------] 85.00% | train_error: 2.46 
+
    +
    +
      [=================================>------] 86.00% | train_error: 2.45 
+
    +
    +
      [=================================>------] 87.00% | train_error: 2.44 
+
    +
    +
      [==================================>-----] 88.00% | train_error: 2.42 
+
    +
    +
      [==================================>-----] 89.00% | train_error: 2.41 
+
    +
    +
      [===================================>----] 90.00% | train_error: 2.40 
+
    +
    +
      [===================================>----] 91.00% | train_error: 2.39 
+
    +
    +
      [===================================>----] 92.00% | train_error: 2.38 
+
    +
    +
      [====================================>---] 93.00% | train_error: 2.37 
+
    +
    +
      [====================================>---] 94.00% | train_error: 2.36 
+
    +
    +
      [=====================================>--] 95.00% | train_error: 2.34 
+
    +
    +
      [=====================================>--] 96.00% | train_error: 2.33 
+
    +
    +
      [=====================================>--] 97.00% | train_error: 2.32 
+
    +
    +
      [======================================>-] 98.00% | train_error: 2.31 
+
    +
    +
      [======================================>-] 99.00% | train_error: 2.30 
+
    +
    +
                                                                            
+
    +
    +
      [=======================================>] 100.0% | train_error: 2.30 
+
    +
    +
    +
    +

    Due to the progress bar we can see the MSE (train_error) throughout +the FFNN’s training. Note that the fit() function has some optional +parameters with defualt arguments. For example, the regularization +hyperparameter can be left ignored if not needed, and equally the FFNN +will by default run for 100 epochs. These can easily be changed, such +as for example:

    +
    +
    +
    linear_regression.reset_weights() # reset weights such that previous runs or reruns don't affect the weights
+
+scores = linear_regression.fit(X_train, t_train, scheduler, lam=1e-4, epochs=1000)
+
    +
    +
    +
    +
    Constant: Eta=0.001, Lambda=0.0001
+
+  [----------------------------------------] 0.000% | train_error: 3.69 
+
    +
    +
      [----------------------------------------] 0.1000% | train_error: 3.67 
+
    +
    +
      [----------------------------------------] 0.2000% | train_error: 3.65 
+
    +
    +
      [----------------------------------------] 0.3000% | train_error: 3.64 
+
    +
    +
      [----------------------------------------] 0.4000% | train_error: 3.62 
+
    +
    +
      [----------------------------------------] 0.5000% | train_error: 3.60 
+
    +
    +
      [----------------------------------------] 0.6000% | train_error: 3.58 
+
    +
    +
      [----------------------------------------] 0.7000% | train_error: 3.57 
+
    +
    +
      [----------------------------------------] 0.8000% | train_error: 3.55 
+
    +
    +
      [----------------------------------------] 0.9000% | train_error: 3.53 
+
    +
    +
      [----------------------------------------] 1.000% | train_error: 3.52 
+
    +
    +
      [----------------------------------------] 1.100% | train_error: 3.50 
+
    +
    +
      [----------------------------------------] 1.200% | train_error: 3.48 
+
    +
    +
      [----------------------------------------] 1.300% | train_error: 3.47 
+
    +
    +
      [----------------------------------------] 1.400% | train_error: 3.45 
+
    +
    +
      [----------------------------------------] 1.500% | train_error: 3.43 
+
    +
    +
      [----------------------------------------] 1.600% | train_error: 3.42 
+
    +
    +
      [----------------------------------------] 1.700% | train_error: 3.40 
+
    +
    +
      [----------------------------------------] 1.800% | train_error: 3.38 
+
    +
    +
      [----------------------------------------] 1.900% | train_error: 3.37 
+
    +
    +
      [----------------------------------------] 2.000% | train_error: 3.35 
+
    +
    +
      [----------------------------------------] 2.100% | train_error: 3.34 
+
    +
    +
      [----------------------------------------] 2.200% | train_error: 3.32 
+
    +
    +
      [----------------------------------------] 2.300% | train_error: 3.31 
+
    +
    +
      [----------------------------------------] 2.400% | train_error: 3.29 
+
    +
    +
      [>---------------------------------------] 2.500% | train_error: 3.27 
+
    +
    +
      [>---------------------------------------] 2.600% | train_error: 3.26 
+
    +
    +
      [>---------------------------------------] 2.700% | train_error: 3.24 
+
    +
    +
      [>---------------------------------------] 2.800% | train_error: 3.23 
+
    +
    +
      [>---------------------------------------] 2.900% | train_error: 3.21 
+
    +
    +
      [>---------------------------------------] 3.000% | train_error: 3.20 
+
    +
    +
      [>---------------------------------------] 3.100% | train_error: 3.18 
+
    +
    +
      [>---------------------------------------] 3.200% | train_error: 3.17 
+
    +
    +
      [>---------------------------------------] 3.300% | train_error: 3.15 
+
    +
    +
      [>---------------------------------------] 3.400% | train_error: 3.14 
+
    +
    +
      [>---------------------------------------] 3.500% | train_error: 3.12 
+
    +
    +
      [>---------------------------------------] 3.600% | train_error: 3.11 
+
    +
    +
      [>---------------------------------------] 3.700% | train_error: 3.09 
+
    +
    +
      [>---------------------------------------] 3.800% | train_error: 3.08 
+
    +
    +
      [>---------------------------------------] 3.900% | train_error: 3.06 
+
    +
    +
      [>---------------------------------------] 4.000% | train_error: 3.05 
+
    +
    +
      [>---------------------------------------] 4.100% | train_error: 3.03 
+
    +
    +
      [>---------------------------------------] 4.200% | train_error: 3.02 
+
    +
    +
      [>---------------------------------------] 4.300% | train_error: 3.00 
+
    +
    +
      [>---------------------------------------] 4.400% | train_error: 2.99 
+
    +
    +
      [>---------------------------------------] 4.500% | train_error: 2.98 
+
    +
    +
      [>---------------------------------------] 4.600% | train_error: 2.96 
+
    +
    +
      [>---------------------------------------] 4.700% | train_error: 2.95 
+
    +
    +
      [>---------------------------------------] 4.800% | train_error: 2.93 
+
    +
    +
      [>---------------------------------------] 4.900% | train_error: 2.92 
+
    +
    +
      [=>--------------------------------------] 5.000% | train_error: 2.91 
+
    +
    +
      [=>--------------------------------------] 5.100% | train_error: 2.89 
+
    +
    +
      [=>--------------------------------------] 5.200% | train_error: 2.88 
+
    +
    +
      [=>--------------------------------------] 5.300% | train_error: 2.86 
+
    +
    +
      [=>--------------------------------------] 5.400% | train_error: 2.85 
+
    +
    +
      [=>--------------------------------------] 5.500% | train_error: 2.84 
+
    +
    +
      [=>--------------------------------------] 5.600% | train_error: 2.82 
+
    +
    +
      [=>--------------------------------------] 5.700% | train_error: 2.81 
+
    +
    +
      [=>--------------------------------------] 5.800% | train_error: 2.80 
+
    +
    +
      [=>--------------------------------------] 5.900% | train_error: 2.78 
+
    +
    +
      [=>--------------------------------------] 6.000% | train_error: 2.77 
+
    +
    +
      [=>--------------------------------------] 6.100% | train_error: 2.76 
+
    +
    +
      [=>--------------------------------------] 6.200% | train_error: 2.74 
+
    +
    +
      [=>--------------------------------------] 6.300% | train_error: 2.73 
+
    +
    +
      [=>--------------------------------------] 6.400% | train_error: 2.72 
+
    +
    +
      [=>--------------------------------------] 6.500% | train_error: 2.70 
+
    +
    +
      [=>--------------------------------------] 6.600% | train_error: 2.69 
+
    +
    +
      [=>--------------------------------------] 6.700% | train_error: 2.68 
+
    +
    +
      [=>--------------------------------------] 6.800% | train_error: 2.67 
+
    +
    +
      [=>--------------------------------------] 6.900% | train_error: 2.65 
+
    +
    +
      [=>--------------------------------------] 7.000% | train_error: 2.64 
+
    +
    +
      [=>--------------------------------------] 7.100% | train_error: 2.63 
+
    +
    +
      [=>--------------------------------------] 7.200% | train_error: 2.62 
+
    +
    +
      [=>--------------------------------------] 7.300% | train_error: 2.60 
+
    +
    +
      [=>--------------------------------------] 7.400% | train_error: 2.59 
+
    +
    +
      [==>-------------------------------------] 7.500% | train_error: 2.58 
+
    +
    +
      [==>-------------------------------------] 7.600% | train_error: 2.57 
+
    +
    +
      [==>-------------------------------------] 7.700% | train_error: 2.55 
+
    +
    +
      [==>-------------------------------------] 7.800% | train_error: 2.54 
+
    +
    +
      [==>-------------------------------------] 7.900% | train_error: 2.53 
+
    +
    +
      [==>-------------------------------------] 8.000% | train_error: 2.52 
+
    +
    +
      [==>-------------------------------------] 8.100% | train_error: 2.51 
+
    +
    +
      [==>-------------------------------------] 8.200% | train_error: 2.49 
+
    +
    +
      [==>-------------------------------------] 8.300% | train_error: 2.48 
+
    +
    +
      [==>-------------------------------------] 8.400% | train_error: 2.47 
+
    +
    +
      [==>-------------------------------------] 8.500% | train_error: 2.46 
+
    +
    +
      [==>-------------------------------------] 8.600% | train_error: 2.45 
+
    +
    +
      [==>-------------------------------------] 8.700% | train_error: 2.44 
+
    +
    +
      [==>-------------------------------------] 8.800% | train_error: 2.42 
+
    +
    +
      [==>-------------------------------------] 8.900% | train_error: 2.41 
+
    +
    +
      [==>-------------------------------------] 9.000% | train_error: 2.40 
+
    +
    +
      [==>-------------------------------------] 9.100% | train_error: 2.39 
+
    +
    +
      [==>-------------------------------------] 9.200% | train_error: 2.38 
+
    +
    +
      [==>-------------------------------------] 9.300% | train_error: 2.37 
+
    +
    +
      [==>-------------------------------------] 9.400% | train_error: 2.36 
+
    +
    +
      [==>-------------------------------------] 9.500% | train_error: 2.34 
+
    +
    +
      [==>-------------------------------------] 9.600% | train_error: 2.33 
+
    +
    +
      [==>-------------------------------------] 9.700% | train_error: 2.32 
+
    +
    +
      [==>-------------------------------------] 9.800% | train_error: 2.31 
+
    +
    +
      [==>-------------------------------------] 9.900% | train_error: 2.30 
+
    +
    +
      [===>------------------------------------] 10.00% | train_error: 2.29 
+
    +
    +
      [===>------------------------------------] 10.10% | train_error: 2.28 
+
    +
    +
      [===>------------------------------------] 10.20% | train_error: 2.27 
+
    +
    +
      [===>------------------------------------] 10.30% | train_error: 2.26 
+
    +
    +
      [===>------------------------------------] 10.40% | train_error: 2.25 
+
    +
    +
      [===>------------------------------------] 10.50% | train_error: 2.23 
+
    +
    +
      [===>------------------------------------] 10.60% | train_error: 2.22 
+
    +
    +
      [===>------------------------------------] 10.70% | train_error: 2.21 
+
    +
    +
      [===>------------------------------------] 10.80% | train_error: 2.20 
+
    +
    +
      [===>------------------------------------] 10.90% | train_error: 2.19 
+
    +
    +
      [===>------------------------------------] 11.00% | train_error: 2.18 
+
    +
    +
      [===>------------------------------------] 11.10% | train_error: 2.17 
+
    +
    +
      [===>------------------------------------] 11.20% | train_error: 2.16 
+
    +
    +
      [===>------------------------------------] 11.30% | train_error: 2.15 
+
    +
    +
      [===>------------------------------------] 11.40% | train_error: 2.14 
+
    +
    +
      [===>------------------------------------] 11.50% | train_error: 2.13 
+
    +
    +
      [===>------------------------------------] 11.60% | train_error: 2.12 
+
    +
    +
      [===>------------------------------------] 11.70% | train_error: 2.11 
+
    +
    +
      [===>------------------------------------] 11.80% | train_error: 2.10 
+
    +
    +
      [===>------------------------------------] 11.90% | train_error: 2.09 
+
    +
    +
      [===>------------------------------------] 12.00% | train_error: 2.08 
+
    +
    +
      [===>------------------------------------] 12.10% | train_error: 2.07 
+
    +
    +
      [===>------------------------------------] 12.20% | train_error: 2.06 
+
    +
    +
      [===>------------------------------------] 12.30% | train_error: 2.05 
+
    +
    +
      [===>------------------------------------] 12.40% | train_error: 2.04 
+
    +
    +
      [====>-----------------------------------] 12.50% | train_error: 2.03 
+
    +
    +
      [====>-----------------------------------] 12.60% | train_error: 2.02 
+
    +
    +
      [====>-----------------------------------] 12.70% | train_error: 2.01 
+
    +
    +
      [====>-----------------------------------] 12.80% | train_error: 2.00 
+
    +
    +
      [====>-----------------------------------] 12.90% | train_error: 1.99 
+
    +
    +
      [====>-----------------------------------] 13.00% | train_error: 1.98 
+
    +
    +
      [====>-----------------------------------] 13.10% | train_error: 1.97 
+
    +
    +
      [====>-----------------------------------] 13.20% | train_error: 1.96 
+
    +
    +
      [====>-----------------------------------] 13.30% | train_error: 1.96 
+
    +
    +
      [====>-----------------------------------] 13.40% | train_error: 1.95 
+
    +
    +
      [====>-----------------------------------] 13.50% | train_error: 1.94 
+
    +
    +
      [====>-----------------------------------] 13.60% | train_error: 1.93 
+
    +
    +
      [====>-----------------------------------] 13.70% | train_error: 1.92 
+
    +
    +
      [====>-----------------------------------] 13.80% | train_error: 1.91 
+
    +
    +
      [====>-----------------------------------] 13.90% | train_error: 1.90 
+
    +
    +
      [====>-----------------------------------] 14.00% | train_error: 1.89 
+
    +
    +
      [====>-----------------------------------] 14.10% | train_error: 1.88 
+
    +
    +
      [====>-----------------------------------] 14.20% | train_error: 1.87 
+
    +
    +
      [====>-----------------------------------] 14.30% | train_error: 1.86 
+
    +
    +
      [====>-----------------------------------] 14.40% | train_error: 1.86 
+
    +
    +
      [====>-----------------------------------] 14.50% | train_error: 1.85 
+
    +
    +
      [====>-----------------------------------] 14.60% | train_error: 1.84 
+
    +
    +
      [====>-----------------------------------] 14.70% | train_error: 1.83 
+
    +
    +
      [====>-----------------------------------] 14.80% | train_error: 1.82 
+
    +
    +
      [====>-----------------------------------] 14.90% | train_error: 1.81 
+
    +
    +
      [=====>----------------------------------] 15.00% | train_error: 1.80 
+
    +
    +
      [=====>----------------------------------] 15.10% | train_error: 1.79 
+
    +
    +
      [=====>----------------------------------] 15.20% | train_error: 1.79 
+
    +
    +
      [=====>----------------------------------] 15.30% | train_error: 1.78 
+
    +
    +
      [=====>----------------------------------] 15.40% | train_error: 1.77 
+
    +
    +
      [=====>----------------------------------] 15.50% | train_error: 1.76 
+
    +
    +
      [=====>----------------------------------] 15.60% | train_error: 1.75 
+
    +
    +
      [=====>----------------------------------] 15.70% | train_error: 1.74 
+
    +
    +
      [=====>----------------------------------] 15.80% | train_error: 1.74 
+
    +
    +
      [=====>----------------------------------] 15.90% | train_error: 1.73 
+
    +
    +
      [=====>----------------------------------] 16.00% | train_error: 1.72 
+
    +
    +
      [=====>----------------------------------] 16.10% | train_error: 1.71 
+
    +
    +
      [=====>----------------------------------] 16.20% | train_error: 1.70 
+
    +
    +
      [=====>----------------------------------] 16.30% | train_error: 1.69 
+
    +
    +
      [=====>----------------------------------] 16.40% | train_error: 1.69 
+
    +
    +
      [=====>----------------------------------] 16.50% | train_error: 1.68 
+
    +
    +
      [=====>----------------------------------] 16.60% | train_error: 1.67 
+
    +
    +
      [=====>----------------------------------] 16.70% | train_error: 1.66 
+
    +
    +
      [=====>----------------------------------] 16.80% | train_error: 1.65 
+
    +
    +
      [=====>----------------------------------] 16.90% | train_error: 1.65 
+
    +
    +
      [=====>----------------------------------] 17.00% | train_error: 1.64 
+
    +
    +
      [=====>----------------------------------] 17.10% | train_error: 1.63 
+
    +
    +
      [=====>----------------------------------] 17.20% | train_error: 1.62 
+
    +
    +
      [=====>----------------------------------] 17.30% | train_error: 1.62 
+
    +
    +
      [=====>----------------------------------] 17.40% | train_error: 1.61 
+
    +
    +
      [======>---------------------------------] 17.50% | train_error: 1.60 
+
    +
    +
      [======>---------------------------------] 17.60% | train_error: 1.59 
+
    +
    +
      [======>---------------------------------] 17.70% | train_error: 1.59 
+
    +
    +
      [======>---------------------------------] 17.80% | train_error: 1.58 
+
    +
    +
      [======>---------------------------------] 17.90% | train_error: 1.57 
+
    +
    +
      [======>---------------------------------] 18.00% | train_error: 1.56 
+
    +
    +
      [======>---------------------------------] 18.10% | train_error: 1.56 
+
    +
    +
      [======>---------------------------------] 18.20% | train_error: 1.55 
+
    +
    +
      [======>---------------------------------] 18.30% | train_error: 1.54 
+
    +
    +
      [======>---------------------------------] 18.40% | train_error: 1.53 
+
    +
    +
      [======>---------------------------------] 18.50% | train_error: 1.53 
+
    +
    +
      [======>---------------------------------] 18.60% | train_error: 1.52 
+
    +
    +
      [======>---------------------------------] 18.70% | train_error: 1.51 
+
    +
    +
      [======>---------------------------------] 18.80% | train_error: 1.50 
+
    +
    +
      [======>---------------------------------] 18.90% | train_error: 1.50 
+
    +
    +
      [======>---------------------------------] 19.00% | train_error: 1.49 
+
    +
    +
      [======>---------------------------------] 19.10% | train_error: 1.48 
+
    +
    +
      [======>---------------------------------] 19.20% | train_error: 1.48 
+
    +
    +
      [======>---------------------------------] 19.30% | train_error: 1.47 
+
    +
    +
      [======>---------------------------------] 19.40% | train_error: 1.46 
+
    +
    +
      [======>---------------------------------] 19.50% | train_error: 1.46 
+
    +
    +
      [======>---------------------------------] 19.60% | train_error: 1.45 
+
    +
    +
      [======>---------------------------------] 19.70% | train_error: 1.44 
+
    +
    +
      [======>---------------------------------] 19.80% | train_error: 1.43 
+
    +
    +
      [======>---------------------------------] 19.90% | train_error: 1.43 
+
    +
    +
      [=======>--------------------------------] 20.00% | train_error: 1.42 
+
    +
    +
      [=======>--------------------------------] 20.10% | train_error: 1.41 
+
    +
    +
      [=======>--------------------------------] 20.20% | train_error: 1.41 
+
    +
    +
      [=======>--------------------------------] 20.30% | train_error: 1.40 
+
    +
    +
      [=======>--------------------------------] 20.40% | train_error: 1.39 
+
    +
    +
      [=======>--------------------------------] 20.50% | train_error: 1.39 
+
    +
    +
      [=======>--------------------------------] 20.60% | train_error: 1.38 
+
    +
    +
      [=======>--------------------------------] 20.70% | train_error: 1.37 
+
    +
    +
      [=======>--------------------------------] 20.80% | train_error: 1.37 
+
    +
    +
      [=======>--------------------------------] 20.90% | train_error: 1.36 
+
    +
    +
      [=======>--------------------------------] 21.00% | train_error: 1.35 
+
    +
    +
      [=======>--------------------------------] 21.10% | train_error: 1.35 
+
    +
    +
      [=======>--------------------------------] 21.20% | train_error: 1.34 
+
    +
    +
      [=======>--------------------------------] 21.30% | train_error: 1.34 
+
    +
    +
      [=======>--------------------------------] 21.40% | train_error: 1.33 
+
    +
    +
      [=======>--------------------------------] 21.50% | train_error: 1.32 
+
    +
    +
      [=======>--------------------------------] 21.60% | train_error: 1.32 
+
    +
    +
      [=======>--------------------------------] 21.70% | train_error: 1.31 
+
    +
    +
      [=======>--------------------------------] 21.80% | train_error: 1.30 
+
    +
    +
      [=======>--------------------------------] 21.90% | train_error: 1.30 
+
    +
    +
      [=======>--------------------------------] 22.00% | train_error: 1.29 
+
    +
    +
      [=======>--------------------------------] 22.10% | train_error: 1.29 
+
    +
    +
      [=======>--------------------------------] 22.20% | train_error: 1.28 
+
    +
    +
      [=======>--------------------------------] 22.30% | train_error: 1.27 
+
    +
    +
      [=======>--------------------------------] 22.40% | train_error: 1.27 
+
    +
    +
      [========>-------------------------------] 22.50% | train_error: 1.26 
+
    +
    +
      [========>-------------------------------] 22.60% | train_error: 1.26 
+
    +
    +
      [========>-------------------------------] 22.70% | train_error: 1.25 
+
    +
    +
      [========>-------------------------------] 22.80% | train_error: 1.24 
+
    +
    +
      [========>-------------------------------] 22.90% | train_error: 1.24 
+
    +
    +
      [========>-------------------------------] 23.00% | train_error: 1.23 
+
    +
    +
      [========>-------------------------------] 23.10% | train_error: 1.23 
+
    +
    +
      [========>-------------------------------] 23.20% | train_error: 1.22 
+
    +
    +
      [========>-------------------------------] 23.30% | train_error: 1.21 
+
    +
    +
      [========>-------------------------------] 23.40% | train_error: 1.21 
+
    +
    +
      [========>-------------------------------] 23.50% | train_error: 1.20 
+
    +
    +
      [========>-------------------------------] 23.60% | train_error: 1.20 
+
    +
    +
      [========>-------------------------------] 23.70% | train_error: 1.19 
+
    +
    +
      [========>-------------------------------] 23.80% | train_error: 1.19 
+
    +
    +
      [========>-------------------------------] 23.90% | train_error: 1.18 
+
    +
    +
      [========>-------------------------------] 24.00% | train_error: 1.17 
+
    +
    +
      [========>-------------------------------] 24.10% | train_error: 1.17 
+
    +
    +
      [========>-------------------------------] 24.20% | train_error: 1.16 
+
    +
    +
      [========>-------------------------------] 24.30% | train_error: 1.16 
+
    +
    +
      [========>-------------------------------] 24.40% | train_error: 1.15 
+
    +
    +
      [========>-------------------------------] 24.50% | train_error: 1.15 
+
    +
    +
      [========>-------------------------------] 24.60% | train_error: 1.14 
+
    +
    +
      [========>-------------------------------] 24.70% | train_error: 1.14 
+
    +
    +
      [========>-------------------------------] 24.80% | train_error: 1.13 
+
    +
    +
      [========>-------------------------------] 24.90% | train_error: 1.13 
+
    +
    +
      [=========>------------------------------] 25.00% | train_error: 1.12 
+
    +
    +
      [=========>------------------------------] 25.10% | train_error: 1.11 
+
    +
    +
      [=========>------------------------------] 25.20% | train_error: 1.11 
+
    +
    +
      [=========>------------------------------] 25.30% | train_error: 1.10 
+
    +
    +
      [=========>------------------------------] 25.40% | train_error: 1.10 
+
    +
    +
      [=========>------------------------------] 25.50% | train_error: 1.09 
+
    +
    +
      [=========>------------------------------] 25.60% | train_error: 1.09 
+
    +
    +
      [=========>------------------------------] 25.70% | train_error: 1.08 
+
    +
    +
      [=========>------------------------------] 25.80% | train_error: 1.08 
+
    +
    +
      [=========>------------------------------] 25.90% | train_error: 1.07 
+
    +
    +
      [=========>------------------------------] 26.00% | train_error: 1.07 
+
    +
    +
      [=========>------------------------------] 26.10% | train_error: 1.06 
+
    +
    +
      [=========>------------------------------] 26.20% | train_error: 1.06 
+
    +
    +
      [=========>------------------------------] 26.30% | train_error: 1.05 
+
    +
    +
      [=========>------------------------------] 26.40% | train_error: 1.05 
+
    +
    +
      [=========>------------------------------] 26.50% | train_error: 1.04 
+
    +
    +
      [=========>------------------------------] 26.60% | train_error: 1.04 
+
    +
    +
      [=========>------------------------------] 26.70% | train_error: 1.03 
+
    +
    +
      [=========>------------------------------] 26.80% | train_error: 1.03 
+
    +
    +
      [=========>------------------------------] 26.90% | train_error: 1.02 
+
    +
    +
      [=========>------------------------------] 27.00% | train_error: 1.02 
+
    +
    +
      [=========>------------------------------] 27.10% | train_error: 1.01 
+
    +
    +
      [=========>------------------------------] 27.20% | train_error: 1.01 
+
    +
    +
      [=========>------------------------------] 27.30% | train_error: 1.00 
+
    +
    +
      [=========>------------------------------] 27.40% | train_error: 0.999 
+
    +
    +
      [==========>-----------------------------] 27.50% | train_error: 0.994 
+
    +
    +
      [==========>-----------------------------] 27.60% | train_error: 0.990 
+
    +
    +
      [==========>-----------------------------] 27.70% | train_error: 0.985 
+
    +
    +
      [==========>-----------------------------] 27.80% | train_error: 0.980 
+
    +
    +
      [==========>-----------------------------] 27.90% | train_error: 0.976 
+
    +
    +
      [==========>-----------------------------] 28.00% | train_error: 0.971 
+
    +
    +
      [==========>-----------------------------] 28.10% | train_error: 0.966 
+
    +
    +
      [==========>-----------------------------] 28.20% | train_error: 0.962 
+
    +
    +
      [==========>-----------------------------] 28.30% | train_error: 0.957 
+
    +
    +
      [==========>-----------------------------] 28.40% | train_error: 0.953 
+
    +
    +
      [==========>-----------------------------] 28.50% | train_error: 0.948 
+
    +
    +
      [==========>-----------------------------] 28.60% | train_error: 0.944 
+
    +
    +
      [==========>-----------------------------] 28.70% | train_error: 0.939 
+
    +
    +
      [==========>-----------------------------] 28.80% | train_error: 0.935 
+
    +
    +
      [==========>-----------------------------] 28.90% | train_error: 0.930 
+
    +
    +
      [==========>-----------------------------] 29.00% | train_error: 0.926 
+
    +
    +
      [==========>-----------------------------] 29.10% | train_error: 0.922 
+
    +
    +
      [==========>-----------------------------] 29.20% | train_error: 0.917 
+
    +
    +
      [==========>-----------------------------] 29.30% | train_error: 0.913 
+
    +
    +
      [==========>-----------------------------] 29.40% | train_error: 0.909 
+
    +
    +
      [==========>-----------------------------] 29.50% | train_error: 0.904 
+
    +
    +
      [==========>-----------------------------] 29.60% | train_error: 0.900 
+
    +
    +
      [==========>-----------------------------] 29.70% | train_error: 0.896 
+
    +
    +
      [==========>-----------------------------] 29.80% | train_error: 0.891 
+
    +
    +
      [==========>-----------------------------] 29.90% | train_error: 0.887 
+
    +
    +
      [===========>----------------------------] 30.00% | train_error: 0.883 
+
    +
    +
      [===========>----------------------------] 30.10% | train_error: 0.879 
+
    +
    +
      [===========>----------------------------] 30.20% | train_error: 0.875 
+
    +
    +
      [===========>----------------------------] 30.30% | train_error: 0.870 
+
    +
    +
      [===========>----------------------------] 30.40% | train_error: 0.866 
+
    +
    +
      [===========>----------------------------] 30.50% | train_error: 0.862 
+
    +
    +
      [===========>----------------------------] 30.60% | train_error: 0.858 
+
    +
    +
      [===========>----------------------------] 30.70% | train_error: 0.854 
+
    +
    +
      [===========>----------------------------] 30.80% | train_error: 0.850 
+
    +
    +
      [===========>----------------------------] 30.90% | train_error: 0.846 
+
    +
    +
      [===========>----------------------------] 31.00% | train_error: 0.842 
+
    +
    +
      [===========>----------------------------] 31.10% | train_error: 0.838 
+
    +
    +
      [===========>----------------------------] 31.20% | train_error: 0.834 
+
    +
    +
      [===========>----------------------------] 31.30% | train_error: 0.830 
+
    +
    +
      [===========>----------------------------] 31.40% | train_error: 0.826 
+
    +
    +
      [===========>----------------------------] 31.50% | train_error: 0.822 
+
    +
    +
      [===========>----------------------------] 31.60% | train_error: 0.818 
+
    +
    +
      [===========>----------------------------] 31.70% | train_error: 0.814 
+
    +
    +
      [===========>----------------------------] 31.80% | train_error: 0.811 
+
    +
    +
      [===========>----------------------------] 31.90% | train_error: 0.807 
+
    +
    +
      [===========>----------------------------] 32.00% | train_error: 0.803 
+
    +
    +
      [===========>----------------------------] 32.10% | train_error: 0.799 
+
    +
    +
      [===========>----------------------------] 32.20% | train_error: 0.795 
+
    +
    +
      [===========>----------------------------] 32.30% | train_error: 0.792 
+
    +
    +
      [===========>----------------------------] 32.40% | train_error: 0.788 
+
    +
    +
      [============>---------------------------] 32.50% | train_error: 0.784 
+
    +
    +
      [============>---------------------------] 32.60% | train_error: 0.780 
+
    +
    +
      [============>---------------------------] 32.70% | train_error: 0.777 
+
    +
    +
      [============>---------------------------] 32.80% | train_error: 0.773 
+
    +
    +
      [============>---------------------------] 32.90% | train_error: 0.769 
+
    +
    +
      [============>---------------------------] 33.00% | train_error: 0.766 
+
    +
    +
      [============>---------------------------] 33.10% | train_error: 0.762 
+
    +
    +
      [============>---------------------------] 33.20% | train_error: 0.759 
+
    +
    +
      [============>---------------------------] 33.30% | train_error: 0.755 
+
    +
    +
      [============>---------------------------] 33.40% | train_error: 0.751 
+
    +
    +
      [============>---------------------------] 33.50% | train_error: 0.748 
+
    +
    +
      [============>---------------------------] 33.60% | train_error: 0.744 
+
    +
    +
      [============>---------------------------] 33.70% | train_error: 0.741 
+
    +
    +
      [============>---------------------------] 33.80% | train_error: 0.737 
+
    +
    +
      [============>---------------------------] 33.90% | train_error: 0.734 
+
    +
    +
      [============>---------------------------] 34.00% | train_error: 0.730 
+
    +
    +
      [============>---------------------------] 34.10% | train_error: 0.727 
+
    +
    +
      [============>---------------------------] 34.20% | train_error: 0.723 
+
    +
    +
      [============>---------------------------] 34.30% | train_error: 0.720 
+
    +
    +
      [============>---------------------------] 34.40% | train_error: 0.717 
+
    +
    +
      [============>---------------------------] 34.50% | train_error: 0.713 
+
    +
    +
      [============>---------------------------] 34.60% | train_error: 0.710 
+
    +
    +
      [============>---------------------------] 34.70% | train_error: 0.706 
+
    +
    +
      [============>---------------------------] 34.80% | train_error: 0.703 
+
    +
    +
      [============>---------------------------] 34.90% | train_error: 0.700 
+
    +
    +
      [=============>--------------------------] 35.00% | train_error: 0.696 
+
    +
    +
      [=============>--------------------------] 35.10% | train_error: 0.693 
+
    +
    +
      [=============>--------------------------] 35.20% | train_error: 0.690 
+
    +
    +
      [=============>--------------------------] 35.30% | train_error: 0.687 
+
    +
    +
      [=============>--------------------------] 35.40% | train_error: 0.683 
+
    +
    +
      [=============>--------------------------] 35.50% | train_error: 0.680 
+
    +
    +
      [=============>--------------------------] 35.60% | train_error: 0.677 
+
    +
    +
      [=============>--------------------------] 35.70% | train_error: 0.674 
+
    +
    +
      [=============>--------------------------] 35.80% | train_error: 0.670 
+
    +
    +
      [=============>--------------------------] 35.90% | train_error: 0.667 
+
    +
    +
      [=============>--------------------------] 36.00% | train_error: 0.664 
+
    +
    +
      [=============>--------------------------] 36.10% | train_error: 0.661 
+
    +
    +
      [=============>--------------------------] 36.20% | train_error: 0.658 
+
    +
    +
      [=============>--------------------------] 36.30% | train_error: 0.655 
+
    +
    +
      [=============>--------------------------] 36.40% | train_error: 0.652 
+
    +
    +
      [=============>--------------------------] 36.50% | train_error: 0.649 
+
    +
    +
      [=============>--------------------------] 36.60% | train_error: 0.646 
+
    +
    +
      [=============>--------------------------] 36.70% | train_error: 0.642 
+
    +
    +
      [=============>--------------------------] 36.80% | train_error: 0.639 
+
    +
    +
      [=============>--------------------------] 36.90% | train_error: 0.636 
+
    +
    +
      [=============>--------------------------] 37.00% | train_error: 0.633 
+
    +
    +
      [=============>--------------------------] 37.10% | train_error: 0.630 
+
    +
    +
      [=============>--------------------------] 37.20% | train_error: 0.627 
+
    +
    +
      [=============>--------------------------] 37.30% | train_error: 0.624 
+
    +
    +
      [=============>--------------------------] 37.40% | train_error: 0.622 
+
    +
    +
      [==============>-------------------------] 37.50% | train_error: 0.619 
+
    +
    +
      [==============>-------------------------] 37.60% | train_error: 0.616 
+
    +
    +
      [==============>-------------------------] 37.70% | train_error: 0.613 
+
    +
    +
      [==============>-------------------------] 37.80% | train_error: 0.610 
+
    +
    +
      [==============>-------------------------] 37.90% | train_error: 0.607 
+
    +
    +
      [==============>-------------------------] 38.00% | train_error: 0.604 
+
    +
    +
      [==============>-------------------------] 38.10% | train_error: 0.601 
+
    +
    +
      [==============>-------------------------] 38.20% | train_error: 0.598 
+
    +
    +
      [==============>-------------------------] 38.30% | train_error: 0.596 
+
    +
    +
      [==============>-------------------------] 38.40% | train_error: 0.593 
+
    +
    +
      [==============>-------------------------] 38.50% | train_error: 0.590 
+
    +
    +
      [==============>-------------------------] 38.60% | train_error: 0.587 
+
    +
    +
      [==============>-------------------------] 38.70% | train_error: 0.584 
+
    +
    +
      [==============>-------------------------] 38.80% | train_error: 0.582 
+
    +
    +
      [==============>-------------------------] 38.90% | train_error: 0.579 
+
    +
    +
      [==============>-------------------------] 39.00% | train_error: 0.576 
+
    +
    +
      [==============>-------------------------] 39.10% | train_error: 0.573 
+
    +
    +
      [==============>-------------------------] 39.20% | train_error: 0.571 
+
    +
    +
      [==============>-------------------------] 39.30% | train_error: 0.568 
+
    +
    +
      [==============>-------------------------] 39.40% | train_error: 0.565 
+
    +
    +
      [==============>-------------------------] 39.50% | train_error: 0.563 
+
    +
    +
      [==============>-------------------------] 39.60% | train_error: 0.560 
+
    +
    +
      [==============>-------------------------] 39.70% | train_error: 0.557 
+
    +
    +
      [==============>-------------------------] 39.80% | train_error: 0.555 
+
    +
    +
      [==============>-------------------------] 39.90% | train_error: 0.552 
+
    +
    +
      [===============>------------------------] 40.00% | train_error: 0.549 
+
    +
    +
      [===============>------------------------] 40.10% | train_error: 0.547 
+
    +
    +
      [===============>------------------------] 40.20% | train_error: 0.544 
+
    +
    +
      [===============>------------------------] 40.30% | train_error: 0.542 
+
    +
    +
      [===============>------------------------] 40.40% | train_error: 0.539 
+
    +
    +
      [===============>------------------------] 40.50% | train_error: 0.537 
+
    +
    +
      [===============>------------------------] 40.60% | train_error: 0.534 
+
    +
    +
      [===============>------------------------] 40.70% | train_error: 0.532 
+
    +
    +
      [===============>------------------------] 40.80% | train_error: 0.529 
+
    +
    +
      [===============>------------------------] 40.90% | train_error: 0.527 
+
    +
    +
      [===============>------------------------] 41.00% | train_error: 0.524 
+
    +
    +
      [===============>------------------------] 41.10% | train_error: 0.522 
+
    +
    +
      [===============>------------------------] 41.20% | train_error: 0.519 
+
    +
    +
      [===============>------------------------] 41.30% | train_error: 0.517 
+
    +
    +
      [===============>------------------------] 41.40% | train_error: 0.514 
+
    +
    +
      [===============>------------------------] 41.50% | train_error: 0.512 
+
    +
    +
      [===============>------------------------] 41.60% | train_error: 0.509 
+
    +
    +
      [===============>------------------------] 41.70% | train_error: 0.507 
+
    +
    +
      [===============>------------------------] 41.80% | train_error: 0.505 
+
    +
    +
      [===============>------------------------] 41.90% | train_error: 0.502 
+
    +
    +
      [===============>------------------------] 42.00% | train_error: 0.500 
+
    +
    +
      [===============>------------------------] 42.10% | train_error: 0.498 
+
    +
    +
      [===============>------------------------] 42.20% | train_error: 0.495 
+
    +
    +
      [===============>------------------------] 42.30% | train_error: 0.493 
+
    +
    +
      [===============>------------------------] 42.40% | train_error: 0.491 
+
    +
    +
      [================>-----------------------] 42.50% | train_error: 0.488 
+
    +
    +
      [================>-----------------------] 42.60% | train_error: 0.486 
+
    +
    +
      [================>-----------------------] 42.70% | train_error: 0.484 
+
    +
    +
      [================>-----------------------] 42.80% | train_error: 0.481 
+
    +
    +
      [================>-----------------------] 42.90% | train_error: 0.479 
+
    +
    +
      [================>-----------------------] 43.00% | train_error: 0.477 
+
    +
    +
      [================>-----------------------] 43.10% | train_error: 0.475 
+
    +
    +
      [================>-----------------------] 43.20% | train_error: 0.472 
+
    +
    +
      [================>-----------------------] 43.30% | train_error: 0.470 
+
    +
    +
      [================>-----------------------] 43.40% | train_error: 0.468 
+
    +
    +
      [================>-----------------------] 43.50% | train_error: 0.466 
+
    +
    +
      [================>-----------------------] 43.60% | train_error: 0.463 
+
    +
    +
      [================>-----------------------] 43.70% | train_error: 0.461 
+
    +
    +
      [================>-----------------------] 43.80% | train_error: 0.459 
+
    +
    +
      [================>-----------------------] 43.90% | train_error: 0.457 
+
    +
    +
      [================>-----------------------] 44.00% | train_error: 0.455 
+
    +
    +
      [================>-----------------------] 44.10% | train_error: 0.453 
+
    +
    +
      [================>-----------------------] 44.20% | train_error: 0.451 
+
    +
    +
      [================>-----------------------] 44.30% | train_error: 0.448 
+
    +
    +
      [================>-----------------------] 44.40% | train_error: 0.446 
+
    +
    +
      [================>-----------------------] 44.50% | train_error: 0.444 
+
    +
    +
      [================>-----------------------] 44.60% | train_error: 0.442 
+
    +
    +
      [================>-----------------------] 44.70% | train_error: 0.440 
+
    +
    +
      [================>-----------------------] 44.80% | train_error: 0.438 
+
    +
    +
      [================>-----------------------] 44.90% | train_error: 0.436 
+
    +
    +
      [=================>----------------------] 45.00% | train_error: 0.434 
+
    +
    +
      [=================>----------------------] 45.10% | train_error: 0.432 
+
    +
    +
      [=================>----------------------] 45.20% | train_error: 0.430 
+
    +
    +
      [=================>----------------------] 45.30% | train_error: 0.428 
+
    +
    +
      [=================>----------------------] 45.40% | train_error: 0.426 
+
    +
    +
      [=================>----------------------] 45.50% | train_error: 0.424 
+
    +
    +
      [=================>----------------------] 45.60% | train_error: 0.422 
+
    +
    +
      [=================>----------------------] 45.70% | train_error: 0.420 
+
    +
    +
      [=================>----------------------] 45.80% | train_error: 0.418 
+
    +
    +
      [=================>----------------------] 45.90% | train_error: 0.416 
+
    +
    +
      [=================>----------------------] 46.00% | train_error: 0.414 
+
    +
    +
      [=================>----------------------] 46.10% | train_error: 0.412 
+
    +
    +
      [=================>----------------------] 46.20% | train_error: 0.410 
+
    +
    +
      [=================>----------------------] 46.30% | train_error: 0.408 
+
    +
    +
      [=================>----------------------] 46.40% | train_error: 0.406 
+
    +
    +
      [=================>----------------------] 46.50% | train_error: 0.404 
+
    +
    +
      [=================>----------------------] 46.60% | train_error: 0.402 
+
    +
    +
      [=================>----------------------] 46.70% | train_error: 0.400 
+
    +
    +
      [=================>----------------------] 46.80% | train_error: 0.398 
+
    +
    +
      [=================>----------------------] 46.90% | train_error: 0.397 
+
    +
    +
      [=================>----------------------] 47.00% | train_error: 0.395 
+
    +
    +
      [=================>----------------------] 47.10% | train_error: 0.393 
+
    +
    +
      [=================>----------------------] 47.20% | train_error: 0.391 
+
    +
    +
      [=================>----------------------] 47.30% | train_error: 0.389 
+
    +
    +
      [=================>----------------------] 47.40% | train_error: 0.387 
+
    +
    +
      [==================>---------------------] 47.50% | train_error: 0.386 
+
    +
    +
      [==================>---------------------] 47.60% | train_error: 0.384 
+
    +
    +
      [==================>---------------------] 47.70% | train_error: 0.382 
+
    +
    +
      [==================>---------------------] 47.80% | train_error: 0.380 
+
    +
    +
      [==================>---------------------] 47.90% | train_error: 0.378 
+
    +
    +
      [==================>---------------------] 48.00% | train_error: 0.377 
+
    +
    +
      [==================>---------------------] 48.10% | train_error: 0.375 
+
    +
    +
      [==================>---------------------] 48.20% | train_error: 0.373 
+
    +
    +
      [==================>---------------------] 48.30% | train_error: 0.371 
+
    +
    +
      [==================>---------------------] 48.40% | train_error: 0.370 
+
    +
    +
      [==================>---------------------] 48.50% | train_error: 0.368 
+
    +
    +
      [==================>---------------------] 48.60% | train_error: 0.366 
+
    +
    +
      [==================>---------------------] 48.70% | train_error: 0.364 
+
    +
    +
      [==================>---------------------] 48.80% | train_error: 0.363 
+
    +
    +
      [==================>---------------------] 48.90% | train_error: 0.361 
+
    +
    +
      [==================>---------------------] 49.00% | train_error: 0.359 
+
    +
    +
      [==================>---------------------] 49.10% | train_error: 0.358 
+
    +
    +
      [==================>---------------------] 49.20% | train_error: 0.356 
+
    +
    +
      [==================>---------------------] 49.30% | train_error: 0.354 
+
    +
    +
      [==================>---------------------] 49.40% | train_error: 0.353 
+
    +
    +
      [==================>---------------------] 49.50% | train_error: 0.351 
+
    +
    +
      [==================>---------------------] 49.60% | train_error: 0.349 
+
    +
    +
      [==================>---------------------] 49.70% | train_error: 0.348 
+
    +
    +
      [==================>---------------------] 49.80% | train_error: 0.346 
+
    +
    +
      [==================>---------------------] 49.90% | train_error: 0.344 
+
    +
    +
      [===================>--------------------] 50.00% | train_error: 0.343 
+
    +
    +
      [===================>--------------------] 50.10% | train_error: 0.341 
+
    +
    +
      [===================>--------------------] 50.20% | train_error: 0.339 
+
    +
    +
      [===================>--------------------] 50.30% | train_error: 0.338 
+
    +
    +
      [===================>--------------------] 50.40% | train_error: 0.336 
+
    +
    +
      [===================>--------------------] 50.50% | train_error: 0.335 
+
    +
    +
      [===================>--------------------] 50.60% | train_error: 0.333 
+
    +
    +
      [===================>--------------------] 50.70% | train_error: 0.332 
+
    +
    +
      [===================>--------------------] 50.80% | train_error: 0.330 
+
    +
    +
      [===================>--------------------] 50.90% | train_error: 0.328 
+
    +
    +
      [===================>--------------------] 51.00% | train_error: 0.327 
+
    +
    +
      [===================>--------------------] 51.10% | train_error: 0.325 
+
    +
    +
      [===================>--------------------] 51.20% | train_error: 0.324 
+
    +
    +
      [===================>--------------------] 51.30% | train_error: 0.322 
+
    +
    +
      [===================>--------------------] 51.40% | train_error: 0.321 
+
    +
    +
      [===================>--------------------] 51.50% | train_error: 0.319 
+
    +
    +
      [===================>--------------------] 51.60% | train_error: 0.318 
+
    +
    +
      [===================>--------------------] 51.70% | train_error: 0.316 
+
    +
    +
      [===================>--------------------] 51.80% | train_error: 0.315 
+
    +
    +
      [===================>--------------------] 51.90% | train_error: 0.313 
+
    +
    +
      [===================>--------------------] 52.00% | train_error: 0.312 
+
    +
    +
      [===================>--------------------] 52.10% | train_error: 0.310 
+
    +
    +
      [===================>--------------------] 52.20% | train_error: 0.309 
+
    +
    +
      [===================>--------------------] 52.30% | train_error: 0.308 
+
    +
    +
      [===================>--------------------] 52.40% | train_error: 0.306 
+
    +
    +
      [====================>-------------------] 52.50% | train_error: 0.305 
+
    +
    +
      [====================>-------------------] 52.60% | train_error: 0.303 
+
    +
    +
      [====================>-------------------] 52.70% | train_error: 0.302 
+
    +
    +
      [====================>-------------------] 52.80% | train_error: 0.300 
+
    +
    +
      [====================>-------------------] 52.90% | train_error: 0.299 
+
    +
    +
      [====================>-------------------] 53.00% | train_error: 0.298 
+
    +
    +
      [====================>-------------------] 53.10% | train_error: 0.296 
+
    +
    +
      [====================>-------------------] 53.20% | train_error: 0.295 
+
    +
    +
      [====================>-------------------] 53.30% | train_error: 0.293 
+
    +
    +
      [====================>-------------------] 53.40% | train_error: 0.292 
+
    +
    +
      [====================>-------------------] 53.50% | train_error: 0.291 
+
    +
    +
      [====================>-------------------] 53.60% | train_error: 0.289 
+
    +
    +
      [====================>-------------------] 53.70% | train_error: 0.288 
+
    +
    +
      [====================>-------------------] 53.80% | train_error: 0.287 
+
    +
    +
      [====================>-------------------] 53.90% | train_error: 0.285 
+
    +
    +
      [====================>-------------------] 54.00% | train_error: 0.284 
+
    +
    +
      [====================>-------------------] 54.10% | train_error: 0.283 
+
    +
    +
      [====================>-------------------] 54.20% | train_error: 0.281 
+
    +
    +
      [====================>-------------------] 54.30% | train_error: 0.280 
+
    +
    +
      [====================>-------------------] 54.40% | train_error: 0.279 
+
    +
    +
      [====================>-------------------] 54.50% | train_error: 0.277 
+
    +
    +
      [====================>-------------------] 54.60% | train_error: 0.276 
+
    +
    +
      [====================>-------------------] 54.70% | train_error: 0.275 
+
    +
    +
      [====================>-------------------] 54.80% | train_error: 0.273 
+
    +
    +
      [====================>-------------------] 54.90% | train_error: 0.272 
+
    +
    +
      [=====================>------------------] 55.00% | train_error: 0.271 
+
    +
    +
      [=====================>------------------] 55.10% | train_error: 0.270 
+
    +
    +
      [=====================>------------------] 55.20% | train_error: 0.268 
+
    +
    +
      [=====================>------------------] 55.30% | train_error: 0.267 
+
    +
    +
      [=====================>------------------] 55.40% | train_error: 0.266 
+
    +
    +
      [=====================>------------------] 55.50% | train_error: 0.265 
+
    +
    +
      [=====================>------------------] 55.60% | train_error: 0.263 
+
    +
    +
      [=====================>------------------] 55.70% | train_error: 0.262 
+
    +
    +
      [=====================>------------------] 55.80% | train_error: 0.261 
+
    +
    +
      [=====================>------------------] 55.90% | train_error: 0.260 
+
    +
    +
      [=====================>------------------] 56.00% | train_error: 0.259 
+
    +
    +
      [=====================>------------------] 56.10% | train_error: 0.257 
+
    +
    +
      [=====================>------------------] 56.20% | train_error: 0.256 
+
    +
    +
      [=====================>------------------] 56.30% | train_error: 0.255 
+
    +
    +
      [=====================>------------------] 56.40% | train_error: 0.254 
+
    +
    +
      [=====================>------------------] 56.50% | train_error: 0.253 
+
    +
    +
      [=====================>------------------] 56.60% | train_error: 0.251 
+
    +
    +
      [=====================>------------------] 56.70% | train_error: 0.250 
+
    +
    +
      [=====================>------------------] 56.80% | train_error: 0.249 
+
    +
    +
      [=====================>------------------] 56.90% | train_error: 0.248 
+
    +
    +
      [=====================>------------------] 57.00% | train_error: 0.247 
+
    +
    +
      [=====================>------------------] 57.10% | train_error: 0.246 
+
    +
    +
      [=====================>------------------] 57.20% | train_error: 0.244 
+
    +
    +
      [=====================>------------------] 57.30% | train_error: 0.243 
+
    +
    +
      [=====================>------------------] 57.40% | train_error: 0.242 
+
    +
    +
      [======================>-----------------] 57.50% | train_error: 0.241 
+
    +
    +
      [======================>-----------------] 57.60% | train_error: 0.240 
+
    +
    +
      [======================>-----------------] 57.70% | train_error: 0.239 
+
    +
    +
      [======================>-----------------] 57.80% | train_error: 0.238 
+
    +
    +
      [======================>-----------------] 57.90% | train_error: 0.237 
+
    +
    +
      [======================>-----------------] 58.00% | train_error: 0.235 
+
    +
    +
      [======================>-----------------] 58.10% | train_error: 0.234 
+
    +
    +
      [======================>-----------------] 58.20% | train_error: 0.233 
+
    +
    +
      [======================>-----------------] 58.30% | train_error: 0.232 
+
    +
    +
      [======================>-----------------] 58.40% | train_error: 0.231 
+
    +
    +
      [======================>-----------------] 58.50% | train_error: 0.230 
+
    +
    +
      [======================>-----------------] 58.60% | train_error: 0.229 
+
    +
    +
      [======================>-----------------] 58.70% | train_error: 0.228 
+
    +
    +
      [======================>-----------------] 58.80% | train_error: 0.227 
+
    +
    +
      [======================>-----------------] 58.90% | train_error: 0.226 
+
    +
    +
      [======================>-----------------] 59.00% | train_error: 0.225 
+
    +
    +
      [======================>-----------------] 59.10% | train_error: 0.224 
+
    +
    +
      [======================>-----------------] 59.20% | train_error: 0.223 
+
    +
    +
      [======================>-----------------] 59.30% | train_error: 0.222 
+
    +
    +
      [======================>-----------------] 59.40% | train_error: 0.221 
+
    +
    +
      [======================>-----------------] 59.50% | train_error: 0.219 
+
    +
    +
      [======================>-----------------] 59.60% | train_error: 0.218 
+
    +
    +
      [======================>-----------------] 59.70% | train_error: 0.217 
+
    +
    +
      [======================>-----------------] 59.80% | train_error: 0.216 
+
    +
    +
      [======================>-----------------] 59.90% | train_error: 0.215 
+
    +
    +
      [=======================>----------------] 60.00% | train_error: 0.214 
+
    +
    +
      [=======================>----------------] 60.10% | train_error: 0.213 
+
    +
    +
      [=======================>----------------] 60.20% | train_error: 0.212 
+
    +
    +
      [=======================>----------------] 60.30% | train_error: 0.211 
+
    +
    +
      [=======================>----------------] 60.40% | train_error: 0.210 
+
    +
    +
      [=======================>----------------] 60.50% | train_error: 0.209 
+
    +
    +
      [=======================>----------------] 60.60% | train_error: 0.209 
+
    +
    +
      [=======================>----------------] 60.70% | train_error: 0.208 
+
    +
    +
      [=======================>----------------] 60.80% | train_error: 0.207 
+
    +
    +
      [=======================>----------------] 60.90% | train_error: 0.206 
+
    +
    +
      [=======================>----------------] 61.00% | train_error: 0.205 
+
    +
    +
      [=======================>----------------] 61.10% | train_error: 0.204 
+
    +
    +
      [=======================>----------------] 61.20% | train_error: 0.203 
+
    +
    +
      [=======================>----------------] 61.30% | train_error: 0.202 
+
    +
    +
      [=======================>----------------] 61.40% | train_error: 0.201 
+
    +
    +
      [=======================>----------------] 61.50% | train_error: 0.200 
+
    +
    +
      [=======================>----------------] 61.60% | train_error: 0.199 
+
    +
    +
      [=======================>----------------] 61.70% | train_error: 0.198 
+
    +
    +
      [=======================>----------------] 61.80% | train_error: 0.197 
+
    +
    +
      [=======================>----------------] 61.90% | train_error: 0.196 
+
    +
    +
      [=======================>----------------] 62.00% | train_error: 0.195 
+
    +
    +
      [=======================>----------------] 62.10% | train_error: 0.194 
+
    +
    +
      [=======================>----------------] 62.20% | train_error: 0.194 
+
    +
    +
      [=======================>----------------] 62.30% | train_error: 0.193 
+
    +
    +
      [=======================>----------------] 62.40% | train_error: 0.192 
+
    +
    +
      [========================>---------------] 62.50% | train_error: 0.191 
+
    +
    +
      [========================>---------------] 62.60% | train_error: 0.190 
+
    +
    +
      [========================>---------------] 62.70% | train_error: 0.189 
+
    +
    +
      [========================>---------------] 62.80% | train_error: 0.188 
+
    +
    +
      [========================>---------------] 62.90% | train_error: 0.187 
+
    +
    +
      [========================>---------------] 63.00% | train_error: 0.186 
+
    +
    +
      [========================>---------------] 63.10% | train_error: 0.186 
+
    +
    +
      [========================>---------------] 63.20% | train_error: 0.185 
+
    +
    +
      [========================>---------------] 63.30% | train_error: 0.184 
+
    +
    +
      [========================>---------------] 63.40% | train_error: 0.183 
+
    +
    +
      [========================>---------------] 63.50% | train_error: 0.182 
+
    +
    +
      [========================>---------------] 63.60% | train_error: 0.181 
+
    +
    +
      [========================>---------------] 63.70% | train_error: 0.180 
+
    +
    +
      [========================>---------------] 63.80% | train_error: 0.180 
+
    +
    +
      [========================>---------------] 63.90% | train_error: 0.179 
+
    +
    +
      [========================>---------------] 64.00% | train_error: 0.178 
+
    +
    +
      [========================>---------------] 64.10% | train_error: 0.177 
+
    +
    +
      [========================>---------------] 64.20% | train_error: 0.176 
+
    +
    +
      [========================>---------------] 64.30% | train_error: 0.176 
+
    +
    +
      [========================>---------------] 64.40% | train_error: 0.175 
+
    +
    +
      [========================>---------------] 64.50% | train_error: 0.174 
+
    +
    +
      [========================>---------------] 64.60% | train_error: 0.173 
+
    +
    +
      [========================>---------------] 64.70% | train_error: 0.172 
+
    +
    +
      [========================>---------------] 64.80% | train_error: 0.171 
+
    +
    +
      [========================>---------------] 64.90% | train_error: 0.171 
+
    +
    +
      [=========================>--------------] 65.00% | train_error: 0.170 
+
    +
    +
      [=========================>--------------] 65.10% | train_error: 0.169 
+
    +
    +
      [=========================>--------------] 65.20% | train_error: 0.168 
+
    +
    +
      [=========================>--------------] 65.30% | train_error: 0.168 
+
    +
    +
      [=========================>--------------] 65.40% | train_error: 0.167 
+
    +
    +
      [=========================>--------------] 65.50% | train_error: 0.166 
+
    +
    +
      [=========================>--------------] 65.60% | train_error: 0.165 
+
    +
    +
      [=========================>--------------] 65.70% | train_error: 0.164 
+
    +
    +
      [=========================>--------------] 65.80% | train_error: 0.164 
+
    +
    +
      [=========================>--------------] 65.90% | train_error: 0.163 
+
    +
    +
      [=========================>--------------] 66.00% | train_error: 0.162 
+
    +
    +
      [=========================>--------------] 66.10% | train_error: 0.161 
+
    +
    +
      [=========================>--------------] 66.20% | train_error: 0.161 
+
    +
    +
      [=========================>--------------] 66.30% | train_error: 0.160 
+
    +
    +
      [=========================>--------------] 66.40% | train_error: 0.159 
+
    +
    +
      [=========================>--------------] 66.50% | train_error: 0.158 
+
    +
    +
      [=========================>--------------] 66.60% | train_error: 0.158 
+
    +
    +
      [=========================>--------------] 66.70% | train_error: 0.157 
+
    +
    +
      [=========================>--------------] 66.80% | train_error: 0.156 
+
    +
    +
      [=========================>--------------] 66.90% | train_error: 0.156 
+
    +
    +
      [=========================>--------------] 67.00% | train_error: 0.155 
+
    +
    +
      [=========================>--------------] 67.10% | train_error: 0.154 
+
    +
    +
      [=========================>--------------] 67.20% | train_error: 0.153 
+
    +
    +
      [=========================>--------------] 67.30% | train_error: 0.153 
+
    +
    +
      [=========================>--------------] 67.40% | train_error: 0.152 
+
    +
    +
      [==========================>-------------] 67.50% | train_error: 0.151 
+
    +
    +
      [==========================>-------------] 67.60% | train_error: 0.151 
+
    +
    +
      [==========================>-------------] 67.70% | train_error: 0.150 
+
    +
    +
      [==========================>-------------] 67.80% | train_error: 0.149 
+
    +
    +
      [==========================>-------------] 67.90% | train_error: 0.149 
+
    +
    +
      [==========================>-------------] 68.00% | train_error: 0.148 
+
    +
    +
      [==========================>-------------] 68.10% | train_error: 0.147 
+
    +
    +
      [==========================>-------------] 68.20% | train_error: 0.146 
+
    +
    +
      [==========================>-------------] 68.30% | train_error: 0.146 
+
    +
    +
      [==========================>-------------] 68.40% | train_error: 0.145 
+
    +
    +
      [==========================>-------------] 68.50% | train_error: 0.144 
+
    +
    +
      [==========================>-------------] 68.60% | train_error: 0.144 
+
    +
    +
      [==========================>-------------] 68.70% | train_error: 0.143 
+
    +
    +
      [==========================>-------------] 68.80% | train_error: 0.142 
+
    +
    +
      [==========================>-------------] 68.90% | train_error: 0.142 
+
    +
    +
      [==========================>-------------] 69.00% | train_error: 0.141 
+
    +
    +
      [==========================>-------------] 69.10% | train_error: 0.141 
+
    +
    +
      [==========================>-------------] 69.20% | train_error: 0.140 
+
    +
    +
      [==========================>-------------] 69.30% | train_error: 0.139 
+
    +
    +
      [==========================>-------------] 69.40% | train_error: 0.139 
+
    +
    +
      [==========================>-------------] 69.50% | train_error: 0.138 
+
    +
    +
      [==========================>-------------] 69.60% | train_error: 0.137 
+
    +
    +
      [==========================>-------------] 69.70% | train_error: 0.137 
+
    +
    +
      [==========================>-------------] 69.80% | train_error: 0.136 
+
    +
    +
      [==========================>-------------] 69.90% | train_error: 0.135 
+
    +
    +
      [===========================>------------] 70.00% | train_error: 0.135 
+
    +
    +
      [===========================>------------] 70.10% | train_error: 0.134 
+
    +
    +
      [===========================>------------] 70.20% | train_error: 0.134 
+
    +
    +
      [===========================>------------] 70.30% | train_error: 0.133 
+
    +
    +
      [===========================>------------] 70.40% | train_error: 0.132 
+
    +
    +
      [===========================>------------] 70.50% | train_error: 0.132 
+
    +
    +
      [===========================>------------] 70.60% | train_error: 0.131 
+
    +
    +
      [===========================>------------] 70.70% | train_error: 0.131 
+
    +
    +
      [===========================>------------] 70.80% | train_error: 0.130 
+
    +
    +
      [===========================>------------] 70.90% | train_error: 0.129 
+
    +
    +
      [===========================>------------] 71.00% | train_error: 0.129 
+
    +
    +
      [===========================>------------] 71.10% | train_error: 0.128 
+
    +
    +
      [===========================>------------] 71.20% | train_error: 0.128 
+
    +
    +
      [===========================>------------] 71.30% | train_error: 0.127 
+
    +
    +
      [===========================>------------] 71.40% | train_error: 0.126 
+
    +
    +
      [===========================>------------] 71.50% | train_error: 0.126 
+
    +
    +
      [===========================>------------] 71.60% | train_error: 0.125 
+
    +
    +
      [===========================>------------] 71.70% | train_error: 0.125 
+
    +
    +
      [===========================>------------] 71.80% | train_error: 0.124 
+
    +
    +
      [===========================>------------] 71.90% | train_error: 0.124 
+
    +
    +
      [===========================>------------] 72.00% | train_error: 0.123 
+
    +
    +
      [===========================>------------] 72.10% | train_error: 0.122 
+
    +
    +
      [===========================>------------] 72.20% | train_error: 0.122 
+
    +
    +
      [===========================>------------] 72.30% | train_error: 0.121 
+
    +
    +
      [===========================>------------] 72.40% | train_error: 0.121 
+
    +
    +
      [============================>-----------] 72.50% | train_error: 0.120 
+
    +
    +
      [============================>-----------] 72.60% | train_error: 0.120 
+
    +
    +
      [============================>-----------] 72.70% | train_error: 0.119 
+
    +
    +
      [============================>-----------] 72.80% | train_error: 0.119 
+
    +
    +
      [============================>-----------] 72.90% | train_error: 0.118 
+
    +
    +
      [============================>-----------] 73.00% | train_error: 0.117 
+
    +
    +
      [============================>-----------] 73.10% | train_error: 0.117 
+
    +
    +
      [============================>-----------] 73.20% | train_error: 0.116 
+
    +
    +
      [============================>-----------] 73.30% | train_error: 0.116 
+
    +
    +
      [============================>-----------] 73.40% | train_error: 0.115 
+
    +
    +
      [============================>-----------] 73.50% | train_error: 0.115 
+
    +
    +
      [============================>-----------] 73.60% | train_error: 0.114 
+
    +
    +
      [============================>-----------] 73.70% | train_error: 0.114 
+
    +
    +
      [============================>-----------] 73.80% | train_error: 0.113 
+
    +
    +
      [============================>-----------] 73.90% | train_error: 0.113 
+
    +
    +
      [============================>-----------] 74.00% | train_error: 0.112 
+
    +
    +
      [============================>-----------] 74.10% | train_error: 0.112 
+
    +
    +
      [============================>-----------] 74.20% | train_error: 0.111 
+
    +
    +
      [============================>-----------] 74.30% | train_error: 0.111 
+
    +
    +
      [============================>-----------] 74.40% | train_error: 0.110 
+
    +
    +
      [============================>-----------] 74.50% | train_error: 0.110 
+
    +
    +
      [============================>-----------] 74.60% | train_error: 0.109 
+
    +
    +
      [============================>-----------] 74.70% | train_error: 0.109 
+
    +
    +
      [============================>-----------] 74.80% | train_error: 0.108 
+
    +
    +
      [============================>-----------] 74.90% | train_error: 0.108 
+
    +
    +
      [=============================>----------] 75.00% | train_error: 0.107 
+
    +
    +
      [=============================>----------] 75.10% | train_error: 0.107 
+
    +
    +
      [=============================>----------] 75.20% | train_error: 0.106 
+
    +
    +
      [=============================>----------] 75.30% | train_error: 0.106 
+
    +
    +
      [=============================>----------] 75.40% | train_error: 0.105 
+
    +
    +
      [=============================>----------] 75.50% | train_error: 0.105 
+
    +
    +
      [=============================>----------] 75.60% | train_error: 0.104 
+
    +
    +
      [=============================>----------] 75.70% | train_error: 0.104 
+
    +
    +
      [=============================>----------] 75.80% | train_error: 0.103 
+
    +
    +
      [=============================>----------] 75.90% | train_error: 0.103 
+
    +
    +
      [=============================>----------] 76.00% | train_error: 0.102 
+
    +
    +
      [=============================>----------] 76.10% | train_error: 0.102 
+
    +
    +
      [=============================>----------] 76.20% | train_error: 0.101 
+
    +
    +
      [=============================>----------] 76.30% | train_error: 0.101 
+
    +
    +
      [=============================>----------] 76.40% | train_error: 0.101 
+
    +
    +
      [=============================>----------] 76.50% | train_error: 0.100 
+
    +
    +
      [=============================>----------] 76.60% | train_error: 0.0996 
+
    +
    +
      [=============================>----------] 76.70% | train_error: 0.0992 
+
    +
    +
      [=============================>----------] 76.80% | train_error: 0.0987 
+
    +
    +
      [=============================>----------] 76.90% | train_error: 0.0983 
+
    +
    +
      [=============================>----------] 77.00% | train_error: 0.0978 
+
    +
    +
      [=============================>----------] 77.10% | train_error: 0.0974 
+
    +
    +
      [=============================>----------] 77.20% | train_error: 0.0969 
+
    +
    +
      [=============================>----------] 77.30% | train_error: 0.0965 
+
    +
    +
      [=============================>----------] 77.40% | train_error: 0.0961 
+
    +
    +
      [==============================>---------] 77.50% | train_error: 0.0956 
+
    +
    +
      [==============================>---------] 77.60% | train_error: 0.0952 
+
    +
    +
      [==============================>---------] 77.70% | train_error: 0.0948 
+
    +
    +
      [==============================>---------] 77.80% | train_error: 0.0943 
+
    +
    +
      [==============================>---------] 77.90% | train_error: 0.0939 
+
    +
    +
      [==============================>---------] 78.00% | train_error: 0.0935 
+
    +
    +
      [==============================>---------] 78.10% | train_error: 0.0930 
+
    +
    +
      [==============================>---------] 78.20% | train_error: 0.0926 
+
    +
    +
      [==============================>---------] 78.30% | train_error: 0.0922 
+
    +
    +
      [==============================>---------] 78.40% | train_error: 0.0918 
+
    +
    +
      [==============================>---------] 78.50% | train_error: 0.0914 
+
    +
    +
      [==============================>---------] 78.60% | train_error: 0.0910 
+
    +
    +
      [==============================>---------] 78.70% | train_error: 0.0905 
+
    +
    +
      [==============================>---------] 78.80% | train_error: 0.0901 
+
    +
    +
      [==============================>---------] 78.90% | train_error: 0.0897 
+
    +
    +
      [==============================>---------] 79.00% | train_error: 0.0893 
+
    +
    +
      [==============================>---------] 79.10% | train_error: 0.0889 
+
    +
    +
      [==============================>---------] 79.20% | train_error: 0.0885 
+
    +
    +
      [==============================>---------] 79.30% | train_error: 0.0881 
+
    +
    +
      [==============================>---------] 79.40% | train_error: 0.0877 
+
    +
    +
      [==============================>---------] 79.50% | train_error: 0.0873 
+
    +
    +
      [==============================>---------] 79.60% | train_error: 0.0869 
+
    +
    +
      [==============================>---------] 79.70% | train_error: 0.0865 
+
    +
    +
      [==============================>---------] 79.80% | train_error: 0.0861 
+
    +
    +
      [==============================>---------] 79.90% | train_error: 0.0858 
+
    +
    +
      [===============================>--------] 80.00% | train_error: 0.0854 
+
    +
    +
      [===============================>--------] 80.10% | train_error: 0.0850 
+
    +
    +
      [===============================>--------] 80.20% | train_error: 0.0846 
+
    +
    +
      [===============================>--------] 80.30% | train_error: 0.0842 
+
    +
    +
      [===============================>--------] 80.40% | train_error: 0.0838 
+
    +
    +
      [===============================>--------] 80.50% | train_error: 0.0835 
+
    +
    +
      [===============================>--------] 80.60% | train_error: 0.0831 
+
    +
    +
      [===============================>--------] 80.70% | train_error: 0.0827 
+
    +
    +
      [===============================>--------] 80.80% | train_error: 0.0823 
+
    +
    +
      [===============================>--------] 80.90% | train_error: 0.0820 
+
    +
    +
      [===============================>--------] 81.00% | train_error: 0.0816 
+
    +
    +
      [===============================>--------] 81.10% | train_error: 0.0812 
+
    +
    +
      [===============================>--------] 81.20% | train_error: 0.0809 
+
    +
    +
      [===============================>--------] 81.30% | train_error: 0.0805 
+
    +
    +
      [===============================>--------] 81.40% | train_error: 0.0801 
+
    +
    +
      [===============================>--------] 81.50% | train_error: 0.0798 
+
    +
    +
      [===============================>--------] 81.60% | train_error: 0.0794 
+
    +
    +
      [===============================>--------] 81.70% | train_error: 0.0791 
+
    +
    +
      [===============================>--------] 81.80% | train_error: 0.0787 
+
    +
    +
      [===============================>--------] 81.90% | train_error: 0.0784 
+
    +
    +
      [===============================>--------] 82.00% | train_error: 0.0780 
+
    +
    +
      [===============================>--------] 82.10% | train_error: 0.0776 
+
    +
    +
      [===============================>--------] 82.20% | train_error: 0.0773 
+
    +
    +
      [===============================>--------] 82.30% | train_error: 0.0770 
+
    +
    +
      [===============================>--------] 82.40% | train_error: 0.0766 
+
    +
    +
      [================================>-------] 82.50% | train_error: 0.0763 
+
    +
    +
      [================================>-------] 82.60% | train_error: 0.0759 
+
    +
    +
      [================================>-------] 82.70% | train_error: 0.0756 
+
    +
    +
      [================================>-------] 82.80% | train_error: 0.0752 
+
    +
    +
      [================================>-------] 82.90% | train_error: 0.0749 
+
    +
    +
      [================================>-------] 83.00% | train_error: 0.0746 
+
    +
    +
      [================================>-------] 83.10% | train_error: 0.0742 
+
    +
    +
      [================================>-------] 83.20% | train_error: 0.0739 
+
    +
    +
      [================================>-------] 83.30% | train_error: 0.0736 
+
    +
    +
      [================================>-------] 83.40% | train_error: 0.0732 
+
    +
    +
      [================================>-------] 83.50% | train_error: 0.0729 
+
    +
    +
      [================================>-------] 83.60% | train_error: 0.0726 
+
    +
    +
      [================================>-------] 83.70% | train_error: 0.0723 
+
    +
    +
      [================================>-------] 83.80% | train_error: 0.0719 
+
    +
    +
      [================================>-------] 83.90% | train_error: 0.0716 
+
    +
    +
      [================================>-------] 84.00% | train_error: 0.0713 
+
    +
    +
      [================================>-------] 84.10% | train_error: 0.0710 
+
    +
    +
      [================================>-------] 84.20% | train_error: 0.0707 
+
    +
    +
      [================================>-------] 84.30% | train_error: 0.0703 
+
    +
    +
      [================================>-------] 84.40% | train_error: 0.0700 
+
    +
    +
      [================================>-------] 84.50% | train_error: 0.0697 
+
    +
    +
      [================================>-------] 84.60% | train_error: 0.0694 
+
    +
    +
      [================================>-------] 84.70% | train_error: 0.0691 
+
    +
    +
      [================================>-------] 84.80% | train_error: 0.0688 
+
    +
    +
      [================================>-------] 84.90% | train_error: 0.0685 
+
    +
    +
      [=================================>------] 85.00% | train_error: 0.0682 
+
    +
    +
      [=================================>------] 85.10% | train_error: 0.0679 
+
    +
    +
      [=================================>------] 85.20% | train_error: 0.0676 
+
    +
    +
      [=================================>------] 85.30% | train_error: 0.0673 
+
    +
    +
      [=================================>------] 85.40% | train_error: 0.0670 
+
    +
    +
      [=================================>------] 85.50% | train_error: 0.0667 
+
    +
    +
      [=================================>------] 85.60% | train_error: 0.0664 
+
    +
    +
      [=================================>------] 85.70% | train_error: 0.0661 
+
    +
    +
      [=================================>------] 85.80% | train_error: 0.0658 
+
    +
    +
      [=================================>------] 85.90% | train_error: 0.0655 
+
    +
    +
      [=================================>------] 86.00% | train_error: 0.0652 
+
    +
    +
      [=================================>------] 86.10% | train_error: 0.0649 
+
    +
    +
      [=================================>------] 86.20% | train_error: 0.0646 
+
    +
    +
      [=================================>------] 86.30% | train_error: 0.0643 
+
    +
    +
      [=================================>------] 86.40% | train_error: 0.0641 
+
    +
    +
      [=================================>------] 86.50% | train_error: 0.0638 
+
    +
    +
      [=================================>------] 86.60% | train_error: 0.0635 
+
    +
    +
      [=================================>------] 86.70% | train_error: 0.0632 
+
    +
    +
      [=================================>------] 86.80% | train_error: 0.0629 
+
    +
    +
      [=================================>------] 86.90% | train_error: 0.0626 
+
    +
    +
      [=================================>------] 87.00% | train_error: 0.0624 
+
    +
    +
      [=================================>------] 87.10% | train_error: 0.0621 
+
    +
    +
      [=================================>------] 87.20% | train_error: 0.0618 
+
    +
    +
      [=================================>------] 87.30% | train_error: 0.0615 
+
    +
    +
      [=================================>------] 87.40% | train_error: 0.0613 
+
    +
    +
      [==================================>-----] 87.50% | train_error: 0.0610 
+
    +
    +
      [==================================>-----] 87.60% | train_error: 0.0607 
+
    +
    +
      [==================================>-----] 87.70% | train_error: 0.0605 
+
    +
    +
      [==================================>-----] 87.80% | train_error: 0.0602 
+
    +
    +
      [==================================>-----] 87.90% | train_error: 0.0599 
+
    +
    +
      [==================================>-----] 88.00% | train_error: 0.0597 
+
    +
    +
      [==================================>-----] 88.10% | train_error: 0.0594 
+
    +
    +
      [==================================>-----] 88.20% | train_error: 0.0591 
+
    +
    +
      [==================================>-----] 88.30% | train_error: 0.0589 
+
    +
    +
      [==================================>-----] 88.40% | train_error: 0.0586 
+
    +
    +
      [==================================>-----] 88.50% | train_error: 0.0584 
+
    +
    +
      [==================================>-----] 88.60% | train_error: 0.0581 
+
    +
    +
      [==================================>-----] 88.70% | train_error: 0.0578 
+
    +
    +
      [==================================>-----] 88.80% | train_error: 0.0576 
+
    +
    +
      [==================================>-----] 88.90% | train_error: 0.0573 
+
    +
    +
      [==================================>-----] 89.00% | train_error: 0.0571 
+
    +
    +
      [==================================>-----] 89.10% | train_error: 0.0568 
+
    +
    +
      [==================================>-----] 89.20% | train_error: 0.0566 
+
    +
    +
      [==================================>-----] 89.30% | train_error: 0.0563 
+
    +
    +
      [==================================>-----] 89.40% | train_error: 0.0561 
+
    +
    +
      [==================================>-----] 89.50% | train_error: 0.0558 
+
    +
    +
      [==================================>-----] 89.60% | train_error: 0.0556 
+
    +
    +
      [==================================>-----] 89.70% | train_error: 0.0553 
+
    +
    +
      [==================================>-----] 89.80% | train_error: 0.0551 
+
    +
    +
      [==================================>-----] 89.90% | train_error: 0.0549 
+
    +
    +
      [===================================>----] 90.00% | train_error: 0.0546 
+
    +
    +
      [===================================>----] 90.10% | train_error: 0.0544 
+
    +
    +
      [===================================>----] 90.20% | train_error: 0.0541 
+
    +
    +
      [===================================>----] 90.30% | train_error: 0.0539 
+
    +
    +
      [===================================>----] 90.40% | train_error: 0.0537 
+
    +
    +
      [===================================>----] 90.50% | train_error: 0.0534 
+
    +
    +
      [===================================>----] 90.60% | train_error: 0.0532 
+
    +
    +
      [===================================>----] 90.70% | train_error: 0.0530 
+
    +
    +
      [===================================>----] 90.80% | train_error: 0.0527 
+
    +
    +
      [===================================>----] 90.90% | train_error: 0.0525 
+
    +
    +
      [===================================>----] 91.00% | train_error: 0.0523 
+
    +
    +
      [===================================>----] 91.10% | train_error: 0.0520 
+
    +
    +
      [===================================>----] 91.20% | train_error: 0.0518 
+
    +
    +
      [===================================>----] 91.30% | train_error: 0.0516 
+
    +
    +
      [===================================>----] 91.40% | train_error: 0.0514 
+
    +
    +
      [===================================>----] 91.50% | train_error: 0.0511 
+
    +
    +
      [===================================>----] 91.60% | train_error: 0.0509 
+
    +
    +
      [===================================>----] 91.70% | train_error: 0.0507 
+
    +
    +
      [===================================>----] 91.80% | train_error: 0.0505 
+
    +
    +
      [===================================>----] 91.90% | train_error: 0.0503 
+
    +
    +
      [===================================>----] 92.00% | train_error: 0.0500 
+
    +
    +
      [===================================>----] 92.10% | train_error: 0.0498 
+
    +
    +
      [===================================>----] 92.20% | train_error: 0.0496 
+
    +
    +
      [===================================>----] 92.30% | train_error: 0.0494 
+
    +
    +
      [===================================>----] 92.40% | train_error: 0.0492 
+
    +
    +
      [====================================>---] 92.50% | train_error: 0.0490 
+
    +
    +
      [====================================>---] 92.60% | train_error: 0.0487 
+
    +
    +
      [====================================>---] 92.70% | train_error: 0.0485 
+
    +
    +
      [====================================>---] 92.80% | train_error: 0.0483 
+
    +
    +
      [====================================>---] 92.90% | train_error: 0.0481 
+
    +
    +
      [====================================>---] 93.00% | train_error: 0.0479 
+
    +
    +
      [====================================>---] 93.10% | train_error: 0.0477 
+
    +
    +
      [====================================>---] 93.20% | train_error: 0.0475 
+
    +
    +
      [====================================>---] 93.30% | train_error: 0.0473 
+
    +
    +
      [====================================>---] 93.40% | train_error: 0.0471 
+
    +
    +
      [====================================>---] 93.50% | train_error: 0.0469 
+
    +
    +
      [====================================>---] 93.60% | train_error: 0.0467 
+
    +
    +
      [====================================>---] 93.70% | train_error: 0.0465 
+
    +
    +
      [====================================>---] 93.80% | train_error: 0.0463 
+
    +
    +
      [====================================>---] 93.90% | train_error: 0.0461 
+
    +
    +
      [====================================>---] 94.00% | train_error: 0.0459 
+
    +
    +
      [====================================>---] 94.10% | train_error: 0.0457 
+
    +
    +
      [====================================>---] 94.20% | train_error: 0.0455 
+
    +
    +
      [====================================>---] 94.30% | train_error: 0.0453 
+
    +
    +
      [====================================>---] 94.40% | train_error: 0.0451 
+
    +
    +
      [====================================>---] 94.50% | train_error: 0.0449 
+
    +
    +
      [====================================>---] 94.60% | train_error: 0.0447 
+
    +
    +
      [====================================>---] 94.70% | train_error: 0.0445 
+
    +
    +
      [====================================>---] 94.80% | train_error: 0.0443 
+
    +
    +
      [====================================>---] 94.90% | train_error: 0.0441 
+
    +
    +
      [=====================================>--] 95.00% | train_error: 0.0439 
+
    +
    +
      [=====================================>--] 95.10% | train_error: 0.0437 
+
    +
    +
      [=====================================>--] 95.20% | train_error: 0.0435 
+
    +
    +
      [=====================================>--] 95.30% | train_error: 0.0434 
+
    +
    +
      [=====================================>--] 95.40% | train_error: 0.0432 
+
    +
    +
      [=====================================>--] 95.50% | train_error: 0.0430 
+
    +
    +
      [=====================================>--] 95.60% | train_error: 0.0428 
+
    +
    +
      [=====================================>--] 95.70% | train_error: 0.0426 
+
    +
    +
      [=====================================>--] 95.80% | train_error: 0.0424 
+
    +
    +
      [=====================================>--] 95.90% | train_error: 0.0423 
+
    +
    +
      [=====================================>--] 96.00% | train_error: 0.0421 
+
    +
    +
      [=====================================>--] 96.10% | train_error: 0.0419 
+
    +
    +
      [=====================================>--] 96.20% | train_error: 0.0417 
+
    +
    +
      [=====================================>--] 96.30% | train_error: 0.0415 
+
    +
    +
      [=====================================>--] 96.40% | train_error: 0.0414 
+
    +
    +
      [=====================================>--] 96.50% | train_error: 0.0412 
+
    +
    +
      [=====================================>--] 96.60% | train_error: 0.0410 
+
    +
    +
      [=====================================>--] 96.70% | train_error: 0.0408 
+
    +
    +
      [=====================================>--] 96.80% | train_error: 0.0407 
+
    +
    +
      [=====================================>--] 96.90% | train_error: 0.0405 
+
    +
    +
      [=====================================>--] 97.00% | train_error: 0.0403 
+
    +
    +
      [=====================================>--] 97.10% | train_error: 0.0401 
+
    +
    +
      [=====================================>--] 97.20% | train_error: 0.0400 
+
    +
    +
      [=====================================>--] 97.30% | train_error: 0.0398 
+
    +
    +
      [=====================================>--] 97.40% | train_error: 0.0396 
+
    +
    +
      [======================================>-] 97.50% | train_error: 0.0395 
+
    +
    +
      [======================================>-] 97.60% | train_error: 0.0393 
+
    +
    +
      [======================================>-] 97.70% | train_error: 0.0391 
+
    +
    +
      [======================================>-] 97.80% | train_error: 0.0389 
+
    +
    +
      [======================================>-] 97.90% | train_error: 0.0388 
+
    +
    +
      [======================================>-] 98.00% | train_error: 0.0386 
+
    +
    +
      [======================================>-] 98.10% | train_error: 0.0385 
+
    +
    +
      [======================================>-] 98.20% | train_error: 0.0383 
+
    +
    +
      [======================================>-] 98.30% | train_error: 0.0381 
+
    +
    +
      [======================================>-] 98.40% | train_error: 0.0380 
+
    +
    +
      [======================================>-] 98.50% | train_error: 0.0378 
+
    +
    +
      [======================================>-] 98.60% | train_error: 0.0376 
+
    +
    +
      [======================================>-] 98.70% | train_error: 0.0375 
+
    +
    +
      [======================================>-] 98.80% | train_error: 0.0373 
+
    +
    +
      [======================================>-] 98.90% | train_error: 0.0372 
+
    +
    +
      [======================================>-] 99.00% | train_error: 0.0370 
+
    +
    +
      [======================================>-] 99.10% | train_error: 0.0369 
+
    +
    +
      [======================================>-] 99.20% | train_error: 0.0367 
+
    +
    +
      [======================================>-] 99.30% | train_error: 0.0365 
+
    +
    +
      [======================================>-] 99.40% | train_error: 0.0364 
+
    +
    +
      [======================================>-] 99.50% | train_error: 0.0362 
+
    +
    +
      [======================================>-] 99.60% | train_error: 0.0361 
+
    +
    +
      [======================================>-] 99.70% | train_error: 0.0359 
+
    +
    +
      [======================================>-] 99.80% | train_error: 0.0358 
+
    +
    +
      [======================================>-] 99.90% | train_error: 0.0356 
+
    +
    +
                                                                              
+
    +
    +
      [=======================================>] 100.0% | train_error: 0.0356 
+
    +
    +
    +
    +

    We see that given more epochs to train on, the regressor reaches a lower MSE.

    +

    Let us then switch to a binary classification. We use a binary +classification dataset, and follow a similar setup to the regression +case.

    +
    +
    +
    from sklearn.datasets import load_breast_cancer
+from sklearn.preprocessing import MinMaxScaler
+
+wisconsin = load_breast_cancer()
+X = wisconsin.data
+target = wisconsin.target
+target = target.reshape(target.shape[0], 1)
+
+X_train, X_val, t_train, t_val = train_test_split(X, target)
+
+scaler = MinMaxScaler()
+scaler.fit(X_train)
+X_train = scaler.transform(X_train)
+X_val = scaler.transform(X_val)
+
    +
    +
    +
    +
    +
    +
    input_nodes = X_train.shape[1]
+output_nodes = 1
+
+logistic_regression = FFNN((input_nodes, output_nodes), output_func=sigmoid, cost_func=CostLogReg, seed=2023)
+
    +
    +
    +
    +

    We will now make use of our validation data by passing it into our fit function as a keyword argument

    +
    +
    +
    logistic_regression.reset_weights() # reset weights such that previous runs or reruns don't affect the weights
+
+scheduler = Adam(eta=1e-3, rho=0.9, rho2=0.999)
+scores = logistic_regression.fit(X_train, t_train, scheduler, epochs=1000, X_val=X_val, t_val=t_val)
+
    +
    +
    +
    +
    Adam: Eta=0.001, Lambda=0
+
    +
    +
    
+
    +
    +
      [----------------------------------------] 0.000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 0.1000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 0.2000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 0.3000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 0.4000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 0.5000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 0.6000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 0.7000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 0.8000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 0.9000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 1.000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 1.100% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 1.200% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 1.300% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 1.400% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 1.500% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 1.600% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 1.700% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 1.800% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 1.900% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 2.000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 2.100% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 2.200% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 2.300% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [----------------------------------------] 2.400% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 2.500% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 2.600% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 2.700% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 2.800% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 2.900% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 3.000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 3.100% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 3.200% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 3.300% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 3.400% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 3.500% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 3.600% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 3.700% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 3.800% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 3.900% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 4.000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 4.100% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 4.200% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 4.300% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 4.400% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 4.500% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 4.600% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 4.700% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 4.800% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [>---------------------------------------] 4.900% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 5.000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 5.100% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 5.200% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 5.300% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 5.400% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 5.500% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 5.600% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 5.700% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 5.800% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 5.900% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 6.000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 6.100% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 6.200% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 6.300% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 6.400% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 6.500% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 6.600% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 6.700% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 6.800% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 6.900% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 7.000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 7.100% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [=>--------------------------------------] 7.200% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [=>--------------------------------------] 7.300% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [=>--------------------------------------] 7.400% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 7.500% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 7.600% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 7.700% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 7.800% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 7.900% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 8.000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 8.100% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 8.200% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 8.300% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 8.400% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 8.500% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 8.600% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 8.700% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 8.800% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 8.900% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 9.000% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 9.100% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 9.200% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 9.300% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 9.400% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 9.500% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 9.600% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 9.700% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 9.800% | train_error: 12.9 | train_acc: 0.376 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [==>-------------------------------------] 9.900% | train_error: 13.0 | train_acc: 0.373 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 10.00% | train_error: 13.0 | train_acc: 0.373 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 10.10% | train_error: 13.1 | train_acc: 0.366 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 10.20% | train_error: 13.1 | train_acc: 0.366 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 10.30% | train_error: 13.1 | train_acc: 0.366 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 10.40% | train_error: 13.1 | train_acc: 0.366 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 10.50% | train_error: 13.0 | train_acc: 0.371 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 10.60% | train_error: 13.0 | train_acc: 0.371 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 10.70% | train_error: 13.0 | train_acc: 0.371 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 10.80% | train_error: 13.1 | train_acc: 0.369 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 10.90% | train_error: 13.1 | train_acc: 0.369 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 11.00% | train_error: 13.1 | train_acc: 0.369 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 11.10% | train_error: 13.1 | train_acc: 0.369 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 11.20% | train_error: 13.1 | train_acc: 0.369 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 11.30% | train_error: 13.1 | train_acc: 0.369 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 11.40% | train_error: 13.1 | train_acc: 0.369 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 11.50% | train_error: 13.1 | train_acc: 0.369 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 11.60% | train_error: 13.1 | train_acc: 0.369 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 11.70% | train_error: 13.1 | train_acc: 0.369 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 11.80% | train_error: 13.1 | train_acc: 0.369 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 11.90% | train_error: 13.1 | train_acc: 0.366 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 12.00% | train_error: 13.1 | train_acc: 0.366 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 12.10% | train_error: 13.1 | train_acc: 0.366 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 12.20% | train_error: 13.1 | train_acc: 0.366 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 12.30% | train_error: 13.1 | train_acc: 0.366 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [===>------------------------------------] 12.40% | train_error: 13.1 | train_acc: 0.366 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [====>-----------------------------------] 12.50% | train_error: 13.1 | train_acc: 0.366 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [====>-----------------------------------] 12.60% | train_error: 13.1 | train_acc: 0.366 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [====>-----------------------------------] 12.70% | train_error: 13.1 | train_acc: 0.366 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [====>-----------------------------------] 12.80% | train_error: 13.1 | train_acc: 0.366 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [====>-----------------------------------] 12.90% | train_error: 13.1 | train_acc: 0.366 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [====>-----------------------------------] 13.00% | train_error: 13.1 | train_acc: 0.366 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [====>-----------------------------------] 13.10% | train_error: 13.2 | train_acc: 0.362 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [====>-----------------------------------] 13.20% | train_error: 13.2 | train_acc: 0.362 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [====>-----------------------------------] 13.30% | train_error: 13.2 | train_acc: 0.362 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [====>-----------------------------------] 13.40% | train_error: 13.2 | train_acc: 0.362 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [====>-----------------------------------] 13.50% | train_error: 13.2 | train_acc: 0.362 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [====>-----------------------------------] 13.60% | train_error: 13.2 | train_acc: 0.362 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [====>-----------------------------------] 13.70% | train_error: 13.2 | train_acc: 0.362 | val_error: 12.8 | val_acc: 0.385 
+
    +
    +
      [====>-----------------------------------] 13.80% | train_error: 13.3 | train_acc: 0.359 | val_error: 12.9 | val_acc: 0.378 
+
    +
    +
      [====>-----------------------------------] 13.90% | train_error: 13.4 | train_acc: 0.354 | val_error: 12.9 | val_acc: 0.378 
+
    +
    +
      [====>-----------------------------------] 14.00% | train_error: 13.4 | train_acc: 0.354 | val_error: 13.0 | val_acc: 0.371 
+
    +
    +
      [====>-----------------------------------] 14.10% | train_error: 13.4 | train_acc: 0.354 | val_error: 13.0 | val_acc: 0.371 
+
    +
    +
      [====>-----------------------------------] 14.20% | train_error: 13.4 | train_acc: 0.354 | val_error: 13.0 | val_acc: 0.371 
+
    +
    +
      [====>-----------------------------------] 14.30% | train_error: 13.4 | train_acc: 0.354 | val_error: 13.0 | val_acc: 0.371 
+
    +
    +
      [====>-----------------------------------] 14.40% | train_error: 13.4 | train_acc: 0.354 | val_error: 13.0 | val_acc: 0.371 
+
    +
    +
      [====>-----------------------------------] 14.50% | train_error: 13.4 | train_acc: 0.354 | val_error: 13.0 | val_acc: 0.371 
+
    +
    +
      [====>-----------------------------------] 14.60% | train_error: 13.4 | train_acc: 0.354 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [====>-----------------------------------] 14.70% | train_error: 13.4 | train_acc: 0.354 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [====>-----------------------------------] 14.80% | train_error: 13.4 | train_acc: 0.352 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [====>-----------------------------------] 14.90% | train_error: 13.4 | train_acc: 0.352 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 15.00% | train_error: 13.5 | train_acc: 0.347 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 15.10% | train_error: 13.6 | train_acc: 0.345 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 15.20% | train_error: 13.6 | train_acc: 0.345 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 15.30% | train_error: 13.8 | train_acc: 0.336 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 15.40% | train_error: 13.8 | train_acc: 0.336 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 15.50% | train_error: 13.8 | train_acc: 0.336 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 15.60% | train_error: 13.8 | train_acc: 0.333 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 15.70% | train_error: 13.8 | train_acc: 0.333 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 15.80% | train_error: 13.8 | train_acc: 0.333 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 15.90% | train_error: 13.8 | train_acc: 0.333 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 16.00% | train_error: 13.8 | train_acc: 0.333 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 16.10% | train_error: 13.8 | train_acc: 0.333 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 16.20% | train_error: 13.8 | train_acc: 0.333 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 16.30% | train_error: 14.0 | train_acc: 0.326 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 16.40% | train_error: 14.0 | train_acc: 0.326 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 16.50% | train_error: 14.0 | train_acc: 0.326 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [=====>----------------------------------] 16.60% | train_error: 14.0 | train_acc: 0.326 | val_error: 13.3 | val_acc: 0.357 
+
    +
    +
      [=====>----------------------------------] 16.70% | train_error: 14.1 | train_acc: 0.322 | val_error: 13.5 | val_acc: 0.350 
+
    +
    +
      [=====>----------------------------------] 16.80% | train_error: 14.1 | train_acc: 0.322 | val_error: 13.5 | val_acc: 0.350 
+
    +
    +
      [=====>----------------------------------] 16.90% | train_error: 14.1 | train_acc: 0.319 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [=====>----------------------------------] 17.00% | train_error: 14.1 | train_acc: 0.319 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [=====>----------------------------------] 17.10% | train_error: 14.1 | train_acc: 0.319 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [=====>----------------------------------] 17.20% | train_error: 14.2 | train_acc: 0.317 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [=====>----------------------------------] 17.30% | train_error: 14.2 | train_acc: 0.317 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [=====>----------------------------------] 17.40% | train_error: 14.2 | train_acc: 0.317 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 17.50% | train_error: 14.2 | train_acc: 0.317 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 17.60% | train_error: 14.3 | train_acc: 0.312 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 17.70% | train_error: 14.4 | train_acc: 0.308 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 17.80% | train_error: 14.4 | train_acc: 0.308 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 17.90% | train_error: 14.4 | train_acc: 0.308 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 18.00% | train_error: 14.4 | train_acc: 0.308 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 18.10% | train_error: 14.4 | train_acc: 0.305 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 18.20% | train_error: 14.4 | train_acc: 0.305 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 18.30% | train_error: 14.4 | train_acc: 0.305 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 18.40% | train_error: 14.5 | train_acc: 0.298 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 18.50% | train_error: 14.5 | train_acc: 0.298 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 18.60% | train_error: 14.6 | train_acc: 0.296 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 18.70% | train_error: 14.6 | train_acc: 0.293 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 18.80% | train_error: 14.7 | train_acc: 0.291 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 18.90% | train_error: 14.7 | train_acc: 0.291 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 19.00% | train_error: 14.7 | train_acc: 0.291 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 19.10% | train_error: 14.7 | train_acc: 0.291 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [======>---------------------------------] 19.20% | train_error: 14.7 | train_acc: 0.291 | val_error: 13.5 | val_acc: 0.350 
+
    +
    +
      [======>---------------------------------] 19.30% | train_error: 14.8 | train_acc: 0.286 | val_error: 13.5 | val_acc: 0.350 
+
    +
    +
      [======>---------------------------------] 19.40% | train_error: 14.8 | train_acc: 0.284 | val_error: 13.5 | val_acc: 0.350 
+
    +
    +
      [======>---------------------------------] 19.50% | train_error: 14.8 | train_acc: 0.284 | val_error: 13.5 | val_acc: 0.350 
+
    +
    +
      [======>---------------------------------] 19.60% | train_error: 14.9 | train_acc: 0.282 | val_error: 13.5 | val_acc: 0.350 
+
    +
    +
      [======>---------------------------------] 19.70% | train_error: 14.9 | train_acc: 0.282 | val_error: 13.5 | val_acc: 0.350 
+
    +
    +
      [======>---------------------------------] 19.80% | train_error: 14.9 | train_acc: 0.282 | val_error: 13.5 | val_acc: 0.350 
+
    +
    +
      [======>---------------------------------] 19.90% | train_error: 14.9 | train_acc: 0.282 | val_error: 13.5 | val_acc: 0.350 
+
    +
    +
      [=======>--------------------------------] 20.00% | train_error: 14.9 | train_acc: 0.279 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [=======>--------------------------------] 20.10% | train_error: 15.1 | train_acc: 0.272 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [=======>--------------------------------] 20.20% | train_error: 15.1 | train_acc: 0.272 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [=======>--------------------------------] 20.30% | train_error: 15.1 | train_acc: 0.272 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [=======>--------------------------------] 20.40% | train_error: 15.1 | train_acc: 0.270 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [=======>--------------------------------] 20.50% | train_error: 15.1 | train_acc: 0.270 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [=======>--------------------------------] 20.60% | train_error: 15.4 | train_acc: 0.258 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [=======>--------------------------------] 20.70% | train_error: 15.4 | train_acc: 0.258 | val_error: 13.8 | val_acc: 0.336 
+
    +
    +
      [=======>--------------------------------] 20.80% | train_error: 15.4 | train_acc: 0.258 | val_error: 13.8 | val_acc: 0.336 
+
    +
    +
      [=======>--------------------------------] 20.90% | train_error: 15.4 | train_acc: 0.258 | val_error: 13.8 | val_acc: 0.336 
+
    +
    +
      [=======>--------------------------------] 21.00% | train_error: 15.4 | train_acc: 0.258 | val_error: 13.8 | val_acc: 0.336 
+
    +
    +
      [=======>--------------------------------] 21.10% | train_error: 15.4 | train_acc: 0.258 | val_error: 13.8 | val_acc: 0.336 
+
    +
    +
      [=======>--------------------------------] 21.20% | train_error: 15.3 | train_acc: 0.261 | val_error: 13.9 | val_acc: 0.329 
+
    +
    +
      [=======>--------------------------------] 21.30% | train_error: 15.5 | train_acc: 0.254 | val_error: 13.9 | val_acc: 0.329 
+
    +
    +
      [=======>--------------------------------] 21.40% | train_error: 15.5 | train_acc: 0.254 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [=======>--------------------------------] 21.50% | train_error: 15.5 | train_acc: 0.254 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [=======>--------------------------------] 21.60% | train_error: 15.5 | train_acc: 0.254 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [=======>--------------------------------] 21.70% | train_error: 15.4 | train_acc: 0.256 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [=======>--------------------------------] 21.80% | train_error: 15.4 | train_acc: 0.256 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [=======>--------------------------------] 21.90% | train_error: 15.4 | train_acc: 0.256 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [=======>--------------------------------] 22.00% | train_error: 15.4 | train_acc: 0.256 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [=======>--------------------------------] 22.10% | train_error: 15.6 | train_acc: 0.249 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [=======>--------------------------------] 22.20% | train_error: 15.6 | train_acc: 0.249 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [=======>--------------------------------] 22.30% | train_error: 15.6 | train_acc: 0.249 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [=======>--------------------------------] 22.40% | train_error: 15.7 | train_acc: 0.244 | val_error: 14.3 | val_acc: 0.308 
+
    +
    +
      [========>-------------------------------] 22.50% | train_error: 15.7 | train_acc: 0.242 | val_error: 14.3 | val_acc: 0.308 
+
    +
    +
      [========>-------------------------------] 22.60% | train_error: 15.7 | train_acc: 0.242 | val_error: 14.3 | val_acc: 0.308 
+
    +
    +
      [========>-------------------------------] 22.70% | train_error: 15.7 | train_acc: 0.242 | val_error: 14.5 | val_acc: 0.301 
+
    +
    +
      [========>-------------------------------] 22.80% | train_error: 15.7 | train_acc: 0.242 | val_error: 14.5 | val_acc: 0.301 
+
    +
    +
      [========>-------------------------------] 22.90% | train_error: 15.8 | train_acc: 0.239 | val_error: 14.5 | val_acc: 0.301 
+
    +
    +
      [========>-------------------------------] 23.00% | train_error: 15.9 | train_acc: 0.235 | val_error: 14.5 | val_acc: 0.301 
+
    +
    +
      [========>-------------------------------] 23.10% | train_error: 15.9 | train_acc: 0.235 | val_error: 14.5 | val_acc: 0.301 
+
    +
    +
      [========>-------------------------------] 23.20% | train_error: 15.9 | train_acc: 0.232 | val_error: 14.6 | val_acc: 0.294 
+
    +
    +
      [========>-------------------------------] 23.30% | train_error: 15.9 | train_acc: 0.232 | val_error: 14.6 | val_acc: 0.294 
+
    +
    +
      [========>-------------------------------] 23.40% | train_error: 15.9 | train_acc: 0.232 | val_error: 14.6 | val_acc: 0.294 
+
    +
    +
      [========>-------------------------------] 23.50% | train_error: 15.9 | train_acc: 0.232 | val_error: 14.9 | val_acc: 0.280 
+
    +
    +
      [========>-------------------------------] 23.60% | train_error: 15.9 | train_acc: 0.232 | val_error: 14.8 | val_acc: 0.287 
+
    +
    +
      [========>-------------------------------] 23.70% | train_error: 15.9 | train_acc: 0.232 | val_error: 14.8 | val_acc: 0.287 
+
    +
    +
      [========>-------------------------------] 23.80% | train_error: 16.0 | train_acc: 0.230 | val_error: 14.8 | val_acc: 0.287 
+
    +
    +
      [========>-------------------------------] 23.90% | train_error: 16.0 | train_acc: 0.230 | val_error: 14.9 | val_acc: 0.280 
+
    +
    +
      [========>-------------------------------] 24.00% | train_error: 16.0 | train_acc: 0.230 | val_error: 14.9 | val_acc: 0.280 
+
    +
    +
      [========>-------------------------------] 24.10% | train_error: 16.0 | train_acc: 0.230 | val_error: 15.1 | val_acc: 0.273 
+
    +
    +
      [========>-------------------------------] 24.20% | train_error: 16.0 | train_acc: 0.230 | val_error: 15.1 | val_acc: 0.273 
+
    +
    +
      [========>-------------------------------] 24.30% | train_error: 16.0 | train_acc: 0.230 | val_error: 15.1 | val_acc: 0.273 
+
    +
    +
      [========>-------------------------------] 24.40% | train_error: 16.0 | train_acc: 0.228 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [========>-------------------------------] 24.50% | train_error: 16.0 | train_acc: 0.228 | val_error: 15.4 | val_acc: 0.259 
+
    +
    +
      [========>-------------------------------] 24.60% | train_error: 16.0 | train_acc: 0.228 | val_error: 15.4 | val_acc: 0.259 
+
    +
    +
      [========>-------------------------------] 24.70% | train_error: 16.0 | train_acc: 0.228 | val_error: 15.4 | val_acc: 0.259 
+
    +
    +
      [========>-------------------------------] 24.80% | train_error: 16.0 | train_acc: 0.228 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [========>-------------------------------] 24.90% | train_error: 16.0 | train_acc: 0.228 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=========>------------------------------] 25.00% | train_error: 16.0 | train_acc: 0.228 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=========>------------------------------] 25.10% | train_error: 16.0 | train_acc: 0.228 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=========>------------------------------] 25.20% | train_error: 16.0 | train_acc: 0.228 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=========>------------------------------] 25.30% | train_error: 16.0 | train_acc: 0.228 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=========>------------------------------] 25.40% | train_error: 16.0 | train_acc: 0.228 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [=========>------------------------------] 25.50% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 25.60% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 25.70% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 25.80% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 25.90% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 26.00% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 26.10% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 26.20% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 26.30% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 26.40% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 26.50% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 26.60% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 26.70% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 26.80% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 26.90% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 27.00% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 27.10% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [=========>------------------------------] 27.20% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [=========>------------------------------] 27.30% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [=========>------------------------------] 27.40% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 27.50% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 27.60% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 27.70% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 27.80% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 27.90% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 28.00% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 28.10% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 28.20% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 28.30% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 28.40% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 28.50% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 28.60% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 28.70% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 28.80% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 28.90% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 29.00% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 29.10% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 29.20% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 29.30% | train_error: 16.0 | train_acc: 0.230 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 29.40% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 29.50% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 29.60% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 29.70% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 29.80% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [==========>-----------------------------] 29.90% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 30.00% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 30.10% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 30.20% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 30.30% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 30.40% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 30.50% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 30.60% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 30.70% | train_error: 15.7 | train_acc: 0.242 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 30.80% | train_error: 15.7 | train_acc: 0.242 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 30.90% | train_error: 15.7 | train_acc: 0.242 | val_error: 15.8 | val_acc: 0.238 
+
    +
    +
      [===========>----------------------------] 31.00% | train_error: 15.7 | train_acc: 0.242 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 31.10% | train_error: 15.7 | train_acc: 0.242 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 31.20% | train_error: 15.7 | train_acc: 0.242 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 31.30% | train_error: 15.7 | train_acc: 0.242 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 31.40% | train_error: 15.7 | train_acc: 0.242 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 31.50% | train_error: 15.7 | train_acc: 0.242 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 31.60% | train_error: 15.7 | train_acc: 0.244 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 31.70% | train_error: 15.5 | train_acc: 0.251 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 31.80% | train_error: 15.5 | train_acc: 0.251 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 31.90% | train_error: 15.6 | train_acc: 0.246 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 32.00% | train_error: 15.6 | train_acc: 0.246 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 32.10% | train_error: 15.6 | train_acc: 0.246 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 32.20% | train_error: 15.6 | train_acc: 0.246 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 32.30% | train_error: 15.6 | train_acc: 0.246 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [===========>----------------------------] 32.40% | train_error: 15.6 | train_acc: 0.246 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [============>---------------------------] 32.50% | train_error: 15.6 | train_acc: 0.246 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [============>---------------------------] 32.60% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [============>---------------------------] 32.70% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [============>---------------------------] 32.80% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [============>---------------------------] 32.90% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [============>---------------------------] 33.00% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [============>---------------------------] 33.10% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [============>---------------------------] 33.20% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [============>---------------------------] 33.30% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [============>---------------------------] 33.40% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [============>---------------------------] 33.50% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [============>---------------------------] 33.60% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [============>---------------------------] 33.70% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [============>---------------------------] 33.80% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [============>---------------------------] 33.90% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.7 | val_acc: 0.245 
+
    +
    +
      [============>---------------------------] 34.00% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [============>---------------------------] 34.10% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [============>---------------------------] 34.20% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [============>---------------------------] 34.30% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [============>---------------------------] 34.40% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [============>---------------------------] 34.50% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [============>---------------------------] 34.60% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [============>---------------------------] 34.70% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [============>---------------------------] 34.80% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [============>---------------------------] 34.90% | train_error: 15.9 | train_acc: 0.235 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=============>--------------------------] 35.00% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=============>--------------------------] 35.10% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=============>--------------------------] 35.20% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=============>--------------------------] 35.30% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=============>--------------------------] 35.40% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=============>--------------------------] 35.50% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=============>--------------------------] 35.60% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=============>--------------------------] 35.70% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=============>--------------------------] 35.80% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=============>--------------------------] 35.90% | train_error: 15.8 | train_acc: 0.237 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=============>--------------------------] 36.00% | train_error: 15.7 | train_acc: 0.244 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=============>--------------------------] 36.10% | train_error: 15.7 | train_acc: 0.244 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=============>--------------------------] 36.20% | train_error: 15.7 | train_acc: 0.244 | val_error: 15.5 | val_acc: 0.252 
+
    +
    +
      [=============>--------------------------] 36.30% | train_error: 15.7 | train_acc: 0.244 | val_error: 15.4 | val_acc: 0.259 
+
    +
    +
      [=============>--------------------------] 36.40% | train_error: 15.7 | train_acc: 0.244 | val_error: 15.4 | val_acc: 0.259 
+
    +
    +
      [=============>--------------------------] 36.50% | train_error: 15.7 | train_acc: 0.244 | val_error: 15.4 | val_acc: 0.259 
+
    +
    +
      [=============>--------------------------] 36.60% | train_error: 15.7 | train_acc: 0.244 | val_error: 15.4 | val_acc: 0.259 
+
    +
    +
      [=============>--------------------------] 36.70% | train_error: 15.7 | train_acc: 0.244 | val_error: 15.4 | val_acc: 0.259 
+
    +
    +
      [=============>--------------------------] 36.80% | train_error: 15.7 | train_acc: 0.244 | val_error: 15.4 | val_acc: 0.259 
+
    +
    +
      [=============>--------------------------] 36.90% | train_error: 15.7 | train_acc: 0.244 | val_error: 15.4 | val_acc: 0.259 
+
    +
    +
      [=============>--------------------------] 37.00% | train_error: 15.7 | train_acc: 0.244 | val_error: 15.4 | val_acc: 0.259 
+
    +
    +
      [=============>--------------------------] 37.10% | train_error: 15.7 | train_acc: 0.244 | val_error: 15.4 | val_acc: 0.259 
+
    +
    +
      [=============>--------------------------] 37.20% | train_error: 15.7 | train_acc: 0.244 | val_error: 15.4 | val_acc: 0.259 
+
    +
    +
      [=============>--------------------------] 37.30% | train_error: 15.7 | train_acc: 0.244 | val_error: 15.4 | val_acc: 0.259 
+
    +
    +
      [=============>--------------------------] 37.40% | train_error: 15.6 | train_acc: 0.249 | val_error: 15.4 | val_acc: 0.259 
+
    +
    +
      [==============>-------------------------] 37.50% | train_error: 15.6 | train_acc: 0.249 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 37.60% | train_error: 15.6 | train_acc: 0.249 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 37.70% | train_error: 15.6 | train_acc: 0.249 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 37.80% | train_error: 15.6 | train_acc: 0.249 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 37.90% | train_error: 15.6 | train_acc: 0.249 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 38.00% | train_error: 15.6 | train_acc: 0.249 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 38.10% | train_error: 15.6 | train_acc: 0.249 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 38.20% | train_error: 15.6 | train_acc: 0.249 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 38.30% | train_error: 15.6 | train_acc: 0.249 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 38.40% | train_error: 15.6 | train_acc: 0.249 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 38.50% | train_error: 15.6 | train_acc: 0.249 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 38.60% | train_error: 15.4 | train_acc: 0.256 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 38.70% | train_error: 15.3 | train_acc: 0.261 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 38.80% | train_error: 15.3 | train_acc: 0.261 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 38.90% | train_error: 15.4 | train_acc: 0.258 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 39.00% | train_error: 15.4 | train_acc: 0.258 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 39.10% | train_error: 15.4 | train_acc: 0.258 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 39.20% | train_error: 15.4 | train_acc: 0.258 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 39.30% | train_error: 15.2 | train_acc: 0.268 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 39.40% | train_error: 15.2 | train_acc: 0.268 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 39.50% | train_error: 15.2 | train_acc: 0.268 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 39.60% | train_error: 15.2 | train_acc: 0.268 | val_error: 15.2 | val_acc: 0.266 
+
    +
    +
      [==============>-------------------------] 39.70% | train_error: 15.2 | train_acc: 0.268 | val_error: 15.1 | val_acc: 0.273 
+
    +
    +
      [==============>-------------------------] 39.80% | train_error: 15.2 | train_acc: 0.268 | val_error: 15.1 | val_acc: 0.273 
+
    +
    +
      [==============>-------------------------] 39.90% | train_error: 15.1 | train_acc: 0.272 | val_error: 15.1 | val_acc: 0.273 
+
    +
    +
      [===============>------------------------] 40.00% | train_error: 15.1 | train_acc: 0.272 | val_error: 15.1 | val_acc: 0.273 
+
    +
    +
      [===============>------------------------] 40.10% | train_error: 15.1 | train_acc: 0.272 | val_error: 15.1 | val_acc: 0.273 
+
    +
    +
      [===============>------------------------] 40.20% | train_error: 15.1 | train_acc: 0.272 | val_error: 15.1 | val_acc: 0.273 
+
    +
    +
      [===============>------------------------] 40.30% | train_error: 15.1 | train_acc: 0.272 | val_error: 15.1 | val_acc: 0.273 
+
    +
    +
      [===============>------------------------] 40.40% | train_error: 15.1 | train_acc: 0.272 | val_error: 15.1 | val_acc: 0.273 
+
    +
    +
      [===============>------------------------] 40.50% | train_error: 15.0 | train_acc: 0.277 | val_error: 15.1 | val_acc: 0.273 
+
    +
    +
      [===============>------------------------] 40.60% | train_error: 15.0 | train_acc: 0.277 | val_error: 15.1 | val_acc: 0.273 
+
    +
    +
      [===============>------------------------] 40.70% | train_error: 15.0 | train_acc: 0.277 | val_error: 15.1 | val_acc: 0.273 
+
    +
    +
      [===============>------------------------] 40.80% | train_error: 15.0 | train_acc: 0.277 | val_error: 15.1 | val_acc: 0.273 
+
    +
    +
      [===============>------------------------] 40.90% | train_error: 15.0 | train_acc: 0.277 | val_error: 14.9 | val_acc: 0.280 
+
    +
    +
      [===============>------------------------] 41.00% | train_error: 15.0 | train_acc: 0.277 | val_error: 14.9 | val_acc: 0.280 
+
    +
    +
      [===============>------------------------] 41.10% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.9 | val_acc: 0.280 
+
    +
    +
      [===============>------------------------] 41.20% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.6 | val_acc: 0.294 
+
    +
    +
      [===============>------------------------] 41.30% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.5 | val_acc: 0.301 
+
    +
    +
      [===============>------------------------] 41.40% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.5 | val_acc: 0.301 
+
    +
    +
      [===============>------------------------] 41.50% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.3 | val_acc: 0.308 
+
    +
    +
      [===============>------------------------] 41.60% | train_error: 15.0 | train_acc: 0.277 | val_error: 14.3 | val_acc: 0.308 
+
    +
    +
      [===============>------------------------] 41.70% | train_error: 15.0 | train_acc: 0.277 | val_error: 14.3 | val_acc: 0.308 
+
    +
    +
      [===============>------------------------] 41.80% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.3 | val_acc: 0.308 
+
    +
    +
      [===============>------------------------] 41.90% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [===============>------------------------] 42.00% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [===============>------------------------] 42.10% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [===============>------------------------] 42.20% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [===============>------------------------] 42.30% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [===============>------------------------] 42.40% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 42.50% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 42.60% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 42.70% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 42.80% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 42.90% | train_error: 14.9 | train_acc: 0.279 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 43.00% | train_error: 14.9 | train_acc: 0.282 | val_error: 14.1 | val_acc: 0.322 
+
    +
    +
      [================>-----------------------] 43.10% | train_error: 14.9 | train_acc: 0.282 | val_error: 14.1 | val_acc: 0.322 
+
    +
    +
      [================>-----------------------] 43.20% | train_error: 14.9 | train_acc: 0.282 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 43.30% | train_error: 14.9 | train_acc: 0.282 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 43.40% | train_error: 14.9 | train_acc: 0.282 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 43.50% | train_error: 14.9 | train_acc: 0.282 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 43.60% | train_error: 14.9 | train_acc: 0.282 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 43.70% | train_error: 14.9 | train_acc: 0.282 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 43.80% | train_error: 14.9 | train_acc: 0.282 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 43.90% | train_error: 14.9 | train_acc: 0.282 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 44.00% | train_error: 14.8 | train_acc: 0.284 | val_error: 14.1 | val_acc: 0.322 
+
    +
    +
      [================>-----------------------] 44.10% | train_error: 14.8 | train_acc: 0.284 | val_error: 14.1 | val_acc: 0.322 
+
    +
    +
      [================>-----------------------] 44.20% | train_error: 14.7 | train_acc: 0.289 | val_error: 14.1 | val_acc: 0.322 
+
    +
    +
      [================>-----------------------] 44.30% | train_error: 14.7 | train_acc: 0.289 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 44.40% | train_error: 14.7 | train_acc: 0.289 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 44.50% | train_error: 14.7 | train_acc: 0.289 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 44.60% | train_error: 14.7 | train_acc: 0.289 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 44.70% | train_error: 14.7 | train_acc: 0.289 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 44.80% | train_error: 14.7 | train_acc: 0.289 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [================>-----------------------] 44.90% | train_error: 14.7 | train_acc: 0.289 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [=================>----------------------] 45.00% | train_error: 14.7 | train_acc: 0.289 | val_error: 14.2 | val_acc: 0.315 
+
    +
    +
      [=================>----------------------] 45.10% | train_error: 14.7 | train_acc: 0.291 | val_error: 14.1 | val_acc: 0.322 
+
    +
    +
      [=================>----------------------] 45.20% | train_error: 14.6 | train_acc: 0.296 | val_error: 14.1 | val_acc: 0.322 
+
    +
    +
      [=================>----------------------] 45.30% | train_error: 14.6 | train_acc: 0.296 | val_error: 14.1 | val_acc: 0.322 
+
    +
    +
      [=================>----------------------] 45.40% | train_error: 14.5 | train_acc: 0.300 | val_error: 14.1 | val_acc: 0.322 
+
    +
    +
      [=================>----------------------] 45.50% | train_error: 14.5 | train_acc: 0.300 | val_error: 14.1 | val_acc: 0.322 
+
    +
    +
      [=================>----------------------] 45.60% | train_error: 14.4 | train_acc: 0.308 | val_error: 14.1 | val_acc: 0.322 
+
    +
    +
      [=================>----------------------] 45.70% | train_error: 14.4 | train_acc: 0.308 | val_error: 14.1 | val_acc: 0.322 
+
    +
    +
      [=================>----------------------] 45.80% | train_error: 14.4 | train_acc: 0.308 | val_error: 13.9 | val_acc: 0.329 
+
    +
    +
      [=================>----------------------] 45.90% | train_error: 14.4 | train_acc: 0.308 | val_error: 13.9 | val_acc: 0.329 
+
    +
    +
      [=================>----------------------] 46.00% | train_error: 14.3 | train_acc: 0.310 | val_error: 13.9 | val_acc: 0.329 
+
    +
    +
      [=================>----------------------] 46.10% | train_error: 14.3 | train_acc: 0.310 | val_error: 13.9 | val_acc: 0.329 
+
    +
    +
      [=================>----------------------] 46.20% | train_error: 14.3 | train_acc: 0.312 | val_error: 13.9 | val_acc: 0.329 
+
    +
    +
      [=================>----------------------] 46.30% | train_error: 14.2 | train_acc: 0.315 | val_error: 13.9 | val_acc: 0.329 
+
    +
    +
      [=================>----------------------] 46.40% | train_error: 14.2 | train_acc: 0.315 | val_error: 13.9 | val_acc: 0.329 
+
    +
    +
      [=================>----------------------] 46.50% | train_error: 14.2 | train_acc: 0.315 | val_error: 13.9 | val_acc: 0.329 
+
    +
    +
      [=================>----------------------] 46.60% | train_error: 14.2 | train_acc: 0.315 | val_error: 13.9 | val_acc: 0.329 
+
    +
    +
      [=================>----------------------] 46.70% | train_error: 14.2 | train_acc: 0.315 | val_error: 13.9 | val_acc: 0.329 
+
    +
    +
      [=================>----------------------] 46.80% | train_error: 14.1 | train_acc: 0.319 | val_error: 13.8 | val_acc: 0.336 
+
    +
    +
      [=================>----------------------] 46.90% | train_error: 14.1 | train_acc: 0.319 | val_error: 13.8 | val_acc: 0.336 
+
    +
    +
      [=================>----------------------] 47.00% | train_error: 14.1 | train_acc: 0.322 | val_error: 13.8 | val_acc: 0.336 
+
    +
    +
      [=================>----------------------] 47.10% | train_error: 14.1 | train_acc: 0.322 | val_error: 13.8 | val_acc: 0.336 
+
    +
    +
      [=================>----------------------] 47.20% | train_error: 14.1 | train_acc: 0.322 | val_error: 13.8 | val_acc: 0.336 
+
    +
    +
      [=================>----------------------] 47.30% | train_error: 14.0 | train_acc: 0.324 | val_error: 13.8 | val_acc: 0.336 
+
    +
    +
      [=================>----------------------] 47.40% | train_error: 14.0 | train_acc: 0.324 | val_error: 13.8 | val_acc: 0.336 
+
    +
    +
      [==================>---------------------] 47.50% | train_error: 14.0 | train_acc: 0.324 | val_error: 13.8 | val_acc: 0.336 
+
    +
    +
      [==================>---------------------] 47.60% | train_error: 14.0 | train_acc: 0.326 | val_error: 13.6 | val_acc: 0.343 
+
    +
    +
      [==================>---------------------] 47.70% | train_error: 13.9 | train_acc: 0.329 | val_error: 13.5 | val_acc: 0.350 
+
    +
    +
      [==================>---------------------] 47.80% | train_error: 13.9 | train_acc: 0.329 | val_error: 13.5 | val_acc: 0.350 
+
    +
    +
      [==================>---------------------] 47.90% | train_error: 13.7 | train_acc: 0.338 | val_error: 13.5 | val_acc: 0.350 
+
    +
    +
      [==================>---------------------] 48.00% | train_error: 13.6 | train_acc: 0.343 | val_error: 13.3 | val_acc: 0.357 
+
    +
    +
      [==================>---------------------] 48.10% | train_error: 13.6 | train_acc: 0.343 | val_error: 13.3 | val_acc: 0.357 
+
    +
    +
      [==================>---------------------] 48.20% | train_error: 13.6 | train_acc: 0.343 | val_error: 13.3 | val_acc: 0.357 
+
    +
    +
      [==================>---------------------] 48.30% | train_error: 13.6 | train_acc: 0.343 | val_error: 13.3 | val_acc: 0.357 
+
    +
    +
      [==================>---------------------] 48.40% | train_error: 13.6 | train_acc: 0.343 | val_error: 13.3 | val_acc: 0.357 
+
    +
    +
      [==================>---------------------] 48.50% | train_error: 13.5 | train_acc: 0.347 | val_error: 13.3 | val_acc: 0.357 
+
    +
    +
      [==================>---------------------] 48.60% | train_error: 13.5 | train_acc: 0.347 | val_error: 13.3 | val_acc: 0.357 
+
    +
    +
      [==================>---------------------] 48.70% | train_error: 13.5 | train_acc: 0.347 | val_error: 13.3 | val_acc: 0.357 
+
    +
    +
      [==================>---------------------] 48.80% | train_error: 13.5 | train_acc: 0.347 | val_error: 13.2 | val_acc: 0.364 
+
    +
    +
      [==================>---------------------] 48.90% | train_error: 13.4 | train_acc: 0.352 | val_error: 12.9 | val_acc: 0.378 
+
    +
    +
      [==================>---------------------] 49.00% | train_error: 13.4 | train_acc: 0.352 | val_error: 12.9 | val_acc: 0.378 
+
    +
    +
      [==================>---------------------] 49.10% | train_error: 13.4 | train_acc: 0.352 | val_error: 12.9 | val_acc: 0.378 
+
    +
    +
      [==================>---------------------] 49.20% | train_error: 13.4 | train_acc: 0.352 | val_error: 12.9 | val_acc: 0.378 
+
    +
    +
      [==================>---------------------] 49.30% | train_error: 13.2 | train_acc: 0.362 | val_error: 12.9 | val_acc: 0.378 
+
    +
    +
      [==================>---------------------] 49.40% | train_error: 13.2 | train_acc: 0.362 | val_error: 12.9 | val_acc: 0.378 
+
    +
    +
      [==================>---------------------] 49.50% | train_error: 13.2 | train_acc: 0.362 | val_error: 12.9 | val_acc: 0.378 
+
    +
    +
      [==================>---------------------] 49.60% | train_error: 13.2 | train_acc: 0.362 | val_error: 12.9 | val_acc: 0.378 
+
    +
    +
      [==================>---------------------] 49.70% | train_error: 13.2 | train_acc: 0.362 | val_error: 12.9 | val_acc: 0.378 
+
    +
    +
      [==================>---------------------] 49.80% | train_error: 13.2 | train_acc: 0.362 | val_error: 12.9 | val_acc: 0.378 
+
    +
    +
      [==================>---------------------] 49.90% | train_error: 13.2 | train_acc: 0.362 | val_error: 12.9 | val_acc: 0.378 
+
    +
    +
      [===================>--------------------] 50.00% | train_error: 13.2 | train_acc: 0.364 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [===================>--------------------] 50.10% | train_error: 13.2 | train_acc: 0.364 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [===================>--------------------] 50.20% | train_error: 13.0 | train_acc: 0.373 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [===================>--------------------] 50.30% | train_error: 13.0 | train_acc: 0.373 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [===================>--------------------] 50.40% | train_error: 13.0 | train_acc: 0.371 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [===================>--------------------] 50.50% | train_error: 13.0 | train_acc: 0.371 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [===================>--------------------] 50.60% | train_error: 13.0 | train_acc: 0.371 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [===================>--------------------] 50.70% | train_error: 12.8 | train_acc: 0.380 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [===================>--------------------] 50.80% | train_error: 12.8 | train_acc: 0.383 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [===================>--------------------] 50.90% | train_error: 12.8 | train_acc: 0.383 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [===================>--------------------] 51.00% | train_error: 12.8 | train_acc: 0.383 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [===================>--------------------] 51.10% | train_error: 12.7 | train_acc: 0.385 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [===================>--------------------] 51.20% | train_error: 12.7 | train_acc: 0.385 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [===================>--------------------] 51.30% | train_error: 12.7 | train_acc: 0.385 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [===================>--------------------] 51.40% | train_error: 12.7 | train_acc: 0.385 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [===================>--------------------] 51.50% | train_error: 12.6 | train_acc: 0.390 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [===================>--------------------] 51.60% | train_error: 12.6 | train_acc: 0.390 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [===================>--------------------] 51.70% | train_error: 12.6 | train_acc: 0.390 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [===================>--------------------] 51.80% | train_error: 12.8 | train_acc: 0.380 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [===================>--------------------] 51.90% | train_error: 12.8 | train_acc: 0.380 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [===================>--------------------] 52.00% | train_error: 12.8 | train_acc: 0.380 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [===================>--------------------] 52.10% | train_error: 12.8 | train_acc: 0.380 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [===================>--------------------] 52.20% | train_error: 12.8 | train_acc: 0.383 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [===================>--------------------] 52.30% | train_error: 12.8 | train_acc: 0.383 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [===================>--------------------] 52.40% | train_error: 12.8 | train_acc: 0.383 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 52.50% | train_error: 12.8 | train_acc: 0.383 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 52.60% | train_error: 12.6 | train_acc: 0.390 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 52.70% | train_error: 12.6 | train_acc: 0.390 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 52.80% | train_error: 12.6 | train_acc: 0.390 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 52.90% | train_error: 12.6 | train_acc: 0.390 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 53.00% | train_error: 12.6 | train_acc: 0.390 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 53.10% | train_error: 12.6 | train_acc: 0.390 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 53.20% | train_error: 12.6 | train_acc: 0.392 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 53.30% | train_error: 12.6 | train_acc: 0.392 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 53.40% | train_error: 12.6 | train_acc: 0.394 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 53.50% | train_error: 12.6 | train_acc: 0.394 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 53.60% | train_error: 12.6 | train_acc: 0.394 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 53.70% | train_error: 12.6 | train_acc: 0.394 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 53.80% | train_error: 12.6 | train_acc: 0.394 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 53.90% | train_error: 12.6 | train_acc: 0.394 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 54.00% | train_error: 12.6 | train_acc: 0.394 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [====================>-------------------] 54.10% | train_error: 12.5 | train_acc: 0.397 | val_error: 12.3 | val_acc: 0.406 
+
    +
    +
      [====================>-------------------] 54.20% | train_error: 12.5 | train_acc: 0.397 | val_error: 12.3 | val_acc: 0.406 
+
    +
    +
      [====================>-------------------] 54.30% | train_error: 12.5 | train_acc: 0.397 | val_error: 12.3 | val_acc: 0.406 
+
    +
    +
      [====================>-------------------] 54.40% | train_error: 12.5 | train_acc: 0.397 | val_error: 12.3 | val_acc: 0.406 
+
    +
    +
      [====================>-------------------] 54.50% | train_error: 12.5 | train_acc: 0.397 | val_error: 12.3 | val_acc: 0.406 
+
    +
    +
      [====================>-------------------] 54.60% | train_error: 12.4 | train_acc: 0.401 | val_error: 12.3 | val_acc: 0.406 
+
    +
    +
      [====================>-------------------] 54.70% | train_error: 12.4 | train_acc: 0.404 | val_error: 12.3 | val_acc: 0.406 
+
    +
    +
      [====================>-------------------] 54.80% | train_error: 12.2 | train_acc: 0.411 | val_error: 12.3 | val_acc: 0.406 
+
    +
    +
      [====================>-------------------] 54.90% | train_error: 12.1 | train_acc: 0.415 | val_error: 12.2 | val_acc: 0.413 
+
    +
    +
      [=====================>------------------] 55.00% | train_error: 12.1 | train_acc: 0.415 | val_error: 12.0 | val_acc: 0.420 
+
    +
    +
      [=====================>------------------] 55.10% | train_error: 12.1 | train_acc: 0.415 | val_error: 12.0 | val_acc: 0.420 
+
    +
    +
      [=====================>------------------] 55.20% | train_error: 12.1 | train_acc: 0.415 | val_error: 12.0 | val_acc: 0.420 
+
    +
    +
      [=====================>------------------] 55.30% | train_error: 12.1 | train_acc: 0.418 | val_error: 12.2 | val_acc: 0.413 
+
    +
    +
      [=====================>------------------] 55.40% | train_error: 11.7 | train_acc: 0.437 | val_error: 12.0 | val_acc: 0.420 
+
    +
    +
      [=====================>------------------] 55.50% | train_error: 11.7 | train_acc: 0.434 | val_error: 12.0 | val_acc: 0.420 
+
    +
    +
      [=====================>------------------] 55.60% | train_error: 11.7 | train_acc: 0.434 | val_error: 12.0 | val_acc: 0.420 
+
    +
    +
      [=====================>------------------] 55.70% | train_error: 11.7 | train_acc: 0.437 | val_error: 12.0 | val_acc: 0.420 
+
    +
    +
      [=====================>------------------] 55.80% | train_error: 11.7 | train_acc: 0.437 | val_error: 11.9 | val_acc: 0.427 
+
    +
    +
      [=====================>------------------] 55.90% | train_error: 11.7 | train_acc: 0.437 | val_error: 11.9 | val_acc: 0.427 
+
    +
    +
      [=====================>------------------] 56.00% | train_error: 11.7 | train_acc: 0.437 | val_error: 11.9 | val_acc: 0.427 
+
    +
    +
      [=====================>------------------] 56.10% | train_error: 11.7 | train_acc: 0.437 | val_error: 11.7 | val_acc: 0.434 
+
    +
    +
      [=====================>------------------] 56.20% | train_error: 11.7 | train_acc: 0.437 | val_error: 11.7 | val_acc: 0.434 
+
    +
    +
      [=====================>------------------] 56.30% | train_error: 11.7 | train_acc: 0.437 | val_error: 11.7 | val_acc: 0.434 
+
    +
    +
      [=====================>------------------] 56.40% | train_error: 11.5 | train_acc: 0.444 | val_error: 11.7 | val_acc: 0.434 
+
    +
    +
      [=====================>------------------] 56.50% | train_error: 11.5 | train_acc: 0.444 | val_error: 11.7 | val_acc: 0.434 
+
    +
    +
      [=====================>------------------] 56.60% | train_error: 11.6 | train_acc: 0.441 | val_error: 11.7 | val_acc: 0.434 
+
    +
    +
      [=====================>------------------] 56.70% | train_error: 11.3 | train_acc: 0.453 | val_error: 11.7 | val_acc: 0.434 
+
    +
    +
      [=====================>------------------] 56.80% | train_error: 11.3 | train_acc: 0.453 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [=====================>------------------] 56.90% | train_error: 11.3 | train_acc: 0.453 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [=====================>------------------] 57.00% | train_error: 11.3 | train_acc: 0.453 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [=====================>------------------] 57.10% | train_error: 11.3 | train_acc: 0.453 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [=====================>------------------] 57.20% | train_error: 11.3 | train_acc: 0.453 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [=====================>------------------] 57.30% | train_error: 11.3 | train_acc: 0.453 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [=====================>------------------] 57.40% | train_error: 11.3 | train_acc: 0.453 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [======================>-----------------] 57.50% | train_error: 11.4 | train_acc: 0.451 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [======================>-----------------] 57.60% | train_error: 11.4 | train_acc: 0.451 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 57.70% | train_error: 11.4 | train_acc: 0.451 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 57.80% | train_error: 11.4 | train_acc: 0.451 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 57.90% | train_error: 11.3 | train_acc: 0.455 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 58.00% | train_error: 11.2 | train_acc: 0.460 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 58.10% | train_error: 10.9 | train_acc: 0.472 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 58.20% | train_error: 10.9 | train_acc: 0.472 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 58.30% | train_error: 10.9 | train_acc: 0.472 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 58.40% | train_error: 10.9 | train_acc: 0.472 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 58.50% | train_error: 10.9 | train_acc: 0.472 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 58.60% | train_error: 10.9 | train_acc: 0.472 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 58.70% | train_error: 10.8 | train_acc: 0.477 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 58.80% | train_error: 10.8 | train_acc: 0.477 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 58.90% | train_error: 10.8 | train_acc: 0.477 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 59.00% | train_error: 10.7 | train_acc: 0.484 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 59.10% | train_error: 10.7 | train_acc: 0.484 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 59.20% | train_error: 10.7 | train_acc: 0.486 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 59.30% | train_error: 10.7 | train_acc: 0.486 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [======================>-----------------] 59.40% | train_error: 10.7 | train_acc: 0.486 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [======================>-----------------] 59.50% | train_error: 10.7 | train_acc: 0.486 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [======================>-----------------] 59.60% | train_error: 10.7 | train_acc: 0.486 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [======================>-----------------] 59.70% | train_error: 10.6 | train_acc: 0.488 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [======================>-----------------] 59.80% | train_error: 10.6 | train_acc: 0.488 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [======================>-----------------] 59.90% | train_error: 10.6 | train_acc: 0.491 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [=======================>----------------] 60.00% | train_error: 10.5 | train_acc: 0.493 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [=======================>----------------] 60.10% | train_error: 10.5 | train_acc: 0.493 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [=======================>----------------] 60.20% | train_error: 10.5 | train_acc: 0.493 | val_error: 11.3 | val_acc: 0.455 
+
    +
    +
      [=======================>----------------] 60.30% | train_error: 10.5 | train_acc: 0.493 | val_error: 11.0 | val_acc: 0.469 
+
    +
    +
      [=======================>----------------] 60.40% | train_error: 10.5 | train_acc: 0.493 | val_error: 11.0 | val_acc: 0.469 
+
    +
    +
      [=======================>----------------] 60.50% | train_error: 10.5 | train_acc: 0.493 | val_error: 11.0 | val_acc: 0.469 
+
    +
    +
      [=======================>----------------] 60.60% | train_error: 10.3 | train_acc: 0.502 | val_error: 11.0 | val_acc: 0.469 
+
    +
    +
      [=======================>----------------] 60.70% | train_error: 10.3 | train_acc: 0.502 | val_error: 10.7 | val_acc: 0.483 
+
    +
    +
      [=======================>----------------] 60.80% | train_error: 10.3 | train_acc: 0.502 | val_error: 10.7 | val_acc: 0.483 
+
    +
    +
      [=======================>----------------] 60.90% | train_error: 10.3 | train_acc: 0.502 | val_error: 10.7 | val_acc: 0.483 
+
    +
    +
      [=======================>----------------] 61.00% | train_error: 10.2 | train_acc: 0.507 | val_error: 10.7 | val_acc: 0.483 
+
    +
    +
      [=======================>----------------] 61.10% | train_error: 10.2 | train_acc: 0.507 | val_error: 10.7 | val_acc: 0.483 
+
    +
    +
      [=======================>----------------] 61.20% | train_error: 10.2 | train_acc: 0.509 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [=======================>----------------] 61.30% | train_error: 10.2 | train_acc: 0.509 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [=======================>----------------] 61.40% | train_error: 10.2 | train_acc: 0.509 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [=======================>----------------] 61.50% | train_error: 10.2 | train_acc: 0.509 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [=======================>----------------] 61.60% | train_error: 10.1 | train_acc: 0.512 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [=======================>----------------] 61.70% | train_error: 10.1 | train_acc: 0.512 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [=======================>----------------] 61.80% | train_error: 10.1 | train_acc: 0.512 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [=======================>----------------] 61.90% | train_error: 10.1 | train_acc: 0.512 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [=======================>----------------] 62.00% | train_error: 10.0 | train_acc: 0.516 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [=======================>----------------] 62.10% | train_error: 9.97 | train_acc: 0.519 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [=======================>----------------] 62.20% | train_error: 9.97 | train_acc: 0.519 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [=======================>----------------] 62.30% | train_error: 9.88 | train_acc: 0.523 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [=======================>----------------] 62.40% | train_error: 9.88 | train_acc: 0.523 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [========================>---------------] 62.50% | train_error: 9.78 | train_acc: 0.528 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [========================>---------------] 62.60% | train_error: 9.68 | train_acc: 0.533 | val_error: 10.3 | val_acc: 0.503 
+
    +
    +
      [========================>---------------] 62.70% | train_error: 9.68 | train_acc: 0.533 | val_error: 10.00 | val_acc: 0.517 
+
    +
    +
      [========================>---------------] 62.80% | train_error: 9.53 | train_acc: 0.540 | val_error: 10.00 | val_acc: 0.517 
+
    +
    +
      [========================>---------------] 62.90% | train_error: 9.44 | train_acc: 0.545 | val_error: 10.00 | val_acc: 0.517 
+
    +
    +
      [========================>---------------] 63.00% | train_error: 9.39 | train_acc: 0.547 | val_error: 10.00 | val_acc: 0.517 
+
    +
    +
      [========================>---------------] 63.10% | train_error: 9.29 | train_acc: 0.552 | val_error: 10.00 | val_acc: 0.517 
+
    +
    +
      [========================>---------------] 63.20% | train_error: 9.29 | train_acc: 0.552 | val_error: 10.00 | val_acc: 0.517 
+
    +
    +
      [========================>---------------] 63.30% | train_error: 9.24 | train_acc: 0.554 | val_error: 9.85 | val_acc: 0.524 
+
    +
    +
      [========================>---------------] 63.40% | train_error: 9.24 | train_acc: 0.554 | val_error: 9.85 | val_acc: 0.524 
+
    +
    +
      [========================>---------------] 63.50% | train_error: 8.85 | train_acc: 0.573 | val_error: 9.85 | val_acc: 0.524 
+
    +
    +
      [========================>---------------] 63.60% | train_error: 8.85 | train_acc: 0.573 | val_error: 9.85 | val_acc: 0.524 
+
    +
    +
      [========================>---------------] 63.70% | train_error: 8.76 | train_acc: 0.577 | val_error: 9.56 | val_acc: 0.538 
+
    +
    +
      [========================>---------------] 63.80% | train_error: 8.76 | train_acc: 0.577 | val_error: 9.56 | val_acc: 0.538 
+
    +
    +
      [========================>---------------] 63.90% | train_error: 8.76 | train_acc: 0.577 | val_error: 9.56 | val_acc: 0.538 
+
    +
    +
      [========================>---------------] 64.00% | train_error: 8.76 | train_acc: 0.577 | val_error: 9.56 | val_acc: 0.538 
+
    +
    +
      [========================>---------------] 64.10% | train_error: 8.71 | train_acc: 0.580 | val_error: 9.56 | val_acc: 0.538 
+
    +
    +
      [========================>---------------] 64.20% | train_error: 8.71 | train_acc: 0.580 | val_error: 9.42 | val_acc: 0.545 
+
    +
    +
      [========================>---------------] 64.30% | train_error: 8.71 | train_acc: 0.580 | val_error: 9.42 | val_acc: 0.545 
+
    +
    +
      [========================>---------------] 64.40% | train_error: 8.56 | train_acc: 0.587 | val_error: 9.42 | val_acc: 0.545 
+
    +
    +
      [========================>---------------] 64.50% | train_error: 8.56 | train_acc: 0.587 | val_error: 9.42 | val_acc: 0.545 
+
    +
    +
      [========================>---------------] 64.60% | train_error: 8.51 | train_acc: 0.589 | val_error: 9.42 | val_acc: 0.545 
+
    +
    +
      [========================>---------------] 64.70% | train_error: 8.46 | train_acc: 0.592 | val_error: 9.42 | val_acc: 0.545 
+
    +
    +
      [========================>---------------] 64.80% | train_error: 8.32 | train_acc: 0.599 | val_error: 9.42 | val_acc: 0.545 
+
    +
    +
      [========================>---------------] 64.90% | train_error: 8.22 | train_acc: 0.603 | val_error: 9.42 | val_acc: 0.545 
+
    +
    +
      [=========================>--------------] 65.00% | train_error: 8.12 | train_acc: 0.608 | val_error: 9.42 | val_acc: 0.545 
+
    +
    +
      [=========================>--------------] 65.10% | train_error: 8.08 | train_acc: 0.610 | val_error: 9.27 | val_acc: 0.552 
+
    +
    +
      [=========================>--------------] 65.20% | train_error: 8.03 | train_acc: 0.613 | val_error: 9.27 | val_acc: 0.552 
+
    +
    +
      [=========================>--------------] 65.30% | train_error: 8.03 | train_acc: 0.613 | val_error: 9.27 | val_acc: 0.552 
+
    +
    +
      [=========================>--------------] 65.40% | train_error: 8.03 | train_acc: 0.613 | val_error: 9.13 | val_acc: 0.559 
+
    +
    +
      [=========================>--------------] 65.50% | train_error: 8.03 | train_acc: 0.613 | val_error: 9.13 | val_acc: 0.559 
+
    +
    +
      [=========================>--------------] 65.60% | train_error: 8.03 | train_acc: 0.613 | val_error: 8.98 | val_acc: 0.566 
+
    +
    +
      [=========================>--------------] 65.70% | train_error: 8.03 | train_acc: 0.613 | val_error: 8.98 | val_acc: 0.566 
+
    +
    +
      [=========================>--------------] 65.80% | train_error: 8.03 | train_acc: 0.613 | val_error: 8.84 | val_acc: 0.573 
+
    +
    +
      [=========================>--------------] 65.90% | train_error: 7.98 | train_acc: 0.615 | val_error: 8.70 | val_acc: 0.580 
+
    +
    +
      [=========================>--------------] 66.00% | train_error: 7.98 | train_acc: 0.615 | val_error: 8.55 | val_acc: 0.587 
+
    +
    +
      [=========================>--------------] 66.10% | train_error: 7.88 | train_acc: 0.620 | val_error: 8.55 | val_acc: 0.587 
+
    +
    +
      [=========================>--------------] 66.20% | train_error: 7.88 | train_acc: 0.620 | val_error: 8.55 | val_acc: 0.587 
+
    +
    +
      [=========================>--------------] 66.30% | train_error: 7.88 | train_acc: 0.620 | val_error: 8.70 | val_acc: 0.580 
+
    +
    +
      [=========================>--------------] 66.40% | train_error: 7.88 | train_acc: 0.620 | val_error: 8.70 | val_acc: 0.580 
+
    +
    +
      [=========================>--------------] 66.50% | train_error: 7.88 | train_acc: 0.620 | val_error: 8.70 | val_acc: 0.580 
+
    +
    +
      [=========================>--------------] 66.60% | train_error: 7.73 | train_acc: 0.627 | val_error: 8.70 | val_acc: 0.580 
+
    +
    +
      [=========================>--------------] 66.70% | train_error: 7.73 | train_acc: 0.627 | val_error: 8.70 | val_acc: 0.580 
+
    +
    +
      [=========================>--------------] 66.80% | train_error: 7.73 | train_acc: 0.627 | val_error: 8.70 | val_acc: 0.580 
+
    +
    +
      [=========================>--------------] 66.90% | train_error: 7.73 | train_acc: 0.627 | val_error: 8.70 | val_acc: 0.580 
+
    +
    +
      [=========================>--------------] 67.00% | train_error: 7.69 | train_acc: 0.629 | val_error: 8.55 | val_acc: 0.587 
+
    +
    +
      [=========================>--------------] 67.10% | train_error: 7.69 | train_acc: 0.629 | val_error: 8.55 | val_acc: 0.587 
+
    +
    +
      [=========================>--------------] 67.20% | train_error: 7.69 | train_acc: 0.629 | val_error: 8.41 | val_acc: 0.594 
+
    +
    +
      [=========================>--------------] 67.30% | train_error: 7.69 | train_acc: 0.629 | val_error: 8.41 | val_acc: 0.594 
+
    +
    +
      [=========================>--------------] 67.40% | train_error: 7.69 | train_acc: 0.629 | val_error: 8.26 | val_acc: 0.601 
+
    +
    +
      [==========================>-------------] 67.50% | train_error: 7.69 | train_acc: 0.629 | val_error: 8.12 | val_acc: 0.608 
+
    +
    +
      [==========================>-------------] 67.60% | train_error: 7.69 | train_acc: 0.629 | val_error: 8.12 | val_acc: 0.608 
+
    +
    +
      [==========================>-------------] 67.70% | train_error: 7.69 | train_acc: 0.629 | val_error: 7.97 | val_acc: 0.615 
+
    +
    +
      [==========================>-------------] 67.80% | train_error: 7.54 | train_acc: 0.636 | val_error: 7.97 | val_acc: 0.615 
+
    +
    +
      [==========================>-------------] 67.90% | train_error: 7.54 | train_acc: 0.636 | val_error: 7.97 | val_acc: 0.615 
+
    +
    +
      [==========================>-------------] 68.00% | train_error: 7.54 | train_acc: 0.636 | val_error: 7.97 | val_acc: 0.615 
+
    +
    +
      [==========================>-------------] 68.10% | train_error: 7.44 | train_acc: 0.641 | val_error: 7.97 | val_acc: 0.615 
+
    +
    +
      [==========================>-------------] 68.20% | train_error: 7.44 | train_acc: 0.641 | val_error: 7.97 | val_acc: 0.615 
+
    +
    +
      [==========================>-------------] 68.30% | train_error: 7.30 | train_acc: 0.648 | val_error: 7.97 | val_acc: 0.615 
+
    +
    +
      [==========================>-------------] 68.40% | train_error: 7.30 | train_acc: 0.648 | val_error: 7.97 | val_acc: 0.615 
+
    +
    +
      [==========================>-------------] 68.50% | train_error: 7.30 | train_acc: 0.648 | val_error: 7.83 | val_acc: 0.622 
+
    +
    +
      [==========================>-------------] 68.60% | train_error: 7.10 | train_acc: 0.657 | val_error: 7.83 | val_acc: 0.622 
+
    +
    +
      [==========================>-------------] 68.70% | train_error: 7.01 | train_acc: 0.662 | val_error: 7.83 | val_acc: 0.622 
+
    +
    +
      [==========================>-------------] 68.80% | train_error: 6.91 | train_acc: 0.667 | val_error: 7.97 | val_acc: 0.615 
+
    +
    +
      [==========================>-------------] 68.90% | train_error: 6.91 | train_acc: 0.667 | val_error: 7.97 | val_acc: 0.615 
+
    +
    +
      [==========================>-------------] 69.00% | train_error: 6.81 | train_acc: 0.671 | val_error: 7.83 | val_acc: 0.622 
+
    +
    +
      [==========================>-------------] 69.10% | train_error: 6.81 | train_acc: 0.671 | val_error: 7.68 | val_acc: 0.629 
+
    +
    +
      [==========================>-------------] 69.20% | train_error: 6.81 | train_acc: 0.671 | val_error: 7.68 | val_acc: 0.629 
+
    +
    +
      [==========================>-------------] 69.30% | train_error: 6.81 | train_acc: 0.671 | val_error: 7.68 | val_acc: 0.629 
+
    +
    +
      [==========================>-------------] 69.40% | train_error: 6.76 | train_acc: 0.674 | val_error: 7.68 | val_acc: 0.629 
+
    +
    +
      [==========================>-------------] 69.50% | train_error: 6.76 | train_acc: 0.674 | val_error: 7.68 | val_acc: 0.629 
+
    +
    +
      [==========================>-------------] 69.60% | train_error: 6.71 | train_acc: 0.676 | val_error: 7.68 | val_acc: 0.629 
+
    +
    +
      [==========================>-------------] 69.70% | train_error: 6.71 | train_acc: 0.676 | val_error: 7.68 | val_acc: 0.629 
+
    +
    +
      [==========================>-------------] 69.80% | train_error: 6.71 | train_acc: 0.676 | val_error: 7.68 | val_acc: 0.629 
+
    +
    +
      [==========================>-------------] 69.90% | train_error: 6.71 | train_acc: 0.676 | val_error: 7.68 | val_acc: 0.629 
+
    +
    +
      [===========================>------------] 70.00% | train_error: 6.91 | train_acc: 0.667 | val_error: 7.68 | val_acc: 0.629 
+
    +
    +
      [===========================>------------] 70.10% | train_error: 6.91 | train_acc: 0.667 | val_error: 7.68 | val_acc: 0.629 
+
    +
    +
      [===========================>------------] 70.20% | train_error: 6.86 | train_acc: 0.669 | val_error: 7.68 | val_acc: 0.629 
+
    +
    +
      [===========================>------------] 70.30% | train_error: 6.86 | train_acc: 0.669 | val_error: 7.68 | val_acc: 0.629 
+
    +
    +
      [===========================>------------] 70.40% | train_error: 6.86 | train_acc: 0.669 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [===========================>------------] 70.50% | train_error: 6.71 | train_acc: 0.676 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [===========================>------------] 70.60% | train_error: 6.71 | train_acc: 0.676 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [===========================>------------] 70.70% | train_error: 6.71 | train_acc: 0.676 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [===========================>------------] 70.80% | train_error: 6.71 | train_acc: 0.676 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [===========================>------------] 70.90% | train_error: 6.71 | train_acc: 0.676 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [===========================>------------] 71.00% | train_error: 6.71 | train_acc: 0.676 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [===========================>------------] 71.10% | train_error: 6.66 | train_acc: 0.678 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [===========================>------------] 71.20% | train_error: 6.57 | train_acc: 0.683 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [===========================>------------] 71.30% | train_error: 6.57 | train_acc: 0.683 | val_error: 7.39 | val_acc: 0.643 
+
    +
    +
      [===========================>------------] 71.40% | train_error: 6.57 | train_acc: 0.683 | val_error: 7.39 | val_acc: 0.643 
+
    +
    +
      [===========================>------------] 71.50% | train_error: 6.57 | train_acc: 0.683 | val_error: 7.39 | val_acc: 0.643 
+
    +
    +
      [===========================>------------] 71.60% | train_error: 6.57 | train_acc: 0.683 | val_error: 7.39 | val_acc: 0.643 
+
    +
    +
      [===========================>------------] 71.70% | train_error: 6.57 | train_acc: 0.683 | val_error: 7.25 | val_acc: 0.650 
+
    +
    +
      [===========================>------------] 71.80% | train_error: 6.52 | train_acc: 0.685 | val_error: 7.25 | val_acc: 0.650 
+
    +
    +
      [===========================>------------] 71.90% | train_error: 6.52 | train_acc: 0.685 | val_error: 7.25 | val_acc: 0.650 
+
    +
    +
      [===========================>------------] 72.00% | train_error: 6.52 | train_acc: 0.685 | val_error: 7.25 | val_acc: 0.650 
+
    +
    +
      [===========================>------------] 72.10% | train_error: 6.52 | train_acc: 0.685 | val_error: 7.25 | val_acc: 0.650 
+
    +
    +
      [===========================>------------] 72.20% | train_error: 6.47 | train_acc: 0.688 | val_error: 7.25 | val_acc: 0.650 
+
    +
    +
      [===========================>------------] 72.30% | train_error: 6.42 | train_acc: 0.690 | val_error: 7.10 | val_acc: 0.657 
+
    +
    +
      [===========================>------------] 72.40% | train_error: 6.42 | train_acc: 0.690 | val_error: 7.10 | val_acc: 0.657 
+
    +
    +
      [============================>-----------] 72.50% | train_error: 6.42 | train_acc: 0.690 | val_error: 7.10 | val_acc: 0.657 
+
    +
    +
      [============================>-----------] 72.60% | train_error: 6.42 | train_acc: 0.690 | val_error: 6.81 | val_acc: 0.671 
+
    +
    +
      [============================>-----------] 72.70% | train_error: 6.37 | train_acc: 0.692 | val_error: 6.81 | val_acc: 0.671 
+
    +
    +
      [============================>-----------] 72.80% | train_error: 6.32 | train_acc: 0.695 | val_error: 6.81 | val_acc: 0.671 
+
    +
    +
      [============================>-----------] 72.90% | train_error: 6.32 | train_acc: 0.695 | val_error: 6.81 | val_acc: 0.671 
+
    +
    +
      [============================>-----------] 73.00% | train_error: 6.32 | train_acc: 0.695 | val_error: 6.81 | val_acc: 0.671 
+
    +
    +
      [============================>-----------] 73.10% | train_error: 6.32 | train_acc: 0.695 | val_error: 6.81 | val_acc: 0.671 
+
    +
    +
      [============================>-----------] 73.20% | train_error: 6.32 | train_acc: 0.695 | val_error: 6.81 | val_acc: 0.671 
+
    +
    +
      [============================>-----------] 73.30% | train_error: 6.32 | train_acc: 0.695 | val_error: 6.81 | val_acc: 0.671 
+
    +
    +
      [============================>-----------] 73.40% | train_error: 6.32 | train_acc: 0.695 | val_error: 6.81 | val_acc: 0.671 
+
    +
    +
      [============================>-----------] 73.50% | train_error: 6.23 | train_acc: 0.700 | val_error: 6.81 | val_acc: 0.671 
+
    +
    +
      [============================>-----------] 73.60% | train_error: 6.23 | train_acc: 0.700 | val_error: 6.81 | val_acc: 0.671 
+
    +
    +
      [============================>-----------] 73.70% | train_error: 6.23 | train_acc: 0.700 | val_error: 6.67 | val_acc: 0.678 
+
    +
    +
      [============================>-----------] 73.80% | train_error: 6.23 | train_acc: 0.700 | val_error: 6.67 | val_acc: 0.678 
+
    +
    +
      [============================>-----------] 73.90% | train_error: 6.18 | train_acc: 0.702 | val_error: 6.67 | val_acc: 0.678 
+
    +
    +
      [============================>-----------] 74.00% | train_error: 5.98 | train_acc: 0.711 | val_error: 6.67 | val_acc: 0.678 
+
    +
    +
      [============================>-----------] 74.10% | train_error: 5.93 | train_acc: 0.714 | val_error: 6.67 | val_acc: 0.678 
+
    +
    +
      [============================>-----------] 74.20% | train_error: 5.84 | train_acc: 0.718 | val_error: 6.67 | val_acc: 0.678 
+
    +
    +
      [============================>-----------] 74.30% | train_error: 5.84 | train_acc: 0.718 | val_error: 6.67 | val_acc: 0.678 
+
    +
    +
      [============================>-----------] 74.40% | train_error: 5.84 | train_acc: 0.718 | val_error: 6.67 | val_acc: 0.678 
+
    +
    +
      [============================>-----------] 74.50% | train_error: 5.79 | train_acc: 0.721 | val_error: 6.67 | val_acc: 0.678 
+
    +
    +
      [============================>-----------] 74.60% | train_error: 5.64 | train_acc: 0.728 | val_error: 6.67 | val_acc: 0.678 
+
    +
    +
      [============================>-----------] 74.70% | train_error: 5.64 | train_acc: 0.728 | val_error: 6.67 | val_acc: 0.678 
+
    +
    +
      [============================>-----------] 74.80% | train_error: 5.59 | train_acc: 0.730 | val_error: 6.67 | val_acc: 0.678 
+
    +
    +
      [============================>-----------] 74.90% | train_error: 5.59 | train_acc: 0.730 | val_error: 6.38 | val_acc: 0.692 
+
    +
    +
      [=============================>----------] 75.00% | train_error: 5.59 | train_acc: 0.730 | val_error: 6.38 | val_acc: 0.692 
+
    +
    +
      [=============================>----------] 75.10% | train_error: 5.50 | train_acc: 0.735 | val_error: 6.23 | val_acc: 0.699 
+
    +
    +
      [=============================>----------] 75.20% | train_error: 5.30 | train_acc: 0.744 | val_error: 6.23 | val_acc: 0.699 
+
    +
    +
      [=============================>----------] 75.30% | train_error: 5.30 | train_acc: 0.744 | val_error: 6.23 | val_acc: 0.699 
+
    +
    +
      [=============================>----------] 75.40% | train_error: 5.30 | train_acc: 0.744 | val_error: 6.23 | val_acc: 0.699 
+
    +
    +
      [=============================>----------] 75.50% | train_error: 5.16 | train_acc: 0.751 | val_error: 6.23 | val_acc: 0.699 
+
    +
    +
      [=============================>----------] 75.60% | train_error: 5.11 | train_acc: 0.754 | val_error: 6.09 | val_acc: 0.706 
+
    +
    +
      [=============================>----------] 75.70% | train_error: 5.06 | train_acc: 0.756 | val_error: 5.94 | val_acc: 0.713 
+
    +
    +
      [=============================>----------] 75.80% | train_error: 5.06 | train_acc: 0.756 | val_error: 5.94 | val_acc: 0.713 
+
    +
    +
      [=============================>----------] 75.90% | train_error: 5.06 | train_acc: 0.756 | val_error: 5.94 | val_acc: 0.713 
+
    +
    +
      [=============================>----------] 76.00% | train_error: 5.06 | train_acc: 0.756 | val_error: 5.94 | val_acc: 0.713 
+
    +
    +
      [=============================>----------] 76.10% | train_error: 5.01 | train_acc: 0.758 | val_error: 5.94 | val_acc: 0.713 
+
    +
    +
      [=============================>----------] 76.20% | train_error: 5.01 | train_acc: 0.758 | val_error: 5.94 | val_acc: 0.713 
+
    +
    +
      [=============================>----------] 76.30% | train_error: 4.91 | train_acc: 0.763 | val_error: 5.80 | val_acc: 0.720 
+
    +
    +
      [=============================>----------] 76.40% | train_error: 4.91 | train_acc: 0.763 | val_error: 5.80 | val_acc: 0.720 
+
    +
    +
      [=============================>----------] 76.50% | train_error: 4.91 | train_acc: 0.763 | val_error: 5.80 | val_acc: 0.720 
+
    +
    +
      [=============================>----------] 76.60% | train_error: 4.91 | train_acc: 0.763 | val_error: 5.80 | val_acc: 0.720 
+
    +
    +
      [=============================>----------] 76.70% | train_error: 4.91 | train_acc: 0.763 | val_error: 5.80 | val_acc: 0.720 
+
    +
    +
      [=============================>----------] 76.80% | train_error: 4.91 | train_acc: 0.763 | val_error: 5.80 | val_acc: 0.720 
+
    +
    +
      [=============================>----------] 76.90% | train_error: 4.67 | train_acc: 0.775 | val_error: 5.80 | val_acc: 0.720 
+
    +
    +
      [=============================>----------] 77.00% | train_error: 4.67 | train_acc: 0.775 | val_error: 5.80 | val_acc: 0.720 
+
    +
    +
      [=============================>----------] 77.10% | train_error: 4.67 | train_acc: 0.775 | val_error: 5.80 | val_acc: 0.720 
+
    +
    +
      [=============================>----------] 77.20% | train_error: 4.67 | train_acc: 0.775 | val_error: 5.65 | val_acc: 0.727 
+
    +
    +
      [=============================>----------] 77.30% | train_error: 4.67 | train_acc: 0.775 | val_error: 5.65 | val_acc: 0.727 
+
    +
    +
      [=============================>----------] 77.40% | train_error: 4.67 | train_acc: 0.775 | val_error: 5.65 | val_acc: 0.727 
+
    +
    +
      [==============================>---------] 77.50% | train_error: 4.67 | train_acc: 0.775 | val_error: 5.65 | val_acc: 0.727 
+
    +
    +
      [==============================>---------] 77.60% | train_error: 4.67 | train_acc: 0.775 | val_error: 5.65 | val_acc: 0.727 
+
    +
    +
      [==============================>---------] 77.70% | train_error: 4.67 | train_acc: 0.775 | val_error: 5.36 | val_acc: 0.741 
+
    +
    +
      [==============================>---------] 77.80% | train_error: 4.67 | train_acc: 0.775 | val_error: 5.36 | val_acc: 0.741 
+
    +
    +
      [==============================>---------] 77.90% | train_error: 4.67 | train_acc: 0.775 | val_error: 5.36 | val_acc: 0.741 
+
    +
    +
      [==============================>---------] 78.00% | train_error: 4.67 | train_acc: 0.775 | val_error: 5.36 | val_acc: 0.741 
+
    +
    +
      [==============================>---------] 78.10% | train_error: 4.67 | train_acc: 0.775 | val_error: 5.36 | val_acc: 0.741 
+
    +
    +
      [==============================>---------] 78.20% | train_error: 4.62 | train_acc: 0.777 | val_error: 5.36 | val_acc: 0.741 
+
    +
    +
      [==============================>---------] 78.30% | train_error: 4.57 | train_acc: 0.779 | val_error: 5.22 | val_acc: 0.748 
+
    +
    +
      [==============================>---------] 78.40% | train_error: 4.57 | train_acc: 0.779 | val_error: 5.22 | val_acc: 0.748 
+
    +
    +
      [==============================>---------] 78.50% | train_error: 4.57 | train_acc: 0.779 | val_error: 5.22 | val_acc: 0.748 
+
    +
    +
      [==============================>---------] 78.60% | train_error: 4.57 | train_acc: 0.779 | val_error: 5.22 | val_acc: 0.748 
+
    +
    +
      [==============================>---------] 78.70% | train_error: 4.57 | train_acc: 0.779 | val_error: 5.22 | val_acc: 0.748 
+
    +
    +
      [==============================>---------] 78.80% | train_error: 4.57 | train_acc: 0.779 | val_error: 5.22 | val_acc: 0.748 
+
    +
    +
      [==============================>---------] 78.90% | train_error: 4.57 | train_acc: 0.779 | val_error: 5.07 | val_acc: 0.755 
+
    +
    +
      [==============================>---------] 79.00% | train_error: 4.52 | train_acc: 0.782 | val_error: 5.07 | val_acc: 0.755 
+
    +
    +
      [==============================>---------] 79.10% | train_error: 4.52 | train_acc: 0.782 | val_error: 4.93 | val_acc: 0.762 
+
    +
    +
      [==============================>---------] 79.20% | train_error: 4.43 | train_acc: 0.786 | val_error: 4.78 | val_acc: 0.769 
+
    +
    +
      [==============================>---------] 79.30% | train_error: 4.38 | train_acc: 0.789 | val_error: 4.78 | val_acc: 0.769 
+
    +
    +
      [==============================>---------] 79.40% | train_error: 4.13 | train_acc: 0.800 | val_error: 4.78 | val_acc: 0.769 
+
    +
    +
      [==============================>---------] 79.50% | train_error: 4.13 | train_acc: 0.800 | val_error: 4.78 | val_acc: 0.769 
+
    +
    +
      [==============================>---------] 79.60% | train_error: 4.13 | train_acc: 0.800 | val_error: 4.78 | val_acc: 0.769 
+
    +
    +
      [==============================>---------] 79.70% | train_error: 4.09 | train_acc: 0.803 | val_error: 4.78 | val_acc: 0.769 
+
    +
    +
      [==============================>---------] 79.80% | train_error: 4.09 | train_acc: 0.803 | val_error: 4.78 | val_acc: 0.769 
+
    +
    +
      [==============================>---------] 79.90% | train_error: 4.09 | train_acc: 0.803 | val_error: 4.64 | val_acc: 0.776 
+
    +
    +
      [===============================>--------] 80.00% | train_error: 4.09 | train_acc: 0.803 | val_error: 4.64 | val_acc: 0.776 
+
    +
    +
      [===============================>--------] 80.10% | train_error: 4.09 | train_acc: 0.803 | val_error: 4.49 | val_acc: 0.783 
+
    +
    +
      [===============================>--------] 80.20% | train_error: 4.04 | train_acc: 0.805 | val_error: 4.49 | val_acc: 0.783 
+
    +
    +
      [===============================>--------] 80.30% | train_error: 4.09 | train_acc: 0.803 | val_error: 4.49 | val_acc: 0.783 
+
    +
    +
      [===============================>--------] 80.40% | train_error: 4.09 | train_acc: 0.803 | val_error: 4.49 | val_acc: 0.783 
+
    +
    +
      [===============================>--------] 80.50% | train_error: 4.28 | train_acc: 0.793 | val_error: 4.35 | val_acc: 0.790 
+
    +
    +
      [===============================>--------] 80.60% | train_error: 4.28 | train_acc: 0.793 | val_error: 4.35 | val_acc: 0.790 
+
    +
    +
      [===============================>--------] 80.70% | train_error: 4.28 | train_acc: 0.793 | val_error: 4.35 | val_acc: 0.790 
+
    +
    +
      [===============================>--------] 80.80% | train_error: 4.28 | train_acc: 0.793 | val_error: 4.35 | val_acc: 0.790 
+
    +
    +
      [===============================>--------] 80.90% | train_error: 4.28 | train_acc: 0.793 | val_error: 4.35 | val_acc: 0.790 
+
    +
    +
      [===============================>--------] 81.00% | train_error: 4.28 | train_acc: 0.793 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [===============================>--------] 81.10% | train_error: 4.28 | train_acc: 0.793 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [===============================>--------] 81.20% | train_error: 4.28 | train_acc: 0.793 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [===============================>--------] 81.30% | train_error: 4.28 | train_acc: 0.793 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [===============================>--------] 81.40% | train_error: 4.28 | train_acc: 0.793 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [===============================>--------] 81.50% | train_error: 4.28 | train_acc: 0.793 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [===============================>--------] 81.60% | train_error: 4.28 | train_acc: 0.793 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [===============================>--------] 81.70% | train_error: 4.28 | train_acc: 0.793 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [===============================>--------] 81.80% | train_error: 4.28 | train_acc: 0.793 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [===============================>--------] 81.90% | train_error: 4.28 | train_acc: 0.793 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [===============================>--------] 82.00% | train_error: 4.28 | train_acc: 0.793 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [===============================>--------] 82.10% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [===============================>--------] 82.20% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [===============================>--------] 82.30% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [===============================>--------] 82.40% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [================================>-------] 82.50% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [================================>-------] 82.60% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [================================>-------] 82.70% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [================================>-------] 82.80% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [================================>-------] 82.90% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [================================>-------] 83.00% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [================================>-------] 83.10% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [================================>-------] 83.20% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [================================>-------] 83.30% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [================================>-------] 83.40% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [================================>-------] 83.50% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [================================>-------] 83.60% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [================================>-------] 83.70% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [================================>-------] 83.80% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [================================>-------] 83.90% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [================================>-------] 84.00% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [================================>-------] 84.10% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [================================>-------] 84.20% | train_error: 4.33 | train_acc: 0.791 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [================================>-------] 84.30% | train_error: 4.33 | train_acc: 0.791 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [================================>-------] 84.40% | train_error: 4.33 | train_acc: 0.791 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [================================>-------] 84.50% | train_error: 4.33 | train_acc: 0.791 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [================================>-------] 84.60% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [================================>-------] 84.70% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [================================>-------] 84.80% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [================================>-------] 84.90% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [=================================>------] 85.00% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [=================================>------] 85.10% | train_error: 4.23 | train_acc: 0.796 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [=================================>------] 85.20% | train_error: 4.18 | train_acc: 0.798 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [=================================>------] 85.30% | train_error: 4.18 | train_acc: 0.798 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [=================================>------] 85.40% | train_error: 4.18 | train_acc: 0.798 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [=================================>------] 85.50% | train_error: 4.18 | train_acc: 0.798 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [=================================>------] 85.60% | train_error: 4.13 | train_acc: 0.800 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [=================================>------] 85.70% | train_error: 4.13 | train_acc: 0.800 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [=================================>------] 85.80% | train_error: 4.09 | train_acc: 0.803 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [=================================>------] 85.90% | train_error: 4.09 | train_acc: 0.803 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [=================================>------] 86.00% | train_error: 4.09 | train_acc: 0.803 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [=================================>------] 86.10% | train_error: 4.09 | train_acc: 0.803 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [=================================>------] 86.20% | train_error: 4.09 | train_acc: 0.803 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [=================================>------] 86.30% | train_error: 4.09 | train_acc: 0.803 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [=================================>------] 86.40% | train_error: 4.09 | train_acc: 0.803 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [=================================>------] 86.50% | train_error: 4.09 | train_acc: 0.803 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [=================================>------] 86.60% | train_error: 4.04 | train_acc: 0.805 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [=================================>------] 86.70% | train_error: 4.04 | train_acc: 0.805 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [=================================>------] 86.80% | train_error: 4.04 | train_acc: 0.805 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [=================================>------] 86.90% | train_error: 3.99 | train_acc: 0.808 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [=================================>------] 87.00% | train_error: 3.89 | train_acc: 0.812 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [=================================>------] 87.10% | train_error: 3.89 | train_acc: 0.812 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [=================================>------] 87.20% | train_error: 3.89 | train_acc: 0.812 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [=================================>------] 87.30% | train_error: 3.89 | train_acc: 0.812 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [=================================>------] 87.40% | train_error: 3.79 | train_acc: 0.817 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [==================================>-----] 87.50% | train_error: 3.79 | train_acc: 0.817 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [==================================>-----] 87.60% | train_error: 3.89 | train_acc: 0.812 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [==================================>-----] 87.70% | train_error: 3.84 | train_acc: 0.815 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [==================================>-----] 87.80% | train_error: 3.84 | train_acc: 0.815 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [==================================>-----] 87.90% | train_error: 3.84 | train_acc: 0.815 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [==================================>-----] 88.00% | train_error: 3.84 | train_acc: 0.815 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [==================================>-----] 88.10% | train_error: 3.84 | train_acc: 0.815 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [==================================>-----] 88.20% | train_error: 3.84 | train_acc: 0.815 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [==================================>-----] 88.30% | train_error: 3.84 | train_acc: 0.815 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [==================================>-----] 88.40% | train_error: 3.84 | train_acc: 0.815 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [==================================>-----] 88.50% | train_error: 3.70 | train_acc: 0.822 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [==================================>-----] 88.60% | train_error: 3.70 | train_acc: 0.822 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [==================================>-----] 88.70% | train_error: 3.70 | train_acc: 0.822 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [==================================>-----] 88.80% | train_error: 3.70 | train_acc: 0.822 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [==================================>-----] 88.90% | train_error: 3.70 | train_acc: 0.822 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [==================================>-----] 89.00% | train_error: 3.70 | train_acc: 0.822 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [==================================>-----] 89.10% | train_error: 3.70 | train_acc: 0.822 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [==================================>-----] 89.20% | train_error: 3.70 | train_acc: 0.822 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [==================================>-----] 89.30% | train_error: 3.70 | train_acc: 0.822 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [==================================>-----] 89.40% | train_error: 3.70 | train_acc: 0.822 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [==================================>-----] 89.50% | train_error: 3.70 | train_acc: 0.822 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [==================================>-----] 89.60% | train_error: 3.70 | train_acc: 0.822 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [==================================>-----] 89.70% | train_error: 3.70 | train_acc: 0.822 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [==================================>-----] 89.80% | train_error: 3.65 | train_acc: 0.824 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [==================================>-----] 89.90% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [===================================>----] 90.00% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [===================================>----] 90.10% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [===================================>----] 90.20% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [===================================>----] 90.30% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [===================================>----] 90.40% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 90.50% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 90.60% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 90.70% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 90.80% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 90.90% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 91.00% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 91.10% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 91.20% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 91.30% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 91.40% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 91.50% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 91.60% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 91.70% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 91.80% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 91.90% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 92.00% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 92.10% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 92.20% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 92.30% | train_error: 3.60 | train_acc: 0.826 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [===================================>----] 92.40% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 92.50% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 92.60% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 92.70% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 92.80% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 92.90% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 93.00% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 93.10% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 93.20% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 93.30% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 93.40% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 93.50% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 93.60% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 93.70% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 93.80% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 93.90% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 94.00% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 94.10% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 94.20% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 94.30% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 94.40% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 94.50% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 94.60% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 94.70% | train_error: 3.65 | train_acc: 0.824 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 94.80% | train_error: 3.65 | train_acc: 0.824 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [====================================>---] 94.90% | train_error: 3.65 | train_acc: 0.824 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [=====================================>--] 95.00% | train_error: 3.65 | train_acc: 0.824 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [=====================================>--] 95.10% | train_error: 3.65 | train_acc: 0.824 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [=====================================>--] 95.20% | train_error: 3.65 | train_acc: 0.824 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [=====================================>--] 95.30% | train_error: 3.65 | train_acc: 0.824 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [=====================================>--] 95.40% | train_error: 3.65 | train_acc: 0.824 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [=====================================>--] 95.50% | train_error: 3.65 | train_acc: 0.824 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [=====================================>--] 95.60% | train_error: 3.65 | train_acc: 0.824 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 95.70% | train_error: 3.65 | train_acc: 0.824 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 95.80% | train_error: 3.65 | train_acc: 0.824 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 95.90% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 96.00% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 96.10% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 96.20% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 96.30% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 96.40% | train_error: 3.55 | train_acc: 0.829 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 96.50% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 96.60% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 96.70% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 96.80% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 96.90% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 97.00% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 97.10% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 97.20% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 97.30% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [=====================================>--] 97.40% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [======================================>-] 97.50% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [======================================>-] 97.60% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [======================================>-] 97.70% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [======================================>-] 97.80% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [======================================>-] 97.90% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [======================================>-] 98.00% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [======================================>-] 98.10% | train_error: 3.50 | train_acc: 0.831 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [======================================>-] 98.20% | train_error: 3.45 | train_acc: 0.833 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [======================================>-] 98.30% | train_error: 3.45 | train_acc: 0.833 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [======================================>-] 98.40% | train_error: 3.41 | train_acc: 0.836 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [======================================>-] 98.50% | train_error: 3.36 | train_acc: 0.838 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [======================================>-] 98.60% | train_error: 3.26 | train_acc: 0.843 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [======================================>-] 98.70% | train_error: 3.26 | train_acc: 0.843 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [======================================>-] 98.80% | train_error: 3.26 | train_acc: 0.843 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [======================================>-] 98.90% | train_error: 3.26 | train_acc: 0.843 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [======================================>-] 99.00% | train_error: 3.26 | train_acc: 0.843 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [======================================>-] 99.10% | train_error: 3.26 | train_acc: 0.843 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [======================================>-] 99.20% | train_error: 3.26 | train_acc: 0.843 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [======================================>-] 99.30% | train_error: 3.26 | train_acc: 0.843 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [======================================>-] 99.40% | train_error: 3.26 | train_acc: 0.843 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [======================================>-] 99.50% | train_error: 3.26 | train_acc: 0.843 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [======================================>-] 99.60% | train_error: 3.26 | train_acc: 0.843 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [======================================>-] 99.70% | train_error: 3.26 | train_acc: 0.843 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [======================================>-] 99.80% | train_error: 3.26 | train_acc: 0.843 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [======================================>-] 99.90% | train_error: 3.21 | train_acc: 0.845 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
                                                                                                                                  
+
    +
    +
      [=======================================>] 100.0% | train_error: 3.21 | train_acc: 0.845 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
    +
    +

    Finally, we will create a neural network with 2 hidden layers with activation functions.

    +
    +
    +
    input_nodes = X_train.shape[1]
+hidden_nodes1 = 100
+hidden_nodes2 = 30
+output_nodes = 1
+
+dims = (input_nodes, hidden_nodes1, hidden_nodes2, output_nodes)
+
+neural_network = FFNN(dims, hidden_func=RELU, output_func=sigmoid, cost_func=CostLogReg, seed=2023)
+
    +
    +
    +
    +
    +
    +
    neural_network.reset_weights() # reset weights such that previous runs or reruns don't affect the weights
+
+scheduler = Adam(eta=1e-4, rho=0.9, rho2=0.999)
+scores = neural_network.fit(X_train, t_train, scheduler, epochs=1000, X_val=X_val, t_val=t_val)
+
    +
    +
    +
    +
    Adam: Eta=0.0001, Lambda=0
+
    +
    +
      [----------------------------------------] 0.000% | train_error: 11.3 | train_acc: 0.453 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [----------------------------------------] 0.1000% | train_error: 11.4 | train_acc: 0.448 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [----------------------------------------] 0.2000% | train_error: 11.4 | train_acc: 0.448 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [----------------------------------------] 0.3000% | train_error: 11.4 | train_acc: 0.448 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [----------------------------------------] 0.4000% | train_error: 11.4 | train_acc: 0.448 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [----------------------------------------] 0.5000% | train_error: 11.4 | train_acc: 0.448 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [----------------------------------------] 0.6000% | train_error: 11.4 | train_acc: 0.448 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [----------------------------------------] 0.7000% | train_error: 11.5 | train_acc: 0.444 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [----------------------------------------] 0.8000% | train_error: 11.5 | train_acc: 0.444 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [----------------------------------------] 0.9000% | train_error: 11.3 | train_acc: 0.453 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [----------------------------------------] 1.000% | train_error: 11.3 | train_acc: 0.453 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [----------------------------------------] 1.100% | train_error: 11.3 | train_acc: 0.453 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [----------------------------------------] 1.200% | train_error: 11.3 | train_acc: 0.453 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [----------------------------------------] 1.300% | train_error: 11.3 | train_acc: 0.453 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [----------------------------------------] 1.400% | train_error: 11.4 | train_acc: 0.448 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [----------------------------------------] 1.500% | train_error: 11.4 | train_acc: 0.451 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [----------------------------------------] 1.600% | train_error: 11.5 | train_acc: 0.444 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [----------------------------------------] 1.700% | train_error: 11.5 | train_acc: 0.444 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [----------------------------------------] 1.800% | train_error: 11.6 | train_acc: 0.441 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [----------------------------------------] 1.900% | train_error: 11.6 | train_acc: 0.441 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [----------------------------------------] 2.000% | train_error: 11.6 | train_acc: 0.441 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [----------------------------------------] 2.100% | train_error: 11.6 | train_acc: 0.439 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [----------------------------------------] 2.200% | train_error: 11.6 | train_acc: 0.439 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [----------------------------------------] 2.300% | train_error: 11.8 | train_acc: 0.430 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [----------------------------------------] 2.400% | train_error: 11.9 | train_acc: 0.425 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [>---------------------------------------] 2.500% | train_error: 11.9 | train_acc: 0.425 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [>---------------------------------------] 2.600% | train_error: 11.9 | train_acc: 0.427 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [>---------------------------------------] 2.700% | train_error: 11.9 | train_acc: 0.427 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [>---------------------------------------] 2.800% | train_error: 11.9 | train_acc: 0.427 | val_error: 10.7 | val_acc: 0.483 
+
    +
    +
      [>---------------------------------------] 2.900% | train_error: 11.9 | train_acc: 0.427 | val_error: 10.7 | val_acc: 0.483 
+
    +
    +
      [>---------------------------------------] 3.000% | train_error: 11.9 | train_acc: 0.427 | val_error: 10.7 | val_acc: 0.483 
+
    +
    +
      [>---------------------------------------] 3.100% | train_error: 11.9 | train_acc: 0.427 | val_error: 10.7 | val_acc: 0.483 
+
    +
    +
      [>---------------------------------------] 3.200% | train_error: 11.9 | train_acc: 0.427 | val_error: 10.7 | val_acc: 0.483 
+
    +
    +
      [>---------------------------------------] 3.300% | train_error: 11.9 | train_acc: 0.425 | val_error: 10.9 | val_acc: 0.476 
+
    +
    +
      [>---------------------------------------] 3.400% | train_error: 11.9 | train_acc: 0.427 | val_error: 10.9 | val_acc: 0.476 
+
    +
    +
      [>---------------------------------------] 3.500% | train_error: 11.9 | train_acc: 0.427 | val_error: 11.0 | val_acc: 0.469 
+
    +
    +
      [>---------------------------------------] 3.600% | train_error: 11.8 | train_acc: 0.432 | val_error: 11.0 | val_acc: 0.469 
+
    +
    +
      [>---------------------------------------] 3.700% | train_error: 11.6 | train_acc: 0.439 | val_error: 11.0 | val_acc: 0.469 
+
    +
    +
      [>---------------------------------------] 3.800% | train_error: 11.6 | train_acc: 0.439 | val_error: 11.0 | val_acc: 0.469 
+
    +
    +
      [>---------------------------------------] 3.900% | train_error: 11.7 | train_acc: 0.434 | val_error: 11.3 | val_acc: 0.455 
+
    +
    +
      [>---------------------------------------] 4.000% | train_error: 11.7 | train_acc: 0.434 | val_error: 11.3 | val_acc: 0.455 
+
    +
    +
      [>---------------------------------------] 4.100% | train_error: 11.8 | train_acc: 0.430 | val_error: 11.2 | val_acc: 0.462 
+
    +
    +
      [>---------------------------------------] 4.200% | train_error: 11.9 | train_acc: 0.425 | val_error: 11.2 | val_acc: 0.462 
+
    +
    +
      [>---------------------------------------] 4.300% | train_error: 12.0 | train_acc: 0.423 | val_error: 11.2 | val_acc: 0.462 
+
    +
    +
      [>---------------------------------------] 4.400% | train_error: 11.9 | train_acc: 0.427 | val_error: 11.2 | val_acc: 0.462 
+
    +
    +
      [>---------------------------------------] 4.500% | train_error: 11.8 | train_acc: 0.430 | val_error: 11.2 | val_acc: 0.462 
+
    +
    +
      [>---------------------------------------] 4.600% | train_error: 11.8 | train_acc: 0.432 | val_error: 11.2 | val_acc: 0.462 
+
    +
    +
      [>---------------------------------------] 4.700% | train_error: 11.8 | train_acc: 0.430 | val_error: 11.3 | val_acc: 0.455 
+
    +
    +
      [>---------------------------------------] 4.800% | train_error: 11.7 | train_acc: 0.434 | val_error: 11.3 | val_acc: 0.455 
+
    +
    +
      [>---------------------------------------] 4.900% | train_error: 11.5 | train_acc: 0.446 | val_error: 11.3 | val_acc: 0.455 
+
    +
    +
      [=>--------------------------------------] 5.000% | train_error: 11.5 | train_acc: 0.446 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [=>--------------------------------------] 5.100% | train_error: 11.5 | train_acc: 0.446 | val_error: 11.3 | val_acc: 0.455 
+
    +
    +
      [=>--------------------------------------] 5.200% | train_error: 11.5 | train_acc: 0.446 | val_error: 11.2 | val_acc: 0.462 
+
    +
    +
      [=>--------------------------------------] 5.300% | train_error: 11.5 | train_acc: 0.444 | val_error: 11.0 | val_acc: 0.469 
+
    +
    +
      [=>--------------------------------------] 5.400% | train_error: 11.5 | train_acc: 0.444 | val_error: 11.0 | val_acc: 0.469 
+
    +
    +
      [=>--------------------------------------] 5.500% | train_error: 11.5 | train_acc: 0.444 | val_error: 11.0 | val_acc: 0.469 
+
    +
    +
      [=>--------------------------------------] 5.600% | train_error: 11.5 | train_acc: 0.444 | val_error: 11.3 | val_acc: 0.455 
+
    +
    +
      [=>--------------------------------------] 5.700% | train_error: 11.5 | train_acc: 0.444 | val_error: 11.3 | val_acc: 0.455 
+
    +
    +
      [=>--------------------------------------] 5.800% | train_error: 11.9 | train_acc: 0.425 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [=>--------------------------------------] 5.900% | train_error: 11.9 | train_acc: 0.425 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [=>--------------------------------------] 6.000% | train_error: 12.0 | train_acc: 0.420 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [=>--------------------------------------] 6.100% | train_error: 12.0 | train_acc: 0.420 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [=>--------------------------------------] 6.200% | train_error: 12.1 | train_acc: 0.418 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [=>--------------------------------------] 6.300% | train_error: 12.1 | train_acc: 0.418 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [=>--------------------------------------] 6.400% | train_error: 11.9 | train_acc: 0.425 | val_error: 11.7 | val_acc: 0.434 
+
    +
    +
      [=>--------------------------------------] 6.500% | train_error: 11.9 | train_acc: 0.427 | val_error: 11.9 | val_acc: 0.427 
+
    +
    +
      [=>--------------------------------------] 6.600% | train_error: 11.8 | train_acc: 0.432 | val_error: 12.0 | val_acc: 0.420 
+
    +
    +
      [=>--------------------------------------] 6.700% | train_error: 11.5 | train_acc: 0.444 | val_error: 12.2 | val_acc: 0.413 
+
    +
    +
      [=>--------------------------------------] 6.800% | train_error: 11.4 | train_acc: 0.448 | val_error: 12.3 | val_acc: 0.406 
+
    +
    +
      [=>--------------------------------------] 6.900% | train_error: 11.2 | train_acc: 0.458 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [=>--------------------------------------] 7.000% | train_error: 11.2 | train_acc: 0.458 | val_error: 12.3 | val_acc: 0.406 
+
    +
    +
      [=>--------------------------------------] 7.100% | train_error: 11.3 | train_acc: 0.455 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [=>--------------------------------------] 7.200% | train_error: 11.3 | train_acc: 0.455 | val_error: 12.6 | val_acc: 0.392 
+
    +
    +
      [=>--------------------------------------] 7.300% | train_error: 11.3 | train_acc: 0.455 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [=>--------------------------------------] 7.400% | train_error: 11.3 | train_acc: 0.453 | val_error: 12.3 | val_acc: 0.406 
+
    +
    +
      [==>-------------------------------------] 7.500% | train_error: 11.3 | train_acc: 0.455 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [==>-------------------------------------] 7.600% | train_error: 11.5 | train_acc: 0.446 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [==>-------------------------------------] 7.700% | train_error: 11.3 | train_acc: 0.453 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [==>-------------------------------------] 7.800% | train_error: 11.4 | train_acc: 0.448 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [==>-------------------------------------] 7.900% | train_error: 11.4 | train_acc: 0.448 | val_error: 12.3 | val_acc: 0.406 
+
    +
    +
      [==>-------------------------------------] 8.000% | train_error: 11.4 | train_acc: 0.451 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [==>-------------------------------------] 8.100% | train_error: 11.4 | train_acc: 0.448 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [==>-------------------------------------] 8.200% | train_error: 11.3 | train_acc: 0.453 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [==>-------------------------------------] 8.300% | train_error: 11.3 | train_acc: 0.453 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [==>-------------------------------------] 8.400% | train_error: 11.4 | train_acc: 0.451 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [==>-------------------------------------] 8.500% | train_error: 11.4 | train_acc: 0.451 | val_error: 12.5 | val_acc: 0.399 
+
    +
    +
      [==>-------------------------------------] 8.600% | train_error: 11.4 | train_acc: 0.451 | val_error: 12.3 | val_acc: 0.406 
+
    +
    +
      [==>-------------------------------------] 8.700% | train_error: 11.2 | train_acc: 0.458 | val_error: 12.3 | val_acc: 0.406 
+
    +
    +
      [==>-------------------------------------] 8.800% | train_error: 11.2 | train_acc: 0.458 | val_error: 12.2 | val_acc: 0.413 
+
    +
    +
      [==>-------------------------------------] 8.900% | train_error: 11.2 | train_acc: 0.458 | val_error: 12.0 | val_acc: 0.420 
+
    +
    +
      [==>-------------------------------------] 9.000% | train_error: 11.2 | train_acc: 0.458 | val_error: 12.0 | val_acc: 0.420 
+
    +
    +
      [==>-------------------------------------] 9.100% | train_error: 11.2 | train_acc: 0.458 | val_error: 11.9 | val_acc: 0.427 
+
    +
    +
      [==>-------------------------------------] 9.200% | train_error: 11.2 | train_acc: 0.458 | val_error: 11.9 | val_acc: 0.427 
+
    +
    +
      [==>-------------------------------------] 9.300% | train_error: 11.2 | train_acc: 0.460 | val_error: 11.9 | val_acc: 0.427 
+
    +
    +
      [==>-------------------------------------] 9.400% | train_error: 11.0 | train_acc: 0.469 | val_error: 11.9 | val_acc: 0.427 
+
    +
    +
      [==>-------------------------------------] 9.500% | train_error: 11.0 | train_acc: 0.469 | val_error: 11.9 | val_acc: 0.427 
+
    +
    +
      [==>-------------------------------------] 9.600% | train_error: 10.8 | train_acc: 0.479 | val_error: 11.9 | val_acc: 0.427 
+
    +
    +
      [==>-------------------------------------] 9.700% | train_error: 10.7 | train_acc: 0.484 | val_error: 11.7 | val_acc: 0.434 
+
    +
    +
      [==>-------------------------------------] 9.800% | train_error: 10.7 | train_acc: 0.484 | val_error: 11.7 | val_acc: 0.434 
+
    +
    +
      [==>-------------------------------------] 9.900% | train_error: 10.7 | train_acc: 0.484 | val_error: 11.7 | val_acc: 0.434 
+
    +
    +
      [===>------------------------------------] 10.00% | train_error: 10.7 | train_acc: 0.484 | val_error: 11.7 | val_acc: 0.434 
+
    +
    +
      [===>------------------------------------] 10.10% | train_error: 10.7 | train_acc: 0.486 | val_error: 11.7 | val_acc: 0.434 
+
    +
    +
      [===>------------------------------------] 10.20% | train_error: 10.7 | train_acc: 0.486 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [===>------------------------------------] 10.30% | train_error: 10.7 | train_acc: 0.486 | val_error: 11.6 | val_acc: 0.441 
+
    +
    +
      [===>------------------------------------] 10.40% | train_error: 10.7 | train_acc: 0.486 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [===>------------------------------------] 10.50% | train_error: 10.4 | train_acc: 0.500 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [===>------------------------------------] 10.60% | train_error: 10.4 | train_acc: 0.500 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [===>------------------------------------] 10.70% | train_error: 10.4 | train_acc: 0.500 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [===>------------------------------------] 10.80% | train_error: 10.4 | train_acc: 0.500 | val_error: 11.4 | val_acc: 0.448 
+
    +
    +
      [===>------------------------------------] 10.90% | train_error: 10.2 | train_acc: 0.507 | val_error: 11.3 | val_acc: 0.455 
+
    +
    +
      [===>------------------------------------] 11.00% | train_error: 9.83 | train_acc: 0.526 | val_error: 11.3 | val_acc: 0.455 
+
    +
    +
      [===>------------------------------------] 11.10% | train_error: 9.83 | train_acc: 0.526 | val_error: 11.3 | val_acc: 0.455 
+
    +
    +
      [===>------------------------------------] 11.20% | train_error: 9.83 | train_acc: 0.526 | val_error: 11.3 | val_acc: 0.455 
+
    +
    +
      [===>------------------------------------] 11.30% | train_error: 9.83 | train_acc: 0.526 | val_error: 11.2 | val_acc: 0.462 
+
    +
    +
      [===>------------------------------------] 11.40% | train_error: 9.83 | train_acc: 0.526 | val_error: 11.2 | val_acc: 0.462 
+
    +
    +
      [===>------------------------------------] 11.50% | train_error: 9.83 | train_acc: 0.526 | val_error: 11.2 | val_acc: 0.462 
+
    +
    +
      [===>------------------------------------] 11.60% | train_error: 9.83 | train_acc: 0.526 | val_error: 11.2 | val_acc: 0.462 
+
    +
    +
      [===>------------------------------------] 11.70% | train_error: 9.73 | train_acc: 0.531 | val_error: 11.2 | val_acc: 0.462 
+
    +
    +
      [===>------------------------------------] 11.80% | train_error: 9.63 | train_acc: 0.535 | val_error: 11.2 | val_acc: 0.462 
+
    +
    +
      [===>------------------------------------] 11.90% | train_error: 9.63 | train_acc: 0.535 | val_error: 11.2 | val_acc: 0.462 
+
    +
    +
      [===>------------------------------------] 12.00% | train_error: 9.53 | train_acc: 0.540 | val_error: 10.9 | val_acc: 0.476 
+
    +
    +
      [===>------------------------------------] 12.10% | train_error: 9.53 | train_acc: 0.540 | val_error: 10.9 | val_acc: 0.476 
+
    +
    +
      [===>------------------------------------] 12.20% | train_error: 9.49 | train_acc: 0.542 | val_error: 10.9 | val_acc: 0.476 
+
    +
    +
      [===>------------------------------------] 12.30% | train_error: 9.49 | train_acc: 0.542 | val_error: 10.9 | val_acc: 0.476 
+
    +
    +
      [===>------------------------------------] 12.40% | train_error: 9.44 | train_acc: 0.545 | val_error: 10.9 | val_acc: 0.476 
+
    +
    +
      [====>-----------------------------------] 12.50% | train_error: 9.44 | train_acc: 0.545 | val_error: 10.9 | val_acc: 0.476 
+
    +
    +
      [====>-----------------------------------] 12.60% | train_error: 9.39 | train_acc: 0.547 | val_error: 10.9 | val_acc: 0.476 
+
    +
    +
      [====>-----------------------------------] 12.70% | train_error: 9.39 | train_acc: 0.547 | val_error: 10.7 | val_acc: 0.483 
+
    +
    +
      [====>-----------------------------------] 12.80% | train_error: 9.39 | train_acc: 0.547 | val_error: 10.7 | val_acc: 0.483 
+
    +
    +
      [====>-----------------------------------] 12.90% | train_error: 9.34 | train_acc: 0.549 | val_error: 10.7 | val_acc: 0.483 
+
    +
    +
      [====>-----------------------------------] 13.00% | train_error: 9.10 | train_acc: 0.561 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [====>-----------------------------------] 13.10% | train_error: 9.05 | train_acc: 0.563 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [====>-----------------------------------] 13.20% | train_error: 9.05 | train_acc: 0.563 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [====>-----------------------------------] 13.30% | train_error: 8.80 | train_acc: 0.575 | val_error: 10.6 | val_acc: 0.490 
+
    +
    +
      [====>-----------------------------------] 13.40% | train_error: 8.76 | train_acc: 0.577 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [====>-----------------------------------] 13.50% | train_error: 8.56 | train_acc: 0.587 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [====>-----------------------------------] 13.60% | train_error: 8.56 | train_acc: 0.587 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [====>-----------------------------------] 13.70% | train_error: 8.42 | train_acc: 0.594 | val_error: 10.4 | val_acc: 0.497 
+
    +
    +
      [====>-----------------------------------] 13.80% | train_error: 8.42 | train_acc: 0.594 | val_error: 10.3 | val_acc: 0.503 
+
    +
    +
      [====>-----------------------------------] 13.90% | train_error: 8.42 | train_acc: 0.594 | val_error: 10.1 | val_acc: 0.510 
+
    +
    +
      [====>-----------------------------------] 14.00% | train_error: 8.42 | train_acc: 0.594 | val_error: 10.1 | val_acc: 0.510 
+
    +
    +
      [====>-----------------------------------] 14.10% | train_error: 8.32 | train_acc: 0.599 | val_error: 10.1 | val_acc: 0.510 
+
    +
    +
      [====>-----------------------------------] 14.20% | train_error: 8.32 | train_acc: 0.599 | val_error: 10.1 | val_acc: 0.510 
+
    +
    +
      [====>-----------------------------------] 14.30% | train_error: 8.22 | train_acc: 0.603 | val_error: 10.1 | val_acc: 0.510 
+
    +
    +
      [====>-----------------------------------] 14.40% | train_error: 8.22 | train_acc: 0.603 | val_error: 10.1 | val_acc: 0.510 
+
    +
    +
      [====>-----------------------------------] 14.50% | train_error: 8.22 | train_acc: 0.603 | val_error: 10.1 | val_acc: 0.510 
+
    +
    +
      [====>-----------------------------------] 14.60% | train_error: 8.22 | train_acc: 0.603 | val_error: 10.1 | val_acc: 0.510 
+
    +
    +
      [====>-----------------------------------] 14.70% | train_error: 8.17 | train_acc: 0.606 | val_error: 10.1 | val_acc: 0.510 
+
    +
    +
      [====>-----------------------------------] 14.80% | train_error: 8.17 | train_acc: 0.606 | val_error: 10.1 | val_acc: 0.510 
+
    +
    +
      [====>-----------------------------------] 14.90% | train_error: 8.17 | train_acc: 0.606 | val_error: 10.1 | val_acc: 0.510 
+
    +
    +
      [=====>----------------------------------] 15.00% | train_error: 8.08 | train_acc: 0.610 | val_error: 9.85 | val_acc: 0.524 
+
    +
    +
      [=====>----------------------------------] 15.10% | train_error: 7.98 | train_acc: 0.615 | val_error: 9.71 | val_acc: 0.531 
+
    +
    +
      [=====>----------------------------------] 15.20% | train_error: 7.93 | train_acc: 0.617 | val_error: 9.71 | val_acc: 0.531 
+
    +
    +
      [=====>----------------------------------] 15.30% | train_error: 7.93 | train_acc: 0.617 | val_error: 9.71 | val_acc: 0.531 
+
    +
    +
      [=====>----------------------------------] 15.40% | train_error: 7.93 | train_acc: 0.617 | val_error: 9.71 | val_acc: 0.531 
+
    +
    +
      [=====>----------------------------------] 15.50% | train_error: 7.93 | train_acc: 0.617 | val_error: 9.71 | val_acc: 0.531 
+
    +
    +
      [=====>----------------------------------] 15.60% | train_error: 7.93 | train_acc: 0.617 | val_error: 9.71 | val_acc: 0.531 
+
    +
    +
      [=====>----------------------------------] 15.70% | train_error: 7.93 | train_acc: 0.617 | val_error: 9.71 | val_acc: 0.531 
+
    +
    +
      [=====>----------------------------------] 15.80% | train_error: 7.93 | train_acc: 0.617 | val_error: 9.56 | val_acc: 0.538 
+
    +
    +
      [=====>----------------------------------] 15.90% | train_error: 7.93 | train_acc: 0.617 | val_error: 9.27 | val_acc: 0.552 
+
    +
    +
      [=====>----------------------------------] 16.00% | train_error: 7.93 | train_acc: 0.617 | val_error: 9.27 | val_acc: 0.552 
+
    +
    +
      [=====>----------------------------------] 16.10% | train_error: 7.93 | train_acc: 0.617 | val_error: 9.27 | val_acc: 0.552 
+
    +
    +
      [=====>----------------------------------] 16.20% | train_error: 7.88 | train_acc: 0.620 | val_error: 9.27 | val_acc: 0.552 
+
    +
    +
      [=====>----------------------------------] 16.30% | train_error: 7.69 | train_acc: 0.629 | val_error: 9.27 | val_acc: 0.552 
+
    +
    +
      [=====>----------------------------------] 16.40% | train_error: 7.69 | train_acc: 0.629 | val_error: 9.13 | val_acc: 0.559 
+
    +
    +
      [=====>----------------------------------] 16.50% | train_error: 7.69 | train_acc: 0.629 | val_error: 9.13 | val_acc: 0.559 
+
    +
    +
      [=====>----------------------------------] 16.60% | train_error: 7.69 | train_acc: 0.629 | val_error: 9.13 | val_acc: 0.559 
+
    +
    +
      [=====>----------------------------------] 16.70% | train_error: 7.69 | train_acc: 0.629 | val_error: 8.98 | val_acc: 0.566 
+
    +
    +
      [=====>----------------------------------] 16.80% | train_error: 7.59 | train_acc: 0.634 | val_error: 8.84 | val_acc: 0.573 
+
    +
    +
      [=====>----------------------------------] 16.90% | train_error: 7.49 | train_acc: 0.638 | val_error: 8.84 | val_acc: 0.573 
+
    +
    +
      [=====>----------------------------------] 17.00% | train_error: 7.39 | train_acc: 0.643 | val_error: 8.70 | val_acc: 0.580 
+
    +
    +
      [=====>----------------------------------] 17.10% | train_error: 7.39 | train_acc: 0.643 | val_error: 8.55 | val_acc: 0.587 
+
    +
    +
      [=====>----------------------------------] 17.20% | train_error: 7.30 | train_acc: 0.648 | val_error: 8.41 | val_acc: 0.594 
+
    +
    +
      [=====>----------------------------------] 17.30% | train_error: 7.30 | train_acc: 0.648 | val_error: 8.26 | val_acc: 0.601 
+
    +
    +
      [=====>----------------------------------] 17.40% | train_error: 7.15 | train_acc: 0.655 | val_error: 8.26 | val_acc: 0.601 
+
    +
    +
      [======>---------------------------------] 17.50% | train_error: 7.05 | train_acc: 0.660 | val_error: 8.12 | val_acc: 0.608 
+
    +
    +
      [======>---------------------------------] 17.60% | train_error: 7.05 | train_acc: 0.660 | val_error: 7.97 | val_acc: 0.615 
+
    +
    +
      [======>---------------------------------] 17.70% | train_error: 6.91 | train_acc: 0.667 | val_error: 7.97 | val_acc: 0.615 
+
    +
    +
      [======>---------------------------------] 17.80% | train_error: 6.86 | train_acc: 0.669 | val_error: 7.83 | val_acc: 0.622 
+
    +
    +
      [======>---------------------------------] 17.90% | train_error: 6.86 | train_acc: 0.669 | val_error: 7.83 | val_acc: 0.622 
+
    +
    +
      [======>---------------------------------] 18.00% | train_error: 6.86 | train_acc: 0.669 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [======>---------------------------------] 18.10% | train_error: 6.76 | train_acc: 0.674 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [======>---------------------------------] 18.20% | train_error: 6.76 | train_acc: 0.674 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [======>---------------------------------] 18.30% | train_error: 6.62 | train_acc: 0.681 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [======>---------------------------------] 18.40% | train_error: 6.57 | train_acc: 0.683 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [======>---------------------------------] 18.50% | train_error: 6.47 | train_acc: 0.688 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [======>---------------------------------] 18.60% | train_error: 6.47 | train_acc: 0.688 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [======>---------------------------------] 18.70% | train_error: 6.37 | train_acc: 0.692 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [======>---------------------------------] 18.80% | train_error: 6.32 | train_acc: 0.695 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [======>---------------------------------] 18.90% | train_error: 6.28 | train_acc: 0.697 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [======>---------------------------------] 19.00% | train_error: 6.28 | train_acc: 0.697 | val_error: 7.54 | val_acc: 0.636 
+
    +
    +
      [======>---------------------------------] 19.10% | train_error: 6.28 | train_acc: 0.697 | val_error: 7.39 | val_acc: 0.643 
+
    +
    +
      [======>---------------------------------] 19.20% | train_error: 6.28 | train_acc: 0.697 | val_error: 7.39 | val_acc: 0.643 
+
    +
    +
      [======>---------------------------------] 19.30% | train_error: 6.28 | train_acc: 0.697 | val_error: 7.10 | val_acc: 0.657 
+
    +
    +
      [======>---------------------------------] 19.40% | train_error: 6.18 | train_acc: 0.702 | val_error: 7.10 | val_acc: 0.657 
+
    +
    +
      [======>---------------------------------] 19.50% | train_error: 6.18 | train_acc: 0.702 | val_error: 6.81 | val_acc: 0.671 
+
    +
    +
      [======>---------------------------------] 19.60% | train_error: 6.13 | train_acc: 0.704 | val_error: 6.81 | val_acc: 0.671 
+
    +
    +
      [======>---------------------------------] 19.70% | train_error: 6.13 | train_acc: 0.704 | val_error: 6.67 | val_acc: 0.678 
+
    +
    +
      [======>---------------------------------] 19.80% | train_error: 6.13 | train_acc: 0.704 | val_error: 6.52 | val_acc: 0.685 
+
    +
    +
      [======>---------------------------------] 19.90% | train_error: 6.13 | train_acc: 0.704 | val_error: 6.52 | val_acc: 0.685 
+
    +
    +
      [=======>--------------------------------] 20.00% | train_error: 6.13 | train_acc: 0.704 | val_error: 6.52 | val_acc: 0.685 
+
    +
    +
      [=======>--------------------------------] 20.10% | train_error: 6.08 | train_acc: 0.707 | val_error: 6.38 | val_acc: 0.692 
+
    +
    +
      [=======>--------------------------------] 20.20% | train_error: 6.03 | train_acc: 0.709 | val_error: 6.52 | val_acc: 0.685 
+
    +
    +
      [=======>--------------------------------] 20.30% | train_error: 5.64 | train_acc: 0.728 | val_error: 6.52 | val_acc: 0.685 
+
    +
    +
      [=======>--------------------------------] 20.40% | train_error: 5.69 | train_acc: 0.725 | val_error: 6.52 | val_acc: 0.685 
+
    +
    +
      [=======>--------------------------------] 20.50% | train_error: 5.69 | train_acc: 0.725 | val_error: 6.52 | val_acc: 0.685 
+
    +
    +
      [=======>--------------------------------] 20.60% | train_error: 5.59 | train_acc: 0.730 | val_error: 6.52 | val_acc: 0.685 
+
    +
    +
      [=======>--------------------------------] 20.70% | train_error: 5.59 | train_acc: 0.730 | val_error: 6.67 | val_acc: 0.678 
+
    +
    +
      [=======>--------------------------------] 20.80% | train_error: 5.55 | train_acc: 0.732 | val_error: 6.67 | val_acc: 0.678 
+
    +
    +
      [=======>--------------------------------] 20.90% | train_error: 5.50 | train_acc: 0.735 | val_error: 6.52 | val_acc: 0.685 
+
    +
    +
      [=======>--------------------------------] 21.00% | train_error: 5.35 | train_acc: 0.742 | val_error: 6.38 | val_acc: 0.692 
+
    +
    +
      [=======>--------------------------------] 21.10% | train_error: 5.35 | train_acc: 0.742 | val_error: 6.23 | val_acc: 0.699 
+
    +
    +
      [=======>--------------------------------] 21.20% | train_error: 5.30 | train_acc: 0.744 | val_error: 6.23 | val_acc: 0.699 
+
    +
    +
      [=======>--------------------------------] 21.30% | train_error: 5.21 | train_acc: 0.749 | val_error: 6.23 | val_acc: 0.699 
+
    +
    +
      [=======>--------------------------------] 21.40% | train_error: 5.06 | train_acc: 0.756 | val_error: 6.23 | val_acc: 0.699 
+
    +
    +
      [=======>--------------------------------] 21.50% | train_error: 5.06 | train_acc: 0.756 | val_error: 6.09 | val_acc: 0.706 
+
    +
    +
      [=======>--------------------------------] 21.60% | train_error: 5.06 | train_acc: 0.756 | val_error: 6.09 | val_acc: 0.706 
+
    +
    +
      [=======>--------------------------------] 21.70% | train_error: 5.01 | train_acc: 0.758 | val_error: 6.09 | val_acc: 0.706 
+
    +
    +
      [=======>--------------------------------] 21.80% | train_error: 5.01 | train_acc: 0.758 | val_error: 6.09 | val_acc: 0.706 
+
    +
    +
      [=======>--------------------------------] 21.90% | train_error: 4.96 | train_acc: 0.761 | val_error: 6.09 | val_acc: 0.706 
+
    +
    +
      [=======>--------------------------------] 22.00% | train_error: 4.96 | train_acc: 0.761 | val_error: 5.65 | val_acc: 0.727 
+
    +
    +
      [=======>--------------------------------] 22.10% | train_error: 4.72 | train_acc: 0.772 | val_error: 5.65 | val_acc: 0.727 
+
    +
    +
      [=======>--------------------------------] 22.20% | train_error: 4.62 | train_acc: 0.777 | val_error: 5.65 | val_acc: 0.727 
+
    +
    +
      [=======>--------------------------------] 22.30% | train_error: 4.52 | train_acc: 0.782 | val_error: 5.65 | val_acc: 0.727 
+
    +
    +
      [=======>--------------------------------] 22.40% | train_error: 4.62 | train_acc: 0.777 | val_error: 5.65 | val_acc: 0.727 
+
    +
    +
      [========>-------------------------------] 22.50% | train_error: 4.52 | train_acc: 0.782 | val_error: 5.51 | val_acc: 0.734 
+
    +
    +
      [========>-------------------------------] 22.60% | train_error: 4.57 | train_acc: 0.779 | val_error: 5.65 | val_acc: 0.727 
+
    +
    +
      [========>-------------------------------] 22.70% | train_error: 4.52 | train_acc: 0.782 | val_error: 5.65 | val_acc: 0.727 
+
    +
    +
      [========>-------------------------------] 22.80% | train_error: 4.33 | train_acc: 0.791 | val_error: 5.51 | val_acc: 0.734 
+
    +
    +
      [========>-------------------------------] 22.90% | train_error: 4.33 | train_acc: 0.791 | val_error: 5.36 | val_acc: 0.741 
+
    +
    +
      [========>-------------------------------] 23.00% | train_error: 4.33 | train_acc: 0.791 | val_error: 5.36 | val_acc: 0.741 
+
    +
    +
      [========>-------------------------------] 23.10% | train_error: 4.33 | train_acc: 0.791 | val_error: 5.36 | val_acc: 0.741 
+
    +
    +
      [========>-------------------------------] 23.20% | train_error: 4.33 | train_acc: 0.791 | val_error: 5.07 | val_acc: 0.755 
+
    +
    +
      [========>-------------------------------] 23.30% | train_error: 4.33 | train_acc: 0.791 | val_error: 5.07 | val_acc: 0.755 
+
    +
    +
      [========>-------------------------------] 23.40% | train_error: 4.28 | train_acc: 0.793 | val_error: 5.07 | val_acc: 0.755 
+
    +
    +
      [========>-------------------------------] 23.50% | train_error: 4.28 | train_acc: 0.793 | val_error: 5.07 | val_acc: 0.755 
+
    +
    +
      [========>-------------------------------] 23.60% | train_error: 4.13 | train_acc: 0.800 | val_error: 5.07 | val_acc: 0.755 
+
    +
    +
      [========>-------------------------------] 23.70% | train_error: 4.04 | train_acc: 0.805 | val_error: 4.93 | val_acc: 0.762 
+
    +
    +
      [========>-------------------------------] 23.80% | train_error: 4.04 | train_acc: 0.805 | val_error: 4.78 | val_acc: 0.769 
+
    +
    +
      [========>-------------------------------] 23.90% | train_error: 4.04 | train_acc: 0.805 | val_error: 4.78 | val_acc: 0.769 
+
    +
    +
      [========>-------------------------------] 24.00% | train_error: 3.89 | train_acc: 0.812 | val_error: 4.64 | val_acc: 0.776 
+
    +
    +
      [========>-------------------------------] 24.10% | train_error: 3.84 | train_acc: 0.815 | val_error: 4.64 | val_acc: 0.776 
+
    +
    +
      [========>-------------------------------] 24.20% | train_error: 3.79 | train_acc: 0.817 | val_error: 4.64 | val_acc: 0.776 
+
    +
    +
      [========>-------------------------------] 24.30% | train_error: 3.70 | train_acc: 0.822 | val_error: 4.64 | val_acc: 0.776 
+
    +
    +
      [========>-------------------------------] 24.40% | train_error: 3.70 | train_acc: 0.822 | val_error: 4.49 | val_acc: 0.783 
+
    +
    +
      [========>-------------------------------] 24.50% | train_error: 3.65 | train_acc: 0.824 | val_error: 4.35 | val_acc: 0.790 
+
    +
    +
      [========>-------------------------------] 24.60% | train_error: 3.55 | train_acc: 0.829 | val_error: 4.35 | val_acc: 0.790 
+
    +
    +
      [========>-------------------------------] 24.70% | train_error: 3.55 | train_acc: 0.829 | val_error: 4.35 | val_acc: 0.790 
+
    +
    +
      [========>-------------------------------] 24.80% | train_error: 3.50 | train_acc: 0.831 | val_error: 4.64 | val_acc: 0.776 
+
    +
    +
      [========>-------------------------------] 24.90% | train_error: 3.45 | train_acc: 0.833 | val_error: 4.64 | val_acc: 0.776 
+
    +
    +
      [=========>------------------------------] 25.00% | train_error: 3.21 | train_acc: 0.845 | val_error: 4.35 | val_acc: 0.790 
+
    +
    +
      [=========>------------------------------] 25.10% | train_error: 3.21 | train_acc: 0.845 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [=========>------------------------------] 25.20% | train_error: 3.11 | train_acc: 0.850 | val_error: 4.20 | val_acc: 0.797 
+
    +
    +
      [=========>------------------------------] 25.30% | train_error: 3.11 | train_acc: 0.850 | val_error: 4.35 | val_acc: 0.790 
+
    +
    +
      [=========>------------------------------] 25.40% | train_error: 3.11 | train_acc: 0.850 | val_error: 4.06 | val_acc: 0.804 
+
    +
    +
      [=========>------------------------------] 25.50% | train_error: 3.11 | train_acc: 0.850 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [=========>------------------------------] 25.60% | train_error: 3.11 | train_acc: 0.850 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [=========>------------------------------] 25.70% | train_error: 3.11 | train_acc: 0.850 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [=========>------------------------------] 25.80% | train_error: 3.11 | train_acc: 0.850 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [=========>------------------------------] 25.90% | train_error: 3.11 | train_acc: 0.850 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [=========>------------------------------] 26.00% | train_error: 3.21 | train_acc: 0.845 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [=========>------------------------------] 26.10% | train_error: 3.21 | train_acc: 0.845 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [=========>------------------------------] 26.20% | train_error: 3.21 | train_acc: 0.845 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [=========>------------------------------] 26.30% | train_error: 3.21 | train_acc: 0.845 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [=========>------------------------------] 26.40% | train_error: 3.21 | train_acc: 0.845 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [=========>------------------------------] 26.50% | train_error: 3.02 | train_acc: 0.854 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [=========>------------------------------] 26.60% | train_error: 2.77 | train_acc: 0.866 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [=========>------------------------------] 26.70% | train_error: 2.77 | train_acc: 0.866 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [=========>------------------------------] 26.80% | train_error: 2.72 | train_acc: 0.869 | val_error: 3.91 | val_acc: 0.811 
+
    +
    +
      [=========>------------------------------] 26.90% | train_error: 2.68 | train_acc: 0.871 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [=========>------------------------------] 27.00% | train_error: 2.53 | train_acc: 0.878 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [=========>------------------------------] 27.10% | train_error: 2.48 | train_acc: 0.880 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [=========>------------------------------] 27.20% | train_error: 2.48 | train_acc: 0.880 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [=========>------------------------------] 27.30% | train_error: 2.38 | train_acc: 0.885 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [=========>------------------------------] 27.40% | train_error: 2.38 | train_acc: 0.885 | val_error: 3.77 | val_acc: 0.818 
+
    +
    +
      [==========>-----------------------------] 27.50% | train_error: 2.38 | train_acc: 0.885 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [==========>-----------------------------] 27.60% | train_error: 2.29 | train_acc: 0.890 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [==========>-----------------------------] 27.70% | train_error: 2.24 | train_acc: 0.892 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [==========>-----------------------------] 27.80% | train_error: 2.24 | train_acc: 0.892 | val_error: 3.62 | val_acc: 0.825 
+
    +
    +
      [==========>-----------------------------] 27.90% | train_error: 2.19 | train_acc: 0.894 | val_error: 3.48 | val_acc: 0.832 
+
    +
    +
      [==========>-----------------------------] 28.00% | train_error: 2.19 | train_acc: 0.894 | val_error: 3.33 | val_acc: 0.839 
+
    +
    +
      [==========>-----------------------------] 28.10% | train_error: 2.19 | train_acc: 0.894 | val_error: 3.19 | val_acc: 0.846 
+
    +
    +
      [==========>-----------------------------] 28.20% | train_error: 2.19 | train_acc: 0.894 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [==========>-----------------------------] 28.30% | train_error: 2.19 | train_acc: 0.894 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [==========>-----------------------------] 28.40% | train_error: 2.14 | train_acc: 0.897 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [==========>-----------------------------] 28.50% | train_error: 2.09 | train_acc: 0.899 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [==========>-----------------------------] 28.60% | train_error: 2.04 | train_acc: 0.901 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [==========>-----------------------------] 28.70% | train_error: 2.09 | train_acc: 0.899 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [==========>-----------------------------] 28.80% | train_error: 2.09 | train_acc: 0.899 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [==========>-----------------------------] 28.90% | train_error: 2.09 | train_acc: 0.899 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [==========>-----------------------------] 29.00% | train_error: 2.09 | train_acc: 0.899 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [==========>-----------------------------] 29.10% | train_error: 2.09 | train_acc: 0.899 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [==========>-----------------------------] 29.20% | train_error: 2.09 | train_acc: 0.899 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [==========>-----------------------------] 29.30% | train_error: 2.04 | train_acc: 0.901 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [==========>-----------------------------] 29.40% | train_error: 2.04 | train_acc: 0.901 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [==========>-----------------------------] 29.50% | train_error: 2.04 | train_acc: 0.901 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [==========>-----------------------------] 29.60% | train_error: 2.04 | train_acc: 0.901 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [==========>-----------------------------] 29.70% | train_error: 2.04 | train_acc: 0.901 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [==========>-----------------------------] 29.80% | train_error: 1.99 | train_acc: 0.904 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [==========>-----------------------------] 29.90% | train_error: 1.95 | train_acc: 0.906 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 30.00% | train_error: 1.90 | train_acc: 0.908 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 30.10% | train_error: 1.90 | train_acc: 0.908 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 30.20% | train_error: 1.90 | train_acc: 0.908 | val_error: 3.19 | val_acc: 0.846 
+
    +
    +
      [===========>----------------------------] 30.30% | train_error: 1.90 | train_acc: 0.908 | val_error: 3.19 | val_acc: 0.846 
+
    +
    +
      [===========>----------------------------] 30.40% | train_error: 1.90 | train_acc: 0.908 | val_error: 3.19 | val_acc: 0.846 
+
    +
    +
      [===========>----------------------------] 30.50% | train_error: 1.90 | train_acc: 0.908 | val_error: 3.19 | val_acc: 0.846 
+
    +
    +
      [===========>----------------------------] 30.60% | train_error: 1.90 | train_acc: 0.908 | val_error: 3.19 | val_acc: 0.846 
+
    +
    +
      [===========>----------------------------] 30.70% | train_error: 1.90 | train_acc: 0.908 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 30.80% | train_error: 1.90 | train_acc: 0.908 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 30.90% | train_error: 1.90 | train_acc: 0.908 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 31.00% | train_error: 1.75 | train_acc: 0.915 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 31.10% | train_error: 1.75 | train_acc: 0.915 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 31.20% | train_error: 1.61 | train_acc: 0.923 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 31.30% | train_error: 1.61 | train_acc: 0.923 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 31.40% | train_error: 1.56 | train_acc: 0.925 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 31.50% | train_error: 1.56 | train_acc: 0.925 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 31.60% | train_error: 1.56 | train_acc: 0.925 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 31.70% | train_error: 1.51 | train_acc: 0.927 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 31.80% | train_error: 1.51 | train_acc: 0.927 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 31.90% | train_error: 1.51 | train_acc: 0.927 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 32.00% | train_error: 1.51 | train_acc: 0.927 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [===========>----------------------------] 32.10% | train_error: 1.41 | train_acc: 0.932 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [===========>----------------------------] 32.20% | train_error: 1.41 | train_acc: 0.932 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [===========>----------------------------] 32.30% | train_error: 1.41 | train_acc: 0.932 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [===========>----------------------------] 32.40% | train_error: 1.41 | train_acc: 0.932 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [============>---------------------------] 32.50% | train_error: 1.41 | train_acc: 0.932 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [============>---------------------------] 32.60% | train_error: 1.41 | train_acc: 0.932 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [============>---------------------------] 32.70% | train_error: 1.41 | train_acc: 0.932 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [============>---------------------------] 32.80% | train_error: 1.31 | train_acc: 0.937 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [============>---------------------------] 32.90% | train_error: 1.26 | train_acc: 0.939 | val_error: 3.04 | val_acc: 0.853 
+
    +
    +
      [============>---------------------------] 33.00% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [============>---------------------------] 33.10% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [============>---------------------------] 33.20% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [============>---------------------------] 33.30% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.90 | val_acc: 0.860 
+
    +
    +
      [============>---------------------------] 33.40% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.75 | val_acc: 0.867 
+
    +
    +
      [============>---------------------------] 33.50% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.75 | val_acc: 0.867 
+
    +
    +
      [============>---------------------------] 33.60% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.75 | val_acc: 0.867 
+
    +
    +
      [============>---------------------------] 33.70% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.75 | val_acc: 0.867 
+
    +
    +
      [============>---------------------------] 33.80% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.75 | val_acc: 0.867 
+
    +
    +
      [============>---------------------------] 33.90% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.75 | val_acc: 0.867 
+
    +
    +
      [============>---------------------------] 34.00% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.61 | val_acc: 0.874 
+
    +
    +
      [============>---------------------------] 34.10% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.61 | val_acc: 0.874 
+
    +
    +
      [============>---------------------------] 34.20% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.61 | val_acc: 0.874 
+
    +
    +
      [============>---------------------------] 34.30% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.61 | val_acc: 0.874 
+
    +
    +
      [============>---------------------------] 34.40% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.61 | val_acc: 0.874 
+
    +
    +
      [============>---------------------------] 34.50% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.75 | val_acc: 0.867 
+
    +
    +
      [============>---------------------------] 34.60% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.75 | val_acc: 0.867 
+
    +
    +
      [============>---------------------------] 34.70% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.75 | val_acc: 0.867 
+
    +
    +
      [============>---------------------------] 34.80% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.75 | val_acc: 0.867 
+
    +
    +
      [============>---------------------------] 34.90% | train_error: 1.22 | train_acc: 0.941 | val_error: 2.75 | val_acc: 0.867 
+
    +
    +
      [=============>--------------------------] 35.00% | train_error: 1.02 | train_acc: 0.951 | val_error: 2.75 | val_acc: 0.867 
+
    +
    +
      [=============>--------------------------] 35.10% | train_error: 1.02 | train_acc: 0.951 | val_error: 2.75 | val_acc: 0.867 
+
    +
    +
      [=============>--------------------------] 35.20% | train_error: 1.02 | train_acc: 0.951 | val_error: 2.75 | val_acc: 0.867 
+
    +
    +
      [=============>--------------------------] 35.30% | train_error: 1.02 | train_acc: 0.951 | val_error: 2.61 | val_acc: 0.874 
+
    +
    +
      [=============>--------------------------] 35.40% | train_error: 1.02 | train_acc: 0.951 | val_error: 2.61 | val_acc: 0.874 
+
    +
    +
      [=============>--------------------------] 35.50% | train_error: 1.02 | train_acc: 0.951 | val_error: 2.61 | val_acc: 0.874 
+
    +
    +
      [=============>--------------------------] 35.60% | train_error: 1.02 | train_acc: 0.951 | val_error: 2.61 | val_acc: 0.874 
+
    +
    +
      [=============>--------------------------] 35.70% | train_error: 1.02 | train_acc: 0.951 | val_error: 2.61 | val_acc: 0.874 
+
    +
    +
      [=============>--------------------------] 35.80% | train_error: 1.02 | train_acc: 0.951 | val_error: 2.61 | val_acc: 0.874 
+
    +
    +
      [=============>--------------------------] 35.90% | train_error: 0.876 | train_acc: 0.958 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [=============>--------------------------] 36.00% | train_error: 0.876 | train_acc: 0.958 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [=============>--------------------------] 36.10% | train_error: 0.778 | train_acc: 0.962 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [=============>--------------------------] 36.20% | train_error: 0.778 | train_acc: 0.962 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [=============>--------------------------] 36.30% | train_error: 0.778 | train_acc: 0.962 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [=============>--------------------------] 36.40% | train_error: 0.730 | train_acc: 0.965 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [=============>--------------------------] 36.50% | train_error: 0.730 | train_acc: 0.965 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [=============>--------------------------] 36.60% | train_error: 0.730 | train_acc: 0.965 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [=============>--------------------------] 36.70% | train_error: 0.730 | train_acc: 0.965 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [=============>--------------------------] 36.80% | train_error: 0.730 | train_acc: 0.965 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [=============>--------------------------] 36.90% | train_error: 0.730 | train_acc: 0.965 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [=============>--------------------------] 37.00% | train_error: 0.681 | train_acc: 0.967 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [=============>--------------------------] 37.10% | train_error: 0.681 | train_acc: 0.967 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [=============>--------------------------] 37.20% | train_error: 0.681 | train_acc: 0.967 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [=============>--------------------------] 37.30% | train_error: 0.632 | train_acc: 0.969 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [=============>--------------------------] 37.40% | train_error: 0.632 | train_acc: 0.969 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 37.50% | train_error: 0.632 | train_acc: 0.969 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 37.60% | train_error: 0.632 | train_acc: 0.969 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 37.70% | train_error: 0.632 | train_acc: 0.969 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 37.80% | train_error: 0.632 | train_acc: 0.969 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 37.90% | train_error: 0.632 | train_acc: 0.969 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 38.00% | train_error: 0.535 | train_acc: 0.974 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 38.10% | train_error: 0.535 | train_acc: 0.974 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 38.20% | train_error: 0.486 | train_acc: 0.977 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 38.30% | train_error: 0.341 | train_acc: 0.984 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 38.40% | train_error: 0.486 | train_acc: 0.977 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 38.50% | train_error: 0.341 | train_acc: 0.984 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 38.60% | train_error: 0.486 | train_acc: 0.977 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 38.70% | train_error: 0.341 | train_acc: 0.984 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 38.80% | train_error: 0.486 | train_acc: 0.977 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 38.90% | train_error: 0.341 | train_acc: 0.984 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 39.00% | train_error: 0.486 | train_acc: 0.977 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 39.10% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 39.20% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 39.30% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 39.40% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 39.50% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 39.60% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 39.70% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 39.80% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [==============>-------------------------] 39.90% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [===============>------------------------] 40.00% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [===============>------------------------] 40.10% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [===============>------------------------] 40.20% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [===============>------------------------] 40.30% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [===============>------------------------] 40.40% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [===============>------------------------] 40.50% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [===============>------------------------] 40.60% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [===============>------------------------] 40.70% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [===============>------------------------] 40.80% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [===============>------------------------] 40.90% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [===============>------------------------] 41.00% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [===============>------------------------] 41.10% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [===============>------------------------] 41.20% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [===============>------------------------] 41.30% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [===============>------------------------] 41.40% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [===============>------------------------] 41.50% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [===============>------------------------] 41.60% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [===============>------------------------] 41.70% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [===============>------------------------] 41.80% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [===============>------------------------] 41.90% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [===============>------------------------] 42.00% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [===============>------------------------] 42.10% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [===============>------------------------] 42.20% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [===============>------------------------] 42.30% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [===============>------------------------] 42.40% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [================>-----------------------] 42.50% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [================>-----------------------] 42.60% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [================>-----------------------] 42.70% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [================>-----------------------] 42.80% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [================>-----------------------] 42.90% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [================>-----------------------] 43.00% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [================>-----------------------] 43.10% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [================>-----------------------] 43.20% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [================>-----------------------] 43.30% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [================>-----------------------] 43.40% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [================>-----------------------] 43.50% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [================>-----------------------] 43.60% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [================>-----------------------] 43.70% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [================>-----------------------] 43.80% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [================>-----------------------] 43.90% | train_error: 0.243 | train_acc: 0.988 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [================>-----------------------] 44.00% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [================>-----------------------] 44.10% | train_error: 0.243 | train_acc: 0.988 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [================>-----------------------] 44.20% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.46 | val_acc: 0.881 
+
    +
    +
      [================>-----------------------] 44.30% | train_error: 0.243 | train_acc: 0.988 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [================>-----------------------] 44.40% | train_error: 0.292 | train_acc: 0.986 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [================>-----------------------] 44.50% | train_error: 0.243 | train_acc: 0.988 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [================>-----------------------] 44.60% | train_error: 0.243 | train_acc: 0.988 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [================>-----------------------] 44.70% | train_error: 0.243 | train_acc: 0.988 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [================>-----------------------] 44.80% | train_error: 0.243 | train_acc: 0.988 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [================>-----------------------] 44.90% | train_error: 0.243 | train_acc: 0.988 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 45.00% | train_error: 0.243 | train_acc: 0.988 | val_error: 2.32 | val_acc: 0.888 
+
    +
    +
      [=================>----------------------] 45.10% | train_error: 0.243 | train_acc: 0.988 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 45.20% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 45.30% | train_error: 0.243 | train_acc: 0.988 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 45.40% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 45.50% | train_error: 0.243 | train_acc: 0.988 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 45.60% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 45.70% | train_error: 0.243 | train_acc: 0.988 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 45.80% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 45.90% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 46.00% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 46.10% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=================>----------------------] 46.20% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 46.30% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=================>----------------------] 46.40% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 46.50% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=================>----------------------] 46.60% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 46.70% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=================>----------------------] 46.80% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 46.90% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=================>----------------------] 47.00% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 47.10% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=================>----------------------] 47.20% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [=================>----------------------] 47.30% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=================>----------------------] 47.40% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [==================>---------------------] 47.50% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [==================>---------------------] 47.60% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [==================>---------------------] 47.70% | train_error: 0.195 | train_acc: 0.991 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [==================>---------------------] 47.80% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [==================>---------------------] 47.90% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [==================>---------------------] 48.00% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [==================>---------------------] 48.10% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [==================>---------------------] 48.20% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [==================>---------------------] 48.30% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [==================>---------------------] 48.40% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [==================>---------------------] 48.50% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [==================>---------------------] 48.60% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [==================>---------------------] 48.70% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [==================>---------------------] 48.80% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [==================>---------------------] 48.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [==================>---------------------] 49.00% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [==================>---------------------] 49.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [==================>---------------------] 49.20% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [==================>---------------------] 49.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [==================>---------------------] 49.40% | train_error: 0.146 | train_acc: 0.993 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [==================>---------------------] 49.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [==================>---------------------] 49.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [==================>---------------------] 49.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [==================>---------------------] 49.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [==================>---------------------] 49.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [===================>--------------------] 50.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [===================>--------------------] 50.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [===================>--------------------] 50.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [===================>--------------------] 50.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [===================>--------------------] 50.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [===================>--------------------] 50.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [===================>--------------------] 50.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [===================>--------------------] 50.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [===================>--------------------] 50.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [===================>--------------------] 50.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [===================>--------------------] 51.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [===================>--------------------] 51.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [===================>--------------------] 51.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [===================>--------------------] 51.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [===================>--------------------] 51.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [===================>--------------------] 51.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [===================>--------------------] 51.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [===================>--------------------] 51.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [===================>--------------------] 51.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [===================>--------------------] 51.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [===================>--------------------] 52.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.17 | val_acc: 0.895 
+
    +
    +
      [===================>--------------------] 52.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [===================>--------------------] 52.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [===================>--------------------] 52.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [===================>--------------------] 52.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 52.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 52.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 52.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 52.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [====================>-------------------] 52.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 53.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 53.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 53.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [====================>-------------------] 53.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 53.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 53.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 53.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [====================>-------------------] 53.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 53.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [====================>-------------------] 53.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 54.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [====================>-------------------] 54.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 54.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 54.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 54.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 54.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [====================>-------------------] 54.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [====================>-------------------] 54.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [====================>-------------------] 54.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [====================>-------------------] 54.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=====================>------------------] 55.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=====================>------------------] 55.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=====================>------------------] 55.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=====================>------------------] 55.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=====================>------------------] 55.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=====================>------------------] 55.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=====================>------------------] 55.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=====================>------------------] 55.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=====================>------------------] 55.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=====================>------------------] 55.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=====================>------------------] 56.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=====================>------------------] 56.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=====================>------------------] 56.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=====================>------------------] 56.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=====================>------------------] 56.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=====================>------------------] 56.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=====================>------------------] 56.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=====================>------------------] 56.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=====================>------------------] 56.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=====================>------------------] 56.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=====================>------------------] 57.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=====================>------------------] 57.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=====================>------------------] 57.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 2.03 | val_acc: 0.902 
+
    +
    +
      [=====================>------------------] 57.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=====================>------------------] 57.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 57.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 57.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 57.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 57.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 57.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 58.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 58.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 58.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 58.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 58.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 58.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 58.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 58.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 58.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 58.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 59.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 59.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 59.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 59.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 59.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 59.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 59.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 59.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 59.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [======================>-----------------] 59.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 60.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 60.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 60.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 60.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 60.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 60.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 60.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 60.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 60.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 60.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 61.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 61.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 61.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 61.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 61.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 61.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 61.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 61.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 61.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 61.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 62.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 62.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 62.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 62.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=======================>----------------] 62.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 62.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 62.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 62.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 62.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 62.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 63.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 63.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 63.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 63.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 63.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 63.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 63.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 63.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 63.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 63.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [========================>---------------] 64.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 64.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [========================>---------------] 64.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 64.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [========================>---------------] 64.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 64.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [========================>---------------] 64.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 64.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [========================>---------------] 64.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [========================>---------------] 64.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=========================>--------------] 65.00% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=========================>--------------] 65.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=========================>--------------] 65.20% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=========================>--------------] 65.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=========================>--------------] 65.40% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=========================>--------------] 65.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=========================>--------------] 65.60% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=========================>--------------] 65.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=========================>--------------] 65.80% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=========================>--------------] 65.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=========================>--------------] 66.00% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=========================>--------------] 66.10% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=========================>--------------] 66.20% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=========================>--------------] 66.30% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=========================>--------------] 66.40% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=========================>--------------] 66.50% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=========================>--------------] 66.60% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=========================>--------------] 66.70% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=========================>--------------] 66.80% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=========================>--------------] 66.90% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=========================>--------------] 67.00% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=========================>--------------] 67.10% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=========================>--------------] 67.20% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [=========================>--------------] 67.30% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=========================>--------------] 67.40% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [==========================>-------------] 67.50% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==========================>-------------] 67.60% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [==========================>-------------] 67.70% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==========================>-------------] 67.80% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [==========================>-------------] 67.90% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==========================>-------------] 68.00% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [==========================>-------------] 68.10% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==========================>-------------] 68.20% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [==========================>-------------] 68.30% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==========================>-------------] 68.40% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [==========================>-------------] 68.50% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==========================>-------------] 68.60% | train_error: 0.146 | train_acc: 0.993 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [==========================>-------------] 68.70% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==========================>-------------] 68.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [==========================>-------------] 68.90% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==========================>-------------] 69.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [==========================>-------------] 69.10% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==========================>-------------] 69.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [==========================>-------------] 69.30% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==========================>-------------] 69.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [==========================>-------------] 69.50% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==========================>-------------] 69.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [==========================>-------------] 69.70% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==========================>-------------] 69.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.88 | val_acc: 0.909 
+
    +
    +
      [==========================>-------------] 69.90% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 70.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 70.10% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 70.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 70.30% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 70.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 70.50% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 70.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 70.70% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 70.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 70.90% | train_error: 0.0486 | train_acc: 0.998 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 71.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 71.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 71.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 71.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 71.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 71.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 71.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 71.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 71.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 71.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 72.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 72.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 72.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 72.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===========================>------------] 72.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 72.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 72.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 72.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 72.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 72.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 73.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 73.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 73.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 73.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 73.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 73.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 73.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 73.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 73.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 73.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 74.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 74.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 74.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 74.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 74.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 74.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 74.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 74.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 74.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [============================>-----------] 74.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 75.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 75.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 75.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 75.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 75.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 75.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 75.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 75.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 75.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 75.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 76.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 76.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 76.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 76.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 76.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 76.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 76.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 76.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 76.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 76.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 77.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 77.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [=============================>----------] 77.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=============================>----------] 77.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [=============================>----------] 77.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==============================>---------] 77.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==============================>---------] 77.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==============================>---------] 77.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==============================>---------] 77.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==============================>---------] 77.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==============================>---------] 78.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==============================>---------] 78.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==============================>---------] 78.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==============================>---------] 78.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==============================>---------] 78.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==============================>---------] 78.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==============================>---------] 78.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==============================>---------] 78.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==============================>---------] 78.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==============================>---------] 78.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==============================>---------] 79.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==============================>---------] 79.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==============================>---------] 79.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==============================>---------] 79.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==============================>---------] 79.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==============================>---------] 79.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==============================>---------] 79.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==============================>---------] 79.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==============================>---------] 79.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==============================>---------] 79.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [===============================>--------] 80.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===============================>--------] 80.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [===============================>--------] 80.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===============================>--------] 80.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [===============================>--------] 80.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===============================>--------] 80.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [===============================>--------] 80.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===============================>--------] 80.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [===============================>--------] 80.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===============================>--------] 80.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [===============================>--------] 81.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===============================>--------] 81.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [===============================>--------] 81.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===============================>--------] 81.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [===============================>--------] 81.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===============================>--------] 81.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [===============================>--------] 81.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===============================>--------] 81.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [===============================>--------] 81.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===============================>--------] 81.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [===============================>--------] 82.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===============================>--------] 82.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [===============================>--------] 82.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===============================>--------] 82.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [===============================>--------] 82.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [================================>-------] 82.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [================================>-------] 82.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [================================>-------] 82.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [================================>-------] 82.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [================================>-------] 82.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [================================>-------] 83.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [================================>-------] 83.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [================================>-------] 83.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [================================>-------] 83.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [================================>-------] 83.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [================================>-------] 83.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [================================>-------] 83.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [================================>-------] 83.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [================================>-------] 83.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [================================>-------] 83.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [================================>-------] 84.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [================================>-------] 84.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [================================>-------] 84.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [================================>-------] 84.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [================================>-------] 84.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [================================>-------] 84.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [================================>-------] 84.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [================================>-------] 84.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [================================>-------] 84.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [================================>-------] 84.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [=================================>------] 85.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=================================>------] 85.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [=================================>------] 85.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=================================>------] 85.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [=================================>------] 85.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=================================>------] 85.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [=================================>------] 85.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=================================>------] 85.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [=================================>------] 85.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=================================>------] 85.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [=================================>------] 86.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=================================>------] 86.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [=================================>------] 86.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=================================>------] 86.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [=================================>------] 86.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=================================>------] 86.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [=================================>------] 86.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=================================>------] 86.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [=================================>------] 86.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=================================>------] 86.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [=================================>------] 87.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=================================>------] 87.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [=================================>------] 87.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=================================>------] 87.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [=================================>------] 87.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==================================>-----] 87.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==================================>-----] 87.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==================================>-----] 87.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==================================>-----] 87.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==================================>-----] 87.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==================================>-----] 88.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==================================>-----] 88.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==================================>-----] 88.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==================================>-----] 88.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==================================>-----] 88.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==================================>-----] 88.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==================================>-----] 88.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==================================>-----] 88.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==================================>-----] 88.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==================================>-----] 88.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==================================>-----] 89.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==================================>-----] 89.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==================================>-----] 89.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==================================>-----] 89.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==================================>-----] 89.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==================================>-----] 89.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==================================>-----] 89.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==================================>-----] 89.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [==================================>-----] 89.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [==================================>-----] 89.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.59 | val_acc: 0.923 
+
    +
    +
      [===================================>----] 90.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 90.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 90.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 90.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 90.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 90.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 90.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 90.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 90.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 90.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 91.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 91.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 91.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 91.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 91.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 91.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 91.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 91.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 91.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 91.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 92.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 92.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 92.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 92.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [===================================>----] 92.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 92.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 92.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 92.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 92.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 92.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 93.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 93.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 93.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 93.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 93.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 93.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 93.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 93.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 93.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 93.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 94.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 94.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 94.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 94.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 94.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 94.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 94.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 94.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 94.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [====================================>---] 94.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 95.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 95.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 95.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 95.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 95.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 95.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 95.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 95.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 95.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 95.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 96.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 96.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 96.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 96.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 96.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 96.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 96.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 96.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 96.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 96.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 97.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 97.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 97.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 97.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [=====================================>--] 97.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 97.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 97.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 97.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 97.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 97.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 98.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 98.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 98.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 98.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 98.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 98.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 98.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 98.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 98.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 98.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 99.00% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 99.10% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 99.20% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 99.30% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 99.40% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 99.50% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 99.60% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 99.70% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 99.80% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
      [======================================>-] 99.90% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
                                                                                                                                    
+
    +
    +
      [=======================================>] 100.0% | train_error: 0.0973 | train_acc: 0.995 | val_error: 1.74 | val_acc: 0.916 
+
    +
    +
    +
    +
    +
    +

    Multiclass classification¶

    +

    Finally, we will demonstrate the use case of multiclass classification +using our FFNN with the famous MNIST dataset, which contain images of +digits between the range of 0 to 9.

    +
    +
    +
    from sklearn.datasets import load_digits
+
+def onehot(target: np.ndarray):
+    onehot = np.zeros((target.size, target.max() + 1))
+    onehot[np.arange(target.size), target] = 1
+    return onehot
+
+digits = load_digits()
+
+X = digits.data
+target = digits.target
+target = onehot(target)
+
+input_nodes = 64
+hidden_nodes1 = 100
+hidden_nodes2 = 30
+output_nodes = 10
+
+dims = (input_nodes, hidden_nodes1, hidden_nodes2, output_nodes)
+
+multiclass = FFNN(dims, hidden_func=LRELU, output_func=softmax, cost_func=CostCrossEntropy)
+
+multiclass.reset_weights() # reset weights such that previous runs or reruns don't affect the weights
+
+scheduler = Adam(eta=1e-4, rho=0.9, rho2=0.999)
+scores = multiclass.fit(X, target, scheduler, epochs=1000)
+
    +
    +
    +
    +
    Adam: Eta=0.0001, Lambda=0
+
    +
    +
      [----------------------------------------] 0.000% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [----------------------------------------] 0.1000% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [----------------------------------------] 0.2000% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [----------------------------------------] 0.3000% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [----------------------------------------] 0.4000% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [----------------------------------------] 0.5000% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [----------------------------------------] 0.6000% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 0.7000% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 0.8000% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 0.9000% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 1.000% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 1.100% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 1.200% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 1.300% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 1.400% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 1.500% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 1.600% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 1.700% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 1.800% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 1.900% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 2.000% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 2.100% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 2.200% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 2.300% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [----------------------------------------] 2.400% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 2.500% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 2.600% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 2.700% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 2.800% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 2.900% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 3.000% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 3.100% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 3.200% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 3.300% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 3.400% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 3.500% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 3.600% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 3.700% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 3.800% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 3.900% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 4.000% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 4.100% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 4.200% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 4.300% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [>---------------------------------------] 4.400% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [>---------------------------------------] 4.500% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [>---------------------------------------] 4.600% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [>---------------------------------------] 4.700% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [>---------------------------------------] 4.800% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [>---------------------------------------] 4.900% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [=>--------------------------------------] 5.000% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [=>--------------------------------------] 5.100% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [=>--------------------------------------] 5.200% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [=>--------------------------------------] 5.300% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [=>--------------------------------------] 5.400% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [=>--------------------------------------] 5.500% | train_error: 1.84 | train_acc: 0.823 
+
    +
    +
      [=>--------------------------------------] 5.600% | train_error: 1.84 | train_acc: 0.823 
+
    +
    +
      [=>--------------------------------------] 5.700% | train_error: 1.84 | train_acc: 0.822 
+
    +
    +
      [=>--------------------------------------] 5.800% | train_error: 1.84 | train_acc: 0.822 
+
    +
    +
      [=>--------------------------------------] 5.900% | train_error: 1.84 | train_acc: 0.822 
+
    +
    +
      [=>--------------------------------------] 6.000% | train_error: 1.84 | train_acc: 0.823 
+
    +
    +
      [=>--------------------------------------] 6.100% | train_error: 1.84 | train_acc: 0.823 
+
    +
    +
      [=>--------------------------------------] 6.200% | train_error: 1.84 | train_acc: 0.823 
+
    +
    +
      [=>--------------------------------------] 6.300% | train_error: 1.84 | train_acc: 0.823 
+
    +
    +
      [=>--------------------------------------] 6.400% | train_error: 1.84 | train_acc: 0.823 
+
    +
    +
      [=>--------------------------------------] 6.500% | train_error: 1.84 | train_acc: 0.823 
+
    +
    +
      [=>--------------------------------------] 6.600% | train_error: 1.84 | train_acc: 0.823 
+
    +
    +
      [=>--------------------------------------] 6.700% | train_error: 1.84 | train_acc: 0.823 
+
    +
    +
      [=>--------------------------------------] 6.800% | train_error: 1.84 | train_acc: 0.822 
+
    +
    +
      [=>--------------------------------------] 6.900% | train_error: 1.85 | train_acc: 0.822 
+
    +
    +
      [=>--------------------------------------] 7.000% | train_error: 1.85 | train_acc: 0.822 
+
    +
    +
      [=>--------------------------------------] 7.100% | train_error: 1.85 | train_acc: 0.821 
+
    +
    +
      [=>--------------------------------------] 7.200% | train_error: 1.85 | train_acc: 0.821 
+
    +
    +
      [=>--------------------------------------] 7.300% | train_error: 1.85 | train_acc: 0.821 
+
    +
    +
      [=>--------------------------------------] 7.400% | train_error: 1.85 | train_acc: 0.821 
+
    +
    +
      [==>-------------------------------------] 7.500% | train_error: 1.86 | train_acc: 0.821 
+
    +
    +
      [==>-------------------------------------] 7.600% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [==>-------------------------------------] 7.700% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [==>-------------------------------------] 7.800% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [==>-------------------------------------] 7.900% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [==>-------------------------------------] 8.000% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [==>-------------------------------------] 8.100% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [==>-------------------------------------] 8.200% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [==>-------------------------------------] 8.300% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [==>-------------------------------------] 8.400% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [==>-------------------------------------] 8.500% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [==>-------------------------------------] 8.600% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [==>-------------------------------------] 8.700% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [==>-------------------------------------] 8.800% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [==>-------------------------------------] 8.900% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [==>-------------------------------------] 9.000% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [==>-------------------------------------] 9.100% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [==>-------------------------------------] 9.200% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [==>-------------------------------------] 9.300% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [==>-------------------------------------] 9.400% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [==>-------------------------------------] 9.500% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [==>-------------------------------------] 9.600% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [==>-------------------------------------] 9.700% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [==>-------------------------------------] 9.800% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [==>-------------------------------------] 9.900% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [===>------------------------------------] 10.00% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [===>------------------------------------] 10.10% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [===>------------------------------------] 10.20% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [===>------------------------------------] 10.30% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [===>------------------------------------] 10.40% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [===>------------------------------------] 10.50% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [===>------------------------------------] 10.60% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [===>------------------------------------] 10.70% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [===>------------------------------------] 10.80% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [===>------------------------------------] 10.90% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [===>------------------------------------] 11.00% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [===>------------------------------------] 11.10% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [===>------------------------------------] 11.20% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [===>------------------------------------] 11.30% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [===>------------------------------------] 11.40% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [===>------------------------------------] 11.50% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [===>------------------------------------] 11.60% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [===>------------------------------------] 11.70% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [===>------------------------------------] 11.80% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [===>------------------------------------] 11.90% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [===>------------------------------------] 12.00% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [===>------------------------------------] 12.10% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [===>------------------------------------] 12.20% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [===>------------------------------------] 12.30% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [===>------------------------------------] 12.40% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [====>-----------------------------------] 12.50% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [====>-----------------------------------] 12.60% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [====>-----------------------------------] 12.70% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [====>-----------------------------------] 12.80% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [====>-----------------------------------] 12.90% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [====>-----------------------------------] 13.00% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [====>-----------------------------------] 13.10% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [====>-----------------------------------] 13.20% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [====>-----------------------------------] 13.30% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [====>-----------------------------------] 13.40% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [====>-----------------------------------] 13.50% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [====>-----------------------------------] 13.60% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [====>-----------------------------------] 13.70% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [====>-----------------------------------] 13.80% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [====>-----------------------------------] 13.90% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [====>-----------------------------------] 14.00% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [====>-----------------------------------] 14.10% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [====>-----------------------------------] 14.20% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [====>-----------------------------------] 14.30% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [====>-----------------------------------] 14.40% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [====>-----------------------------------] 14.50% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [====>-----------------------------------] 14.60% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [====>-----------------------------------] 14.70% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [====>-----------------------------------] 14.80% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [====>-----------------------------------] 14.90% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [=====>----------------------------------] 15.00% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [=====>----------------------------------] 15.10% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [=====>----------------------------------] 15.20% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [=====>----------------------------------] 15.30% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [=====>----------------------------------] 15.40% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [=====>----------------------------------] 15.50% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [=====>----------------------------------] 15.60% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [=====>----------------------------------] 15.70% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [=====>----------------------------------] 15.80% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [=====>----------------------------------] 15.90% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [=====>----------------------------------] 16.00% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [=====>----------------------------------] 16.10% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [=====>----------------------------------] 16.20% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [=====>----------------------------------] 16.30% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [=====>----------------------------------] 16.40% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [=====>----------------------------------] 16.50% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=====>----------------------------------] 16.60% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=====>----------------------------------] 16.70% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=====>----------------------------------] 16.80% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=====>----------------------------------] 16.90% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=====>----------------------------------] 17.00% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=====>----------------------------------] 17.10% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=====>----------------------------------] 17.20% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=====>----------------------------------] 17.30% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=====>----------------------------------] 17.40% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 17.50% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 17.60% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 17.70% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 17.80% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 17.90% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 18.00% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 18.10% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 18.20% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [======>---------------------------------] 18.30% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [======>---------------------------------] 18.40% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 18.50% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [======>---------------------------------] 18.60% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 18.70% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 18.80% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 18.90% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 19.00% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 19.10% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 19.20% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 19.30% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 19.40% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 19.50% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 19.60% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 19.70% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [======>---------------------------------] 19.80% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [======>---------------------------------] 19.90% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 20.00% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 20.10% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 20.20% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 20.30% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 20.40% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [=======>--------------------------------] 20.50% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 20.60% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 20.70% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 20.80% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 20.90% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 21.00% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 21.10% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 21.20% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 21.30% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 21.40% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 21.50% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [=======>--------------------------------] 21.60% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [=======>--------------------------------] 21.70% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [=======>--------------------------------] 21.80% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [=======>--------------------------------] 21.90% | train_error: 1.88 | train_acc: 0.818 
+
    +
    +
      [=======>--------------------------------] 22.00% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 22.10% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 22.20% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 22.30% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [=======>--------------------------------] 22.40% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [========>-------------------------------] 22.50% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [========>-------------------------------] 22.60% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [========>-------------------------------] 22.70% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [========>-------------------------------] 22.80% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [========>-------------------------------] 22.90% | train_error: 1.88 | train_acc: 0.819 
+
    +
    +
      [========>-------------------------------] 23.00% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [========>-------------------------------] 23.10% | train_error: 1.87 | train_acc: 0.819 
+
    +
    +
      [========>-------------------------------] 23.20% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [========>-------------------------------] 23.30% | train_error: 1.87 | train_acc: 0.820 
+
    +
    +
      [========>-------------------------------] 23.40% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [========>-------------------------------] 23.50% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [========>-------------------------------] 23.60% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [========>-------------------------------] 23.70% | train_error: 1.86 | train_acc: 0.821 
+
    +
    +
      [========>-------------------------------] 23.80% | train_error: 1.86 | train_acc: 0.821 
+
    +
    +
      [========>-------------------------------] 23.90% | train_error: 1.86 | train_acc: 0.821 
+
    +
    +
      [========>-------------------------------] 24.00% | train_error: 1.86 | train_acc: 0.821 
+
    +
    +
      [========>-------------------------------] 24.10% | train_error: 1.86 | train_acc: 0.821 
+
    +
    +
      [========>-------------------------------] 24.20% | train_error: 1.86 | train_acc: 0.820 
+
    +
    +
      [========>-------------------------------] 24.30% | train_error: 1.86 | train_acc: 0.821 
+
    +
    +
      [========>-------------------------------] 24.40% | train_error: 1.86 | train_acc: 0.821 
+
    +
    +
      [========>-------------------------------] 24.50% | train_error: 1.85 | train_acc: 0.821 
+
    +
    +
      [========>-------------------------------] 24.60% | train_error: 1.85 | train_acc: 0.821 
+
    +
    +
      [========>-------------------------------] 24.70% | train_error: 1.85 | train_acc: 0.822 
+
    +
    +
      [========>-------------------------------] 24.80% | train_error: 1.85 | train_acc: 0.821 
+
    +
    +
      [========>-------------------------------] 24.90% | train_error: 1.85 | train_acc: 0.822 
+
    +
    +
      [=========>------------------------------] 25.00% | train_error: 1.85 | train_acc: 0.822 
+
    +
    +
      [=========>------------------------------] 25.10% | train_error: 1.84 | train_acc: 0.822 
+
    +
    +
      [=========>------------------------------] 25.20% | train_error: 1.84 | train_acc: 0.822 
+
    +
    +
      [=========>------------------------------] 25.30% | train_error: 1.84 | train_acc: 0.822 
+
    +
    +
      [=========>------------------------------] 25.40% | train_error: 1.84 | train_acc: 0.822 
+
    +
    +
      [=========>------------------------------] 25.50% | train_error: 1.84 | train_acc: 0.822 
+
    +
    +
      [=========>------------------------------] 25.60% | train_error: 1.84 | train_acc: 0.823 
+
    +
    +
      [=========>------------------------------] 25.70% | train_error: 1.84 | train_acc: 0.823 
+
    +
    +
      [=========>------------------------------] 25.80% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [=========>------------------------------] 25.90% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [=========>------------------------------] 26.00% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [=========>------------------------------] 26.10% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [=========>------------------------------] 26.20% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [=========>------------------------------] 26.30% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [=========>------------------------------] 26.40% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [=========>------------------------------] 26.50% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [=========>------------------------------] 26.60% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [=========>------------------------------] 26.70% | train_error: 1.83 | train_acc: 0.823 
+
    +
    +
      [=========>------------------------------] 26.80% | train_error: 1.83 | train_acc: 0.824 
+
    +
    +
      [=========>------------------------------] 26.90% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [=========>------------------------------] 27.00% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [=========>------------------------------] 27.10% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [=========>------------------------------] 27.20% | train_error: 1.82 | train_acc: 0.824 
+
    +
    +
      [=========>------------------------------] 27.30% | train_error: 1.82 | train_acc: 0.825 
+
    +
    +
      [=========>------------------------------] 27.40% | train_error: 1.82 | train_acc: 0.825 
+
    +
    +
      [==========>-----------------------------] 27.50% | train_error: 1.82 | train_acc: 0.825 
+
    +
    +
      [==========>-----------------------------] 27.60% | train_error: 1.82 | train_acc: 0.825 
+
    +
    +
      [==========>-----------------------------] 27.70% | train_error: 1.81 | train_acc: 0.825 
+
    +
    +
      [==========>-----------------------------] 27.80% | train_error: 1.81 | train_acc: 0.825 
+
    +
    +
      [==========>-----------------------------] 27.90% | train_error: 1.81 | train_acc: 0.825 
+
    +
    +
      [==========>-----------------------------] 28.00% | train_error: 1.81 | train_acc: 0.825 
+
    +
    +
      [==========>-----------------------------] 28.10% | train_error: 1.81 | train_acc: 0.825 
+
    +
    +
      [==========>-----------------------------] 28.20% | train_error: 1.81 | train_acc: 0.825 
+
    +
    +
      [==========>-----------------------------] 28.30% | train_error: 1.81 | train_acc: 0.825 
+
    +
    +
      [==========>-----------------------------] 28.40% | train_error: 1.80 | train_acc: 0.826 
+
    +
    +
      [==========>-----------------------------] 28.50% | train_error: 1.80 | train_acc: 0.826 
+
    +
    +
      [==========>-----------------------------] 28.60% | train_error: 1.80 | train_acc: 0.826 
+
    +
    +
      [==========>-----------------------------] 28.70% | train_error: 1.80 | train_acc: 0.826 
+
    +
    +
      [==========>-----------------------------] 28.80% | train_error: 1.80 | train_acc: 0.826 
+
    +
    +
      [==========>-----------------------------] 28.90% | train_error: 1.80 | train_acc: 0.826 
+
    +
    +
      [==========>-----------------------------] 29.00% | train_error: 1.80 | train_acc: 0.826 
+
    +
    +
      [==========>-----------------------------] 29.10% | train_error: 1.80 | train_acc: 0.826 
+
    +
    +
      [==========>-----------------------------] 29.20% | train_error: 1.80 | train_acc: 0.827 
+
    +
    +
      [==========>-----------------------------] 29.30% | train_error: 1.80 | train_acc: 0.827 
+
    +
    +
      [==========>-----------------------------] 29.40% | train_error: 1.80 | train_acc: 0.826 
+
    +
    +
      [==========>-----------------------------] 29.50% | train_error: 1.80 | train_acc: 0.827 
+
    +
    +
      [==========>-----------------------------] 29.60% | train_error: 1.80 | train_acc: 0.827 
+
    +
    +
      [==========>-----------------------------] 29.70% | train_error: 1.80 | train_acc: 0.826 
+
    +
    +
      [==========>-----------------------------] 29.80% | train_error: 1.79 | train_acc: 0.827 
+
    +
    +
      [==========>-----------------------------] 29.90% | train_error: 1.79 | train_acc: 0.827 
+
    +
    +
      [===========>----------------------------] 30.00% | train_error: 1.79 | train_acc: 0.827 
+
    +
    +
      [===========>----------------------------] 30.10% | train_error: 1.79 | train_acc: 0.828 
+
    +
    +
      [===========>----------------------------] 30.20% | train_error: 1.79 | train_acc: 0.827 
+
    +
    +
      [===========>----------------------------] 30.30% | train_error: 1.79 | train_acc: 0.827 
+
    +
    +
      [===========>----------------------------] 30.40% | train_error: 1.79 | train_acc: 0.827 
+
    +
    +
      [===========>----------------------------] 30.50% | train_error: 1.79 | train_acc: 0.828 
+
    +
    +
      [===========>----------------------------] 30.60% | train_error: 1.78 | train_acc: 0.828 
+
    +
    +
      [===========>----------------------------] 30.70% | train_error: 1.78 | train_acc: 0.828 
+
    +
    +
      [===========>----------------------------] 30.80% | train_error: 1.78 | train_acc: 0.828 
+
    +
    +
      [===========>----------------------------] 30.90% | train_error: 1.78 | train_acc: 0.828 
+
    +
    +
      [===========>----------------------------] 31.00% | train_error: 1.78 | train_acc: 0.828 
+
    +
    +
      [===========>----------------------------] 31.10% | train_error: 1.78 | train_acc: 0.828 
+
    +
    +
      [===========>----------------------------] 31.20% | train_error: 1.78 | train_acc: 0.828 
+
    +
    +
      [===========>----------------------------] 31.30% | train_error: 1.78 | train_acc: 0.828 
+
    +
    +
      [===========>----------------------------] 31.40% | train_error: 1.78 | train_acc: 0.829 
+
    +
    +
      [===========>----------------------------] 31.50% | train_error: 1.78 | train_acc: 0.829 
+
    +
    +
      [===========>----------------------------] 31.60% | train_error: 1.77 | train_acc: 0.829 
+
    +
    +
      [===========>----------------------------] 31.70% | train_error: 1.78 | train_acc: 0.829 
+
    +
    +
      [===========>----------------------------] 31.80% | train_error: 1.78 | train_acc: 0.829 
+
    +
    +
      [===========>----------------------------] 31.90% | train_error: 1.77 | train_acc: 0.829 
+
    +
    +
      [===========>----------------------------] 32.00% | train_error: 1.77 | train_acc: 0.829 
+
    +
    +
      [===========>----------------------------] 32.10% | train_error: 1.76 | train_acc: 0.830 
+
    +
    +
      [===========>----------------------------] 32.20% | train_error: 1.77 | train_acc: 0.829 
+
    +
    +
      [===========>----------------------------] 32.30% | train_error: 1.76 | train_acc: 0.830 
+
    +
    +
      [===========>----------------------------] 32.40% | train_error: 1.76 | train_acc: 0.830 
+
    +
    +
      [============>---------------------------] 32.50% | train_error: 1.76 | train_acc: 0.830 
+
    +
    +
      [============>---------------------------] 32.60% | train_error: 1.76 | train_acc: 0.830 
+
    +
    +
      [============>---------------------------] 32.70% | train_error: 1.76 | train_acc: 0.830 
+
    +
    +
      [============>---------------------------] 32.80% | train_error: 1.76 | train_acc: 0.830 
+
    +
    +
      [============>---------------------------] 32.90% | train_error: 1.76 | train_acc: 0.831 
+
    +
    +
      [============>---------------------------] 33.00% | train_error: 1.75 | train_acc: 0.831 
+
    +
    +
      [============>---------------------------] 33.10% | train_error: 1.75 | train_acc: 0.831 
+
    +
    +
      [============>---------------------------] 33.20% | train_error: 1.75 | train_acc: 0.831 
+
    +
    +
      [============>---------------------------] 33.30% | train_error: 1.75 | train_acc: 0.831 
+
    +
    +
      [============>---------------------------] 33.40% | train_error: 1.75 | train_acc: 0.831 
+
    +
    +
      [============>---------------------------] 33.50% | train_error: 1.75 | train_acc: 0.831 
+
    +
    +
      [============>---------------------------] 33.60% | train_error: 1.75 | train_acc: 0.831 
+
    +
    +
      [============>---------------------------] 33.70% | train_error: 1.75 | train_acc: 0.831 
+
    +
    +
      [============>---------------------------] 33.80% | train_error: 1.75 | train_acc: 0.831 
+
    +
    +
      [============>---------------------------] 33.90% | train_error: 1.75 | train_acc: 0.831 
+
    +
    +
      [============>---------------------------] 34.00% | train_error: 1.75 | train_acc: 0.831 
+
    +
    +
      [============>---------------------------] 34.10% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [============>---------------------------] 34.20% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [============>---------------------------] 34.30% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [============>---------------------------] 34.40% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [============>---------------------------] 34.50% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [============>---------------------------] 34.60% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [============>---------------------------] 34.70% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [============>---------------------------] 34.80% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [============>---------------------------] 34.90% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [=============>--------------------------] 35.00% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [=============>--------------------------] 35.10% | train_error: 1.73 | train_acc: 0.834 
+
    +
    +
      [=============>--------------------------] 35.20% | train_error: 1.73 | train_acc: 0.834 
+
    +
    +
      [=============>--------------------------] 35.30% | train_error: 1.72 | train_acc: 0.834 
+
    +
    +
      [=============>--------------------------] 35.40% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [=============>--------------------------] 35.50% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [=============>--------------------------] 35.60% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [=============>--------------------------] 35.70% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [=============>--------------------------] 35.80% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [=============>--------------------------] 35.90% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [=============>--------------------------] 36.00% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [=============>--------------------------] 36.10% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [=============>--------------------------] 36.20% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [=============>--------------------------] 36.30% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [=============>--------------------------] 36.40% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [=============>--------------------------] 36.50% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [=============>--------------------------] 36.60% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [=============>--------------------------] 36.70% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [=============>--------------------------] 36.80% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [=============>--------------------------] 36.90% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [=============>--------------------------] 37.00% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [=============>--------------------------] 37.10% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [=============>--------------------------] 37.20% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [=============>--------------------------] 37.30% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [=============>--------------------------] 37.40% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [==============>-------------------------] 37.50% | train_error: 1.74 | train_acc: 0.832 
+
    +
    +
      [==============>-------------------------] 37.60% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [==============>-------------------------] 37.70% | train_error: 1.72 | train_acc: 0.834 
+
    +
    +
      [==============>-------------------------] 37.80% | train_error: 1.73 | train_acc: 0.834 
+
    +
    +
      [==============>-------------------------] 37.90% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [==============>-------------------------] 38.00% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [==============>-------------------------] 38.10% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [==============>-------------------------] 38.20% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [==============>-------------------------] 38.30% | train_error: 1.72 | train_acc: 0.834 
+
    +
    +
      [==============>-------------------------] 38.40% | train_error: 1.73 | train_acc: 0.834 
+
    +
    +
      [==============>-------------------------] 38.50% | train_error: 1.73 | train_acc: 0.834 
+
    +
    +
      [==============>-------------------------] 38.60% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [==============>-------------------------] 38.70% | train_error: 1.73 | train_acc: 0.834 
+
    +
    +
      [==============>-------------------------] 38.80% | train_error: 1.72 | train_acc: 0.834 
+
    +
    +
      [==============>-------------------------] 38.90% | train_error: 1.72 | train_acc: 0.834 
+
    +
    +
      [==============>-------------------------] 39.00% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [==============>-------------------------] 39.10% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [==============>-------------------------] 39.20% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [==============>-------------------------] 39.30% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [==============>-------------------------] 39.40% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [==============>-------------------------] 39.50% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [==============>-------------------------] 39.60% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [==============>-------------------------] 39.70% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [==============>-------------------------] 39.80% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [==============>-------------------------] 39.90% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [===============>------------------------] 40.00% | train_error: 1.73 | train_acc: 0.833 
+
    +
    +
      [===============>------------------------] 40.10% | train_error: 1.72 | train_acc: 0.834 
+
    +
    +
      [===============>------------------------] 40.20% | train_error: 1.72 | train_acc: 0.834 
+
    +
    +
      [===============>------------------------] 40.30% | train_error: 1.72 | train_acc: 0.834 
+
    +
    +
      [===============>------------------------] 40.40% | train_error: 1.71 | train_acc: 0.835 
+
    +
    +
      [===============>------------------------] 40.50% | train_error: 1.71 | train_acc: 0.835 
+
    +
    +
      [===============>------------------------] 40.60% | train_error: 1.71 | train_acc: 0.835 
+
    +
    +
      [===============>------------------------] 40.70% | train_error: 1.71 | train_acc: 0.835 
+
    +
    +
      [===============>------------------------] 40.80% | train_error: 1.71 | train_acc: 0.835 
+
    +
    +
      [===============>------------------------] 40.90% | train_error: 1.71 | train_acc: 0.835 
+
    +
    +
      [===============>------------------------] 41.00% | train_error: 1.71 | train_acc: 0.835 
+
    +
    +
      [===============>------------------------] 41.10% | train_error: 1.71 | train_acc: 0.835 
+
    +
    +
      [===============>------------------------] 41.20% | train_error: 1.71 | train_acc: 0.835 
+
    +
    +
      [===============>------------------------] 41.30% | train_error: 1.71 | train_acc: 0.835 
+
    +
    +
      [===============>------------------------] 41.40% | train_error: 1.71 | train_acc: 0.835 
+
    +
    +
      [===============>------------------------] 41.50% | train_error: 1.70 | train_acc: 0.836 
+
    +
    +
      [===============>------------------------] 41.60% | train_error: 1.70 | train_acc: 0.836 
+
    +
    +
      [===============>------------------------] 41.70% | train_error: 1.70 | train_acc: 0.836 
+
    +
    +
      [===============>------------------------] 41.80% | train_error: 1.70 | train_acc: 0.836 
+
    +
    +
      [===============>------------------------] 41.90% | train_error: 1.70 | train_acc: 0.836 
+
    +
    +
      [===============>------------------------] 42.00% | train_error: 1.70 | train_acc: 0.836 
+
    +
    +
      [===============>------------------------] 42.10% | train_error: 1.69 | train_acc: 0.837 
+
    +
    +
      [===============>------------------------] 42.20% | train_error: 1.69 | train_acc: 0.837 
+
    +
    +
      [===============>------------------------] 42.30% | train_error: 1.69 | train_acc: 0.837 
+
    +
    +
      [===============>------------------------] 42.40% | train_error: 1.69 | train_acc: 0.837 
+
    +
    +
      [================>-----------------------] 42.50% | train_error: 1.69 | train_acc: 0.837 
+
    +
    +
      [================>-----------------------] 42.60% | train_error: 1.69 | train_acc: 0.837 
+
    +
    +
      [================>-----------------------] 42.70% | train_error: 1.68 | train_acc: 0.838 
+
    +
    +
      [================>-----------------------] 42.80% | train_error: 1.68 | train_acc: 0.838 
+
    +
    +
      [================>-----------------------] 42.90% | train_error: 1.68 | train_acc: 0.838 
+
    +
    +
      [================>-----------------------] 43.00% | train_error: 1.68 | train_acc: 0.838 
+
    +
    +
      [================>-----------------------] 43.10% | train_error: 1.68 | train_acc: 0.838 
+
    +
    +
      [================>-----------------------] 43.20% | train_error: 1.67 | train_acc: 0.839 
+
    +
    +
      [================>-----------------------] 43.30% | train_error: 1.67 | train_acc: 0.839 
+
    +
    +
      [================>-----------------------] 43.40% | train_error: 1.67 | train_acc: 0.839 
+
    +
    +
      [================>-----------------------] 43.50% | train_error: 1.67 | train_acc: 0.839 
+
    +
    +
      [================>-----------------------] 43.60% | train_error: 1.66 | train_acc: 0.840 
+
    +
    +
      [================>-----------------------] 43.70% | train_error: 1.66 | train_acc: 0.840 
+
    +
    +
      [================>-----------------------] 43.80% | train_error: 1.65 | train_acc: 0.840 
+
    +
    +
      [================>-----------------------] 43.90% | train_error: 1.65 | train_acc: 0.841 
+
    +
    +
      [================>-----------------------] 44.00% | train_error: 1.65 | train_acc: 0.841 
+
    +
    +
      [================>-----------------------] 44.10% | train_error: 1.64 | train_acc: 0.841 
+
    +
    +
      [================>-----------------------] 44.20% | train_error: 1.64 | train_acc: 0.842 
+
    +
    +
      [================>-----------------------] 44.30% | train_error: 1.62 | train_acc: 0.843 
+
    +
    +
      [================>-----------------------] 44.40% | train_error: 1.62 | train_acc: 0.843 
+
    +
    +
      [================>-----------------------] 44.50% | train_error: 1.62 | train_acc: 0.843 
+
    +
    +
      [================>-----------------------] 44.60% | train_error: 1.62 | train_acc: 0.844 
+
    +
    +
      [================>-----------------------] 44.70% | train_error: 1.61 | train_acc: 0.844 
+
    +
    +
      [================>-----------------------] 44.80% | train_error: 1.61 | train_acc: 0.845 
+
    +
    +
      [================>-----------------------] 44.90% | train_error: 1.60 | train_acc: 0.846 
+
    +
    +
      [=================>----------------------] 45.00% | train_error: 1.59 | train_acc: 0.846 
+
    +
    +
      [=================>----------------------] 45.10% | train_error: 1.59 | train_acc: 0.846 
+
    +
    +
      [=================>----------------------] 45.20% | train_error: 1.59 | train_acc: 0.847 
+
    +
    +
      [=================>----------------------] 45.30% | train_error: 1.58 | train_acc: 0.847 
+
    +
    +
      [=================>----------------------] 45.40% | train_error: 1.58 | train_acc: 0.847 
+
    +
    +
      [=================>----------------------] 45.50% | train_error: 1.58 | train_acc: 0.848 
+
    +
    +
      [=================>----------------------] 45.60% | train_error: 1.57 | train_acc: 0.848 
+
    +
    +
      [=================>----------------------] 45.70% | train_error: 1.57 | train_acc: 0.849 
+
    +
    +
      [=================>----------------------] 45.80% | train_error: 1.56 | train_acc: 0.849 
+
    +
    +
      [=================>----------------------] 45.90% | train_error: 1.56 | train_acc: 0.850 
+
    +
    +
      [=================>----------------------] 46.00% | train_error: 1.55 | train_acc: 0.850 
+
    +
    +
      [=================>----------------------] 46.10% | train_error: 1.55 | train_acc: 0.851 
+
    +
    +
      [=================>----------------------] 46.20% | train_error: 1.55 | train_acc: 0.851 
+
    +
    +
      [=================>----------------------] 46.30% | train_error: 1.54 | train_acc: 0.852 
+
    +
    +
      [=================>----------------------] 46.40% | train_error: 1.53 | train_acc: 0.852 
+
    +
    +
      [=================>----------------------] 46.50% | train_error: 1.53 | train_acc: 0.852 
+
    +
    +
      [=================>----------------------] 46.60% | train_error: 1.53 | train_acc: 0.853 
+
    +
    +
      [=================>----------------------] 46.70% | train_error: 1.52 | train_acc: 0.853 
+
    +
    +
      [=================>----------------------] 46.80% | train_error: 1.52 | train_acc: 0.854 
+
    +
    +
      [=================>----------------------] 46.90% | train_error: 1.52 | train_acc: 0.854 
+
    +
    +
      [=================>----------------------] 47.00% | train_error: 1.51 | train_acc: 0.854 
+
    +
    +
      [=================>----------------------] 47.10% | train_error: 1.51 | train_acc: 0.854 
+
    +
    +
      [=================>----------------------] 47.20% | train_error: 1.50 | train_acc: 0.855 
+
    +
    +
      [=================>----------------------] 47.30% | train_error: 1.50 | train_acc: 0.855 
+
    +
    +
      [=================>----------------------] 47.40% | train_error: 1.49 | train_acc: 0.856 
+
    +
    +
      [==================>---------------------] 47.50% | train_error: 1.47 | train_acc: 0.858 
+
    +
    +
      [==================>---------------------] 47.60% | train_error: 1.47 | train_acc: 0.858 
+
    +
    +
      [==================>---------------------] 47.70% | train_error: 1.47 | train_acc: 0.858 
+
    +
    +
      [==================>---------------------] 47.80% | train_error: 1.46 | train_acc: 0.859 
+
    +
    +
      [==================>---------------------] 47.90% | train_error: 1.46 | train_acc: 0.859 
+
    +
    +
      [==================>---------------------] 48.00% | train_error: 1.46 | train_acc: 0.859 
+
    +
    +
      [==================>---------------------] 48.10% | train_error: 1.46 | train_acc: 0.859 
+
    +
    +
      [==================>---------------------] 48.20% | train_error: 1.46 | train_acc: 0.859 
+
    +
    +
      [==================>---------------------] 48.30% | train_error: 1.46 | train_acc: 0.859 
+
    +
    +
      [==================>---------------------] 48.40% | train_error: 1.45 | train_acc: 0.860 
+
    +
    +
      [==================>---------------------] 48.50% | train_error: 1.44 | train_acc: 0.861 
+
    +
    +
      [==================>---------------------] 48.60% | train_error: 1.44 | train_acc: 0.861 
+
    +
    +
      [==================>---------------------] 48.70% | train_error: 1.44 | train_acc: 0.861 
+
    +
    +
      [==================>---------------------] 48.80% | train_error: 1.44 | train_acc: 0.861 
+
    +
    +
      [==================>---------------------] 48.90% | train_error: 1.43 | train_acc: 0.862 
+
    +
    +
      [==================>---------------------] 49.00% | train_error: 1.42 | train_acc: 0.863 
+
    +
    +
      [==================>---------------------] 49.10% | train_error: 1.41 | train_acc: 0.864 
+
    +
    +
      [==================>---------------------] 49.20% | train_error: 1.40 | train_acc: 0.865 
+
    +
    +
      [==================>---------------------] 49.30% | train_error: 1.39 | train_acc: 0.866 
+
    +
    +
      [==================>---------------------] 49.40% | train_error: 1.39 | train_acc: 0.866 
+
    +
    +
      [==================>---------------------] 49.50% | train_error: 1.39 | train_acc: 0.866 
+
    +
    +
      [==================>---------------------] 49.60% | train_error: 1.39 | train_acc: 0.866 
+
    +
    +
      [==================>---------------------] 49.70% | train_error: 1.38 | train_acc: 0.867 
+
    +
    +
      [==================>---------------------] 49.80% | train_error: 1.38 | train_acc: 0.867 
+
    +
    +
      [==================>---------------------] 49.90% | train_error: 1.37 | train_acc: 0.868 
+
    +
    +
      [===================>--------------------] 50.00% | train_error: 1.36 | train_acc: 0.869 
+
    +
    +
      [===================>--------------------] 50.10% | train_error: 1.35 | train_acc: 0.869 
+
    +
    +
      [===================>--------------------] 50.20% | train_error: 1.35 | train_acc: 0.870 
+
    +
    +
      [===================>--------------------] 50.30% | train_error: 1.34 | train_acc: 0.870 
+
    +
    +
      [===================>--------------------] 50.40% | train_error: 1.34 | train_acc: 0.870 
+
    +
    +
      [===================>--------------------] 50.50% | train_error: 1.34 | train_acc: 0.870 
+
    +
    +
      [===================>--------------------] 50.60% | train_error: 1.34 | train_acc: 0.871 
+
    +
    +
      [===================>--------------------] 50.70% | train_error: 1.33 | train_acc: 0.872 
+
    +
    +
      [===================>--------------------] 50.80% | train_error: 1.32 | train_acc: 0.873 
+
    +
    +
      [===================>--------------------] 50.90% | train_error: 1.31 | train_acc: 0.873 
+
    +
    +
      [===================>--------------------] 51.00% | train_error: 1.31 | train_acc: 0.874 
+
    +
    +
      [===================>--------------------] 51.10% | train_error: 1.31 | train_acc: 0.874 
+
    +
    +
      [===================>--------------------] 51.20% | train_error: 1.31 | train_acc: 0.874 
+
    +
    +
      [===================>--------------------] 51.30% | train_error: 1.31 | train_acc: 0.874 
+
    +
    +
      [===================>--------------------] 51.40% | train_error: 1.31 | train_acc: 0.874 
+
    +
    +
      [===================>--------------------] 51.50% | train_error: 1.31 | train_acc: 0.874 
+
    +
    +
      [===================>--------------------] 51.60% | train_error: 1.30 | train_acc: 0.874 
+
    +
    +
      [===================>--------------------] 51.70% | train_error: 1.30 | train_acc: 0.875 
+
    +
    +
      [===================>--------------------] 51.80% | train_error: 1.30 | train_acc: 0.875 
+
    +
    +
      [===================>--------------------] 51.90% | train_error: 1.29 | train_acc: 0.875 
+
    +
    +
      [===================>--------------------] 52.00% | train_error: 1.29 | train_acc: 0.875 
+
    +
    +
      [===================>--------------------] 52.10% | train_error: 1.29 | train_acc: 0.875 
+
    +
    +
      [===================>--------------------] 52.20% | train_error: 1.29 | train_acc: 0.875 
+
    +
    +
      [===================>--------------------] 52.30% | train_error: 1.29 | train_acc: 0.876 
+
    +
    +
      [===================>--------------------] 52.40% | train_error: 1.28 | train_acc: 0.876 
+
    +
    +
      [====================>-------------------] 52.50% | train_error: 1.28 | train_acc: 0.876 
+
    +
    +
      [====================>-------------------] 52.60% | train_error: 1.28 | train_acc: 0.877 
+
    +
    +
      [====================>-------------------] 52.70% | train_error: 1.28 | train_acc: 0.877 
+
    +
    +
      [====================>-------------------] 52.80% | train_error: 1.27 | train_acc: 0.877 
+
    +
    +
      [====================>-------------------] 52.90% | train_error: 1.27 | train_acc: 0.877 
+
    +
    +
      [====================>-------------------] 53.00% | train_error: 1.27 | train_acc: 0.877 
+
    +
    +
      [====================>-------------------] 53.10% | train_error: 1.27 | train_acc: 0.878 
+
    +
    +
      [====================>-------------------] 53.20% | train_error: 1.26 | train_acc: 0.878 
+
    +
    +
      [====================>-------------------] 53.30% | train_error: 1.26 | train_acc: 0.878 
+
    +
    +
      [====================>-------------------] 53.40% | train_error: 1.26 | train_acc: 0.879 
+
    +
    +
      [====================>-------------------] 53.50% | train_error: 1.25 | train_acc: 0.879 
+
    +
    +
      [====================>-------------------] 53.60% | train_error: 1.25 | train_acc: 0.880 
+
    +
    +
      [====================>-------------------] 53.70% | train_error: 1.24 | train_acc: 0.880 
+
    +
    +
      [====================>-------------------] 53.80% | train_error: 1.24 | train_acc: 0.880 
+
    +
    +
      [====================>-------------------] 53.90% | train_error: 1.24 | train_acc: 0.880 
+
    +
    +
      [====================>-------------------] 54.00% | train_error: 1.23 | train_acc: 0.881 
+
    +
    +
      [====================>-------------------] 54.10% | train_error: 1.22 | train_acc: 0.882 
+
    +
    +
      [====================>-------------------] 54.20% | train_error: 1.22 | train_acc: 0.882 
+
    +
    +
      [====================>-------------------] 54.30% | train_error: 1.21 | train_acc: 0.883 
+
    +
    +
      [====================>-------------------] 54.40% | train_error: 1.21 | train_acc: 0.883 
+
    +
    +
      [====================>-------------------] 54.50% | train_error: 1.21 | train_acc: 0.883 
+
    +
    +
      [====================>-------------------] 54.60% | train_error: 1.21 | train_acc: 0.883 
+
    +
    +
      [====================>-------------------] 54.70% | train_error: 1.21 | train_acc: 0.884 
+
    +
    +
      [====================>-------------------] 54.80% | train_error: 1.20 | train_acc: 0.884 
+
    +
    +
      [====================>-------------------] 54.90% | train_error: 1.20 | train_acc: 0.884 
+
    +
    +
      [=====================>------------------] 55.00% | train_error: 1.20 | train_acc: 0.884 
+
    +
    +
      [=====================>------------------] 55.10% | train_error: 1.20 | train_acc: 0.884 
+
    +
    +
      [=====================>------------------] 55.20% | train_error: 1.19 | train_acc: 0.885 
+
    +
    +
      [=====================>------------------] 55.30% | train_error: 1.19 | train_acc: 0.885 
+
    +
    +
      [=====================>------------------] 55.40% | train_error: 1.19 | train_acc: 0.885 
+
    +
    +
      [=====================>------------------] 55.50% | train_error: 1.19 | train_acc: 0.885 
+
    +
    +
      [=====================>------------------] 55.60% | train_error: 1.19 | train_acc: 0.885 
+
    +
    +
      [=====================>------------------] 55.70% | train_error: 1.19 | train_acc: 0.885 
+
    +
    +
      [=====================>------------------] 55.80% | train_error: 1.18 | train_acc: 0.886 
+
    +
    +
      [=====================>------------------] 55.90% | train_error: 1.19 | train_acc: 0.885 
+
    +
    +
      [=====================>------------------] 56.00% | train_error: 1.19 | train_acc: 0.885 
+
    +
    +
      [=====================>------------------] 56.10% | train_error: 1.18 | train_acc: 0.886 
+
    +
    +
      [=====================>------------------] 56.20% | train_error: 1.18 | train_acc: 0.886 
+
    +
    +
      [=====================>------------------] 56.30% | train_error: 1.17 | train_acc: 0.887 
+
    +
    +
      [=====================>------------------] 56.40% | train_error: 1.17 | train_acc: 0.887 
+
    +
    +
      [=====================>------------------] 56.50% | train_error: 1.17 | train_acc: 0.887 
+
    +
    +
      [=====================>------------------] 56.60% | train_error: 1.16 | train_acc: 0.888 
+
    +
    +
      [=====================>------------------] 56.70% | train_error: 1.16 | train_acc: 0.888 
+
    +
    +
      [=====================>------------------] 56.80% | train_error: 1.15 | train_acc: 0.889 
+
    +
    +
      [=====================>------------------] 56.90% | train_error: 1.15 | train_acc: 0.889 
+
    +
    +
      [=====================>------------------] 57.00% | train_error: 1.14 | train_acc: 0.890 
+
    +
    +
      [=====================>------------------] 57.10% | train_error: 1.14 | train_acc: 0.890 
+
    +
    +
      [=====================>------------------] 57.20% | train_error: 1.14 | train_acc: 0.890 
+
    +
    +
      [=====================>------------------] 57.30% | train_error: 1.14 | train_acc: 0.890 
+
    +
    +
      [=====================>------------------] 57.40% | train_error: 1.13 | train_acc: 0.891 
+
    +
    +
      [======================>-----------------] 57.50% | train_error: 1.13 | train_acc: 0.891 
+
    +
    +
      [======================>-----------------] 57.60% | train_error: 1.13 | train_acc: 0.891 
+
    +
    +
      [======================>-----------------] 57.70% | train_error: 1.12 | train_acc: 0.891 
+
    +
    +
      [======================>-----------------] 57.80% | train_error: 1.13 | train_acc: 0.891 
+
    +
    +
      [======================>-----------------] 57.90% | train_error: 1.12 | train_acc: 0.892 
+
    +
    +
      [======================>-----------------] 58.00% | train_error: 1.11 | train_acc: 0.893 
+
    +
    +
      [======================>-----------------] 58.10% | train_error: 1.11 | train_acc: 0.893 
+
    +
    +
      [======================>-----------------] 58.20% | train_error: 1.09 | train_acc: 0.894 
+
    +
    +
      [======================>-----------------] 58.30% | train_error: 1.09 | train_acc: 0.895 
+
    +
    +
      [======================>-----------------] 58.40% | train_error: 1.09 | train_acc: 0.895 
+
    +
    +
      [======================>-----------------] 58.50% | train_error: 1.09 | train_acc: 0.895 
+
    +
    +
      [======================>-----------------] 58.60% | train_error: 1.09 | train_acc: 0.895 
+
    +
    +
      [======================>-----------------] 58.70% | train_error: 1.09 | train_acc: 0.895 
+
    +
    +
      [======================>-----------------] 58.80% | train_error: 1.08 | train_acc: 0.895 
+
    +
    +
      [======================>-----------------] 58.90% | train_error: 1.08 | train_acc: 0.895 
+
    +
    +
      [======================>-----------------] 59.00% | train_error: 1.08 | train_acc: 0.896 
+
    +
    +
      [======================>-----------------] 59.10% | train_error: 1.08 | train_acc: 0.896 
+
    +
    +
      [======================>-----------------] 59.20% | train_error: 1.08 | train_acc: 0.896 
+
    +
    +
      [======================>-----------------] 59.30% | train_error: 1.07 | train_acc: 0.896 
+
    +
    +
      [======================>-----------------] 59.40% | train_error: 1.07 | train_acc: 0.897 
+
    +
    +
      [======================>-----------------] 59.50% | train_error: 1.06 | train_acc: 0.898 
+
    +
    +
      [======================>-----------------] 59.60% | train_error: 1.05 | train_acc: 0.898 
+
    +
    +
      [======================>-----------------] 59.70% | train_error: 1.05 | train_acc: 0.899 
+
    +
    +
      [======================>-----------------] 59.80% | train_error: 1.04 | train_acc: 0.899 
+
    +
    +
      [======================>-----------------] 59.90% | train_error: 1.04 | train_acc: 0.899 
+
    +
    +
      [=======================>----------------] 60.00% | train_error: 1.04 | train_acc: 0.899 
+
    +
    +
      [=======================>----------------] 60.10% | train_error: 1.04 | train_acc: 0.900 
+
    +
    +
      [=======================>----------------] 60.20% | train_error: 1.03 | train_acc: 0.900 
+
    +
    +
      [=======================>----------------] 60.30% | train_error: 1.03 | train_acc: 0.901 
+
    +
    +
      [=======================>----------------] 60.40% | train_error: 1.03 | train_acc: 0.901 
+
    +
    +
      [=======================>----------------] 60.50% | train_error: 1.02 | train_acc: 0.901 
+
    +
    +
      [=======================>----------------] 60.60% | train_error: 1.02 | train_acc: 0.902 
+
    +
    +
      [=======================>----------------] 60.70% | train_error: 1.01 | train_acc: 0.902 
+
    +
    +
      [=======================>----------------] 60.80% | train_error: 1.01 | train_acc: 0.903 
+
    +
    +
      [=======================>----------------] 60.90% | train_error: 1.00 | train_acc: 0.903 
+
    +
    +
      [=======================>----------------] 61.00% | train_error: 1.00 | train_acc: 0.903 
+
    +
    +
      [=======================>----------------] 61.10% | train_error: 1.00 | train_acc: 0.903 
+
    +
    +
      [=======================>----------------] 61.20% | train_error: 1.00 | train_acc: 0.903 
+
    +
    +
      [=======================>----------------] 61.30% | train_error: 0.999 | train_acc: 0.904 
+
    +
    +
      [=======================>----------------] 61.40% | train_error: 0.998 | train_acc: 0.904 
+
    +
    +
      [=======================>----------------] 61.50% | train_error: 0.998 | train_acc: 0.904 
+
    +
    +
      [=======================>----------------] 61.60% | train_error: 0.994 | train_acc: 0.904 
+
    +
    +
      [=======================>----------------] 61.70% | train_error: 0.994 | train_acc: 0.904 
+
    +
    +
      [=======================>----------------] 61.80% | train_error: 0.991 | train_acc: 0.904 
+
    +
    +
      [=======================>----------------] 61.90% | train_error: 0.987 | train_acc: 0.905 
+
    +
    +
      [=======================>----------------] 62.00% | train_error: 0.986 | train_acc: 0.905 
+
    +
    +
      [=======================>----------------] 62.10% | train_error: 0.978 | train_acc: 0.906 
+
    +
    +
      [=======================>----------------] 62.20% | train_error: 0.976 | train_acc: 0.906 
+
    +
    +
      [=======================>----------------] 62.30% | train_error: 0.976 | train_acc: 0.906 
+
    +
    +
      [=======================>----------------] 62.40% | train_error: 0.973 | train_acc: 0.906 
+
    +
    +
      [========================>---------------] 62.50% | train_error: 0.972 | train_acc: 0.906 
+
    +
    +
      [========================>---------------] 62.60% | train_error: 0.968 | train_acc: 0.907 
+
    +
    +
      [========================>---------------] 62.70% | train_error: 0.968 | train_acc: 0.907 
+
    +
    +
      [========================>---------------] 62.80% | train_error: 0.965 | train_acc: 0.907 
+
    +
    +
      [========================>---------------] 62.90% | train_error: 0.966 | train_acc: 0.907 
+
    +
    +
      [========================>---------------] 63.00% | train_error: 0.962 | train_acc: 0.907 
+
    +
    +
      [========================>---------------] 63.10% | train_error: 0.954 | train_acc: 0.908 
+
    +
    +
      [========================>---------------] 63.20% | train_error: 0.951 | train_acc: 0.908 
+
    +
    +
      [========================>---------------] 63.30% | train_error: 0.948 | train_acc: 0.909 
+
    +
    +
      [========================>---------------] 63.40% | train_error: 0.946 | train_acc: 0.909 
+
    +
    +
      [========================>---------------] 63.50% | train_error: 0.943 | train_acc: 0.909 
+
    +
    +
      [========================>---------------] 63.60% | train_error: 0.935 | train_acc: 0.910 
+
    +
    +
      [========================>---------------] 63.70% | train_error: 0.926 | train_acc: 0.911 
+
    +
    +
      [========================>---------------] 63.80% | train_error: 0.926 | train_acc: 0.911 
+
    +
    +
      [========================>---------------] 63.90% | train_error: 0.926 | train_acc: 0.911 
+
    +
    +
      [========================>---------------] 64.00% | train_error: 0.914 | train_acc: 0.912 
+
    +
    +
      [========================>---------------] 64.10% | train_error: 0.914 | train_acc: 0.912 
+
    +
    +
      [========================>---------------] 64.20% | train_error: 0.906 | train_acc: 0.913 
+
    +
    +
      [========================>---------------] 64.30% | train_error: 0.903 | train_acc: 0.913 
+
    +
    +
      [========================>---------------] 64.40% | train_error: 0.900 | train_acc: 0.913 
+
    +
    +
      [========================>---------------] 64.50% | train_error: 0.895 | train_acc: 0.914 
+
    +
    +
      [========================>---------------] 64.60% | train_error: 0.894 | train_acc: 0.914 
+
    +
    +
      [========================>---------------] 64.70% | train_error: 0.891 | train_acc: 0.914 
+
    +
    +
      [========================>---------------] 64.80% | train_error: 0.893 | train_acc: 0.914 
+
    +
    +
      [========================>---------------] 64.90% | train_error: 0.893 | train_acc: 0.914 
+
    +
    +
      [=========================>--------------] 65.00% | train_error: 0.890 | train_acc: 0.914 
+
    +
    +
      [=========================>--------------] 65.10% | train_error: 0.889 | train_acc: 0.914 
+
    +
    +
      [=========================>--------------] 65.20% | train_error: 0.883 | train_acc: 0.915 
+
    +
    +
      [=========================>--------------] 65.30% | train_error: 0.880 | train_acc: 0.915 
+
    +
    +
      [=========================>--------------] 65.40% | train_error: 0.878 | train_acc: 0.915 
+
    +
    +
      [=========================>--------------] 65.50% | train_error: 0.876 | train_acc: 0.915 
+
    +
    +
      [=========================>--------------] 65.60% | train_error: 0.875 | train_acc: 0.916 
+
    +
    +
      [=========================>--------------] 65.70% | train_error: 0.874 | train_acc: 0.916 
+
    +
    +
      [=========================>--------------] 65.80% | train_error: 0.875 | train_acc: 0.916 
+
    +
    +
      [=========================>--------------] 65.90% | train_error: 0.873 | train_acc: 0.916 
+
    +
    +
      [=========================>--------------] 66.00% | train_error: 0.871 | train_acc: 0.916 
+
    +
    +
      [=========================>--------------] 66.10% | train_error: 0.868 | train_acc: 0.916 
+
    +
    +
      [=========================>--------------] 66.20% | train_error: 0.866 | train_acc: 0.916 
+
    +
    +
      [=========================>--------------] 66.30% | train_error: 0.864 | train_acc: 0.917 
+
    +
    +
      [=========================>--------------] 66.40% | train_error: 0.855 | train_acc: 0.918 
+
    +
    +
      [=========================>--------------] 66.50% | train_error: 0.851 | train_acc: 0.918 
+
    +
    +
      [=========================>--------------] 66.60% | train_error: 0.850 | train_acc: 0.918 
+
    +
    +
      [=========================>--------------] 66.70% | train_error: 0.850 | train_acc: 0.918 
+
    +
    +
      [=========================>--------------] 66.80% | train_error: 0.848 | train_acc: 0.918 
+
    +
    +
      [=========================>--------------] 66.90% | train_error: 0.844 | train_acc: 0.919 
+
    +
    +
      [=========================>--------------] 67.00% | train_error: 0.845 | train_acc: 0.918 
+
    +
    +
      [=========================>--------------] 67.10% | train_error: 0.842 | train_acc: 0.919 
+
    +
    +
      [=========================>--------------] 67.20% | train_error: 0.841 | train_acc: 0.919 
+
    +
    +
      [=========================>--------------] 67.30% | train_error: 0.841 | train_acc: 0.919 
+
    +
    +
      [=========================>--------------] 67.40% | train_error: 0.836 | train_acc: 0.919 
+
    +
    +
      [==========================>-------------] 67.50% | train_error: 0.821 | train_acc: 0.921 
+
    +
    +
      [==========================>-------------] 67.60% | train_error: 0.808 | train_acc: 0.922 
+
    +
    +
      [==========================>-------------] 67.70% | train_error: 0.805 | train_acc: 0.922 
+
    +
    +
      [==========================>-------------] 67.80% | train_error: 0.800 | train_acc: 0.923 
+
    +
    +
      [==========================>-------------] 67.90% | train_error: 0.799 | train_acc: 0.923 
+
    +
    +
      [==========================>-------------] 68.00% | train_error: 0.792 | train_acc: 0.924 
+
    +
    +
      [==========================>-------------] 68.10% | train_error: 0.791 | train_acc: 0.924 
+
    +
    +
      [==========================>-------------] 68.20% | train_error: 0.782 | train_acc: 0.925 
+
    +
    +
      [==========================>-------------] 68.30% | train_error: 0.774 | train_acc: 0.925 
+
    +
    +
      [==========================>-------------] 68.40% | train_error: 0.766 | train_acc: 0.926 
+
    +
    +
      [==========================>-------------] 68.50% | train_error: 0.763 | train_acc: 0.926 
+
    +
    +
      [==========================>-------------] 68.60% | train_error: 0.757 | train_acc: 0.927 
+
    +
    +
      [==========================>-------------] 68.70% | train_error: 0.753 | train_acc: 0.927 
+
    +
    +
      [==========================>-------------] 68.80% | train_error: 0.754 | train_acc: 0.927 
+
    +
    +
      [==========================>-------------] 68.90% | train_error: 0.747 | train_acc: 0.928 
+
    +
    +
      [==========================>-------------] 69.00% | train_error: 0.740 | train_acc: 0.929 
+
    +
    +
      [==========================>-------------] 69.10% | train_error: 0.746 | train_acc: 0.928 
+
    +
    +
      [==========================>-------------] 69.20% | train_error: 0.737 | train_acc: 0.929 
+
    +
    +
      [==========================>-------------] 69.30% | train_error: 0.744 | train_acc: 0.928 
+
    +
    +
      [==========================>-------------] 69.40% | train_error: 0.736 | train_acc: 0.929 
+
    +
    +
      [==========================>-------------] 69.50% | train_error: 0.745 | train_acc: 0.928 
+
    +
    +
      [==========================>-------------] 69.60% | train_error: 0.737 | train_acc: 0.929 
+
    +
    +
      [==========================>-------------] 69.70% | train_error: 0.736 | train_acc: 0.929 
+
    +
    +
      [==========================>-------------] 69.80% | train_error: 0.724 | train_acc: 0.930 
+
    +
    +
      [==========================>-------------] 69.90% | train_error: 0.722 | train_acc: 0.930 
+
    +
    +
      [===========================>------------] 70.00% | train_error: 0.718 | train_acc: 0.931 
+
    +
    +
      [===========================>------------] 70.10% | train_error: 0.718 | train_acc: 0.931 
+
    +
    +
      [===========================>------------] 70.20% | train_error: 0.717 | train_acc: 0.931 
+
    +
    +
      [===========================>------------] 70.30% | train_error: 0.712 | train_acc: 0.931 
+
    +
    +
      [===========================>------------] 70.40% | train_error: 0.713 | train_acc: 0.931 
+
    +
    +
      [===========================>------------] 70.50% | train_error: 0.710 | train_acc: 0.931 
+
    +
    +
      [===========================>------------] 70.60% | train_error: 0.708 | train_acc: 0.932 
+
    +
    +
      [===========================>------------] 70.70% | train_error: 0.705 | train_acc: 0.932 
+
    +
    +
      [===========================>------------] 70.80% | train_error: 0.702 | train_acc: 0.932 
+
    +
    +
      [===========================>------------] 70.90% | train_error: 0.701 | train_acc: 0.932 
+
    +
    +
      [===========================>------------] 71.00% | train_error: 0.695 | train_acc: 0.933 
+
    +
    +
      [===========================>------------] 71.10% | train_error: 0.694 | train_acc: 0.933 
+
    +
    +
      [===========================>------------] 71.20% | train_error: 0.691 | train_acc: 0.933 
+
    +
    +
      [===========================>------------] 71.30% | train_error: 0.687 | train_acc: 0.934 
+
    +
    +
      [===========================>------------] 71.40% | train_error: 0.683 | train_acc: 0.934 
+
    +
    +
      [===========================>------------] 71.50% | train_error: 0.682 | train_acc: 0.934 
+
    +
    +
      [===========================>------------] 71.60% | train_error: 0.677 | train_acc: 0.935 
+
    +
    +
      [===========================>------------] 71.70% | train_error: 0.672 | train_acc: 0.935 
+
    +
    +
      [===========================>------------] 71.80% | train_error: 0.669 | train_acc: 0.935 
+
    +
    +
      [===========================>------------] 71.90% | train_error: 0.669 | train_acc: 0.935 
+
    +
    +
      [===========================>------------] 72.00% | train_error: 0.668 | train_acc: 0.936 
+
    +
    +
      [===========================>------------] 72.10% | train_error: 0.665 | train_acc: 0.936 
+
    +
    +
      [===========================>------------] 72.20% | train_error: 0.658 | train_acc: 0.936 
+
    +
    +
      [===========================>------------] 72.30% | train_error: 0.655 | train_acc: 0.937 
+
    +
    +
      [===========================>------------] 72.40% | train_error: 0.654 | train_acc: 0.937 
+
    +
    +
      [============================>-----------] 72.50% | train_error: 0.657 | train_acc: 0.937 
+
    +
    +
      [============================>-----------] 72.60% | train_error: 0.652 | train_acc: 0.937 
+
    +
    +
      [============================>-----------] 72.70% | train_error: 0.647 | train_acc: 0.938 
+
    +
    +
      [============================>-----------] 72.80% | train_error: 0.645 | train_acc: 0.938 
+
    +
    +
      [============================>-----------] 72.90% | train_error: 0.645 | train_acc: 0.938 
+
    +
    +
      [============================>-----------] 73.00% | train_error: 0.630 | train_acc: 0.939 
+
    +
    +
      [============================>-----------] 73.10% | train_error: 0.637 | train_acc: 0.939 
+
    +
    +
      [============================>-----------] 73.20% | train_error: 0.624 | train_acc: 0.940 
+
    +
    +
      [============================>-----------] 73.30% | train_error: 0.630 | train_acc: 0.939 
+
    +
    +
      [============================>-----------] 73.40% | train_error: 0.618 | train_acc: 0.940 
+
    +
    +
      [============================>-----------] 73.50% | train_error: 0.623 | train_acc: 0.940 
+
    +
    +
      [============================>-----------] 73.60% | train_error: 0.611 | train_acc: 0.941 
+
    +
    +
      [============================>-----------] 73.70% | train_error: 0.612 | train_acc: 0.941 
+
    +
    +
      [============================>-----------] 73.80% | train_error: 0.614 | train_acc: 0.941 
+
    +
    +
      [============================>-----------] 73.90% | train_error: 0.608 | train_acc: 0.941 
+
    +
    +
      [============================>-----------] 74.00% | train_error: 0.605 | train_acc: 0.942 
+
    +
    +
      [============================>-----------] 74.10% | train_error: 0.609 | train_acc: 0.941 
+
    +
    +
      [============================>-----------] 74.20% | train_error: 0.604 | train_acc: 0.942 
+
    +
    +
      [============================>-----------] 74.30% | train_error: 0.601 | train_acc: 0.942 
+
    +
    +
      [============================>-----------] 74.40% | train_error: 0.600 | train_acc: 0.942 
+
    +
    +
      [============================>-----------] 74.50% | train_error: 0.601 | train_acc: 0.942 
+
    +
    +
      [============================>-----------] 74.60% | train_error: 0.599 | train_acc: 0.942 
+
    +
    +
      [============================>-----------] 74.70% | train_error: 0.593 | train_acc: 0.943 
+
    +
    +
      [============================>-----------] 74.80% | train_error: 0.592 | train_acc: 0.943 
+
    +
    +
      [============================>-----------] 74.90% | train_error: 0.593 | train_acc: 0.943 
+
    +
    +
      [=============================>----------] 75.00% | train_error: 0.589 | train_acc: 0.943 
+
    +
    +
      [=============================>----------] 75.10% | train_error: 0.590 | train_acc: 0.943 
+
    +
    +
      [=============================>----------] 75.20% | train_error: 0.585 | train_acc: 0.944 
+
    +
    +
      [=============================>----------] 75.30% | train_error: 0.590 | train_acc: 0.943 
+
    +
    +
      [=============================>----------] 75.40% | train_error: 0.580 | train_acc: 0.944 
+
    +
    +
      [=============================>----------] 75.50% | train_error: 0.579 | train_acc: 0.944 
+
    +
    +
      [=============================>----------] 75.60% | train_error: 0.574 | train_acc: 0.945 
+
    +
    +
      [=============================>----------] 75.70% | train_error: 0.578 | train_acc: 0.944 
+
    +
    +
      [=============================>----------] 75.80% | train_error: 0.560 | train_acc: 0.946 
+
    +
    +
      [=============================>----------] 75.90% | train_error: 0.566 | train_acc: 0.945 
+
    +
    +
      [=============================>----------] 76.00% | train_error: 0.564 | train_acc: 0.946 
+
    +
    +
      [=============================>----------] 76.10% | train_error: 0.563 | train_acc: 0.946 
+
    +
    +
      [=============================>----------] 76.20% | train_error: 0.559 | train_acc: 0.946 
+
    +
    +
      [=============================>----------] 76.30% | train_error: 0.560 | train_acc: 0.946 
+
    +
    +
      [=============================>----------] 76.40% | train_error: 0.549 | train_acc: 0.947 
+
    +
    +
      [=============================>----------] 76.50% | train_error: 0.563 | train_acc: 0.946 
+
    +
    +
      [=============================>----------] 76.60% | train_error: 0.542 | train_acc: 0.948 
+
    +
    +
      [=============================>----------] 76.70% | train_error: 0.558 | train_acc: 0.946 
+
    +
    +
      [=============================>----------] 76.80% | train_error: 0.542 | train_acc: 0.948 
+
    +
    +
      [=============================>----------] 76.90% | train_error: 0.556 | train_acc: 0.946 
+
    +
    +
      [=============================>----------] 77.00% | train_error: 0.536 | train_acc: 0.948 
+
    +
    +
      [=============================>----------] 77.10% | train_error: 0.549 | train_acc: 0.947 
+
    +
    +
      [=============================>----------] 77.20% | train_error: 0.529 | train_acc: 0.949 
+
    +
    +
      [=============================>----------] 77.30% | train_error: 0.536 | train_acc: 0.948 
+
    +
    +
      [=============================>----------] 77.40% | train_error: 0.534 | train_acc: 0.949 
+
    +
    +
      [==============================>---------] 77.50% | train_error: 0.532 | train_acc: 0.949 
+
    +
    +
      [==============================>---------] 77.60% | train_error: 0.528 | train_acc: 0.949 
+
    +
    +
      [==============================>---------] 77.70% | train_error: 0.526 | train_acc: 0.949 
+
    +
    +
      [==============================>---------] 77.80% | train_error: 0.515 | train_acc: 0.950 
+
    +
    +
      [==============================>---------] 77.90% | train_error: 0.517 | train_acc: 0.950 
+
    +
    +
      [==============================>---------] 78.00% | train_error: 0.510 | train_acc: 0.951 
+
    +
    +
      [==============================>---------] 78.10% | train_error: 0.511 | train_acc: 0.951 
+
    +
    +
      [==============================>---------] 78.20% | train_error: 0.510 | train_acc: 0.951 
+
    +
    +
      [==============================>---------] 78.30% | train_error: 0.504 | train_acc: 0.951 
+
    +
    +
      [==============================>---------] 78.40% | train_error: 0.510 | train_acc: 0.951 
+
    +
    +
      [==============================>---------] 78.50% | train_error: 0.507 | train_acc: 0.951 
+
    +
    +
      [==============================>---------] 78.60% | train_error: 0.509 | train_acc: 0.951 
+
    +
    +
      [==============================>---------] 78.70% | train_error: 0.499 | train_acc: 0.952 
+
    +
    +
      [==============================>---------] 78.80% | train_error: 0.506 | train_acc: 0.951 
+
    +
    +
      [==============================>---------] 78.90% | train_error: 0.499 | train_acc: 0.952 
+
    +
    +
      [==============================>---------] 79.00% | train_error: 0.504 | train_acc: 0.951 
+
    +
    +
      [==============================>---------] 79.10% | train_error: 0.503 | train_acc: 0.952 
+
    +
    +
      [==============================>---------] 79.20% | train_error: 0.495 | train_acc: 0.952 
+
    +
    +
      [==============================>---------] 79.30% | train_error: 0.495 | train_acc: 0.952 
+
    +
    +
      [==============================>---------] 79.40% | train_error: 0.488 | train_acc: 0.953 
+
    +
    +
      [==============================>---------] 79.50% | train_error: 0.482 | train_acc: 0.953 
+
    +
    +
      [==============================>---------] 79.60% | train_error: 0.473 | train_acc: 0.954 
+
    +
    +
      [==============================>---------] 79.70% | train_error: 0.476 | train_acc: 0.954 
+
    +
    +
      [==============================>---------] 79.80% | train_error: 0.477 | train_acc: 0.954 
+
    +
    +
      [==============================>---------] 79.90% | train_error: 0.468 | train_acc: 0.955 
+
    +
    +
      [===============================>--------] 80.00% | train_error: 0.472 | train_acc: 0.954 
+
    +
    +
      [===============================>--------] 80.10% | train_error: 0.466 | train_acc: 0.955 
+
    +
    +
      [===============================>--------] 80.20% | train_error: 0.473 | train_acc: 0.954 
+
    +
    +
      [===============================>--------] 80.30% | train_error: 0.464 | train_acc: 0.955 
+
    +
    +
      [===============================>--------] 80.40% | train_error: 0.467 | train_acc: 0.955 
+
    +
    +
      [===============================>--------] 80.50% | train_error: 0.458 | train_acc: 0.956 
+
    +
    +
      [===============================>--------] 80.60% | train_error: 0.461 | train_acc: 0.955 
+
    +
    +
      [===============================>--------] 80.70% | train_error: 0.449 | train_acc: 0.957 
+
    +
    +
      [===============================>--------] 80.80% | train_error: 0.464 | train_acc: 0.955 
+
    +
    +
      [===============================>--------] 80.90% | train_error: 0.446 | train_acc: 0.957 
+
    +
    +
      [===============================>--------] 81.00% | train_error: 0.456 | train_acc: 0.956 
+
    +
    +
      [===============================>--------] 81.10% | train_error: 0.449 | train_acc: 0.957 
+
    +
    +
      [===============================>--------] 81.20% | train_error: 0.454 | train_acc: 0.956 
+
    +
    +
      [===============================>--------] 81.30% | train_error: 0.446 | train_acc: 0.957 
+
    +
    +
      [===============================>--------] 81.40% | train_error: 0.443 | train_acc: 0.957 
+
    +
    +
      [===============================>--------] 81.50% | train_error: 0.443 | train_acc: 0.957 
+
    +
    +
      [===============================>--------] 81.60% | train_error: 0.429 | train_acc: 0.959 
+
    +
    +
      [===============================>--------] 81.70% | train_error: 0.434 | train_acc: 0.958 
+
    +
    +
      [===============================>--------] 81.80% | train_error: 0.427 | train_acc: 0.959 
+
    +
    +
      [===============================>--------] 81.90% | train_error: 0.422 | train_acc: 0.959 
+
    +
    +
      [===============================>--------] 82.00% | train_error: 0.419 | train_acc: 0.960 
+
    +
    +
      [===============================>--------] 82.10% | train_error: 0.424 | train_acc: 0.959 
+
    +
    +
      [===============================>--------] 82.20% | train_error: 0.424 | train_acc: 0.959 
+
    +
    +
      [===============================>--------] 82.30% | train_error: 0.422 | train_acc: 0.959 
+
    +
    +
      [===============================>--------] 82.40% | train_error: 0.417 | train_acc: 0.960 
+
    +
    +
      [================================>-------] 82.50% | train_error: 0.413 | train_acc: 0.960 
+
    +
    +
      [================================>-------] 82.60% | train_error: 0.408 | train_acc: 0.961 
+
    +
    +
      [================================>-------] 82.70% | train_error: 0.401 | train_acc: 0.961 
+
    +
    +
      [================================>-------] 82.80% | train_error: 0.402 | train_acc: 0.961 
+
    +
    +
      [================================>-------] 82.90% | train_error: 0.396 | train_acc: 0.962 
+
    +
    +
      [================================>-------] 83.00% | train_error: 0.402 | train_acc: 0.961 
+
    +
    +
      [================================>-------] 83.10% | train_error: 0.399 | train_acc: 0.962 
+
    +
    +
      [================================>-------] 83.20% | train_error: 0.401 | train_acc: 0.961 
+
    +
    +
      [================================>-------] 83.30% | train_error: 0.389 | train_acc: 0.962 
+
    +
    +
      [================================>-------] 83.40% | train_error: 0.397 | train_acc: 0.962 
+
    +
    +
      [================================>-------] 83.50% | train_error: 0.386 | train_acc: 0.963 
+
    +
    +
      [================================>-------] 83.60% | train_error: 0.389 | train_acc: 0.963 
+
    +
    +
      [================================>-------] 83.70% | train_error: 0.386 | train_acc: 0.963 
+
    +
    +
      [================================>-------] 83.80% | train_error: 0.385 | train_acc: 0.963 
+
    +
    +
      [================================>-------] 83.90% | train_error: 0.385 | train_acc: 0.963 
+
    +
    +
      [================================>-------] 84.00% | train_error: 0.382 | train_acc: 0.963 
+
    +
    +
      [================================>-------] 84.10% | train_error: 0.378 | train_acc: 0.963 
+
    +
    +
      [================================>-------] 84.20% | train_error: 0.374 | train_acc: 0.964 
+
    +
    +
      [================================>-------] 84.30% | train_error: 0.372 | train_acc: 0.964 
+
    +
    +
      [================================>-------] 84.40% | train_error: 0.371 | train_acc: 0.964 
+
    +
    +
      [================================>-------] 84.50% | train_error: 0.369 | train_acc: 0.964 
+
    +
    +
      [================================>-------] 84.60% | train_error: 0.364 | train_acc: 0.965 
+
    +
    +
      [================================>-------] 84.70% | train_error: 0.372 | train_acc: 0.964 
+
    +
    +
      [================================>-------] 84.80% | train_error: 0.368 | train_acc: 0.964 
+
    +
    +
      [================================>-------] 84.90% | train_error: 0.362 | train_acc: 0.965 
+
    +
    +
      [=================================>------] 85.00% | train_error: 0.364 | train_acc: 0.965 
+
    +
    +
      [=================================>------] 85.10% | train_error: 0.355 | train_acc: 0.966 
+
    +
    +
      [=================================>------] 85.20% | train_error: 0.356 | train_acc: 0.966 
+
    +
    +
      [=================================>------] 85.30% | train_error: 0.349 | train_acc: 0.966 
+
    +
    +
      [=================================>------] 85.40% | train_error: 0.341 | train_acc: 0.967 
+
    +
    +
      [=================================>------] 85.50% | train_error: 0.347 | train_acc: 0.966 
+
    +
    +
      [=================================>------] 85.60% | train_error: 0.349 | train_acc: 0.966 
+
    +
    +
      [=================================>------] 85.70% | train_error: 0.345 | train_acc: 0.967 
+
    +
    +
      [=================================>------] 85.80% | train_error: 0.346 | train_acc: 0.967 
+
    +
    +
      [=================================>------] 85.90% | train_error: 0.338 | train_acc: 0.968 
+
    +
    +
      [=================================>------] 86.00% | train_error: 0.348 | train_acc: 0.966 
+
    +
    +
      [=================================>------] 86.10% | train_error: 0.344 | train_acc: 0.967 
+
    +
    +
      [=================================>------] 86.20% | train_error: 0.346 | train_acc: 0.967 
+
    +
    +
      [=================================>------] 86.30% | train_error: 0.340 | train_acc: 0.967 
+
    +
    +
      [=================================>------] 86.40% | train_error: 0.339 | train_acc: 0.967 
+
    +
    +
      [=================================>------] 86.50% | train_error: 0.336 | train_acc: 0.968 
+
    +
    +
      [=================================>------] 86.60% | train_error: 0.343 | train_acc: 0.967 
+
    +
    +
      [=================================>------] 86.70% | train_error: 0.336 | train_acc: 0.968 
+
    +
    +
      [=================================>------] 86.80% | train_error: 0.339 | train_acc: 0.967 
+
    +
    +
      [=================================>------] 86.90% | train_error: 0.330 | train_acc: 0.968 
+
    +
    +
      [=================================>------] 87.00% | train_error: 0.338 | train_acc: 0.967 
+
    +
    +
      [=================================>------] 87.10% | train_error: 0.328 | train_acc: 0.969 
+
    +
    +
      [=================================>------] 87.20% | train_error: 0.326 | train_acc: 0.969 
+
    +
    +
      [=================================>------] 87.30% | train_error: 0.317 | train_acc: 0.969 
+
    +
    +
      [=================================>------] 87.40% | train_error: 0.329 | train_acc: 0.968 
+
    +
    +
      [==================================>-----] 87.50% | train_error: 0.317 | train_acc: 0.969 
+
    +
    +
      [==================================>-----] 87.60% | train_error: 0.316 | train_acc: 0.970 
+
    +
    +
      [==================================>-----] 87.70% | train_error: 0.318 | train_acc: 0.969 
+
    +
    +
      [==================================>-----] 87.80% | train_error: 0.315 | train_acc: 0.970 
+
    +
    +
      [==================================>-----] 87.90% | train_error: 0.309 | train_acc: 0.970 
+
    +
    +
      [==================================>-----] 88.00% | train_error: 0.308 | train_acc: 0.970 
+
    +
    +
      [==================================>-----] 88.10% | train_error: 0.296 | train_acc: 0.972 
+
    +
    +
      [==================================>-----] 88.20% | train_error: 0.302 | train_acc: 0.971 
+
    +
    +
      [==================================>-----] 88.30% | train_error: 0.298 | train_acc: 0.971 
+
    +
    +
      [==================================>-----] 88.40% | train_error: 0.300 | train_acc: 0.971 
+
    +
    +
      [==================================>-----] 88.50% | train_error: 0.296 | train_acc: 0.971 
+
    +
    +
      [==================================>-----] 88.60% | train_error: 0.291 | train_acc: 0.972 
+
    +
    +
      [==================================>-----] 88.70% | train_error: 0.287 | train_acc: 0.972 
+
    +
    +
      [==================================>-----] 88.80% | train_error: 0.283 | train_acc: 0.973 
+
    +
    +
      [==================================>-----] 88.90% | train_error: 0.280 | train_acc: 0.973 
+
    +
    +
      [==================================>-----] 89.00% | train_error: 0.285 | train_acc: 0.973 
+
    +
    +
      [==================================>-----] 89.10% | train_error: 0.277 | train_acc: 0.973 
+
    +
    +
      [==================================>-----] 89.20% | train_error: 0.292 | train_acc: 0.972 
+
    +
    +
      [==================================>-----] 89.30% | train_error: 0.289 | train_acc: 0.972 
+
    +
    +
      [==================================>-----] 89.40% | train_error: 0.292 | train_acc: 0.972 
+
    +
    +
      [==================================>-----] 89.50% | train_error: 0.287 | train_acc: 0.972 
+
    +
    +
      [==================================>-----] 89.60% | train_error: 0.285 | train_acc: 0.973 
+
    +
    +
      [==================================>-----] 89.70% | train_error: 0.280 | train_acc: 0.973 
+
    +
    +
      [==================================>-----] 89.80% | train_error: 0.283 | train_acc: 0.973 
+
    +
    +
      [==================================>-----] 89.90% | train_error: 0.277 | train_acc: 0.973 
+
    +
    +
      [===================================>----] 90.00% | train_error: 0.285 | train_acc: 0.973 
+
    +
    +
      [===================================>----] 90.10% | train_error: 0.278 | train_acc: 0.973 
+
    +
    +
      [===================================>----] 90.20% | train_error: 0.266 | train_acc: 0.974 
+
    +
    +
      [===================================>----] 90.30% | train_error: 0.264 | train_acc: 0.975 
+
    +
    +
      [===================================>----] 90.40% | train_error: 0.271 | train_acc: 0.974 
+
    +
    +
      [===================================>----] 90.50% | train_error: 0.265 | train_acc: 0.974 
+
    +
    +
      [===================================>----] 90.60% | train_error: 0.265 | train_acc: 0.974 
+
    +
    +
      [===================================>----] 90.70% | train_error: 0.258 | train_acc: 0.975 
+
    +
    +
      [===================================>----] 90.80% | train_error: 0.263 | train_acc: 0.975 
+
    +
    +
      [===================================>----] 90.90% | train_error: 0.251 | train_acc: 0.976 
+
    +
    +
      [===================================>----] 91.00% | train_error: 0.248 | train_acc: 0.976 
+
    +
    +
      [===================================>----] 91.10% | train_error: 0.248 | train_acc: 0.976 
+
    +
    +
      [===================================>----] 91.20% | train_error: 0.250 | train_acc: 0.976 
+
    +
    +
      [===================================>----] 91.30% | train_error: 0.243 | train_acc: 0.977 
+
    +
    +
      [===================================>----] 91.40% | train_error: 0.241 | train_acc: 0.977 
+
    +
    +
      [===================================>----] 91.50% | train_error: 0.239 | train_acc: 0.977 
+
    +
    +
      [===================================>----] 91.60% | train_error: 0.240 | train_acc: 0.977 
+
    +
    +
      [===================================>----] 91.70% | train_error: 0.239 | train_acc: 0.977 
+
    +
    +
      [===================================>----] 91.80% | train_error: 0.239 | train_acc: 0.977 
+
    +
    +
      [===================================>----] 91.90% | train_error: 0.235 | train_acc: 0.977 
+
    +
    +
      [===================================>----] 92.00% | train_error: 0.233 | train_acc: 0.978 
+
    +
    +
      [===================================>----] 92.10% | train_error: 0.234 | train_acc: 0.977 
+
    +
    +
      [===================================>----] 92.20% | train_error: 0.240 | train_acc: 0.977 
+
    +
    +
      [===================================>----] 92.30% | train_error: 0.238 | train_acc: 0.977 
+
    +
    +
      [===================================>----] 92.40% | train_error: 0.226 | train_acc: 0.978 
+
    +
    +
      [====================================>---] 92.50% | train_error: 0.226 | train_acc: 0.978 
+
    +
    +
      [====================================>---] 92.60% | train_error: 0.229 | train_acc: 0.978 
+
    +
    +
      [====================================>---] 92.70% | train_error: 0.226 | train_acc: 0.978 
+
    +
    +
      [====================================>---] 92.80% | train_error: 0.218 | train_acc: 0.979 
+
    +
    +
      [====================================>---] 92.90% | train_error: 0.219 | train_acc: 0.979 
+
    +
    +
      [====================================>---] 93.00% | train_error: 0.220 | train_acc: 0.979 
+
    +
    +
      [====================================>---] 93.10% | train_error: 0.216 | train_acc: 0.979 
+
    +
    +
      [====================================>---] 93.20% | train_error: 0.217 | train_acc: 0.979 
+
    +
    +
      [====================================>---] 93.30% | train_error: 0.216 | train_acc: 0.979 
+
    +
    +
      [====================================>---] 93.40% | train_error: 0.216 | train_acc: 0.979 
+
    +
    +
      [====================================>---] 93.50% | train_error: 0.213 | train_acc: 0.979 
+
    +
    +
      [====================================>---] 93.60% | train_error: 0.213 | train_acc: 0.979 
+
    +
    +
      [====================================>---] 93.70% | train_error: 0.213 | train_acc: 0.979 
+
    +
    +
      [====================================>---] 93.80% | train_error: 0.205 | train_acc: 0.980 
+
    +
    +
      [====================================>---] 93.90% | train_error: 0.210 | train_acc: 0.980 
+
    +
    +
      [====================================>---] 94.00% | train_error: 0.211 | train_acc: 0.980 
+
    +
    +
      [====================================>---] 94.10% | train_error: 0.209 | train_acc: 0.980 
+
    +
    +
      [====================================>---] 94.20% | train_error: 0.206 | train_acc: 0.980 
+
    +
    +
      [====================================>---] 94.30% | train_error: 0.204 | train_acc: 0.980 
+
    +
    +
      [====================================>---] 94.40% | train_error: 0.210 | train_acc: 0.980 
+
    +
    +
      [====================================>---] 94.50% | train_error: 0.198 | train_acc: 0.981 
+
    +
    +
      [====================================>---] 94.60% | train_error: 0.198 | train_acc: 0.981 
+
    +
    +
      [====================================>---] 94.70% | train_error: 0.202 | train_acc: 0.981 
+
    +
    +
      [====================================>---] 94.80% | train_error: 0.201 | train_acc: 0.981 
+
    +
    +
      [====================================>---] 94.90% | train_error: 0.202 | train_acc: 0.981 
+
    +
    +
      [=====================================>--] 95.00% | train_error: 0.195 | train_acc: 0.981 
+
    +
    +
      [=====================================>--] 95.10% | train_error: 0.203 | train_acc: 0.980 
+
    +
    +
      [=====================================>--] 95.20% | train_error: 0.197 | train_acc: 0.981 
+
    +
    +
      [=====================================>--] 95.30% | train_error: 0.201 | train_acc: 0.981 
+
    +
    +
      [=====================================>--] 95.40% | train_error: 0.187 | train_acc: 0.982 
+
    +
    +
      [=====================================>--] 95.50% | train_error: 0.197 | train_acc: 0.981 
+
    +
    +
      [=====================================>--] 95.60% | train_error: 0.187 | train_acc: 0.982 
+
    +
    +
      [=====================================>--] 95.70% | train_error: 0.195 | train_acc: 0.981 
+
    +
    +
      [=====================================>--] 95.80% | train_error: 0.195 | train_acc: 0.981 
+
    +
    +
      [=====================================>--] 95.90% | train_error: 0.190 | train_acc: 0.982 
+
    +
    +
      [=====================================>--] 96.00% | train_error: 0.190 | train_acc: 0.982 
+
    +
    +
      [=====================================>--] 96.10% | train_error: 0.194 | train_acc: 0.981 
+
    +
    +
      [=====================================>--] 96.20% | train_error: 0.187 | train_acc: 0.982 
+
    +
    +
      [=====================================>--] 96.30% | train_error: 0.190 | train_acc: 0.982 
+
    +
    +
      [=====================================>--] 96.40% | train_error: 0.190 | train_acc: 0.982 
+
    +
    +
      [=====================================>--] 96.50% | train_error: 0.195 | train_acc: 0.981 
+
    +
    +
      [=====================================>--] 96.60% | train_error: 0.188 | train_acc: 0.982 
+
    +
    +
      [=====================================>--] 96.70% | train_error: 0.188 | train_acc: 0.982 
+
    +
    +
      [=====================================>--] 96.80% | train_error: 0.190 | train_acc: 0.982 
+
    +
    +
      [=====================================>--] 96.90% | train_error: 0.191 | train_acc: 0.982 
+
    +
    +
      [=====================================>--] 97.00% | train_error: 0.188 | train_acc: 0.982 
+
    +
    +
      [=====================================>--] 97.10% | train_error: 0.189 | train_acc: 0.982 
+
    +
    +
      [=====================================>--] 97.20% | train_error: 0.175 | train_acc: 0.983 
+
    +
    +
      [=====================================>--] 97.30% | train_error: 0.189 | train_acc: 0.982 
+
    +
    +
      [=====================================>--] 97.40% | train_error: 0.183 | train_acc: 0.982 
+
    +
    +
      [======================================>-] 97.50% | train_error: 0.189 | train_acc: 0.982 
+
    +
    +
      [======================================>-] 97.60% | train_error: 0.181 | train_acc: 0.983 
+
    +
    +
      [======================================>-] 97.70% | train_error: 0.188 | train_acc: 0.982 
+
    +
    +
      [======================================>-] 97.80% | train_error: 0.179 | train_acc: 0.983 
+
    +
    +
      [======================================>-] 97.90% | train_error: 0.190 | train_acc: 0.982 
+
    +
    +
      [======================================>-] 98.00% | train_error: 0.186 | train_acc: 0.982 
+
    +
    +
      [======================================>-] 98.10% | train_error: 0.185 | train_acc: 0.982 
+
    +
    +
      [======================================>-] 98.20% | train_error: 0.182 | train_acc: 0.982 
+
    +
    +
      [======================================>-] 98.30% | train_error: 0.182 | train_acc: 0.982 
+
    +
    +
      [======================================>-] 98.40% | train_error: 0.171 | train_acc: 0.984 
+
    +
    +
      [======================================>-] 98.50% | train_error: 0.178 | train_acc: 0.983 
+
    +
    +
      [======================================>-] 98.60% | train_error: 0.170 | train_acc: 0.984 
+
    +
    +
      [======================================>-] 98.70% | train_error: 0.181 | train_acc: 0.983 
+
    +
    +
      [======================================>-] 98.80% | train_error: 0.166 | train_acc: 0.984 
+
    +
    +
      [======================================>-] 98.90% | train_error: 0.175 | train_acc: 0.983 
+
    +
    +
      [======================================>-] 99.00% | train_error: 0.173 | train_acc: 0.983 
+
    +
    +
      [======================================>-] 99.10% | train_error: 0.173 | train_acc: 0.983 
+
    +
    +
      [======================================>-] 99.20% | train_error: 0.171 | train_acc: 0.984 
+
    +
    +
      [======================================>-] 99.30% | train_error: 0.168 | train_acc: 0.984 
+
    +
    +
      [======================================>-] 99.40% | train_error: 0.167 | train_acc: 0.984 
+
    +
    +
      [======================================>-] 99.50% | train_error: 0.174 | train_acc: 0.983 
+
    +
    +
      [======================================>-] 99.60% | train_error: 0.158 | train_acc: 0.985 
+
    +
    +
      [======================================>-] 99.70% | train_error: 0.173 | train_acc: 0.983 
+
    +
    +
      [======================================>-] 99.80% | train_error: 0.164 | train_acc: 0.984 
+
    +
    +
      [======================================>-] 99.90% | train_error: 0.175 | train_acc: 0.983 
+
    +
    +
                                                                                                
+
    +
    +
      [=======================================>] 100.0% | train_error: 0.175 | train_acc: 0.983 
+
    +
    +
    +
    +
    +