From 195895c035148edf3bc1a71a7366c6e9acf4e5b9 Mon Sep 17 00:00:00 2001 From: Sachin Prasad Date: Sun, 7 Jan 2024 09:23:56 +0000 Subject: [PATCH 1/3] Keraas 3 migration --- ...hoice_task_with_transfer_learning_33_0.png | Bin 0 -> 27005 bytes ...hoice_task_with_transfer_learning_43_0.png | Bin 0 -> 86801 bytes ...e_choice_task_with_transfer_learning.ipynb | 23 +- ...iple_choice_task_with_transfer_learning.md | 7338 ++++++++++++++++- ...iple_choice_task_with_transfer_learning.py | 13 +- 5 files changed, 7242 insertions(+), 132 deletions(-) create mode 100644 examples/nlp/img/multiple_choice_task_with_transfer_learning/multiple_choice_task_with_transfer_learning_33_0.png create mode 100644 examples/nlp/img/multiple_choice_task_with_transfer_learning/multiple_choice_task_with_transfer_learning_43_0.png diff --git a/examples/nlp/img/multiple_choice_task_with_transfer_learning/multiple_choice_task_with_transfer_learning_33_0.png b/examples/nlp/img/multiple_choice_task_with_transfer_learning/multiple_choice_task_with_transfer_learning_33_0.png new file mode 100644 index 0000000000000000000000000000000000000000..f4623bfb37540e3cac61e24e8fd37824d303b3ec GIT binary patch literal 27005 zcmafb1yogQ*Y!qJt^r)76a>5~EucuZ1s>@nYBx-Ei`K1Kf_NE1snL6B#2m#ERJ&;mh)5vm1v$&|J zi=3}H)TWV^;KGAbeIbj(dwYb2H>hg8Y|FMb+=Q3(e_1U}y3;5QyS44O$?!(CFv5c% zwG!SNLtg&>e{H4KqwN^eUt+0yUAM`A zYj)Z5Xpcvv#H2HYn$JQjbcz5`W{11QYpqSUg*O^>d@>)%acXT(lr-ducua3psD5~O zSU#H)MNUP99m};}pHUd{JUYM)SC$Ejh)`U)l682nXZr2kWtHEm2vW+JBSC~9{9*5} zOU_M2S%%f?wLd2$T5lCvel}YByuaK&Q_yb43O`LJX!l6OW&Q8)@bGVe^tmZAQLH>X zDnbqmKbtsfvZiBQbG(O7A&8+uG=ivPnD*pQi@4a$HXQ73bjt7zC8-x0&Bizmm(AJg zx-RlePEE0jit3DwjTwrD$HwZgJJZToTjyt~W)2Pw`3IapNM1{AAP7D~x5gtVsm_Nq z+;wTJ&Iey=JudY)_{OPIr?hR%c2*~;Z$0sHb90-RpUk@fCh~ z`?)TKL<#@(T+f5~AltKN&vNU3J74^){T>}1-Pv>JI?3dO6JES{A=MfsXrDpN{p>0| zJ^hf&e72y&LN7xupT!_Qk9q%k&^WCA2&`<*X71e}yQ${OG7(%4pFVxMy0RkgN6Egv z+Qiv}D-Mgb9b5g5{;A8sMi0Ky+1A;~>Dlsd)nv6O5^tkseF9O=Oq2|K95mOHtGiSN zZ>~{{3-#FlEvfB!uz?kEJlx-*7W1g=FE&k`?M%(osdDKrvrSdaQcG}Mt}0otY;Kk& zrWI5!8S$uCDxc?Y|6Nbzvf9XmPqw3dKfy&!3QgHbj*?bJESnPJyu6+62k^y7(Xc(YcI^m2YJ^cAAZsi>&9-XM0U zAQQ>m4x7yFzH679k}|i^qswV~NJQ@zzrXJ$vOW3|-v95K8c#GF<D|}gpC+bGYK;*xt@R?H=C_LXK7aWmdPQt_XlOF} zHzKZ^UGV;sv$N{E0#PlhQ#^t6VmYK@`|?{uj&V0kzPvhfmXx$-u*_Dmj89$R8F`FL_-VkSK`mQ^Y8hPKV+=#mo02-h44e0-s?9Ib#&(t7W7 zoM#SfV1`T-FRYOA?D&_Ao=6_k8<-LIt(c^s7moQXN-4^tBhvNmhda~g6QE(m*f#q4 zrD48Wk;PCs*Yt>W18oQ+l4c~U9o?O+nF_DU#?7tF7@XdmdrtFp4P zE8)IRX28}dul}jeMD$%hLfMM#W))>(1XZS6V}k4T(pT0ri*d<;qPve$Wn(%xYxX}< z>AET83sv$SBOiZDsWCVqc*oF*P^y+B1Ac zXwngJ$|Gs%kUlfjwW*e-N}c)cY_|PF)?e`G8u@zl49=%X>9iQzPF=WgL1lM?013C5 zliFBaUF}L&V)CaK(}4rvTI^W`$6;f(Q<9K~q-%Au2_Ju#kXG0!?_SRVp}2W_fniez z{fcGTBxPA?DZ11hwa*FhRjylSYXbcI{2-yllh6t>v$8%$uWz9D)Y|P2b&hE&+YSh>d^gEwKElE*t)YAB9xxAZ(wK`dYSrtWMoFY9~G8aPD?Ag`si>^ zO4JcDECm%+_#QRll`+}HCW{RY2}vRq-4@4SFlUL0LvI{Ra(cG=Qn0N1M5) z(h1l+C^Ty6C^G3>U+*xahk zNHl>$r8!QZP}(-u+QjA|@$Ev5)=b~BhvPY0*e2R}pHw7?$Fw_5E>5&S?Ix7+IMKa@ zJMKpZTXVxz6@rdSS!lV1dZ?hP8ul?UvDjq;M+;#Y)KdwSbbTUNZtm!C`DlG6F>nrU z4@W-?%0)7*kb@Ra+jyW@j%D?ZM9H9y-#34nR5}6*KxrpHuB65RXB38YipO= zwJ!}-Y%EnQD@G$-XJK8-7k*ohf79M@hU8ejHSD_4E=fPTGFBIU9$Pv(n;O>*xtM~6 zCNog%P|dh4R^`#7H%n#HbRv5Tg@zoKvA3Q=P`!Ya=A3;^rSo@GR8)VFNn*NEs_L$L zM2itrrU&TKitex6XVs!sb-dg{Vesu^+3=4`w;RfdnmX?lrO7B=fq2ebHKVkmXpKQ zcpPxJ22@m3z>6!5^(=Iz!kz!5=eH6E98kl?2A6ovO?K6@@bQ&2+s~dka|TLCcuh?W zy6FI7OqxI3jufy>DYu*b7|bMx+nB?nG3rfBqdJ?*2LigHCrOEjQZ_{pD9Eh*8_S6+L2|1hiGjST9fNF8qo)GfgL1;0h6L!+a! zAf9zMuB5Wb!i7PP4=1;Gcd4V%zQIeOps0H0y(=0!cX^DH z%66y1fDrEU>m>hciVCHT!H%lOEk8I#D1S|-U#`2(Q{?{Uc_VxPj)((KcxBLcDBZ>B za{yN|Ca9xebz|iPtwz2OKHdQSq8Ogc>Ir40OdI?f+fwus z^4QN@4$tD&Zf0cRVbitD5{++>l%1D%$th^1Y&1%I1Z%1F&NUh#0?;|xVVBQ`rSFK! zBn|agSkhCCFR3`;E=)eNm>_QH$isXv9VAIe?|90^^?O^B3?tcnXji=S6Zr{9Zhmhl zyf1M4);&L!hQd|*eb!7Bs?v%N6r+ne8hMW&<9A+6+E&}eaB6PM z$rr%ZFFvq7aYe1|56{=z&N{zsM1qr^h{?J0m3huSTiw6rCp$$xqipe9c9Jq|e|aZR zZi;e7S@!9y*z`nrNLE+Yex}Yvr{__A7y^3{@|kgu_8<6%nHtkgsxQ~r)QyBLg|}XE zM3Ae{Ncc?Y@tS;Fc_dQwq=6x>VkPnD-Pn6WU$4|Czc2gq%*{2jWw~*>2JN$zUxGfW zXncBnwx@CM#Sukb^a;ahs?6_tN*WH;9R*FC>N!T8582eI!m|p(iFsFk%U9u8)!$h| z<3shqOxA(Q$-&{%{{DVQXefiOu5RKug6AlSR~tIYSKN8n&DCI9j*ydU+6k7de8gw1 zotpoG>wcK2r9SP;y3x;J6ntW?JiJPHW&ekY$?sJb_4W+ihN^oE^ItA)jT{m_^CWe2n%AF3ju^K>>t#pJV~Cuetkrh3G*RCi-^kbch`ybOe;FOJTtB^OQtj?|ZI zw6=OAI7L5VTDc}5%3`^rcZMJTWeA@Iv2bcHRP1ivcSXg5A3AhuPVLDr85$H@qm^`? zClB`Q;ihk&+H=k@5vNT#bpjb3WtR0Kj4C{Qb7Qu8cx=_i@ixEz??J6*+{}EscQuw% z-P%XabYh`pvU+%WAYgXQyrC;CHhj0}5BWIC=e`znX{SZ$R4Cy1^qzr-ivPr9gp=&J zTvqXcN04=JhQIj7>)T5v>O0|8ZI~c8VJ(WwbBVMV;}DyvXwd-&={R#CMhuQ@A#rBv z`P=}PxXASr6N{heixH&DVc(pDKdp@Bv1*ir-I?qaiBe|kr|8$J++J$DY+U?%AE!Jx)+rc+RhwFSKD-2rsOA!=Jia?=DSRG5 zGEUdevNFqB*+GPpQxs|#pJU&(a+BMz#MjO|;%~zho9Jo;@Y11AB{!RT{jwld*}+A( z(@W6T;zC+A`w0sCP4SKSa+(lI1ZikEUFt=)XCM{SN~zHWkGor(MZ3oASq{ zL+{h zKLMpg74n~=L4L+alW9m;3_$LL#HBepBfA^Q_hdcZL;4OGrnet`U=h()QSkxKURk~S z>AbSt8e;!!f(d(C1`b6FH09A_WQFhv~|*ZPVJV6MJGh-gN zwf3a=ot8;5nq*u0Zc@# zA6a{tQR(kNfQZ*yr_+sI{Y4Vj{k<=0a@MFjCG~V;T*3*G7QJE<$H!r4ILP?OnasCK zQ&4I)MR#8NUQzU512@H~E64Y;0~RN)RGHN39u;q8Ridf><6ttY+fiLCS+Rnz@tsM} z*+U>la)y!ybwvdW$;gGPrcHMkF>ls9x0nJ%n zbxgKA&y2Ee%)*YQsS{ehB>Vi#xRnyO_WssE-zN~O+p5uC8XVViqw+KN7iSIu;^{*FU%Rneo!{ zzt^`GATcbh0$J=~AP1cKS$I15NS>J5j$aiej zwSE79mm0MOTPp& zs}qeVDa7g8y1%n#4?RG*z|`1S0@Rzcp0ujbqmNeoZqDtkQpfyY|4FlD*KHm{bD8!G z$<^F=HO&B{XXBrh`mJU{Hj^hqb}FH2YDacq{`^N&dvYHpUiWvU7pPL<2DWZjE`%(k(9QIr= zIyO_xz4Cs|LAI8LYBils-u-`-I~;ADpOS?|4$8Rz^)XL>v@KaS9VN|piioI3oU67P zHm*fmmy29a%dS((W1LhuRNRtusGmi-#Nljci;mm|$+R-dn_U!ln06FpULxU7(RY*I%58 zb^^twJxjjRROIAo@$vEN;|mK5tc}E%%nx9JJ+DdH4{6)UwJ}OGJP*DVA$^uKEpx@I zoEp!jrJ5<@s#I9~TfPz3HFZ5z#h`4JVw4w?uD*kAecIG{E&`;B&il~UrTyc>{(OBO z=!RMCJYdy%EQf{NVe2*Wo;(L`6B<2xz}{@4OpJ^Y9v&Xafq8j(8NQ^KaGSe9#Foo* z7Z}Aj`CfL`sz<-$G*_PRFGf%V#mlI2nWuc)>A8pJHhhK%TC0w?1N0?ZDB>l#;b4qB3i`` z9i)=JNxW_vs8f-YotoV-bj9!0<0B989E&2Y?r8|JXVB{#48#S>vQMcEmD^MN`KP># z8}wOd>o+SR-zIic>9VzyP06k?1GEat35I<5koK00soTk;mYKeuA>*f>N)O{k7u1$^ zYcHwu=JX%c6DxEI0+m)QH?3XVp3$%mM|=$Y6);!(R?EGB0TXA2QQTVDE$3v_;wvV7 zU%}RSjR4vFypryMavV1bcRW2!jEs!tpvRKe(1-*^FBe*S=(=Ql-@W6$#UO9nN}*Bo z#P;Kj+2BQ1^GOY(G|y#H5(Njp&Dk zr>fkVi=~sXv&>}#xM?_A0VRj4FM6SM@W%ql`QE5gQDhsN?tw$2>P4eq?o#vn{%>&^06}`UuORYU~1;C6w;s) zA8lQebIK7fnQYM4tsZ>;aqxv6CMZ10Pr}Y5Y0t%njVnZ~i2&*G{$)o&&eWyqSVNT> zcadwofuM!^AmtPEn>a0tyVem;FH+r-hVqfkEQ`Hseb2mTUMg?eZNmVf_@g&qF!0*m?^}U$Sxvja4?O{JG{n`GT=UcG~;QGFC2( z!I-MZQ)$>jFDY+KW%1PC!|JYYo?Zl!slk`*$#g)RK|7hgwj=nv_!(Wil{@zRDCHiTrR)J)rS49URv!eI)c+O>I&JUctOiPre0{Piq zciGB+37^z_>+OH;I~Od4{8Q)!WdEZVpdR77XLN_Jl(6RoddG~~WEZcPT?=f+;ree9 zeC~LPj2v-Lc!gj4d&K86EQr@v5n1d*SV-$VA)4arv+oYw+|P+P+&6`mi3D2I08wB4 z4<`}+>%N^T^3n1%W^&D4w1vElL-kq2a>UAi2d1KTYJfXgiJtdCaAjrFe3ez%w#>+#sLm}K*|;Kk7*4tG}N#0dmIT^Y^MNjJ9N_czv&Dfu$u5xG;ME?N@fVNQ(n=}Ip z%2qT}_ge&o$%)qqwuvDgy~dyLe}%_>(l+cTlJ#M74~46$(z6W=;$F1qYjt^$r)I|U zf7St%Fn5&80~7$Tw?7pe?Md$lUi3Pf*JozvjUm^RI@BOucQA%4dIgrOPv8=k9ggXDJeh+sE^3pQ=Bz`Rtcx2@an-OO4Nbd${9C`!0Ymo_d0k+_bTk+?_l;?SRSV zaiFfS^sfeYruBaj9tUo3;!=&y2X_73{7d5NX~ajux*WoJq2+yWS-Ho5Lx%)uvRG=y zvGLiA=>1<(tu=Yw+@^NeA7qH~ZSVU?@%KUEGeJq8&0jLhc#)M3-g+D8DVVVy{iP|^ zQVHYiVlk^j{Pz4*fe3Qz4;pFY^pEdsUEx9jm>|YYQzI*CgohpAbudv$SEi$V^_=s6 zRAYtfWe5`fk)Po7E&#n%zpQ@)J;K_nscRfH{p*^u0y~p&Cy_KtI0#pF9#S6gaVP|> zi`N(}ES})cze?YBHfC#xGhHx3NxlUHcs~&N^2T_`c#nQ>kdMNkRmZ6cso z@Giyav+QU;VU#VBw6GR6y=gX=%Vdd5v>4kUmL)$d5sS)U^;$oeg>VY z#t-rgU3E@bx5#aI&xH|bx*Q{Ofye|QBl8YIdW+7_WC9YBClMcD^l`a=1@_uJbqeA3$$$+j` zXUK{`Vnn&+>k{vN0=I6;%wo0pPc3isE+N~??>`w2bjE6T#g=_1*3(xN8hmK&cwF6I z?A8=WSmp{O*}i^vi^%H-S0z74=O{#p6mk7D*Hg1=IXdDrPK+wUz`mFEe=^Uc(s8;A zA|xIagYTO>H{F^H(ElNh+D z{*-32%J1uOb`Ov=p7Wft!HhB;c~9%OomNI|+Wh_eDkdsvEGrePt*xb~WDc$qCpNi8moOGt(vEHd;EyPIw98@od>6jRH|>(M7f3JppuoXlgw4s5h! zd7n@rId2o{P5v8f2IK=`soIoUoi}l4SeQfo^w+OnzqhsJu3w;}+^pat?16+dD`>+i zCmNemo=G(F62ZmxnW24lkxRe*?%v9yQ(gAhFX_S}1y-pRuC9r|R2ahhA@0 z@!bc^n{S^-a+M~}l~>G!>#I}qOfwDfZ80s%HgXAGLwXtNd^+ba*oO-0pNNb~kZNcTFzP`TIwKXMG zRmv@)1dT~bayC|@Vw+Vz9%E@o;s7(X!(gN~px2D|AaCoH&W=Y7N%HjLAZq+tN62S( zd)JHW&vD`znPblV@YNJnKq3(xG{-l;FM|ogvV|VEiJ{u ze0s>8>Gf@@nwb>7ZZvBx5S*$tk&pJmJ;{eNr4MInd{5$gv!x+HmtGEs(GdQ+v?+a! zY^NpeIy8&Gd}I=d4yFi=_;+?EUWN?mg_E>Ck@1<-wId|jT6SZ;bT%Nz-#>s5QTfu@ z^3e0jPp$dbOKCp2rW|s7g`XIV=2{)cxt|`YF3L6ChAmd6@gj$eoTrxWv+gNv46lHhzeMrl=By%&3JDo zu>_AwMPY%yGcU2b2!*XH(ZQ|a8jGbrZ$`=N;v{`@jvTXMb<44ronNC*%?f2Uqj!*) zAycNrot$0amNfm>9YT64(&gJ?u zY4_H68NcI#cZ<&}&p)9DBrEQJCqjB|B;$FQXb09ZVBzD6mmo?{8P^Oae$M?iH@{7; zo(=g}9^_Ro)*$jQeX{vm7w4gZWV7Dw_zQ@Aus=-wCrrVk{ zZTPwcD#>T z$kI=uWd|e16nDHuf51bZcu1K!WhuxCC6MzTBN@%`iQ4)(m(sbmmm0VsGD4mN%U6Ti z&A{Fip(zmHyaTO3gej!KQdZdDQ`G~Z8C_X!pbO1>YE3}(xr#~M9__Z_i|O=7T;h&) z<~M^e&)S!MsR^)EO>m15+t7-GnR2PHR^JLG@}slVgSMqIGgwu6 zDHkA}L4N;wW7rL}oapG}%K?l04#L9_7HecS_0@UEm|>|=>WMCeW9*2s1gv?><$?Qg zV&uty4?=Yf@L9z^_#<7@b)AK$lT_;HwL#3XwadKI`?yY8ZJMT(;?``22cv-lq&~gN#py?Z(d+i{_XWk&uf7YKVm4MLRwQ0DG>3CIb z=5!8GX@LVsw#U<1&UAY2{d4w-$*GSq7-PG(y(pfgm+bwn!WHXUz}1)5rEb`}`2qtR zR{!G%IoKd@c1ZlE|B7g%c4(kHTnWofjXJc^H}!vewkJxAuInRvqejJ1k{)SvmwC)R zd{uhQu#WAcboC<|L%RQ}R1)xC3~p)Uploez4U3D5gYpLsI#atVU5cmbDL0%={6V^# z*{BdQeGo1oA$bBxwT4P_cu?m7$$P_hTC3OFt$QXXgbBeaM_545Sj)35cvuP-G57W; z)d{XraUoqvDbMXUx~sH{C*<5GmRxq|4LSBzx66`U%gji{LjfO$0xiz%=-w#*2CChU zme)t`klH_{eQ&bftX}Jp%nW~5Q>7imqMY&I7TT=_{^JwJ@H(@rrVU)D{db%9(V1m#;v)5@;v{Z|U zkm=YKMYlx)6yDrF#o9XV{)t^}3^N$o|K@V=^-vD+AVUA#mhZ~@8vvZtWKPUo0x3E= z%C9d8$PI?spj89Gqf0atIbP*Uf*)ctD@I1LOycV2l`ZbdNS+!+;EbPw2ZVlVJSgey zK`)$?h0p&Bc%Lg9=r`TaC*;n+l0`^&V1*Rz4r+Sl5?kI%4-m?;ER3I2{+TJZfbOtj zIO9gqwwyckYDnpudR%ANtMl*?Y~LG{M6T~o>Ty(%6yIS{YP;E&Ez(fPfQg~ro29=l zn08-Z?D{prJi^e~)8tI?CjfhrA9UahW7#`|63geNNEU`pBEP&%VPctDryzgq(gXJA0-L3mDGA77KXrmMd!N3$zS z+&5I^135z9P8e}`^Xp{D_Ecsj4<1#v zt=L0FMgEpWL(E`3n^}yxceH}mifGJ6OUM~(_@$~H?{+37{ zDRA|Kha!BoSVq{q*fZxXssOb4m z0~VdJBCa{xS3v0oXJ?q`MKUteTeqVdK{Zq{D^AD05{tTi!Ydfp_fs-X_@`#>&=3YR zLP0k!xvkbij1uLdGPGat-d$JkFWb?Jx;aGz9__Sw;<~fc`zxIbfxdO@oBn|E{Dpxe z8CZ+E`ILttH!v>o^qDfqXtOk9@L{f$zV=8;g3)1~E=s!vZI5dln3f->vL)J9RSGY% zyeQXb;G2PdO{%OEe)#aA_V3EUL9N$5K5Ssi9K^F=SecpS9UL4Yh~#72N*LIfYSe&P zoZIESi&nE<0su!Mo|>-iBI$vGyqik0ck_+h3MEUbs_q__Q93W2k&`t_HCI+uO@bWb zL+A3ykBU>(z+l3#&3vf5c&a5THMiza;~eG9zwtQKE*k(lRo@f%_U(J{56xb``Oe+R z${ws7YrJ7*PD0g|ubTHMFCbR$1N`Sre#h<3yuPqF3H-+pOCR;`Rte~R!ok6DnU++X z=Qd~`QSS-Bh8zm+wydn1sGT?Rj&XpVzJ9J+EQhMHauRCbo%sIVW$ZN-hb!7^fra_8 z7^G}fHMI}_q-;&YWx@dcog8J6{r^eVAr5l}vd{IZ_f&KjrQhFxmZ+zbuLQrSP19)b zi^|fgs_8iQ>%K03K2|?l0;bC>c;R`F3o?K1phiF~ZS9Rlra0x9{U7^H&uz;OV*F8D z=UH9-8gfE0dKQaoA+w@nF`QX844Otg-#yD!C3ZhAdwLWHl<@f)<>itrRnrKHkD2-4 zgM-z+ckf9`z%EiV^r zO?M>&uC&9hal5QPV_;;&{rdV=qUsd?2axnZ90k4igzUJ)d-jdb)$Zn6G@VACc2CKfjuD>{rC={Xz+6_u3rlpVbKgW{OM|AvmfDGE z0yBW>bmvY8M>m0FR4d^jN)c>z)2hC&XC%cI(p~O7Zk|Z7-lPN)nfNV!0*UWHdxGsm zDu}TFP*=RKQ(46fC*P-TUzP*Vdc{xGtF~x4i}O`g>wo|R`NQiml;|KzbBv-+!ozH8 zmrTzlae&6i73sCp!ziw4`7>R*m{ zQFm6qkE0a3l1+7#`*Oc>u!xUG)3LcfX;yc!BckxNL<8Xp4SZrTCAky`!Qt$2xW(!$$z=tWJ@!|$*UaHMGa%hO3(%wh$jri+_C%f@JV!ctm2gWaP5Q(@V(lUSUP4qd}~8 zRF@Kj|Izj)c4#$@xIgy8Q#;|>G5P3GEG<}IS;sQGllczx#s;3pr&K*}G2j|hvENKGl1loNt-h3maoKT;^Av2e*>Ew=P z0{KNP?Pkwlw4@nDYRqyKIjQyk-F%1)*dsND1$}0+ z8=0>c7R+{bc39Zhq^hf{B^vG$^JAYWtV?BvI)8e!{BABIN@yjV0IA){60%bC+;b@j zh!u6Mx8*Q9BX%q#MBg(kCkUVWJmy}!_JOO7GTqvpbLh{$pFnUTmp*!Cp4PaXT*F9; zbB1g7c@O^SJhmY|uS6b$(T1(Jf3u;B68!=Egf4vNO6LUrr6bhp$k*0yvs@%GZ#lFB zF_Vd24hzIf^YN`YM3`#!gITTVMsLEIe0H31YD$dBoLz67JB4_m0z&MxLJP*L|Mjnv zKE*-|Qc-~h-|=SPk4r%hQ7y;%yA|x4IOEx?Z`hn&TmE9uHvIeKs2SW$&9*g{mw5it zM=$}RsI^wK^dDUt6%43E9eARO#(tU%t+-?j>pH5{Q=0l4om{w3e};sGXFfXYAPCri zUX&0=N_+ojpW!I!i2q?iNDjGv=b>uV_K@h%=B5NnUNW;kq3>;gdl>EHx^Qm3ae25s z-zg>mN+N<(Kr4@GqoA3bUHz>Lj?c0WQr$5CUPMPcq>uJDvCwn}_1%z}p-D);uaO=g zv_)KZ8$?q$B37$seepv7&}XhdpFLd$?`ck7Be1{_7GZ~OT0vc<)!{n(H6$q4^10D# zB#_u@tV?tt3>7rd!w*0mU9oso)6wySqjw7*NxyB#C%WhehB?dXPnoxO$&K3!mekHT ziTgvsN>D=`j!qtR1J!Wmo1!kmARepUlc=jG@dQ4Hzx!^Wiag5TG%Yqv7*O5%j8TXl zmG|fkPMLUTi+1v!GyNz*j_`++)8*_AtUO{rRH83Fv#BuEcTHq-r;YlK<+;SBu@%@W zW?SBnEMEU53Jy+3D)c~(en1UY9b#K}viq7%b@(hWSj>9&=x^xUgiA`{l1osmibZZK z0XOFVmIMVo2uVvzeU_MZ&po!3bxvAsy245WyPX{UcN{+B|7UlwArR+zSO!+|>vD2( z_A@{4!qkB_aq{b`ioCJK?3nu$6XWWwec*OxeE@6NK;}BD>p8;=cz97DHhW-rINsBv z0t=2s$Pmhx@B1l@fAik}bG`|Xx}YCK<1W6opTR5; zI?E*S?otA3&9JiRjhc8@2y}@|5O==rE8t`hD-J00poey5m=JPTDy3!dnr!Z#99rrB zSF#rm&8u*a-ak0l_`#O@3+UYv^p1=pMg7 z%Kw6StZ=5A$@38m6`^3_yfJ$OHoH4@{j9YEb)yF2>cuwnOn&trANo0^cu zc_Np?UB0g^5uO-!yOO`Gq9PMs62+L{I6~*6&}p-95k44KV3Lhywq5x8mh3DEN%gOJ zS0|?s*~N+#ukmdV_kru80E75I`72apK(xNSZl4^{g*!9+>&^#Z(D2;7``J*83OZ7J zCN^B)lg;E0wqdeU4MxD)?19noHfnT4dr@RTy_4-7$58{9M0nj{8TC$ms$5)7ltnoP zMhF#TWdkTVw9>$Og$@yg-|+uOD^Qe{es{y<|5OXyuaBI@efWppFc)-tT%l9|aHC^p z7$t1P&8?o=?SQ!C^0ZIKeQnLUrSI=}3fGSHwxjuYf^6zbv=>TmLR`DJl*5#3Vpo?k zl$msx9)I4>>?hA7hrZ6<>G8JKr4i04+Hic;v7`z2nkY$&qII-rx zeRcaC`ar&$WB9WZ7Vn>zhKU5$#OHxN!&mx}4U~7F141*>w0ZlR)&!T$ut%^GOT9y) zvUq>@Xk0EjF#t0F<%4`#7{FcHEOKBjzUO?ZK60mypk*ZFYNiZW#%0>h`*lHoc6<8_ zK0|eB{G^sYEC5*CbUtxwuYdqwpcXT?1w#V-uh{%KYAly18Dd-S2-01hrS?@)PRxP*+sbTA%EQ)RLcqPeV`f!zM9)s(oxM!>9I9PPh22d5#atT-K1bDAXBc^| zK5($x8CHf@RqNqa$%UnJfk~TU>v0MD`ED8bhkb1araFrre<7gyr{YahaQ586oZVc5 zLUI&I42zgSoY?eKF2^K8=fQ)op}Ic}I$$o!1DiJYRk^C)^q}QExlS{^tOD67-nVWkrkUkuP)q{@hHOvU8H_fFl`NG+c+Hm?8|CZZ)EGv^k7xNA zAcW0Pww6M7WyJ!Tlu(6_2~d!za-nYC5lwuCdUZ}PdnnGrPM9Bo%QQURKLn;GMA^oY z4E7#>5`=@6_uA{9OX>baikS=&Y4SL?%f_^_1D%Gu4Hxx;V}oVQ>^*hQR)_y0^>MQ4 zx(H7bxJ>p}A!Zji{q}T&< zrzFaw^gz^v05cE=lOXDk46;8Kjxn|q?&8|Nakiq^$g?~kx;Z$|Cv$1(f)NVk<)ySQ zX&-+5*}ZDT6CS|f$+wy3%dVO@o)88NheeBy=Yt?_@EbY1DmyjZhM<=!E&H&MI*}>qJ?l}Ob6k?rMplYG8*s_ z;c;-+{4iKt z6k~Dkf7lUn;9m}X0ENET#4gwBF~nltIjTSo`r+FX1<9CQ-3Zh<#4%tiPtMf)nidlQ zEgK7POy3^(pn?e!{|>bn56sVrCHCG(Hkve*x+l@{>Yo2c{?8oE+PVe(cBa$vkl~JJ z&PElFtwPFg*W@d}>Qahgo$3mMx`DU<@HdE+GsVFqN6kqGX>z7ZOE3K;4T~`c8mBX4 zZV?KhN%S9KK`xYU%Ms(|3;kKvd+9U*_*>R_t@olsKhXBC_V7PEK{*<+qC=5c^Tyxi z*327i3JAJM{C}Oi?_SPxtP0ibrj(@zSPJ7d-&%@>wMS=U$XOSAX71N`eI?|j91vXN_eQZ0ul~? z04izkcZlqIw4K2)WGZ@AFeu(1AZjvTU6y6(I>}r6dZ-Y*QMMi@cRr-0fcFO(wL(R7 z*Dd>=O6wuiD+1yV%4rUXd1hXen+DD_)Zm#ljCU#o(uqurk0-{*Uqy=&I{G|kJJlA) z8QiEmH8$J$y`kSo>YlelvOyytaD}SKOUK*ZuLW$g#|JKPl)fC)l15cBRN1u55(J9F zul=|DU2n?N-d;6;ESM-h%Wjx}R{;)|#-jADvoqFm6gpJYdfm{1k@IS-Z(icLthsM#_HO%VPR?VDqSy>r;PXZQbVvCAJUKqch z_MN6ACubHCs%R$s7FlxpE^icfn#|uCC!PN}6%wF_qQ?77dYX8!nHch7Mh=5A?%vVo zalHQm&6(GKaV@0qt7ogCUw+}fyN((_a-GoG{r}zK-V{quMs{6HtfoU!?b7vJ|Bwi5 z8t13*eNUbQR0Ke3op)TyXO~Mpb@BzSt4!y){9tG9KG(E47j|U!bMx!@#PKn{1*0oF zb);fhAc&X(+Qto*TEC9N{tse&$L+rp8+Ur< zI4km^;@x=V1ZL- zH#fTSNRCx`Bu@xJ%w@7wc6UF48MO*D7d~`ZZPG4ZtKvV1{86(VV5}0? zdTI}Rw+qVRpx;^p^!{V|IFDVES%H7Mb?)3zA{AcoLcM9=g;Iy63wqb!YuB&)JDp35 zN9W~WoNTVNVrDoNh4+X&9UoO8-OPwI8jevyC!6%xcOI?-eYdg5nO+dAa7wn$!ux(# z$d5t9JL8VSFl9X*e>#Ni#+K&5F>4XutzIFfeW$uF@oT3s1DcZOb_V*Nnr@}i(6%Kg zM9XKxKkFES2u@4op$yDh~s11u`YYVIWXp!0M7{)fb8AQhJnyX`<#6$@nrNm zQD32qdwweD^q^_*?lAz!9GN~Zu$+aGzcF0W0khSi|NU5=D-1H_vzJy)5NR9KLd*iJBw*@qkbiU^1}%H;w|fa&Rf+CQS3O z!vO90$EaguTAN;0{sHyPsERqn0H=8kT<1^56^J7*XTp>eN0fil7VC>&uUH+&hEtx> z-XqsIHqIf)-{|mjmAxev6q(d(C+1mUHaF0tKncy#*O_en1B|zrWz!T<%(p)MZzlj! zJG^e%C*H)g)mijc_QVpd+xvbh_xi>L^n@PAT)J@ydfCxXNE!?hfVz**w-!NpS7ek+ zct~q~CO%94Bio7~QNlwdK@ZjNefv3`s+vJ%FaS z2-lAs`?K)0j|=8tSDOFgEXifJq$3Gy9Txl$1g7w^+QA0h0zO@rT4`*qbQo z>dMU}){q8`%lbW)?HS0IF7lK^=E3NY`&?pkHnystz(iFxe}V`hdN8)EEC#k zPNSWd=lDhYgBpF*|6|76Q0*27PdfRZ$kO~x?(un)Z+YP+vhhtsd;RxU9b9*O4tQ^# zt$uVG653;;ecZ+)s8gK4KNbmtrn69kg4EEYW5w&PaT2#P;o-9X4Q+|gf!3k*Z-S`v zGKQ__|8;ieaW$uXAO8*aZ7qf=lqHl_E!r0?Dpb;*LuxWAaYB1pDvgFrMrjjuvq?f{C>;qT)u-^%n>o#^njj9%rVq_e?y{B$`61mf zyp;I~?HpI1&j`}s39_K@j8(Xo-(H*%2M^Dp;)-YN_-o~zpNEuJS8m>WBEFPviALlJ zb*-&v@@{5k_JF{kGceqiZne6mg7}q3-?eh*q1$n7<~^t(xR)cqL3Bp0Q;H z8?~S=Z6E4H{L9+HIF5fw`J_7O2}z&0oijZZ94c@BIz4oulqxzhUB+StFu@NYSA6)` zNeDz2{5dM8%8Os=kA~BiJmKw?ZQ>Xi6&sx)P1|$j&Rjk*DMjs|g00Cc zewgw3gDLaT@oh<}Nftdv3@%oS+PxArkUm{NG=mhSu^b8C8*c^9bpEoSvP!DqZA;{a z=-<{N+@UJ!6&~1=riHp5CDCZ(=63?G?ISZKFW}0(xf=`-;ch)UF3H>z$emRSzbQAw zqoGcQ7Q6N*F&LtYr}v-d=nYRKYI7XZ#7@L`wHO)xe%h!<0c_yIZQ-irG+9e*oPD#kgP|C6zwTz}Fsvx*`^E8lS<|v?apZ4n8`! zBv40^Tx1LxZTV1e|+0AJqss`!gjP2S{SesoMs z3KC$^YXH&7A$T9O66CaIgkQZXt*xz%*30td=A4Q<8h0{3-V+}!F+}EoS^VndQ;vnz ziB5%LnB|fVQHO}(^fYbF))mW_r+~T=qvq3fK}AwVX7CPaTje_N{JtIfp^*4Rm6HV=i5~2|~;zwWixY>A@eg8~u!NMk+K~>%oHu zOvRk!xcs8-_M0n(gBnE=LrI!~q8y&@bSGoxGt_BE(F=An>l-fnHoBX zJ(VFNyf8%aeEE6&WaQ+2u^Z^J`r&z5nxFQdM$-F_Ipt*!t>bRm%L+mCE{vs5S*JH4 z4?HP%(heOt;f1kgvG_;Iobl&MB%%0xyR%3V>H;?jg}Nf#zQ-H|H8M}B=9;pc&50WQ zx$_qb@Gop8KDv_<2gk>zY<1jq(>}$8LhE9QvYz*0+ZxVf3~WnO-4YSS$uLDj)s!hq z;x($IRNUmEh<}mvo)@1=>4Ik4gIb7=1iK0neJBztx^|fpohwNgJ)T3xte>ZJzD=IW zPD24_>x@tmEORPrRA5_@>K4x?BGW+Q8Qgv@-{-bApO{zCHK>us1YMGpjjFdH}v`tYoJ$H}&q+-%2I&x%5>b-R+Dw9#{ zUshUf$lVIdxmzJsflDnCjvDTQlEh}taTgudoSAC{OUvgI2*5rE2vd>hag-;L2|T9~ z?k~&FH#XGyjnuOiJ4jiGpdTYMXwG2#hMCJ4*)C!@HgZ(bRAqV459EhO!#cYik$ora zBG_BOOdJ-aa?o;blg4G&rkV~)z{2XhHw{{6<=xjuLPd} zPrB&eF+19G#7#`rD`c1@xH^+64Ao&{#$Y^pAZ=J7dk63ZntAmsPVSIuki@N@9TjJTGHG)m+8o1`@76!*{x$7|v8Fk&k^w0KWvRW|Nu^KvBLn4FX`~$Mt>4QIgV0Dq^Ja`N~cs;jgi+Mose%)AX@QKY; z_Vqt4!hZZ@-Kz4?A zMC2x!ch=FJ;0$xKd64&+FU6iiKyNhv914=>^4v)Vb|MTpgS z6RNRo7hj=m&em?X72K$a$4JWlAQsCK2*)ht}Fz@qTP2vh6g?A<5V+69~TkQMDa zHcx@%V5yGp>2EyrQAFimy7byQy|V{Vc%^CnRfh~c{Pfe3?y+H>$S^U^4og`l?cz_l zc=7u}>@XAHjE=mCv6tMq(U=6U^mFbv;q!rZ46=4}r}65L+lG z>lu)yx6ab@O8Xz3GtzVgfsej?-W~13hDxm%0Lp{J%l`cP70edsi zL!zCzMD~m*!XmrRqOkJUurM0vaJ8Fw#$M$nOWu3ga5t@3T{)d}A>x%Mt+?MA6&J?> znlL(maq(i}`1r9;lanmNNKw+JMbM;T4izwzLXa-yE9RYB3AG-{_^pPSLR%`46I+q3+UqnQNk+%Kr-Kk}3 zP8vhQ$Fxid1^+eGnzbwXIIr_?>8L}+Q`ucW+YlrS$4R1s9aJ8!qZ>ILrC7X>Tg{n1 zc`HKxY2TTam+T@KEy(4Ol0Q@76=ZWNEb{K&ys=;K-xZ*5`Fgouc;4a2N{Gl}M5|Q4aBii-6&epR{)9gT89jKYC+Nk^D)7A+umpdZd zHAA0Onzn4hYsVdrg&~ddPxj8XQ34DC7k5D6kZlZyezEc;o-;^v>54{{cj%L^>B85@ zSNf)~kL@a&RoLde_w6>WQDcxV%Y1S8#>)2g=KM6os5~ZQm8i}Qv6Q|8I#Phzr43Lg z;*n=2655>T;UtrKbm-+@nN*4~7Y|^d8l7TY9Dk8(3v_nkN0)w77J>Q=omAJCZE2tR z%?0>PRnL1cg4)Her8!%b&IMdNOXy3~b%@v2>-q6FZZ6?&ZBVtn$eZzFxp^Nd*^JTO zT9;ty4X*}mN?tq4%s3$r+HX4@%VgTo<>FHyOet{40HsyieY6Uj8*^ z&D<@`GgIy!T+JRm}R$9<#yvr5aK zZiLDOk~1ad+Z#y(r@4k#hfgejfA+NN!eOruAOk)#zInL&& z_|7wjLWh$SC(c3SYJ)NBfcr^!}+mhg;;*mJA3u&Ex=&xM%BL3rZnm|d{yShwq9&w z%}6gDX4gkYM_W%An3yOlnqCZZj*chMW8y?3)4dyrV|65nuQ)(cauIzB1qCw2hkg$Z z4&JUX`Ad$zON)CMiBA~M5TU!-&(z5 zjYQgY5xf2eWeC;fR}iy#TNqUssQgRI%A|k?wUshk>bD$B!cYY?l@3S2DP93I&4IRj+J%)WO(40l06w)IcM;SK{k$Jae=v}u;v+NG zCPY+z+9;xE|GBNd%gVApjYE8w3w;Qmo%|Yvw`36hKL~hy?9IPEjm2VCkK%!d zgoZ{-hY0!R-@KB3u+&j<5EI)T!MAML0XGr{Q=@C~cVszenq`hGgF=tBhziTX zgkpfYL0YWVJqoh|0OAc|VwKI!&AqB_Zhpl{H{WXp$37ZcNf&(OnVkUg5=1*>*(uvk z$%v-xb(fE;M)f7Lc9YEOcke1sxutIU`-k=(m)f~pZWS4jubG=XgmWdJaNx(m#Bv48OOOFQx zWL9ziqj>|bieL5ac3Uc2I2?gzzG-}AzZakC?Wice3u`oO0F8w)us}K?>qv`ovcn(W z?b*1DkZMEDog-}fSQXcF(m`Lf*VB(rEXZ$yof4~jB=$hnQi>Kdr<;s=5`jjw`nX~*pd5}q_;QZ7I6yXb@bLJ9`ybC&L z0HDtqewR_)2VbwLczQ&3>aF&dP3nS70aUi?STtFZC~++uxg=6f&nC{`sp*diBMp|O z0*pnWgWctk$e>t&d^<5VOH=Z{;J4-&W+P|Z`<68m3In3BSXuks~95$bD zccVnS*>zjqcWf)eOHc6C&a=Q24I`XQkv+!H2ly!&DD=mviRv@I-+` zj_ine&p4n`e5+O+Hj`8h+P>zve&r=;638^;4vWk5x zr`-aDPg`4C9^-l2e?UC(xylEht%Zf$0jR)@Faoha zLIsrK6vdx$A)E3!x-CTU*C$8(yPdVjqM=ZXu{< zK?H&hz&HSkH2*Tt?C_C(x8bmK2Eur#>cpu>!=RA>B@6 zpf%4jqiBK&p`5FiqLsqq@Rhw7$U3Qvf@>(5dJnel0ap7aM#RZ$qw3noa<3O%LVkb# zjQxRj_ot31Al%g-hbP;>^87bgWI6R^tIS|H^Tx<2M1g8oSwcY^3T8TJCu$S3dBKVfEFX8U1bp^w+ifKGZ#=hdQrY_ zz=~kuV26W9ijk5t8r*i&9RK{jOv$sym@G^J_XbNGY73FH>wmU-H{0C@0zJ#6S!QZ# z=u|V=gV78bqjd_~{{(!kVH{G@*KB{P5yxVPxw;O?t4&Wd7t@i=BjROrttkb39v3|R zg`&DHVF)fF+sge#uZ zoJIA=uxc^MQqRHk8`hEgMRQ#ACq{7a_A4K}Zebcodd0`Z?PY6&#b~%;%>FxS)p98l zD$r(~yu1ZmYa=5g3p8F?%!5iZb{evz$I3=c#a5{g`z)te_F3JtV@(h65Ft^|52QB5dUMX*xRK z03A-nR+q7Who=F_e-Xnl&C$yzhI^C9Mocp4ot>S-O?zF*0W#qtIF-c;V&2B__gy2H z3kcawjEs$~p!Ox_q9nJgQzeVc7)TR6UMO3T2rh~^Tm&=%nj)t<_l z9!}9_!)+#66tcw#x66PGB4@oASsoeVg378YEBqYEzq!e^a^1ndd>hbNIcxuq5E2dj lpN<5=Wq*Bq#x)B4GFL~vmaq5rB#9|0!>uOz>AL$){}=92fsz0K literal 0 HcmV?d00001 diff --git a/examples/nlp/img/multiple_choice_task_with_transfer_learning/multiple_choice_task_with_transfer_learning_43_0.png b/examples/nlp/img/multiple_choice_task_with_transfer_learning/multiple_choice_task_with_transfer_learning_43_0.png new file mode 100644 index 0000000000000000000000000000000000000000..2f905d51c1908eae33fa48de49714b552997b3b6 GIT binary patch literal 86801 zcmb@u2UL{Vwl!L68(Kx$)G7*Si=v<)0-|I^M8tqZL4r1d1WA%Jt*sac3L*-UL?nX} zBnL%_l9OZv$vKCj;LTm?Ip_Yj??3K)>%c`65Irsj$wN%o5-x-cyxHsKXR7?8ZRrQVuXVA--f<4Y^2Ue|WS9x&a zkXv-advi1U*Co5ecYgI;!}iys?rE3ov%h+Y?@borwaKn6QoS~Oeae11 zK;-i^QL2zf$yTjjFrfeT)z=uNp``rZzKw5)OGtXL{?iYB4=!ZFDS;r&%cZRP4OboThj=*(fP(ZBS{<<>d4E9<0e} zYk$1y$X5I(dzoHPflnW!jR@1ySTb(sglF{eGt_>0tHp0WV-i&?zAWByP<0O*+sHYG z$)FqW&b#vq`r2U+-k<-`KGBD1{(caeI_%=CWtzAcdQpHba9e;e*fBDy?zxRs$ zmv8*|j{_(EKh0=L5Whifflfl9PQw13JA-QTJMy|p{SCwdVpNmj({@yQDMl&Pvs(F; zyngiP(dvBKOoxZoXu9|cy7Mqht z{LUF?PAa**>yXa382eUuMp`<;yg4apy00cGAZpoHO6rCTDh|$c>QhL{k(N>3F^gXQo;PrX`zBfj-(JF`Y3byVxHa1=p z`R`#{6~x7Mo_*SR<4E7Sg0a38$22A%btt<2m+|Lr(^61XjjXJci;_8h@Mc&(KO5W0 z=@z@V8tv*!8X5sB7+In<7sh;SdqaJ8)KaNb&clc0ik}{=!W110FBfFL5TGC@=NaHQ z*Q?t4E}gY*YOt|Cp-i-DqPHpu+bXJf$&YEglp`O%;d+YvQ^hS!dW#}o=h^b3b{x~_ zEEvTL+VpkD$iRiwbalhmv5H17E(|ZeOWRca2TR?YfZfy$ZEfw|$vVwA69;i|XVHZj zEgKt~{X9GuS7LnKt7CZetM@T%KXP{2inZaBhISuJ-Q3)2%7Z2N9p|mRpFFvwzV62; zC>F87*HsuC7W=o;KilZXbo|`2Mjy6@Z01x7zg`xgU-42hw4=SfeWJl2ZoinAX6{`E z`HL4XiYV#1d2=f3mj#IU3RxNXH@mR!sLN+{QhWaV`I&R)lF~N){49#cad+ioH!~u4 z<>TR;qk`y1FXeu!S$7eALq}lmp1E*Ad2xZZnTaVfC}?N1(;}@Q!^SMN@yU}X`}XXS zWE7crKzhX?Sz>HjDkp zaq7EM?mJXMJ8T^o#1>{kHf-3i2_wR9h|ngg1f3Q#+*w2--``%z$;YRFNx<7Z85#i2@ZscKe_WJ&*!k6~SIc$ex$#?%T%k?IIn~reDH~rJk5r5*s=1L+|HRu{F_ac_ zE@?7F(9S4(vi9=SDA{Qavp$-RdYUb-q&K<@YGznp^b;_C=Yca6;S!>dZaMHJxGL-d z=aC~*ueDmOI~W+Y9ugO_8mcbl&Q=Q@3>2|b!bi$erv^K_yTk6?TO~3-lG~7C8sc!) zA~3nWzMe_MHnAa5Z?~A37{6hIg2dgm71*Oujuei^&!0z(cH|p$7J08`V2Bx=GWyu; zVNe&VzDHWqVN#KQisi>bwz)_8dMk8}4-_@+%Z@C%USC6dF@K7qIKJqpms>4cW5Q|` z4cZ_1QCp9(93#Ke^oVSFrk&Dz_w4x;(fBbh&$q4ZN>#d*ae{X7@A9&;S1PNjO4O~I zwdd#OKPR_38nC82(rkAZetyQ2`$EX7^xF07epW3u`PMcz&wt&x_etXrquBfv%=tCd zcQ^DFrjoOt&(GT@n024$MF7FNZ|@i$)(jcV+dAG8;=v^S`pug+A38lm=fWKVvliwI zHg4UjJCsEo@@p9$YECb?%_yqtd&E%nD@{pKg#k0d)A-Jiclq+=UAc^6e4d~2=M5Hz ziHqa3=~h4TLFT=3y9-^Jh2AwCd2y^|x0E~I*RNl@jGd@{sph?&g+)b&H|{-q$n$fa z+xB9dJU9M>m)|8WYRJj`iSJxzvF+JqHq>-1Y?>eQQQZ}IHEA@3siP^?(3R)?`}eOe z1d6U}>}|1X6`G zqdeDbn_G?`X#VZu(&$uHT6(0SqT-aNN|L^}gN>@HZ!V9ZMc)&>#&fBshr5Q8r52sp--K!Gys`L|^4+og5nVFfnu~j7-x2~S9X>4qq7^tu6)l%@U z8$P;C)eN}&WDk2LZMWFw2=b2$rZzPk`Rs=)`zpk<=JuI%de z-KSg+Wo2dU6%eS)y7A@BRm?%Mk$UP|_VX_eEi5doJN`7G!!6auInj|eceB`K9kV{$ z^MQc@?1tyO*U!qz%DVZ@%gM_ZAN06?pU3mF*utpC&0=f`13}AyOGeLm^V1C*-*t71 zEvDvvX*ABJ-96{nT^1-{YHF&39sBy#tB(;52jpANIV#$yxtR_%9eF)<`#p6iz3k-4 zlhsGV)07MaW=jG@8c!d7xP?1*+ zxvZg}a7{H)_v+GR%g!k&J#|Rs^%#zGq8aQiw4Wc%@5~Djv?!XPQvI--l`W4N^<_@C z@D4U4kv%-6ZNa>bsiP&oMknF*p zUz7;?7f$I%X8FxC-F&L-ch2#fwR^#++V1=idc;1j+OPQO*G00Zr&q6Ar-Tque6YVV z^dW{A%q(QtQyn4i`D$jy+OR35;_KAgw{O#Kc0QOIsMpe*>h#e(k;ZP8&32@5L=WctwXCl`AuJ;!Bk{`nr8ahULYYoV z;YA&)uOquH)n}#}jV*8nfjiSnheBQh5wS^Q&nRY{i_^&Dvl>!UN8}|L?&{U6cREC= z1H96eLC0?w9h{z?CizM6(xvdYthu7EmWnp^VvF-;Bms+xW;K23D)HmoyZ2P9!?gcl zUf!sT3)=3?La*;{WY;Hwb=^A4xhejyrTI1a`C*l|KhXe#yoFdw* zs+sm#hDdoRAqQIyx5W5p*cM)OFg1O9)68u1Z@&eVm&>|LmiY2}u>s;7i;gN9KO!KY z92y$BnvpSCjJwEj0hv_V({bkO%CISE&)PW6xTYqx$^N>yrXwg6^rS1X`38%z(Z5Yh z8Rw~c7)VRs$FcEmy8I&uIfq3Kb=M0N$LWu$yyKnqOo;Td5cC^N-58(I0DOX!^*w2A zIY;2U^TyHu5l$`F+_CubR|igR6SjWy`kdcu%ztm&``ef}Z=O@*-DN&()FbmWI%;|O z@{i4%HXXe&-IQw9>1btXZ|@J4A6SiX?{yG9BX9%o;c}_2JH%%|?wn2{m%w zwf7%9@SKpBh)7V1z7&jYMz+`-QeIKaIJT*^bqet%qpRv~l*vEtRCM1FCwvqC;B_h7zVqbe?3*@kKE`K_ zXe2|x@r@hNFJHbipX^gKY{^h5@e`=)sR*e_)RVV6BzNgj&zlk#R>w=869^MeF9&#e zg)CdSuG-q(Fk-+lAwJ%Gr0u<6daIx5l(m3<^=az#un!xeW?!%iOJ#SU6BqV;b+v-a zXmD__etmrCi4!L#>arIUckS9`JMcE&ystVUt@*93lDApcZ>Jzvky@Bo-b15U3xv?{PhHp3zA5GH-+mujPkv|*Cw~V*H*s*WY~6kD?fSq z^feNPJ~9#$&!2w-GbNgQJt6IxoSZy2*&h}ieW2tyuhg+)$2blgs0QFj0$g!1EPci! z;kI2s3DpUKK-i+X!!4QQ4KPjm!ddSW%(K(2hHH%-$Nlsj9%>k3l4UB#%f#aRg{&e| zQZ6CRR1DN7XuDP{V-z;YCHUH{Hs*5Jz`zZLZHG^O`t-@-t<2N#qEvOA9Oos1He;`T zKdAZ&)g7~_{UxnD*ZtEB!F6->Wsa|JuVn0-8SOYDBO`z6)ZMwMK?BXjoMnvrP)Z?? z$5c5)-~aOEQuEE?gAH%Bq>_wSH*O5kE`F+*V$}8dIUYO4)6+BYYVHak+A}md1zPRp&ALmyJv=-d z=I^cFeJ!Eh{9D0e{pQw^>Zz&b&XhBifWv!e6Z1bqGv5J$qBHt)HkR76iWZ{9v5Yl^ zf>C~hHXGtIiXL~=toym&DWqWI6ZbrO=F9{63V+s^S44TH@4k{=EE(`q6^4jU2pSQc#(tl9y(Os zbY<^MZ{M`( zn&ZNFpr6xx2kUFiY{$L(_7y~QsHiaX_V%tT#-i#iOgk;sU7g)-obh#Hv?a?SUHa@< zJ}ml?b_|Uxk*Ps6h<)$onD{JtGii&o9yuWcu8}-b({HccS zsYwm%ugf=X+t&L=n4LYJZO@+P;0c&CH8nS~uo&TBe#W|MvC22+Ph$(~G^LonR!_Ig ztE;QyGi<0{yY*0xJ#DgXorUm7&a%C1Y#&iBiCD>(9Pf>BN;hvOSnGr6|QF3d8{r?MM=)PEFsEEQ?WB)pwIEV z<8E(l73~*=r=mOuYn}q=Zr)X#{vGJv6t?<2+SfiwC?*!em>>Kc-ytwE`}gl>61BJX zHm*uCQ11NpZ67ah!a7c~3;u!@a#ybgJI;?vMah`zp-v-Zt=eGOp$o#vE)3iEO3zJH zU5K*xLn7|&4GXOG+#@qFKVBvjT~<<}c=oJodq)SS|DH;J^%Rri2UQcxVoN6*cz1&^Q!D%Y}KH zJ$v_(Fq4LoY+<&{iDTEU<2XpZf)kuh@!G|F4s+(`0!5pzHshdbC)AVhfn4@)nu%h<`px>A zb<+L+q?OwCf}-O@b|T;y8#liGhV5WdT{Krz3%_xT+D}M8%XgZ0`Qwj2CJJ_Y^t@{{ zsuEkAy^v&3S1S5$Aa`gxZT>5x(;K7fJMWuOZBgSq;>lY;@htl_<%nT}E;i=sHEW`} zSNESs>Pgb8+WYC_$COS?+|8ReLtE#M8PrDK>~2ED?oSmYyOeyrkXU!gsbFluZHLE> zIIc%@j9D{tNuB(xt#9wyXF({pFR9;^>1oZ*o|_(asxr-cW*feO|5GXhc@6#R`lDsF ztnno0Q*2h8Ej& z#lbU@dLi`Ht4rz+^8Lh|ve@(nzP$Zid1>{*560vp@D;xO+c7!=j8EGc=aSEvE=vD4 z2YqzqS5Q@4&UIk~`OJ4{&F=@=GNM)z5}VC5`s?Vw9@shUcwYI)Bkr2OzyJPa%$9Ez z{gHFFX((->f5`vw$Nzr}{Pz*`9mmeUapZDpAm}$$b)_Wh$}CEqYLdQU>bM{q+p7pj($lHL+5iga{mBi%glxp~q4zk4to_Ko}^73|d#3 z`U~5{%gM=cs9PBhX4+0hcK7{!l%)4wW4sp{wpg#bnc=%T-|VD2Va}B$=tQ_IBlxlj zRP{2RglyTS#dr0?FAt+4S?~)%f5<#N@R;Wm>e+Su?~Gex5sP$zGO*+2z4o5F=6ccA zHqF5S>zF%Ol!t0zKd?mJR+Q;6rPHCJ4l`d}RI?o&Vr~?Bx%Y=(4B^u*+H}reu;yxW zv`WG?SG;peOUv&HKNX8`hJYu5HkDa9;~ZU zJxV@5!#JhwV!IlHNW3e-FO1ERuTQ@}@e6n*}zpsycU6Z-R+DAsFl62PR$ zKrgSJv<^AYU5NZ>$c;Gt)?PuON%;Q}LwJs;=hXO%N4!3Fo z+hdx$qEG*C>@iy}YN}56+ut{_b~Y`EP71YJT3Wt4<-rnz@LEt- zcHx}gk(x)lBoZB{Q)fIz|5~<^4|);SxWNZ$S;20xFSkD7IzPm$B;!^MM@Pp8_wJR0 zI*bPDZpg2m(i(KfIRm0~IUgt*^X1DIKX-=?HvuAf3^t|8b7#-r^nR!5o&TkNk-JEt z(?(7m1Ui$LV}??!T10tyIg|15sU}*Aawp|pOkj_&U3S+uFfn;o}r-$wd#*zt~lIXd3Th#ys~_vt6>+v&r+I-d`9m-_Pp zmv#ADweVm=>U{Y7*Ur4WPoK7dQZVZ&-{mqm0kMzpR#UAP0)+L9AURbE!b9#Qa5IP-tO zrka{e@mO{(uDKq_Ui#qSLtYdbFKN^99YB?96o-!|uWfR3aZ7Ca0#3;2fFH zZB-fl7f=j{7PN8ax%OAUqvcBMntv2WX*}(|k#*d?8zpqVSw>%008UTPd(~pPvgo{K z+p(LkurM)T2}NewZZq-eJ_2*jId54A)YR8()tclnToK};6r&ni?89vUGV*r?%~Y_Q zdPPt6V>`+sR!)o+bN3gr2UcUxdjspR3Sh^2KYgkXy|vRQ+h$w`AmuFLMgq4V6g7e` zan3HF4p%_J`18*{6Lm_MwrO$D?&d(Hi$Fy|WDbZwiir6`m-nleJlQXgl4||IOK-$+ ziV>o#29sN3FNn^bBti+~2kd|KF#bz6vG~}ct-H0(`nQyoyb!cFT+9+-%mfi?(meZQF_qf*wFp&mGm7_Np(7UxVt}PL$<2Cdc(xzO&a7mBNY&6 z)h{L241Rf=t1as6?%`2~3Yz(8eqLT*kvC^U!gUXadIZ$!P?;^XZl{GXutNr#qSs4z zWX_Kjk4;V{aZ>@ZkupPPW@c_Sg5*fWoK0YDh+zHIaX7U*py5l5?KtW-Y0ni5ObUsA z$$kFm1u#m@rsJ%*46L zt4dI}Hi;b9ZT>sYnDVGUTfH2iuku2xvvnpyvto+dWusI{Pjgh_sXhTk@C6^x-T{X+i6epasmCRGG;13x~7cIX^|Hts^5Q)FZ|J z!R)!%_6Ze)-;bxQUA0OU3TW;ePPMdWe0+Rg;ySBib$xPBJ=uEkT<4pOCVDE)oIYKS zurXOF!+k6|u29Q9VUb&ZOgNPU0#49}w7E&n;1f7yZ-HJa5b%c{q zONe~QlPACAgTapiu{bt5S^+`znrp;JH$qih679_`Yzx##iV6y^pg*}xhFu7JI#HFp z?rFrs{08+>Xsnwz@97N-YEa=+ik8iHXHG(yXA8T)K|01@&<}=7J3=!ek^T>@aLD)ac z!q&0~$FI)&3x?iVvn5g`L1${zV)W8wn^+MLAP-z!t5GIK*{w2=1YK*C+W9-eVTfun zw^XEslYo3~i~1RK{EneT%)AbGyuHw`2+sxzx9(L~7!kx8 zlg0EZ*{Cx#>a-swn@DUMnVAiL=hm>#b%+?a-kRmGS4gOlZSP*+o*vzf{(b{regmBV zo33rVHe=VQDR>K^YGD{Eb{B#|TMVB_2@tWXb=@vdnuyYT2BIBC;Jakmif3`z3k{;L zUuxZ`2|NMXrY3Fp#fu$YPo7+BfOcr_;BXFv{CyyWR{L?c+%FCG(Qa?2)Ohorkx@aZ zCt`S*d;LGbk$<4Qx|Jlm&7N=3uzr8?)G5IOaYb5c&5PWTW5WB#!Kyra^yoLxayQ49 zS-O4v_;GdMb&!xX4OwB#%37}5fZg>#vZW%C-s#WG%shwmZEUT^A=esr{bv~Ljr8h9 z5OS)FLL1b}$d|f{z<;|dfkxaKcQlrz;OupVCDq~oH?HNEEtMtM2ctn_R@WylB zye>?9+;~CZXdbi;5!(rqIX|Oj+T>3In3@~sw_`)TWk+*2C***#QZlPE`&4g#n@}II z)!OdetG{zroPo9~>U3nSaILp8lu5woMU6Ja668Bd$V|d`e|os(vikWLs5gjV1m8db zZ!)6B9@xEGg7_%_fH)Xd`~>H^x&=!w`u!72#dY=5gUz-8!iq3Th06H!&Cia1KD%5d zW8}jcz?s#*{%U%u4m2F5?VP6l=$)~#u>;|;MlVDiRJU#0HrM56Tn%eXa$^=JWclat z4aD|Vg$YIbq5i&c#1H?A)yUL8Zt-J9DbiWZOP`c`0EF8mhDLL~F7Wy+%qhj~;$~rk!RSxbrC#U2y^~aKl>+6jE zA!xySRP3VToaQSIy%4sMgV?NJ`RYDasiyPiCq_na@!oB3|I`1d=?P5fE*X0XFAX^=9$CDRV_?$yO<6y!i>9IULY zNk+}85b&y)t(t95YMAyC>bKm($93uYqpF4F)7i zMnVK4aW(K?)a-aSr;yNPl6dx>e-SP;l#<(5DVtApV^>$#n{n&47r8h%JlOz+p4hqV zqYAWs`FV7QdQra3eRW|?MEs{-&n3fz{7gm%ioe;i(GXkht=vI`!&Mk{c5|Rtk{NUj;JpA$)b0f8K(y zKG|;C2%@*NCxql0a6>L#*~rlQj~@NfF7k5;%Qr3U4O2-aiCheHFes$-73+3{6IBZ) z*n~8`>REY}}joT|2+D)g$=fwzkTSNB^INyy*OBnN}1zqJlcu*08gLhU@GKPkd&25YRjr7;)g`L%w~pB940ntwNa?$YqAcgY z>2L$sHs+9>_~5A|;tDhZ`PXMJg2Ra6VldK&v&EP9x;r9Q2&{h)6!gIb6DL9%U&>$o z*F!A2EIjIUe?)pdKEA6#g1SQzisb_?4@S~JuQ}^~_c#uPyxit?`0(LG*p>W`nVs_d z1{I$E`22@L)<<%3a>}5BssV_xfSN$-63DI?c3QNNv`{r20HQ99F&#}=QgQ247s+>ABy zwvL#>@;G^XFJ%dRkGI)A^Ja`~gYsSukIh7j-SB>4VYM=`#S93oup#V@lDX|tR9FZD z=tFwp0_}Kake{YFPG!eCv5MF#fP6&(a}gvBv&Q9NoCYWyO?_iO<|xN~ z@2}O%eW|kBb*CgOM$(96_I){`o|F_>IqwnT7r570?<^SO76|{y1R` z$;NSTjY!|WfB&=59b2=}c1c1~LiCW=(Rocj4K3CZ$p3HB_^iVbO_>GF3xa2jVcJQv z9)0=BscgZ@aGdr1E_^h;oYPKKE$drW;t;-uj~aYrL~s@8gCIK3>YS!{gi}+JcN}qD zdM?7WZSM77B>d@BodU7-`|uK`TQCZTzJ9Hb4blKMEzN2;7E!YwMPB=D<4dmxGU$jA zDD}L<+(gAIX)iu_K@k*}-5mQSjq~m5x|aFa&69as;bPzr6m0lvF&~>g1S7<=n$92W ztjR_`o}ATu)4`(HRcSf>dog6GmvkQ%zcPwfL|er#1y<0%r9A@!0|m`{t{7AH87%E- zNQ#28f1qUHmOR5QI~L$?U+!Tg@J5{}N1V53C-jYvrM1u zM<}?pe9bjiVgU>xEE`HmC7%@vKXb)Mz_sb2=Axn^PqtZb23XT|B~F0BgrWOnN8i>I zinXXOrOh3K6biy1@6|cr`!e)>-PX(D=RFKG1($qXoibda>)h-y(u=51u? z59~G-h?J-sR-g~$oV2vGEzA!`>%NZuNFPAK{ivcy`anZKq}@jct0S=Ebtn63KvKSg^DzY3Ubpgh@0cjIXyQWZC|JPjOAaLBwQ0(ne8HNdJ;~@elT)mHd^2ppX{js?xOg- zfkI3W37FnKgo-?O<|r(;97r0nhEXW4I6+tJmBHY~562a#>^PID4(tO20_ZbgcxTXF}|}I+$b^_ zexW~M($~3q%_6R)VkT|QD7HAHk&-#AzFO61HzpZeH=T60`vQc9awrVd0jHp#Dn6(J z`r{_Ja>x(_&AMD$9H!MX$4iAc_V2HN`D*()*wW~|JbXC^Q7BXf&vK)#lyctzl@dk6 z19x{z>tU-pb*tW|myO=0*?(V#lvP}+D~;T{M03`cI8uf~uubymtyw{lv1+L=JMuk* zJ{KkbL|;Dv)5BE2+OxYi$U@sPl)HH|o&d{O^>hMrh^^{5^RMB1p!TVz-V6od6av!{ z3Exl?`kGP`FkMCw@%4)UGGTx((vkL4VoN2zkEiUDWRLT>?$9zLcO9{u^~32HkRLs5 zwb{ZfZT0MNXk@}z5}J8nJO^BB(gawC=^8x=e4$}sQU8XdHttI-z5)NMCg`~7l)i`n zrK;bS^Or5?aZD;V0+MhZdOOC)$K|7xVs`j0{;8#f?h$3qA7LfA#a4!pd5CNLV3A3; z2#yNhR_$}|pnH{L}3i1O`P|bY2AlKWEKy1G=K9d+g)m^D_XJ zkC;3@Doe#I>62Nq$%sRe<)YjD+UiM+1_;Ksc&y;4lx4vEOh-vHXaU8vE`S(FkjD^S zNP(9*)nJeY$`puIw;UPt)wgfg07@dUBt$+8upg7A7w$~uJK<~UL8IH|tUwX805LXidN#Q28d;vWV=iim;HP};k! zDF0KLa}w!>LD)9{p#c%3hEUq)0)$oQXMIH*laS>=Ih^t_Sg?(&*_$fmB=D{6c?6ng%j?z&38+NwJ=xFifA&ZMGUHsWtbO( zVxUJHH5qMETAd~s3?_TJME4``LKH>5>`}i5VNLZ3Txf%@_=w;Ex~^F+bo`m({8>^}VgI%_yaS z$wY*2dP!|aJ!8021~(v?;z^RC-sJtg^`%nkBobJ!h_vJ{r8xJ~QAl5Hp%;6x`aZR(VRXaB9PBt2?K5pXuN>*LucT`6gVLKw# zDk4WA5^VL`_}@&v*9B{Mt(LM3G?of4COq!y z2!DAL+_Km?IZJ;;b;MOdqM{!FyKc@KR5W6RI5V)d*n-jb^H$gXhjz|*dDF@iF<%;G z8ungv+^ir;E-0f&r?WBJDH~eHK6+VZIj|3;5IJZLNOL|UFMca>gr~R$8-=&&#Kp0Jg6qpU0=*T@q_L z(Q}cg!(ehjP*|qqOaZZtbJf=C|o^2vBczpV*}C+9VPpE!?N{a zjTau?zkd-+_pP&2`$zrWW|OjSE1-^eE{;*#taTtG#kq5V)y|5ARnex$X%HdIiHpBKJf5*RPW63tlw@McPOgIwG#=Z1QZhD8O-$zEE6Dt^M)&e7 z{mpMy6lZb&5&w&d#45H&-)3p=xp#X#m+m^NbFBN@xMSwb?ZU$6-N$&%M9p-%t{o+1 zr@*S|%d?S-OT^WQkA<*MbIDF<8mNz#6lgNJ{rc?lmr=2494!*d+GIfn*p8P7OtLPH zvJ&mjDCO%4(m>f)7pIxwvLa^*2M0$YXs>LqMS?sa(a3m$wycKLHLxS_Ay?XIAGMqJ zLBa3n-bP=nD^B(WTg1=3Xj`VWPgREcXhg1Lu@+Bmw%pD=vh3bH z?8F}A*-4=m)np@o#G0MbKXT5zd$R3BPcWF)qh<6_JI{TUNTEcxe-ouxe8sT&O`DL+ zzK|t$whmt~(JR?FOS)@7ph(N1NrEUkD2}N1DH9*oa4X=5w+k<$oWJTy+D9$kFW>Ta z;ynH~*{`{%3Lz{FgyKumNWmyP;tcNL_s+*lbEdQA`Z$SEg7i?-0AbSxu8YZoRi*Rj z&4|*ZR{+Ja#@bV>a}LgEangq>@Kqv-atpL$C14;w9z)fq1H)FT>Asc?%N3`XSYTbl z5}%Hv%PG!+rk+@pijONLmwc30RP+WZMq0H1JnGVJ1Z~tGO6_I=zRcH6q_hn;ZS+7_ z$wXD)f&xi@;FxYNl*Tzua*|Sk*r$o4y4C%6=k3d>%MOClszQJ4p4o-Jo|<{|a;5eB z5g>zVheCPzfU$7tn|7eJv@Tx*1vRy3?7-#oxwhD+L0QoO1Jk4p1;DiyzLPM`#ko3r zrPaF5M`M>zavqY+8y?rk=uj*C+!!SiN%L&`5mr!NLQcSs(hypw}#0Mi8jFWTaJ5J#(F z0*i!?Z1#W^_!x_UFBj2CqYUsofgNN+Wb zn!RZE;?&w4qoeDVqGf`d74h)MY;W#zfpL(3(w^8bUDG8D#CQlZ1GK{5aBg+?ad2{4 zfa2F3YD#Tkd^Qa?pcAcMbC18suR8daFOSw;5=ElovQ$a0FBGcv-H(@v54y98#kQhL zn7n{A(-Q{^R02gnqCL{M@!;uDO2@iwS^&qd_MY?YfkCt8(-zGg_+8!8B*tMFGt2_9 zDha31LHfvi>dV`?YuRQVyC6es8{rP86Jvi41AXX&EIk|N#rSsVy}PKm3{a*J%@FM< zyQR@Se}^=@B_{HnA6oXCVv_$rG8%IN#gtya^|+GNUKWSfwd3BBFaBQce(k1ezfw&2 z&I53NX+@LoD`ItUqBgd^T)3M5;KAy_mQ10x`}SBjA2xWE!$Dq%wtg_FklfPiDZ_OU zR=E&CQA&6*KrBC+R!M6NCRS98I*?FC%!9qHi?mi^Cn5BXhw#`c_H2sDi?Okrq%R1G zj0g+#V2$e>($KU*{N##?iqas2Nk>!!adTzbO}meWF9{klUX+3Ofj-*#^9%j(Bq8=N zPmYrM2&S@BLcx6g{5f2czGc1;op1u~ttdFhNYk}KY_2rxndNOakSmxDU%LlAHIsct zS`HK-+3LjGK-$*{MMn4utc7cb?vfN0oNdy$qKrdZg|{U4TM#1#c5h^O_y||`sPzOf z<6@xKc1W$sxj$h2!lH1GPtV=$M&()_BCoO1Cp!gkbHxW~fDY;$wRJI;T!KL+nN1pJ z{o$AU`>^?{AkH9vkYfNfX3u@&&Sh=Fgj0m56b)cnKKx5IFeqV1FhQi?B3s-7M#uBJ zmpd1LI4nmP4BN)5L+GF-KGMKPFe^XhQjaX=Nez3L@OSAdN(xoFP(s6EU201L5;S{fyG20S3eC1P5n! z$)m#zAe)$e$vld(mn+D~$W$fOX+&XTjF&i2{(L>>Mo}U1t ztXUnIe(?2ytuAa<;M-72oe`wQ*dv)uQy*P3GU94grQ}>BW*K-$`f%_VX7>7oPS&SKC3Fq^y=J^p*^#nZ39bgJ{lp^B6?$@q9YqO;G~fK+rl6!Z|cSjXG8-LKVyy z-d}siYnJk*gd7~y)(%kTkGBe)g{vBBt2y|zd~0*cPIZ{`=3u0}Jru&GhplM~gSpmG z4&42d=+OZ$cN7Tp;l+&`HdMbeyeu-^WJc=q&Qa@^$3!U3yd*{Ch!R$iEGVJ_{A(jw zf9>@b*)|O6fON3Z9OKY(2Vr%Zn$rP)i8=HF>9@0a%P9AJkS3e0JKRvEe9$i;k2IDq0xLyk32Cyx#v3SHkaY0LStb}i-QzG|(nvf06oh<$=ESU7OW zoIZ`pp*h{E4lV}p|IeP45XF%4GUnyW6L8~Hba;rxg4vCTkFV_R2Ea$pE71<851;Q^ z*7gfI3FicwU*QUZ>baI+wj|w(6KEq;vbD8!J++cjSs5y0ffQAf`XaxBjPa!ttOQeEu6xM*oh!mNDufUHbQ{F6w-%l6iC~`8tx2PJfkum`=Eo} z63S6&(95Kq2yDdiCZ}4M$Rg3nuY}ev*Z0_SM{xT`1gXa@hE`%3pFos^>%#!b2@ex9 z<)f0MvQ8K~6_bF2aC5>h6z!57zTm(dg=#R!&_P<9o__ghT-F>3_NLD`5U(x$IL z?ETIsWRiEbi_Z1zreAXM&d|@5XZ2LYbL_mRl$0;j;8K8y!mS}l7=*L!UglrpbcJlr zkMe*4gs&wR6IcYav5y)$QrdSvF&>TT8nq@$CJDVfTeneuvBI{&loWP<%m&LrfeE>#ujx0CYgY9U%(=UDmNb(s9@jPf2)E3xtgPtEVWG?d@!06!CfDTF6HG z^(1mgB>L)08MTwK+KBt@muD$$i$b;&;pBcCm@Zw+Z)qkGza{Aoe<^T?axWMMEdrtJ zxY#{Kc~r{ij7@?gh=E1;Xi>;Airq2%GAQ}p=|QLMM{bNbYDpTFae8@r;&PSXjnL&(d^OHoB70)~dm$UO3>(*8Vplj6)k&h*YHoaGRLH0UjJxb^2it;7mS<1tXnj$>Yd;kel5 zl^DxoydJor*?zo)*en6Q^LrSHTZGd0l?W<`Ig>-_!(bctztRds7q!S(!ETbD*PdEM znZyANMO~o|tuA&t9-j*+7!es+L}g0N@3;v13O8efqbDaEHswB0iRAR)Mh$BQR@|lq z>jPma7$e9GUq+$aI6Fu zeM0pJT%R~Xwrzi{B=%jH%1&8Q~{9qi(bj1|97#H#^bdO(WbFG@Rhbp@qO z2jadh64A@}As($fU9_xTR1u(1EPsp1PRi>~rBIR|cJ-&4Z=(EmZpX@{lo$6Lm;Cr+ zpLlkQ%<6Y0=zuksT6VHthC7o@+IHmq$`0WT)7ynCqk$e?A(|a-k@#yFajugGBCUeP zS+l2z9R~G0(K?3(A{7)Aei7**3RN|{!*AlmeqX63%+h8K60#gA#aeXhvah0=_0aDL z)WrMlgD?VVsA4NiTgco3(>Y}|)8%EY>o)?w!P;7jL}}js@mJDf_Uo^|u2&JrmwNkt zeDhK1Ng97cAJzI9ZrLi+JR_=1-|sl?*h3c)plVQ46R1!8xX?JuG;O6aM{SJ;M(mfL z-w?%EK9aFv^1UPfk)!KQrnvIVVK0!v+<`in+>mJp6H`MdS^%s)O!e)Y-~oL~8qp7^ zhsnDyt9Vlp_vM~qHbK_p@ex85P)k@3|8_N4^G!Oz!Ds;?jppP?NeyI*%yi7GIsa#! zBS7qBASjcZKpSBe=nCQS@p7Id)Pgo4mpg%)mIW-bfC+8f(2?uIsPc_+?xWI%wAHqr znu!a4?EQ_iruEPVhhuXj8e%y-4c*@0M3BySq82E{X~ZBJ=)qJ-o`=m}V7@ zgK*sKGMpO&gK8Q)dXu+V=fw#@0T(=xB1rGgt=%h2+kgIEjkKdMi!AGavX)DS_({Sj zC!xQ>5Mn#2C6SjB^=mi?dzrU&&mMo;(Gn~!ACg)z`{ysTqrU}dzLm&sW1CoGDFDG5 z0oaV=)xJ~MUFMQr}KCj|Wght`8Q9!M26gbmQhw2eT!Ho5tv6t|M-uHAM7(>6eU zsgo3%_q@?jL6Q^v5hJtZd1w_&vYphA(a2OqeOLi~oW!}K?%(h1nnw59Lzq{iu$}t> z$0h^H>#&U$nCLh4DZ}r15ooIh7dg?!#TFB$$6(FTMLt&r|3WG;M6rH^4MpUgj-#q1 z*f@KE*6oLLQ3*^9Nib1lw9p@?8H+%htPQ15z9=E6TL97ZBVbHx=(yhRxJQ1KViHI? zS@40QEOh)rA31N9{=T! zds|6;_20jCp5I~P*~+>wvJ(3e{{tYGw701yw-2-o*2ArPFV+rNK5aB_JGr?6@u)AY zKNkMv;y-Me-}sP207knS0gjXb!w$uWaL}`mU&g8azQuS)ObqwB5RX`_H^N^JdO>39 zY?~6*S?vaR5X3&(ZFN5-(ZT7<;QfkGbVeLS4a~f9AL|(GUWUA{xaee_xX`0(FBt-H zm8Aw9?fkmsJ4q)odivAaZmltIG)&e5j#{6(?#o672KT#jA;FVUcta)z{ybeQY8nDL zY49c}2`7ZG78B5ki??ok-2WG?yu3{}T#Sh+KsWpD)(dZqgolON)%Xq^W$N;{t0I;C z$HVD)SvSY!QrYtr-2FYuv{8-iOM^AvS8zK`6bsHNI%SmI5${npLH)%??JV$`C-N=Y zIju+9Y`L8fyVOnIFDE_iuUvXnan;mQo>RD>VZHir>*9iyxxfN#+FgS9Y5rv4Sv1KlOR|DU_t1%1YYpvD;%DV^tt@@&pYu6Jh_rA z*ospUxf^5Zehc|jBwE*Jc5Cjc6VIFqyb2)!8K-=i7rd-1R$&=iNpxv%1EY7dEKw5(l~V%CH!^Rq!y%) z0W?c65QGY$d|J!o<>kHo{bNX%D3;DGcU1>5*b{dl?s}TK7uVR^m;_-`_05&Ph+!FQ z{U^Jl3;|wKZbs8skG{yL*h<`B5emk@nlazSYl!{4Uie8V0|}|yAt6)kuV^8Sv~TQU z4NU0IrbxMEjc4lR-6BgMX!= z9Y!9&h17r=Wekty1<#O|zvusWSFn?ZS=zFxyMgAAe`O%$;BC`N2miavrE+f>=rWj9 zY6;2>q?IL&+d01fVsUvz`zxv-ePX4uo62ITYUx>6fOMl`@fYTrVK@|VZ9P8JdW%4V z?&;K9Z~Nb^{U|+cF}HaKZ8euKO@D-a7U4r5JOioH+C`qM7{vVhk>Ht;Aq=9@j{5>? zPqD>uF%n5@;J|A?B09wWSU@XpEo^DMs25kyjH5;%oFM8*S+J?^jGCD`*5{S|{p&_z z=)&zRZ0-G)xt1lk_yKYqDfgq$$K8^vSN;X9siY$71^-P#OomIl3su^@yrQi~cd#ei z;f+(G3o)0H&Xd+o98+9LR0l@nn(O`Cf)tOFYshA;b-&xNk}73~3maSr0!FjetXcr_ zI5ZkSJ2jYEO_`Xdy>x?u-&d43RLD*zbcogs4GXQ%$~Wv?K_ZKi5L1_tWpj7KtVs5i zfwY7E*r`(4`k2!acd8nFQwtf%2n3M{ZK&Y3`u+xH%js`G_PS!a?qt;az;7$gC6kFJS1AD{WA@XO#3NDs|J?yO5B z#pE9Un||tbb@$08BaMQOfAQP%C*GT=Pjz{En|9SpQv%p;=8xf0p8LNtT#pUUoY@NC7%P%3;IwXTLg7?)${ zqt%RbT7!)@$AuE4+gvmomvRO}VpMmcO_Do$;4dQJgwXCwvPI1S1=D(8`{DMP+LZI$Nt;LX8fH$PlOvTMj{dl&I!@32z0c~MChwzbR1bmge|yG z{H@dx9T@e}Yj@-l1WfckUS4^0029u`0y-YK`Uw(>EZms{OW;Ncz$mtXL3Is{SVCO^ zipb&tNZI4ImFL7FSiLZCO{)3xNJ&)JdSuV=@O`gljlhk0k_XQYgjM&nTvKVOTQ%)t zpH?UG=OmZYP+iRetbAh{xG8Q;_M{JbS}`9j+5S)JzJT0J*m?Z&mL)$mXe$%3%0z`vxA75I{Q zZpErU0cGZJ!ALAhE^<3dOMjGGRdW9xAGJTENyFKWyn(^ncUNR-FzLqxTb_~#x$VB< zlvM9N=FpJG13e%I*`;Bn)z7Tm$i>9O%*S_#>5PQlJ_fgw5*{F~@mYGPB*{t=Y1btw z;B-*PV=0McA;AoB!AZYP@-P<-Za8a59h5clGBF-*_@%L1DPinIkm$Ln!cv?uiR_oR z?=C-;t9yxmPCL%=*m~N7btE;s)U4_8;hoz&Jl&vAUgNm@RCbRtUNh`i-|G;2rAOJk zJT9k4`2|&5e;?Y!mvF_(8yUqG78D#(*02dx$+Ay9X4?Mu{sRa2zyu#b;n?MML3ETW z9hXtMT(4?%9<(115KdQoF;~>MEhI!^m}LbC?sBf%{-BS? zl|`f>S}nEm#Zl7_^9$3Y-5r-qe}>cKGf>W1810|KjraH(A!q|FF4ebS;|kysg)Y(u za10k#L1H@m|FHJw;Z%3;`!H@Om7xqJ8A=kB3~7gi3XwvZWQwF=lQBb?wn{{Wq7p)e z2AMOHj8V6WZAdbOGA79slHa-L{=PrQ_x*W($MeVI*tZ*P+iS1aTGzU+^E|I};Tq+F z-vVy`mSIia?wdEme~MybOO-G^x{;B}1J+5WR1c(*es|K9(_W1?bVf7`HDZ0O;>gdR z+K91_+7om{zl&EGxF_*hXhUw8H`Sjw^MQCCg+xXUUT{tOnt0rOFzYckz%vld#ON04 z25Y0-d|gEh4cewp2_vHslaQ#Io&|3dj!4R<)s1e^anqM4U$GY1q3l(Dik* z@U0lNYvE)I82eM?wnKU3?bb0PyKV9|jUfKeygt<4{?jGR%`4#56y{{|0kw0GI&48T zK4zquTfN9TCZ@z^#KVWo=(u+J-kn8(^;4MI0jD$rwmg3N^mV3f>!+J*cB&+`2YngQ z;paC|s6IyWBFYp;!05=p-sEWC+M2!FM#IiVZ3(_9y4C*kt_%d|v=3zid6$RXq&Skh zzYJRSG&-(p?fbO4PTww6Z=zY>jwf-tL~p^T9wVC&y4z&MnEmNpIdi_s<&oK_gz3!n z`e~E@{47AVsC&<-=uR!tkfsufUWX5RWwHCURq;xhP@ysJ%?X5=Q5b-K4E(o3YqZ*H z1c&YPdRhIPIDVmir|m%JjlkiF_qJ#aRtfF-`W2HIi^17+2xbOnp)Wo%w9IF->5Gp& zKhc}Quhk8NdMxh+h$$i*QwcR}Y6Aiyd+fOL-S+3G020U4)*{{C266E=LaHV_eVRtm zw6OBZut7Dc5!?rD<|F5dDYdmREeCFd_C3NN(vJfHdk`Qa*!U{^@z znE$-!4s5=kv7-;~Aq4$CfX==YCUwi@B990V-3kZH=&GuJ{?UfUM;m+vmc~z0+ppsV zkZs=-#dC&!Z7#qZB(4pUDsCz0pJ{da-qJ+Yp1WbDH}z&lPGV)(78Ir&4&&`N#;>WC z8t&wH6f7vvg79cy6Q4`&^6c z)7=WL=C^0NMHsX$^A)L4X|(D}rX)+zFSe)42`-xIQn=-tXIYTnry#>ObvlUF@a1vH zZ_JEXObh;jCuZZ{j)}INOXQgOsaez;8j&r5f2k;cVs`stbfVm7)f#+@l7j1dY2DSomQD0s=4`bcf`M1fEaI4OQg}xrgo@}8&LJ7rA(Nht9@jWXt0<};gs05 zRqD;B@jtMLdWvqFIZ6NpM#s$5Cjc^3Fp-Rv*#O9o(rzqF~r9{^W4{WGS-~3S#We9$zZhVU2o{N z(JC@CIv$#xeU)#f>yes_DZoGV^#+ZeYG0F@(dqE}YdP}#7_$#G(q^Mot7oqFYSBvC z*nvUa741Wb6(UN+&cp=(LN=0TxXwWg#HBkp9(&Ke;D4&B(5oGbl%C*8y>5vRDjmTt zr80X!OY62MDmEXdLKOFG18&s~FbR*I6&DrV0ICOx+0Q&BSk~=Gv5K*^(;^DlG0>W( z#2y@xhdg-(-EN~Qd{&Bp+immv#E4bR8rrXzHrn)HTKBP;lCWJDrm&swJM?i)zyIC* z@8UhIW9gk>%PfQAK~Nh^6%r>~$b$*7{k>?GRum0ED+mh%JO!!f=(H=M(R!^td-l+F zvVCw0F(f(Ycv~X!B}|h4JI3=rEV~>t;A>$np|bz1+vBUTBJL0;yE@gV^go= z5Au&oY}y3Xj;%xX_#QP&YA%N}Grtvw(AXZ$J`{z0)R`SdNOmy^H;9XCg3+EGye}_g z`E(nlekDQ;H~yn<=M@6$J)1E=4UjX@+V=9(3uc(<^3vu1KV9A1loMR3m+^H&l9R zPf=2=*~?DX-(TxE z&>shiO%|=6rFMnLF@`6L8osW3lrj)7u~e#lQ1Z>R@NYP~I(_@NrEvDo^nCO2RM70N zWkt^75N2Rv&k+D5_5k3}gYfw47E`1c!SO`KG<3Eh6lBZCpKgPj>MO51jWh28bvJGd zF@ptTx(XE#@^Vy6of8FwWOEv~ zwo1gM6A+AOLl6^WD;E4d=4qDQ2|H)D+?4)Fl2Ei&K|EyTIum36$we86!Obmg)4>8Y zdi?yhY69WDZF>HJA8NP@$<6*48BzpXKnA26d8C z_(gp=rmx>UarqKbDiW1py>Jwj9-)PhtS2C#hATM4f}ZX3b7adJ1-~ zR&apFF%W+a00}0X>#4~B!$s_T4~a|;7Q_>@LCdjUvsmCyks{E{68cWXDCs`~l=ETw z*q%gy1(vv@jE${m=!^D)6y-Q%T5bz8&AhNrq{kO~?aq=SuRQy^dUgXC|Jljt*}jR9 zH8Z`M!Cx+TNlHsMg3P@e74?0h;e8CLe~5SweiKE}g#g19(d!4Yj_X5y*E`GRtf?&r zJEL*P z=^TOzdI)xN-X%bLk+SV0Wg`f?!JPNRn;a9l5uJaTurwfj-2^qvb?9QEDJNomudf+P zF)K2K?)jL(*((~?8wMq{2<=SH3W4%s06RwA%~e~`3I_9WtHKmOF9bd$RyxF)3<~61 zm0=)0XQxtUYY8=kiX4gIUec#Pv}TaR^aaSb{h$dw6S(@*AVChGDIpwEU;Mld|KmBg z_REV_FaCA3JlF|mnph!tPoeD2LXkmS$)L!b_~QXW7#;3`17@#rVgT^sWS9Yjr_qYA zeG?x`ra#|E*BtZ{L?%vf0YrmO$XE&Ca}Ir%giS6qdu2u1!c);C)hoVp(w`jQLiR%J z%;ZI2n?-r|V0&GUG#6%}F6KVOUCsuL$3pj}wr^}c8jNaNvhQ10nIv@s2S-i}hmM*Z zBE~wOz}ka~{Ks|sdWUEeJ7$0r*ApBWs2Y&ppUAUWLeUTXn9imU==t5=`(y zEL0r?mqV_ud4%4A%IXLt0NL;(P6TvsY!n^2Z8Wg9=Jmsv?^aZqEak@o?ga~)?XEdS zl&dNPEX%Rnwk>l)$lJ1aCYWjvUn4Uif0O1Z9W_&Gh*+_Q6>()$LT<)t@BB3XZCEhlBY_?!9yZP<)6%xOtqS4B`9YQY61d;;cjZVtiZlsAab}xo~ zK@`hY@R5q5Xn>rX!xT746ws6*Vo7`k##N7@nkGiWXE4ub6VZAQB7{L-kVcy@x&1QQ zz!fF*TfjBPImU_NaB^Wq;fEpiVrs+20bSLn`lQ{XdixxG$`m==ccx1Do zVRllCBiT5Y6xsF^iW^5jJ&Nr4m!@PwR`LSoKxcq`J_bHXj$@(NwtR#`U854jK;4iq z-ph{O@*=8gAaA(6u}*J#Tc(>J-9uTvHZo;k4rqE$+i|B^w57Q~u4Fu~AxTMm@gqz9 zJwH7wKdE=p_7(M4I0$n%9xD6hCP)(K14SY;qyR_VJwdyNBzY>SaQLdOPz(*z8rVXdQKBc|8@k@*LqY*ZPj%}_zuiW`KbTfBe6_k=!(JyuV>3}o{ zQVa{od*dk2evx!m>%akd06G`GObuFNI#zTI--mkFcWnCh#pi;3V+9UHoEs?=mDrh1 z&D@q>21_O;S%tDDrUsK#gtDgbr!+OY)_tm$FYBnN)FR{ew6M|c?3m@#@ryp$VLQoTzI6_(!Q2xMlCGpBb|bnW_Vf;HcJ>;z$DR<;DvUa`!u z-Xzq^m1eNy56v#qQ+xdn6?Ly)%mo{_cytC1AZt@uCxbc;<&{V;{sNjm8;JuQij#gEGE|R*kyH}OlV3uHSFb*?gLJloW*Y-F zM(mbxwdH~e_H$Axu}S6b zGNVmC!V3O&{6p7p{p1kN6xs7zjAu88Wr}l0I=2DfNC?_QFz%vlYX0}hDZsqVn>tT+NZAxM3)ew8Z z#ZMlZ(KY9E7rMKPVuNTUTD>bDT%qk*Gjk=RKKsBA>_&Mj-=aK02o0Ee2vJ2S_7rkl z!9l|u2)6#gsV-^Wpzm-BkNZKx2?TqJ*Pq`{lLQzTc03)HwJ!hRCdE)Z7(3}ECA5%1 zou~3L1A}<1*}tDyYf>k!&_c{IPcAC|2fr-3(Q1uq#e~x814r6VEfU$tE8a1D@lxH< zB88HXlHRUK)(7!KCq!5B=k!|<7Dr19ZjkM6460m*l}_%kOU+m&Ob=UKdm@Pf zjnKR(OOFFgBTe?mn|X&i7_-rg)J_GRLWpbPF5qeHuC$u8KLVhj6&-fmj#q=qZ>^s2a_qUKYmiFr+JGc<&k20Xt{=xaLi@_wum#Ag>Pi!P z(q*=~VSrJ@9Gf6vL5a#0va+Z6WpMs!X*JU$$hRhEOvlcXMpz^}H@Bd$Ih}NE%@*76 z2|^lUPni$z*Sk<@v)20rMtyzkT1Q7JOj-VvjYGLgXXJ6rZ8eZsdIJ1z_aeG=)QU8j zErnYGd?U#-(=spuR|@E<87&mMDQ8|X0P<7L#<~FUKI} z#8%x8jn;>CK}xZ>oiHfULH`RKF8t0=@Kw0`-9x5g&}ibQQxi?P80LD;$nHooN+$@3 z$Zr4@s{_;u+Z5snY!X_v?Ce)Yf?i*3x~2+k|dRj5R{n@wN}cc9y=2pL${V zyXK43qL);I6S~pz9C1j2{&cnmT{QFZq^A}?P_e^o=?$HERj_6lI^$Tg%iBHMFqP=i z(>E^c?DU)&+f&5kIQ4h@a-byDI)vh$`Oj}6fBb46YX#lh6lq}tD|G}7{EVTN^-ph` zy7jFmXVYMs9TeCPK9-y&2!WBXRU@N%De6p!72`q4Zu(qZS6e#@ke?VL;nz{jox7>Y zx5oDV1z^~u?-jhJ2_S{x)q(2>p0*t66SHI43qW!;^WUnGZ!M`a^n+$j%YR^hB;Rh} zNb+YXwZXf_E2-J>&HTg~k%M?e{%r)ZLr1!FF1Eq993zj-Mh8qr*=*JDHp^ZN){<$` zh>Or7Jx@%3Jje+%=xW$}ZTU8+Dv2B$%*Nq?^Qc#kp{66nHp!x-H`w!XBu5H#x7G;kW1gY!%3a8jNWQ%#ph3h@xeI5W z;ai=e-o`wngI8z`@Bj1Gb{ARUg_>i`vbVn>RSIEv|NQRRc@7m3@iJ7M%CE=%ZH1df z0vZ9c;ebgR)**meI+>rG)J3dhdSk8;Gh(9Tf&wWYJu{;P?K8S4#%t%*0^~eX;8Jh8 zhF^CLZ@_V?1%U^4&K#+2+NwNosPHX9Pxo?NT(b*(-L?SVfjg)2!7MmD<>uW z1u)09Dlm)f-n}h(IOC2Oosb2lg2P9LWVbb@|F3$1s~*N5cW)S>LH}Fms4_8da(48| zPFHC=G(%1N%(rDr%(012ZU6q4p1(SJ-xcnU+W=A|A1}}+jzp?PUX-DM+aEQ3O8Z7$ zehJ<$s^ta!O4)toITmr8`c#=t&&TQ@Hwe@@zdNNq3gr@(5Wmq*EKWs!cc*&V+)su8 zHS+WEab)_^ns_)8BkFqQZWL1-LF?UP&785KKoLIkCwT8Se_F#ktXE(|VpFF%W}b^r z9hHAl-OM{9yAAdo_Ze1JmSgPBU>cqfU8VIHut+z`+O0$)y-`wf%$Npfup3^`@{oMV z0mqXAC~^jz4JqiwBqiVBw8fUQlV}t{9m6xOI6l;F2g9pVkfvG?k`Ya7wrEp_)fYJh zkQ|d%VEvazW`3UmTt_2#l7Ra?a;xA_dHWQ4K((mh&LmE zSdDqn zd3VPs`YpJI6D!J@zy{Yv&DofB+o1NKg*G}HtM_MfOiV#6WK;(=M+S1ThgAzi-e9~8 zri3Kg+y*3zDogUv;zdp|oR}qb_xJta9&CobVlVp9EJc5jYTT-6h&=>n4G3tFla9td ziN*MhL)<*D%$EomJJ@d@Y_`&MN<|Stqr}xA`D{FBr*NUAxXT zRy#aY9{;MJYuUyzqi~BhiP$VrPl&*eLB_}l>i%NJF{V3bo>$UZ@De0+g=52G9h>S4 zRUYpmzbn_kQk$?jNCc}n|B;6gqRi}8WIsP z;OMHbJ2C3qI~!Ad{WJLKSqOi04j#PSu88T>o8bXf!tGONcQ)uTStt2mnU6u_1xhTR zf3sZ6z?ylMIP9yCb7uRgXtYV*K4pp)r%O9iSFu>U*AU*my@|{$AZD)8iFwCkUCnax zgP#9mGctZr=`mz9Yu~GQ;0|cG&t%2KyrfcpmAb0zRVzD3-K=W`zAn$EExq@t@qwRP zeSJTu|JVJo8G#0KaH{)cd<`}WipL!OplhS`v_;M?=S7rpbYSf+GmgB=f{Tm_Xo1Xw z8Pdz{HY4T+G55_eFsg;LsngLj7s>OnZ@$OYdF*N9fue62YseG-hTr+y<2l|HbH4dS zS4*nvlILL{5N4{1e&1;Gn)M_`Y{Y~wIj8LzOw7*VkSG{=+`Z65pm<2_p;*nWR>bm* z16>bn>18ecZ&j!wFQC1=3dOZaC{6Ofj6^ipWgx|Et z`a*Df9@<+dz{W_s5drN;nh%sii(s&D*#Rf^2!gR?)&3%RKrBS^hQlNqVIeUzF)}}Ntf7Z{j)P~! z2_!c%_Q-%dtl;Lzl2^0}INYP7x$YXFEMjBEHPn(F`jPUSq63iL?^OSi`gEIaq&&yi z9%joEPkTcP=`!aYDBAIlD`QMl_Y{2#pc!`6yVj)+frnbLY3ekf7yc*jBWRvM7*ajD zv^zE?1?RTm@1Z|a;$8pM0@&#OBzC_O8jHUmQN1fF1k*)q=3CK<^bCk5>A$SFe`)ra zmo%ruz~28!+a2ohKoMCJO%(Dl=0{#_nmq6eTNGGe6(YSuAd0H4MkB{&i<|93M}}k) zFFbS(Sbr%HaQ zTvEbmw5qK))LAzoM`-GFM9A;?CYMokdN24r2>@%o7LcrAQ#rR$DjK7SN}g6#^dDmD z;J}!XVPz0)be&c$I?q1mSmPX&QHXZkX4?s)7D?L4$yo^dgGs|7X?`P9m>ibAP_U77 z;Q~ZDeRi%5pSDw4LINkt##Eoi6s^PZzC!}|lV>)YOO8}KL#CwyQa$t>?5By|7G8Ge zj$h+3jJ$vW&H`c`eVUMmPzhZcSoSqL?R>LF*VJGyOycjwr@ds!29!P(Jv+GuT8dtx z9G;=AemCtVI)1R@{HGU*LzN9V+mhziyGM=QbZi_M*17a{B}c$Aek(J|+`aJqu#E8R zUEYD8csQ~!jJCZTk1oHYK6C~^2>rQk#053mxdc8b&TJesxZ|g}Pbr&L`yX>-emuKizG$I&@gNg1NaVlS}M|AZ6r|SXA>7-WN`v6lqU(+PK*Z~f&Mx| zvbhxyK^+Dkr=Wdy6oNiW42S>q$Vv=+#Ae!8pAbR_Z9_O^ZAZC330mtNAenP$Pq!gw z1q?kW<|QN(X+nn+(KDhqTNeD>Xx?{p0o(_yuO zzMN!2+Taz)xv>9Fib%tkDd{+i>7Tu_NXmakkf`(y@a{X1Oz%*-zXiq`0HqYz*!*he z1xDAlR4CyL*ZG6H+m&KLyjH^r#&Aj~aRjD#(*dF*P&j`=H`0ADc@Z!(cm-L`eOR*< zjUfdyD70DUIRpKDG8FH5hJ+Rv6nir?%&UdyI+vwl?^^n61YS@fckdn@P$cQsx;J(O z>LV|0o!2;{b!3&+8JPY#+wveg;#f+$;KLLyP2zU zXkgTiW8xR?G&;H}PnhUZmvA^&4&-$>-C@B-qp&p7WkzsOg_oIb8GpBfFt(I!bm?>0 z(mRXRJRvk1UD~2Iv;kS!aC;CkGEyvW8LjFct4sYgRM~gTWO`e*ocJUZ3*oS_ZPAWW zYBGWFi5&VUh6?D^nKR))dBQ-?zK4g;)J)s|A2#Pj6*=i#Be=QGZeQcEFA%-OwM!HL3T)33}zN~8Hlp;+JBZ*JjY>lMT0mxM; zC0qzwA)&vZHG7+M5!#TL--{cS&fK!!Fp`3je#=%EjFHOZK>+)kH-EBwE@1H%{oc0Nrpbyd48>6qHAA!yIMV&$ zKrY}+W)(xfZqL?#{+tF^H+MKFPV@a>(~<3p-vm~v4FYpJkdkD_psTpg7Q+{x`V)aC z+XQmb*rywwYSac_njkvWBdb}z1ZfX`|NY`hgn!9bZzwujD%CB5^ z8TiTGt}zqS>f|@yCDGGyQCa>0vO#_WfTn_rKAf8H+|F_Ce&uCM38*t5+;I7KJ{%hx z!o+ZvD!_c0Q}ZQGP2dZ~(AJ5rQHhk9=ha%Y#m66J40TAaUc;Rt{iH3sLuoP%rM3l$ zBH-*a$J{!cYIVYNlYwLB$Zotwx*KS^ zR*8E;&Rux@$iovE!=E#Iymbq0EXF*1eDjZO79j78%UHLyu_Bx&dYR%__Sdl%?0VnH zqR008xQ;DL?RoUtNZkSjEEUVLg{ z@nCQ0j-~`N!1u*li1`&UZNPzNr16dX#qBV%A%6q5Y0pqOfEdyyR)up069=MK55>R< zj(%_=CXRtqfKu;C-M~=J!r{DzpY>tPL-X%yWek)Bqg9^0D=+z8qU9}{VXEP*k)B9D zT%_=(dN+(9f&CKOF>;DAcpuWs(W$&yogv4jmoy`j!&k6K(cDxHUjq%YoM0odYAB|> z1zrH06B(^^nY3tUX2$tzn_KJ7`&^!&z~z0x?#*vRr+ z=>EOJ>leH}{r!!$?2?eYQ{5AbiX0!DvlZQ*_aZ8&Qt5rzR!6aDp4V?5R8PK8u@e#T zm-(WpuI{L-v^q3@iMqP_*4odXh4Tvv9@(N?-*2~mjR-!gk93Hga}o2b&41> zGjnf$e{lXPd{g=Qxw1XFlMkHU;V0ID_|5oZ_UDnNbc;oxi-i&*c2hP%s8Whr%UmuZ zhE6?^Zg4^_qV8U)g~h9)Md5vlJ9aSs*y^_ zf!=`uH8Zm{I1#(jIr+|+r8Jt33XMkBmW`@T)!T42FmUNGInmYuXSE2y*{~80i?u4h z-5>6MRh{~#vRXP^t72qw#nNjXV{RSx3MX=!uN`OoHL)x7dbC+cP_!8(gneT2F3*9D zXGsHNCsN)AqZ$}$t+lIz;$FU7z3&mX?h_uD0wLQRf#b)I+ZVLr;rHrf=Lqu56S84= zJZu~=#}^cSa~VF2BR-R#q#NiN8T})D4fiAQxWlUzzuulz@lHvR%FM|rv(1T1Ok@)h z62dLJ(m1dpS|YTHyhKJ5e*d7UX&^*?7;A%M{o!=<8o&ul`lTP*!S$Z0trLkg{5DZE ztL&k&rnEzbVV77)4D_&lVhb2>9*lUhP>3_#cP3Ar($qPuKpVbcCd_-I19mK6an_%D zp5(ZfTPGLNx(*m^gxzWE?%5EqN0hq+)*JRyqn3#5T|lp2)a!`ETH5AEEvo2pU}tCd zGgs;0UA#bsLRs*+b6YL!+KwDMcHl^czaQ0?Q>92XhBH4uzowzV2U5GUCKnVVJ87&w zOmYz%K*7_RtnbU)nbvwfsq=?H(Ozc*3`iB}$XmRCsZ*f_Ba&+(r69OeAySuo7F>#N zFDk8eD1rurFF@nIwit%N;p6~@%eqobpr&+eRFHC>KBeh4|dhqxqJG?Y*d4vvyR z7x9G*k-ASVoVr0PG*H2u*dt<#M0~L2R%gCI<-(veJySxBH`K=96#QCJwL2yx@XTq=%mdv znu2XL;trOs6A_7R+QfUq|CIpNb%#rVIfmwZ9u`7}lj5uNs8ZLZ49KBNPRJCWk}Wxz zUQDILzIY+X;>`%HQD^S*IQrr|6R8d^ZZ59%=C6bN{CW@l@=*CW=z`Db+U}kCX|UMv z(}?S&!BxA)DyxP{Ni*0i6YWRnNFr^|cgQjGO4l6W+OV4G^lGq^U`_ zQ&YW8SCo6VrlzLR{nWg?RV61lcXi8{d3q`nKSWz)E-sx+djTMBC$(Wu=>=rwkm(SzyDg=@bjoHo3%^otxj^WBR*BY$u=38Q>V#YZlb6Z5(d7mEH)B*^|04`*S zMqIbQAcDYJBhn?%4ZY`ARoA{gB};g&$T%nwmjkUJf51_k_W_r!kzZJwG1G8QLdJzQa&Aa!wwAjWE-n(g zN;=D1VOZpGnzfzXfoD%65;mRa4_-;ZLRLWVrrOx7Nc^*2pFvPiaDn~sh*-Mn6`A7m z;BjC4+N++Sv0-^BX{}U(Xc`gNAn*KoNKUTePMh>U=Hd!4JbajkpP&B+{1Zy8vN~g~ ztu94D%jToH*167)8u(^;_c<#o)&2X~&}CXH_CU*omzQ^6s|N=8$(zML(yt@r>nx8c zF0p5PS??cy`F7=5DurM7gSNW*=oa7Ketv#u6jK}7a+*1UDwzvfqcXoEx}4AZ?4*bl z#l`AVK7*sgPs~StYy=ekn8pD-5Y)?^y-OJ4=&yM!F+g+=6|)M46a9y7MMsm~*PBA` zN*5kVY+${+Z+*u>%zY=G01bLuTNLI#?YBaUtvti7M~BRzdpo(ur@Wt4@TQjf)}so7 z74W9>0mZ_boDBW#$%UYDZ-$5SCq!tdQ^>Iw=3uNo=Gd)ymYA3h2DAk@f*`w&dPquY z>N05Cbrr8!TUnK&Xyd%`>bdWv)wy%4c8Q6EoAZ6f{?aG5I;gB`xOmW|tk3Cs7n{)1 zMJ7_Ax!+w1@LofneTOo&%qpuC0Rz$El&t^J@tYd!HuJLKGdqj-Rn5JaEbF$+N9A8L zwBf5Ji)VpbIz&`N&?*GG0wj96V?Im1KF#mjZykGUzsgAsGR@)Hguv;$8Xkw3e#}e{JRH_PrPlnGx zIn>Xuyx6s~_+5ARnFl*AEKN6HmklFL;g%gmK!&*y82h_|Pe)MTxJn4P3A zfwxolK}U=Sz{z?QSxguI7p8Vbd!-NiRd)>w^9Nj?20W>j+IVBP^4j9FNH#FLK1aPe zNzQ|qANIt#VOI~sw0F92p{!@5q-VtcXyBnnPn9)fk8W;`$i#kqNh6L+VvQvwJaf7< zzvRScc1K*P#V?PSnXH!*jxrsWI##Rg!XF@(EOMg1_DseW_Py$qMLuQbc?*1(UcY%m{+&{GI-+II;t}|KJOmak`4%QxB2mp)nuoDJbvZvQ zw+TyGlFqaSKN0O1*--bfu)O*)w(F~99r2z%>8$=1W3mD57R3*+xf`7zyOp1qh78|Z zK8CkWMR9TK5?HzIw=BP(z`XXb!mUVF64jQNPnIto)86mPNCJ^dfwJW9#t$ESv$N$G z_C6cG#mAJClG45TnL5ShH_jd^;W?mmnPg(@buCae9g@G{*L}bK$1vPihtWgT0Sm=j z_Y0JzR4q5s5-Mh!j&cVUR@b-+O(XZ6!&$(fg#GMo6*ZmAY4NePZM5{_M zl!)mLT^cPoDlF;29`z993LOxkFCpgm@B;e`#dIlo*Py%SCOxC9&m_Nq0CETh2CFQ7 zKxdZbFBh`${@AgU>-JTaMT?MNWcW_tePfz)1!%nTls$eyi+yOxek|*bQ{kdJ5Bo`P z+q?AC(vY*P!&~%paTos1+d4A^LEp-*%Z&p*WgVQ2$E8*x0xGRuhQ|Y4aeT%pI=3>t zP+H8z8so&1&h_%REykCJBPq2EzB|79^DiNCcMt#NjCzWC*~CRyh1H|VJIY!Y1B z1>UO^a3l^EU6o{z&U8R|Y&ox_kto?&__?1w6_47FY=eDu(4yj3D%s_44s$nRE?Hp; zn3uVi{u}G@HS*&gK1LCdfA;gbmI*l zi>OGfHMfMGs6K;|`}k%Q0$>cj~KP}ThCMq>%8^ags-iIk%9bm(!hxi`I+W8{(U^uc-OWS8 z7t5FQ`WSc0xaXNHEi_$*2f}&aIv%lTc|LZ$J{~m#V=rD}vZ!0Ux`hD1bx?+H`B~$A zk*7D-&D5V*a7$(6Q0KS(rJm*y4OV+#^`Wl0UtPUiMwpAsbMtc6n5?XASlKNtH&4hc z7Itr7T^fv}l-yD4*8COV3--9WZim&3Il4bt&|iK?KEUtHt(PxVUZ9)hW44U|Cid`H zs+SO4Fm{2GtJhf*@6p&Wxr9F0>5T_wli__!}Qkr|dx5l+>YY zZv1$FE3DMLRPKN7_97l1PCZML54Unp=z8%yfDse;byZbJ?*=S)>eBfDMpe2R7;U|~ zxZDOe{`Ou`ORpGjYHnamy*=I<{fK~|;MKZ5^<&2x)2hCI{~kYsrGW=20g#BGvd3qf zD|BNG?~R4X=(vS2{sE$O#UByjAcJ5+b<3cqr*{bou*{Nlv_q(Z7%$h{rM~qY!ul|n zlTMi8`W#9q2Yz)EmfDww#MLRAF)L8coq&B6ieZBS7fBdmBcqWeDM*O6!dWf$pWEc+ zyC9p-weMiM6jbKn-!OS^vmrSaY<^r8c<**{b}s3#_p3q#N7d)#l!3xY%GcAFH6$;tkeaKFhGO_BEAW`cFxpXM%)s?>AovfOcaN zAeJDR(H7&;77O89uzdAaK6bJ_{aEbpx8Zhm53=uV+qT6#dbChYP3_j3Q@FCdtbb4- z#HOSy6${ZqUO}hyoX<~fmU^JBZ@{^Cu&S7pC3`2y%x8w_)%@IYsCGysPx0F5TET8Bk{R2AHf5Gwd(7Ys;}JQ-#G#8 zm!6W{o!W?Wq6~H437K8UD|l-9$J{V+dz}>h1A{T5y}|Pd1x09VV&ZR3I52iyKIX85 zLqyeARUEuf`v;koV&qahAm`X1A>oZ_I&}6^%8^a$6^$_1`>$H%s@5piS>M2(XBll% zYJEfXsq&Tc(%$^`BzMBz)qsyLz2Bz9B>v3W0^M+eU9d2qVTbIW|t4D z%B0~`r`UC3D7>Zk*w3&tJeI;%b~62bZnSC)pWNaNoBt+xN~$8Ud9Q49#23z99fMd; zWOdLw)U5i62vwE+0_w{bFGvHYNg7aqmi(G(EDA(}JnWB1%|l;qWo=!K2%QFs8k*~6 z?Nc9e?AtvjVsNrH`FB2KftlIaXE;Ux41BcC&Xh6J(cyr?=#i}o7d`Xt$0y(I6>2_w zxcA{n8=Zc6uc*lPkc6Ge&fD$Ul*Zq2a=l~p?+QfbZ*ckm-?cjmyl+qt^o*<@l-Aae zx+yLjrrr7Fi)xl~#};z|gk!EpbLfB{HHDSMyYri2)0u{SEo}gW^fufXSM=X{ZhhOK zvrXK#z(~-r$t}2ri|d_6>B1)+S1v8R#*C?fyY(-IP{zV2$;)OfC-CKb9!YE|1(P#0 z9HT0R2wq<=s;hlcE+XWLSLqbQrx$H^Q?3D|`V2|l`SfSy|7rosFfyNkxj^`=1gCBT z9Ck%www4q8a)|>Ac+j2w{rx{)uM7GNHPNZNe6gz@=H#qIMP=DOav)OC$6&KB{G1^G zliB$Cn4zJ6e!e2hMSnl;c;5+G$>!!}dV9O{_c*-`wNo!}N@d7Yk>Lt#`{M%p9~IX7 zAH6&}ysPYJ^S=>&FCx0%8IJh?MIGg1#~vMKom;}`A8m;c?BBXRF6^DbFG18_{#^d* zHFWyz<$p-YYGJW%YHEssVbfh!90jP&Hrw#wgKCW4UXKOp6hqYSL^(!^Vg;{1O2n+) zqi07umQ5CUvrEtqx0XVopo^T@Am3@DoNbF=vu#0u=T-H(TQUxsofG5T-QDreS`*A) zqI?9Z=g29;_0BRzZ*gmD>#FG_pG_W!le8kU7IDl=tnYQ>$3{MF;-Y_B=V8k(uYWB@ z8JSA#s`-pXB;4fkE{6H^1iy~})Qg4EsJ!|>Z8q7O_U$izWxvPJa1~mmkhIJt5=Q%)!E($jr@koC(;8K1V!&9uT%_n|Zyp#njM@YV^wv8Uh(Ub^>jP z?FIG;gEoIejHSfg+#bSnbHFdZ%EeXYfP)7}o(B73t7rIOqv4nC0%nZ|s_twQ(1`pCP(9D! zIImaf(C;2JX&e~CJHexqj~_T4DFSYz2*A>xV-k=BAFz5=-0^JTr@`@?CA)<4ejc)N zF4jJ}0Cn;~Jw4$PE*=86-FQWyjPrTHS1y$Tr`?!hmTSM((hRsop{cYlBL|B&A1j4F zpi|DfqF3+QX+fs=;c7w}j}B=$Wg@_^Epiqu&1*Ph=uqwt`Ldc{LRH3^;bf|5=6SSZEFMee+;mA9(*0j>J}GBCp}zH!-t7@+m8F2ry}SNE{qW|)_lM9yhD3!yYFsm3 z|EtCQAipzlCuHt_I2MsGq~EK?xp*c!!86-`KcEl*w)ESW1{c@U8YAW_`cUoxI-#e`ko}@$C0a+VVg$kt$tPjmd00xM6vj%RgrlR|ChnvuP}2WAmlp zzbI$X91Zk|tL)Nmb`g=O`iK~jq)-Wj;#dofNO@Rdl(RmI$Rx3Bc-O8?6*(XV(Tgnhk! z0q;Fv>PP`eiP2koQ|v_}uwlwZDvhRsI3hcqE+z#l3}Ms@N{T3bCCx?N-&S=ibwOn@ z&cUX^zbrUEfX8ueSt!hBGwKw5|HxwGfC)lnsHEsrN}n_Ljw_n1%&bDC$YY@D=N8&d z%9JpcXQxuY!H?XZrxMacdj)f2!u<9y>$pPq}cw2sY z(yfhe|4oEm3w9U4V+NW0dfV+>^pAjOxDvld?(|xX0;*G`bb)2r!il$Mwj$xLUWo)a z{m&m70e-rM9~KlCzi=%y9quO4W4-SEB@BpusE$!a;X(2=Y&&)=-fJz5F|EB@=N7@y z`9&ZS&I*nKA-uP*ZD+_35TOR=h(2a)ZyWvE}9O75W{VybmE= z{p5w)NO7`79?C4PIFm7);p^AE0D+kI&pBJ$3Y@gU6;!zvTvtX@ZK)Tu)4O34SpQBu zJOoWhzL4x#K-cs%C8dJYqL4nFzr;&lKKwtZ5fQEywC-QTQ7(q&52%8%^bNomLaung zzEQ#Trzqe7hRiyd_LpK{TA$k$&#aI5&#p(|GhlPd8mWSTezj^yy^4*!O67D=) zI$M>Ml{+AZVeUi*DTB02-W>jqcl{4A{7gm%4q_|+4;X%CeNJ=0 zkmry)Aq9}SI*{VTxP6K@(hwjZM1@(=Maq;o$oga9(JimdDJvkc- zETYx+8q)t`$5xt1t(>Qo08<2y*C7K}sGf&~tH9XJ?{jgmz=>Ul%tjq`hNbEo?VR$; ztw%rdTxkxo_2`b+11E1P_XA~jUi1l<0}W>KE+Kv;9YBCOw7;wKeEF9!@frgfw?%dhQ-)#?;+KOLTyj)1kbDfSAVqGH%uUrEt2Qt(mECI zz!G-F157eXN3GNl%bUBiADVV{k)@~ZC^%nYsNd0EY|Y+yFxqWoj#slxz5B^^=b_3% zjkwFEsbGNS*PQI5_nqN3tw@fBCd3CLBsuTr+h!TX97+&XL{X7GGU>V9}6x> z1DIaz*1HzCi0@@*5z%Xt+=(MunVBbGI9$%;n6Q>Umx=#?3_BX$O zBS4a6zY3o@91L4IAC{?>JmN^UWSs>dkio1>BS}1vl;lda9C-1_w(DC1vL?0uOR*gv zB6Y>N3vzq~j@+?~^rI^Nqfh?|AFj?_0ti~zb?2)}LQJYK#fH7=8a{!Z<&Sxe;z;#y zKFJMKSi2G%_O()CS9M^Ce0=G-1EX{e6{7`O5_56l&)SeTBv9WO7#Jvnae2tgvh}*1 z!hge>2X-sH4a-S-d1j;e$z4DTod)F&ls?O_?339w*I=2co&ZAr?k0m%4pWQFd)~XgwvnR$l&C>ALkI`LAtr zp7_ju`t%7^AIs;?3nvpB!sYCL!;NAWI=+yIgtwvA_yM_q1(cX5$jG}LhV8BZq7U|F zo&B(WzzO5b=#}sTlxTr!+aSwoMOimR9572PFt&}a3C0G0V_XDIH(x_)mc)N5m#p%m z#-2*d5B(%Acc`Jzx?#e=ImnON86cJv%KvGguWvU3s(W(zfIwKOYZ!>@+wFViCc$I* z`I5&&M7-IS1bk#t;PHh{89O>Uwe--xyC&3 zi~l?^?SS6*%pdJ=<|@Cu>rBS>g#PHXmk9~a(N)7~Bgb3P$R2e8qV;5<1Wh_On} zWB})mwd{cG@Z$^Dtu)jHCt;C6b{z*aM2=)!J+qz^7k3GZJWtGO?%vIaOqH)2HCKp{ zv-IJjqlk@e?(QMuJe&GYvkk7dMflq<{=zJ1d@2*cvwi4*dt^t-fwOFbtJqoeb;Zd& z50Cu2{l?~5zF^#at?c&jScM~_Mq&dtChg(dNY<%P2S6Qx$Cl9^V8iwbMB|YCgoWv} zEMABi52OR5Zl1OIrl|*vdXjq8DPi-dQt%ZoqE@iB2G_iX0lQNip;&$&Gd8XoN~Ami zSn&JvqMgOSxlsy`vKc3{E+MUfB_ay_taekt&cfhaIJHUDG?ydbBW{7+5>XS`TkvD}%c2Bx6@3-4*dr*+ zzcF(&x!dL#vwzzjsXIJOKpgSVs#mntAVo2VH(p_PW58#m$F@k5g9(gzCeZ&ui*v63 z@eG}x&+7WXMN5}pa^Zu%xom##1+ctoXrUOSS|~Bb-DJZyZ~Ps~&m<@%{8T^DaQk(? zy&|POm&-aXwb~vqKJa45rC<(DGuG2%KyBn8yt_ZY!Rl)H>))Cw z(8l3D<&xqe8#x-!hU6w^WE@VqDFwZW;WYK_nT%ZQ21%cA3-@$p)z_C=dz^|S9=H?wwrQ95ZnYifn!;>DX$}S~% z3(9iH@U+!kV`F9|g-#yj3Zb>oo{=fbs-+{0y0HlDD`6=8mRL2Xd!7sXJa6w zaKhW)ifA3{bt@66DDeIz9K6!~d4I2r_IM?z?RON(|+(CXIJ|&iF>bl93(FP zmrhCWPBb5Yki^79L*?)@H~)8*^)K0725IicjI+z&*x(ZrvzBPS&|q=u?$+R|oZb8X zFZx8BV=w#YU)9gtFkPuRu;oyLa%dG`O0n;upEPeLdqHo0WoV^3MH~rE&ik zdj=2;51e%Da_vp~<)Q@UmN{1d>;D;zJf_RVX^bW1V{L71@sFx|s(yuIYFTWM8NS!I z#k?>+{?v6ZHfWj5ggFs@2njjIBkVJ}kY_@e1<8Xb#6iL0fhzR>FtSMLofMDPdM?df z7cPL<{Ym%_A)JtPqq3Zjk-)ew|E5Huxo|f;>km76u)*JfZ_LZs;$2y|MTk(MSi;D`bFa(;68tQc_3Kq_U^ z(%Sv(EUcGzp$weY6QLN}B@9w~_wJIkwY$uZKdIZYd@qG500OL=7-}1EK1MCGvROnb~Sa4_0I6z?G@;v zp-_^U-oA4_9=+sTXl@cvJn8b`qan58GIw#l(qMFiTjdl32kl2X$%hZ(LEs`7a`Rn~ zkbt69O@;RrE$|FmrlNAx|E|4OY|(t}2sgm+<)`O^3liKVcETcLP9UnN-s93b`ueE5 zmSduHJ;=3!kd?idpe3F==WLUOmdh42r*ESarW+2FT7%3NwEqDzAx26d=x4iNQjenrzz}!i>-*QDX{bDZ zWbgD=2XTSGN}R6=M|UxA5NJ4N+?86SwLQ+^z{aN)xdLl~`c=L1Z%1|le9AN=;2pBL zBTMJ@M)8o_f}l_D5p{qgfQK?94KKjX3hpM2e*5^X}1OIhzbe-_CS5oF%U$unh((-ooH{i zMyk!Q+l)l2J)|iF$nzynWR?@AFSmB^o51>F{m~m=sGf1CI6&R8g;*1txzUkt!bH;h zP~nkqwka>XH8g!Ff0X#oM^HhwPaYTDV-YUdG(}I*?5ABvZ7J-N>UVB+pkqjjU%saI zVBfn_r}oep@(Q8MKF91bYSHRz_q5M-9&7lCc4IGkuZdTATP!PdxV)9aPaHK6gsmQOWqeO?kqG)s|r2JYqjye z6M@uEqL&gp^IG4*5jzexX}E*d{D{p z@H_pdsL&30h%6K3Ot=r%6)WN9S8}8GMwVz{Th``;ov_3PXLlDRSyJl7zxj=BW`Ce; zlu4QbOY5qwt!M^%kB8rt&cC}bE>qRA{wZYPC!YomL)Wc3Tbe!+RDIOyZ-p!u$L4F5c zyv6W*DZSjTa7&qGFRvXj!`vS^WBk$w`3JP$wPi}s)5e?V*b z9Y%uepmDeTP{!~k#Et!?uJNLRB0D%1x3BAOvkz%<*O{s6fNGLZOM7A0OSX-Va$I8e zuQMy$+Ei!~vt0T4g`ER+?{B>7A#0#UTPhSuGe==K{fUpHBrcZQ}Py|RTy6^@$vctsKUxB5{gC)DXsW+Y6@^A|kfU!piwBTg<6g}HK z4e0D0IvF{XwE*6cGnZ$!uHNNLY+`OhWhxHvCmZ!s7788<`tqRcayIN0SUE!?8Ck%w zFeH!aIPs7ON?461`1?-ZFTIBWnD;W0LjOQleK+iSTeAjWIC9 z?EerA+}%UKZgJXNusueyv3q3qriYqVjn|fCT$|~5$QLb-yn{0*Yt4MFf{B~O{x%7h zUiXgw5xC}et^?;z8RyH||8{We`P^Hi#|{mdQv}2UZ3xe~6=?E1!kEI*E14U6=iE)S z#z8UOWQZM3dKF5SF6F#yL0H17JWTI2UV_*e6}#7?5R}P*%2*qyv#iIm^^V96pbW!2 z;EUR9n_9g5z0zYW!bkN{H?HjGTb8k3e(AN&M!3pg5G8c*@B@~6)!jLyGX>r2 zjcDY<^!gx`zpLwAOw@jXZWyIrWI#|S`LiF&{zy@|`D$O_+GWXPH7TignT)&X6LAYm zWh-d>JSck2MLKuPAC_peU0A%0x(^otUEIcctrHh7fPTc`AxRcyy94R@caOYpyZH{( zbNs^Z(fscoVQB;e(-Ls=_?0WW{!5KPnnpy~UOdv`={XkHD>^!>)yCg%>#xypz5>9` z)jIi9`3WBS9Q2)x;P%ToJqByYWw`%)diT5L|LL4ZhDKT;<9i?O*joBRZgn&udoj0eaS;Zrf|n`r+n6q&=0eb*a`nb&BT7?)Tu2^69tTAGr6sOcLjTb3B%yleIY8 zP6slJ2y9-v>(AA1`^Ew>C-C=QJ9}&Z6%ycnZ0f9vuO99%2*l$B3Ym962Hth(kRfC_ zbtcCVd<~}|=)frF&he$CSzJ|>F>}y8_6ri_`zKy_e%o4h>d~p)1l37bJ%o8iGy#^+ zPg2|^jk8xLV0I2T9?t_yAMV8u0E{JU>N>FP;i*@q-SRs`Y<2)OS5I{R&?N(>Jy0z$ zW<+j>UgAO4=BqdA2GWV?kF5BPOXJfYM(pjEFbjt=X z;kE-O+i{F9hGi{ha~H+P3*bepX zPwl%$vQ5zb@e8>pchkK*pfS1CMI|Nn_(nsJ<~uW$q9s!OJI&X9pHEwnxNiL!q&JH1 zv$nRT+?D+8Zz@t1zX7)(=pB1_eFB8BK(gHIAsWo3dssQ7=lvUCl1N<9fx3Bk?b8oL zivSKz(p_4Mg#q&<3?m$4t$XyP`R?izFiW@`d6r+XDal;WFY4XbQVG9j(Gh-1(Ptzi ziZ{>6FJv>Agt=`W7`OO`2O%4GT{a89^X`l1%J*nQ5@_anUvKXjklZG@H?7KY3~{;q zW(w0vFOI)7@-8+`uB@(ZMNdSL=@2XHUjSr6<2Ba+OukRL2>C91FTU0(jS81_g;|CD z-MX{8Ha+}QU~Aiw)pN}Z!<~euigN(i^#=&KlSxGYNk}YD;5g)#%bHkEv>B$sm^*_dj3NX}D?vW>Q+_@g4c;_;PuFcK6+@o#q07uGq65Wti1=j| z*-z&i0AF!s+CVZWmr{V4Q!>V>qT+ib&g)EI{?S@+XXpPZHOVcNS=?Wz5@0B?YXL&S zByH{t|IEw`W%+fi5Cq~JpTp)H@x zXupE7w(&BLOlAXYQ5{{~cj%N5o;=xguvGe|(O_G)4JxDQ0|AP`=pVug_Z{>$2@4ZO zu3w-9lt-K}iKp0Ebin_Z$!RsZouN8=@K5n41MoU@h{mIQv&KE3Hvv)*YkaW*(`d9uCK11Dlfq~_X-BSxFJG@Yo?4rn-yEEil8TLEWLtLyr;Z$L!Cwxx7&02;^kZEu4O!`#sv@ zw)A;*3RZ7fc_=tFU?&Ko>sL~5V>CIsL)UrV{io7wn;kfRUv8fU$cJMh`Joo74u@FO zj-*C1!e(`q>qT)rmuZNLvo?uY^30VzCi3aqa z&_wwFw}=NAhxFf)p>xLP!41FWzHO1|A@nhGqN_WcHh-20mtEJfxV|@1?0z2AyS<;@ zdmC^j(CZa!Tkqa^I96X*=kf;Bl2f~%Mu})gy?cA@Zo&f0wU>#nR1+}IICR-qO}Xbk ztj;qWNy*S&ywPY{O=)z~jRp^j$$EGrUgAK#rVq#oJ>a(sJ0hLnUa_%~>14-@P34UI zwbKqHeBiuBLYvoKou)(8jRS!Eimb$c$p(=QzX!%Y9&d$SVzT(fi21_b=n^pf&2zVY z-tgVO3XW6v9!7I{@_&p3(@S^f#gM=<>A8 zV0&U5ki3XSIau`g;jHZJgegDX0IUIjapT#oHM~cTfQ1-cZj&K4!6{)S)ju}^l%ltuyj#nNM$o2J5g^x#f9$(*WC~B~0pwq4akLP z$|OVZaeiFx+c&ZC65sGS4w8PNZ8!jG8#U5P18WG7;L*Uy7Q|R0CfrLP2||lSGsZkWmeR{tx2=D{%y*KDKAElJB~t+txN;7i0op$4OW779QALL z;{-!0_4Zi@e3R|Q>?HDDI6e@tQXLbC;2hwOpNe^aUU7Te4Y^;4~#N$ zAufF9ETj1f6vW`|(losHip7Y7|Lkxm>G7&Vk1rX6FlgPz!C7v)Rb+P0V@4r|ZK}7g zytnN&nK2`jHcXO1=sy=2B_l)jeJ+^OZhtEEJPaZ@_U%q;EO8OO>>-ve@LmokHQXUZp-=O)R$VI~c}&l|gD!=&RXex;#>l{;Tii3rkx0E0{Abod zJ2J;zLG|H6vZ`C>8EzYCys_Dz%cnC>$a^dl%x|(L2+NAVB;q@Dj_ z^S$#s1MD0we)wzoZ)??3Ru#yJKDd1JWt+OxMz+ltJ`DYJ@FtrZ5mL1pI4nX^mE{C3^9_Ono{M*5`*tUywH)Jk!x;EI><8j+p${0D zm_@0pt49cjg&BbmYci2j4+RtAW`UJe*-93?h0=yn1_q>p>#hm0 zs~UfIn_=#FVrt6L?TcAtM6|IHv{Q*iJl2g0;|6N#Dq=6_Kl4MI9zwXAHf^dvbxZ#^ zzP)i>H3JhQHzK`wCfB?Y9OVGbalP zaH438A6HM)&7qd5{Ph@42KO;0g14TYGyKNr%;p)fN($`E<2@!B(6s?NiU95UfN`c(&z zhIax)8SU)N;BC`N?nUBt5rR8qV6_s3Pc{4H$xb8TH~F$n(-MRg4{U|Sq^g1l&>KJI zPHdAnkCds25R4E-D9CSrM014f{)A@9tdm;nzk+_x;?0w~2*vpQFMqZi0Y3_TW{)r9IebHcX*kB);qQ9ySo$s#NgwTv=G$PV?ixu+v zQAF-Pc1#ib(&6F5Qkb5RU_w?O)c!7DWkE|l46aaN0RaI8tv$Wot)i#9IlF1PWyGT; zdufl|3}V(D@Bf;LW*qbpFsLMwBw}CWCv*uB+B-zTH-b2+qf6y!gD@5e!XEj`5m*1| zQ%Q}td|n0yQu-HnlELPci(+A4xN(noTw*3PFoTk#&iVJ>e`9$aIpad)GV5nh0oI&4 zecCHI`REWT!&;(x4hVZ*PaI$89T2e7eiF$p502I}-OmAk*TT<_4Nl?MncO&0pRA## zK7v%jER2bX$?)0{pH6sH)TWw7lCPnoqiaW0;>OQx2WYPEUeCy*^90`9VBsdfr`8x5 zb^@kLTl@M9iG~Pg?!ABh@d8Hqxh*mFQd03buB?e7Ln1erkNJo!3`RQn`}=zdn#b2` zT#S+Q7tSpyDX~I#O(Kt|suQu!!E_M)YHdW|51(0%~^TDUL9}=Q-#)I7MQ=~-{`h5W7dSXd&n-6O4$wx~tr_~~Nx_Ku3 z_Q124YAqvwqVD7G>Kao%!aC~_JrZ8L~(hdTv4o*Gw16v=Nqm#CyOKoNvVc469SE^=M zcp>~*n#*-0qzz>=#I(N*?OQKdwM;?K>nw@V)(pmb_w328xpri#4(WbW;bjIR;R5Ho3XPO(gCkw0kYJ|&6`iceE^SekMom0~$`DE9p=mD<<3u1_^{otgSBWC8>> zhRUZGq&L@=9OU3Qf(nt3*x?S0jqxRD6%B?NYBc6KfpL2&KbwTp$DyIj?#ZO9B! z%N54ae%7OkGD=EaH*Ef=1q5m|ugfR2(Nq|-_`N=OGSQsAYvpHo# z#O8n24AVaYLqiF3N#9^^7!zr@xG;D*iX<0*OXZ((Lvp%r>$ovIwU$EE_(rxNw%%V6 zsP{&PjckP>Xk)NXDP$k93V|b= zs~c>Hp%}<6AdvRnLhfp!Qe~pP0@1A})~W#LUxQz7+EZ64JO=t?defnWMPt`>dZ{#` z8ow~%aq{k+I~5R&2CMND@f$*RF@n;Y4YoR4AGM`UBB7Fp{pX##cegMy_L`(al~`hA zXmAklDvM7MGQF1mArzb{E+(jo?1xZ9Dd#FR&Emo$8r}@IZX1l;jafVxbIW3@qujXO zN90^xcF-Jb1QBOO6lKb1IOZ@@Fw;;5K_Wi*$JF&4S-FmOCxtk8*LS!%tARD{P9uyn z4r!h~dWytN(PH@fi;o}A!5S-X_Nu;QxB1;e?N4HH8rU}j%iBxAn6!jx;LDfFZ;TKW z65to=hKnO6t~1D{tKcG)UNxHNm$7m^{W%vdZf=GG5R5{R$wnf*tAoWU*dbrz8zVkx zOSapG;%T4bO`~41YSnoc2-OMl8@|7{MpQzg3e3M@Xe$XY#CBOfi-B!(hpJj^okb%s z#I8B6cmy;y%Li!MjxJN9#=ml;?S?AFh;>bX4Ly87j*ru8YLRUE4 zMpo7>NwQq$3BqCEN%pFN)Upz^5N?CA;M@CqqC`r!vQ-h@kx1*!~QtxvSrBj<3x zq2LRU%Y|9P@vJq4SfY9J=)S~ghYGOT$sR+6-G1UrTmaihq>{JYZg1PXnK|ElI@a_t zicplO?q(hRnu5p&i2or{JrG0`NRZ+@bMpQ=;&LSz)3Lsi*Iq9TLJg_U3l)TI+oq?d zO*+f=hNgl$$Wfo!bgI>R5Kdj}Sa-xZ9wW;Ec%gwydQV!w-)vyi=pTt-Q6 z|42s6^=e-b_ca`6R4skd^zlWXBCM(ghv|my>yLDI-|O!hca-i`>W)i#C2St^MkPt0 zyPO1QjHId(>sbuk^$6%x-RtkaAp|O9D&QaesHOPcbo|#={S3F&7l0BK>LqyFP(AF& zQGU3nxVQ={*0*Z|9oH$WxVksjeahpG8Ml82e@zBcohQwq;SV-V>xEHJc4UwX%UW5b z&pdi1r#q#D5h4bcXT6zI1{v^NO|_bcN0l9d3XRl%SV{@|2Hg5yUfhEFM8v=$u@*=a z!zMAErqWA)1i58!P*CzUq5|HgVREchAmWceYs z%*?iP=U)hPWe~l+8h7zEcxBGr=I2d6y{L-`3;W2X_^xtj-;Af-4d@`+r@~BQ5?9?C z-{asHyIl$p1!8IiRKo!U*R>AqpHBn2j;SasN1^!L&&+%ZxhQoW8a-&@h2oA{1Law} zVM8@00!)!cTl#J{6}Fsg3d=YBf`r z_kaT<1|6bXby9yWp499oem=>D-)x3_n!`|;5)<~!@s>XT*mO0|%_bqi+l&}1Yl{b# z+WJ^v_ydik4sI@h78#Tg1TcW5l`bZF;+3MQJ5X+Pf;CZv4HiwRZHNGgQYca=+M$YN zqHHfR$+A#$#VA@%BdUke}z(t68yx=UO=IurvR2P5s(JZXlWv?He zvxRn{dyy9L_2#+Ve;K=qkvqJRTxz7+G7wQ5ER!gi) z0rMWaUi0cW;7HGdVh{oKLgFjyEnpVo$k~NM$Gyw^Bv}W= zS_z%Np%uV)2rltw9_ekogjHJsASVWdPGW&W)?&7StwO~233lSXi|SklS5;}@V4WB_$LO^jw+` z0J-$^G(8xqEg!pYV%=@GZ-`Y`SQUL1GtmQP3P_D!gIeX07c(ZTkXvr)>*BH-Fb6Ty z5}i?rexsbk+|!hCsm!^%(mkD*r5Cp$lUvAID`L>m{BESpSWkT@0!_MT+6%0An=>g& zr@M_#U-ZA|A0t~jX%Y-@`1F}G@@y=N3nuCC608&^CoLl*E;oC749i#x_B$+GTxIv} z-Sfnb^C8X;NVaGx@Y+KA|4J;@jv_aFJczp$&7Xf>#(|)1G1hyXtTRhrbUJEFoE|;m z23Em?sX^|qU%!$9PjLA2NiCeu5^>4pw_skK(X-!HnW&?~-{aAmKmOn*Ufob$e8U8r z8ZIo!`4>(J;CnoXNv-=g8@#dX!;sU`_KgSTPoqzDEsMNEtb;hY!M zG>f2M0}2vP@PSC3DjVJmX9#X&hx27Ft{G8Rhtd4oMxtAw;n-@;HfIiUAe`MA)66jI zmg{BNo011TNN-YWVj+4bHCYs5?yR=eD6|P(@#pFm=u7NBz?VxLGD0=ftVi5AbEk|y zG9a7f#lO*m6K(9NS_%Wtnv)_6r$)N94G#$mH+{&-@v@zpYG&c&ECt{vJ2?$V(;H>A z4YYQYv10L0VZ68?KxhYMZ*L1zq);d>LGYlPIJ)WV^}5$mu=NBnw72_0daimL zD=)7c(vrxs3HT#c!jx%R!8rNU#)_l(UZMxVt5w2@aznsDJcyU$`I+fQY0}kiF7}cugjCUZf+Z z_u(sdcJJ9Uf??e${^#^0#IDC#3=0;sa{(#tc^~Q#X5~U97~pDo)Qt&f8aPi1-#vKM|Ev+qZ9FSlhg`3=2Qs&S%-r^o@!tIUHHbSr_8f(}`yz{CH($FbXUj zqaIKb3WGqBntdxTG-a!>Tod8&k&~M{iR(#3$eQ;cg~tLzfnghGI5mb7NcAv`qxw5g z{5o(K;10iqjxHQ*!_w-njhip}8whWSmQ=vGQ;v*FR$5wp?!eM*>D`^bVd)N0P$77W z5bmFK`KWW9HaVFt9v}vl63>tBLUg3#)*9!J+WsDqi&wjN2Pvu$Wo6LTvu2QXN|UQ{ z15Brf+RMSwaoChq6(Cn6ip>ZtlT7O1+#)aTyf$jZCR&=RPfYkkFrX9%s9iZPU{hLJ zN`Lf50O2pdNK*#eDycd{uIg#m`$-eya2;!QKD`Q7JS$1mn&nV#C;fp+8Sw9tj~+B)<`cokfC(Gw`cKs_@Xg~Z{OuQ?(4_+Q zTZ2nsdg-2!|GzzZ?tjzkQJK_BZ+w9lJ1CQSS#mH6;gg$6RK*n`rbR6Fx(_dX4HZ>D zUEKd{!XW%!V#yWx!uh!DEf*3B%=%kvBW-{hAWeIY5ZB&)0dHgl^29j*(jMl0;JbuK z{rVyJUH`_PNY($Y*S~Bq*%GQpKQ1np%dFxM)4@{zY9uw&d25)`6K|^w!$L?5j zbmeZ*M+)?%mxrsOLnI@l;Ye~<0x=&{dQF-GFcywQ8%iGu3RkXdjUmF?87KN+ts-wW zB#KA}OEESX=|4B!LAuREj*OCM_I#|bITrmCthEBY#JbpB?Cb^AFP2e7)B;Y61q{QE zz68t>sr!oY!ZrTVCuaonBb95TmW-rk*17M~|Qe|vyk}xQfHl8%og5mPOz(CWwjNC-nh2+xC zfRyosne@y^56!m=JfwWuKwP695_PWJ@7Qx)4Jirej0IsA>_;&K9rw@IlNv*S4d|f; zm*~Nnsf*uO0H2f1va!D2kSv7~sty1chQ~=z0X(8gU@vr@4Qq_x5mbTcd=iTV&=>gO ziSsuI@wywer!>+oK+^zkSwuu;Cx4?d&?22vAlVgZW`;;@A^;9^<+1{>wXuTDi$sTe z^?6B21u-#4M^1cJ1#$a6Q-sD+bbNTB7U(N%om!Tvk?TkdmPgPZtGZyaw9o=r`jfsb z{Xqa#Gq29)zwWMFU#2!YxNW|;N2wMG`hh}fYl9O9dY@oHWcJ=-w4FAhlwnd9GLh}^ z@cqypM%O?QJ>AzHiqZ0j0G$B*Wp3Pf1$Zb10__T%oSYVzNsv=k{_#1N#1Je(eefhn z+N$*CS~waE%5H#C)Ri<4PcD;gA_SsG5FpgJ8cM>a8v4A;SU> z!G3&aU0wbq_Xnz7@8OmNtyIb3;7_OKfxyYjpk{0sX_A zxHW!*t?isr++9h)2*mLbmtWCYgPXsX0`yN!-2Qi}{ul7hW`|`jP#_a?!J|hng2I=H zsvU;eM^T@I-QN>sZadw|gvKck9z;?XplW@j?2{ni2a`|s_-7QXSn(_FY{6kOs&Wgg z%9d6ggLObCU6_fb1&4DM{yWMr#}3!gNDTW#;;2Ngd32E2ECZ(iv=K2pjand|w)NJD zw@xq%K2_!{aAX;k!TMZUw4B6nRTuDn>`@+`o?$q}(DZ^f2ZcJnpDz%JpmT{iXicUd zXrj(}LBD(HaHQgOVis9^2!92`4DJAhK$b$B=UtG$@mzVog7k)w14k&t`Vrf6WV8x3 zRoJu@Xstrkiu5cmB^i)9UPj2QPBraTG_a7F4s2#*#hw7Leq6;N=$fNmilvAW`-tU) z`$HovT~YWb#;Rs)#tDiGOhhXeBC^sjr<1uhH=;JT7yUTmSd9HmotHT~sZU%O(bx;S zu@2joywUm{M=!+1#VNsME_;B?bGW1@W&7@{RzP`8&^&O>*REeL2LPDo@>?oWS`)_|+eNZT6vwl*f)>9`;!n(Z-B3bQhPVv5C=jCTtN)bDTYdI+cnwoVjM({9FULTCrd zs{pJ!uG*ZmPC1{67`qHZlcBZ{MTq_(e-T@oVB@sutPDoepLjzgd1^kWu`!PPi3D2s#tQQ6XL_ehf?59nIg)E zzKI-63FRj-)MXfj=2VdF(ysZU!aT7Qs@c(Y-rt$088^5BWv)ax`a=kUHz^=SyLd#LdsIw?YCa3n_C6s)LTsXM$srgbsqnlgJEvMjEbLqH+U1h6a*L5b``- zaK0?kO*;nuWaB}9y2 zr1FFUK;9V>Of#b0X=zQWGclfkQdlIOhoMv=r36S?YCKlsH|*yhb}9f2%48Pj?@JFl zar@8I+D?>C<9R`dq<;)zk}4+dK4XxI`yYGzNaUad>ALD@l+r4JDukdm-!X$Cd;4}W zIh@hA|BmX)0xprUk=H3GMkCOXhyapn`u+29>_}<>XE|a$Ozgx^9m*vcs0cwJl)w-G zXo7IOhE76VBsqx5b+SMu{k9YVEB$V_JX|~F1%qP(M^KCqxhmnV@gqJaN8M=uEwf}x zYac#Cc_gP5kqU!ww>1KdV@%6J`+DLlNHskj`akdD)lbE*%#j4rQ#U+iTnXNzgr13Ncl*5Cf0hd;VD%7C4fT$o|?$A|5=t;x8&PfyxG#U*@mB z?9h}UtRC5mNfF&WKzw?-HL&z55xL;wdGyD$QsvkMQ)KdPAagjgE#2&}f1gDW(}k^o z4MtalBV#HkDUn3_U>3Ih|4Zk|QbbPol1p#a+$_6_8a8txdhnrxXiB59`VI>&kMcM` zq2SbtqH{mm3U2dLG761Im|8ab+w$dv5|RO?B`F$U&PKrHT4&S<=UjHU{1Icnueust zkn7EvDhL~uSbQcEgI6hKcuUe&AtbB#@k9U;@+Hxi)@ImT$ zLvZQl{nhgeI1G@+$>7e6)Rlr;$d0}YRwWV*&4gNvs_(Fw1^NHH3&>JGK1(32Ds1dT z4t$8hZ`>~CUjNKSOf$j($p|rDCjC5cP%>g+B6`jRa(!P+B#`wG%!N{hKI`?l=7L)T z##e#xy95DZsxKtXSV|cJtWXy1Ho=t4|G5w2cl4{SkYRt$^ZsXpH5i*jw)52_9ShVY z=+mc9dQN+gPG6mHFJYvrxcBADWr{R7WoJ9cdd$zyuS+uY_p_PQ4Q;JXXj09HybK^S zh{%2tp63R(T)niMV)scL-Z7p-UsNI?~SaCKxIv* zp*(BST~+iV8Xw=o+HD^#mTXqRb+t#4-`?NE8Tc6+EDG%i0uo}{*Ol`OU@13de4pRg zc&qby7j%MN0Qr~i?Cc~S+h>h{Y*Jj%QT%Zg$CGQNUL|0*{X%2aS+j|x8G){*XgA_2 zN-HFn6{vCHo*PM4JZ&H$Q(+v0v3lr!mp2XXE>_lah|tKa*jZU`@Y{gtgR5U5SB$;k z!J%?9!Uy!Ic;|xlTPgDmk30oo%gS02DmQ&39zhNwG_qQd4oHPGzzC{yNo)~ZK)#3F64Fy>C3^%sS^D) z*;rK}%d#>;&AL8>z+Fu|UP#_Sz#FvPf{+M=TA;L%hv8`95dayi7+1{9$cO?&Ytb3( z@mjx{V~XQ%1p#z>3Hp5{`+hjmkS)32J4bNGYF$@?96{nB$!u`5VG7Wn?3W~)_dJXZ ziR~-qV@~IRRm18e3OUhU7M8j~dnxO;hp1Mp=N z5V*AMkZJ|Muwig{zk2sPrsoxPA$-HBVw)H;%m$7^8Q5;J$n+5Wbh|3Tl|Z8b%E<$( zY5PfTtxum(%MOF~tp}VJrm;^zqzS@p{7wcIiJ3IkpCrlP_dCV1SC5e|1VarWstOB< z$E;VGPNM=D8ha%cy(bOt)x|~uIk6F5B9UC9J}G;!agPbwG&rixt*7UCRo&N^mL%aP z7*0BfAdT|h{Puv5I_w)qftfdCx}ZZrsBVDqMEx_mzGwYP93uGdQ5oz;h7qBbl_^t} zl|~>$xO}Dxws%@|uaRs%2_0cn50hB95f%OdxB8k6cIKIGUwW1eE7mRkHb9;tF3#ID z-r5Kz?VkLvc@Wb8$%;5M+aSsCHq4v|c|U~Rp^qr8Nk~70MuLJ+3^$+%h}xA{ZZuge z>jB0R&*BioZ~}l603VF`kFdQ+6ullA8Y+;ZR+_xy=#95%W#$kj8Q#wmTc_R`N3s_| zy~zvU(w2ii#SLhS8^w~P&zd!BIO-wt;TES9O&Cz^C~rBsp$+1Njp7CPyBtjp8d_SN z_u1LvDA~M(EZ=}Ma^fG2bSwbwo8Qh^UIXJV1kYUydf6e#$u(_9J?7E@D=?}x_co># z0W16@G}fSj>Qx-czZhCAMex14iY5MICPl^&OICtY2;|Z&&$erbfnHJ`M+#D<_EU1} z82Bs5zpX>@2?<5$#)xC3i6N7StGz}*cKAKjh8qCCp#%L|7Xb~Qh7&RA2u^U8UAx}d z2q7~`td6~AfOkgU@*z4Gb2#P1@lzm67&crxbZbr})r1pRAmOYrI(ad>dV6=39;4E; zM=st3&q8Cg5-k;lmr}DG9V1jtcR=FO?6xyAK`| z$D!8ZZ1%S|5)@_%R-n7{9wRk?=5D^e(a=?%;@|8H1)SiJ5WSjLS2C%8xAVX(P&o2V z!m7EH)?Rf4)tX*K*i+)qlz~gAEXxB&ZN3AFUF$43crI~x+1s&k!9}#LLHa)dY^t}> zkWth{qem&jB5~^>)gRqA(s2f@p`g{Dp#zQ|z5bxG zdTB{eMWD|CVD-zh4+#p~fZW}mKmYNc(5)g!q}9ilE~CMW;0w)}jpU9E?dhKh=}1G82akbPJ)ERtpIx{@4zf)98PK6KabQ(OR_%zwk;yM8f^oVH^4c}+_{ zi~K){{THzGeb z2pJs$YCee-Zf5m&Mx9hb(JlF_os}cJlHnvivcvgS@>xzW_>lJ+w1#+SXsy-6p9R;B8 z5fS*v%C5j)_lPQ1Dd*qe+~6n(NVCO^q?~~QwA}*mCCnwUry-u{8@2kK5yc#N1?Ge+TfBJG3=+p&}Gh(yx zDI}1iFzW)*6Mnpc%0Li_830yStEIz$>I?s?UwuHn2Vms))Wl_1UkTVsMkk=8*VBF2 zU=5l$UnYiMpyXEp95P}`OLZfg7?jVQTg)h^8dlW&JiYCM3dx#VlFNUS{rk)43 zHD=1n=L=1alex5DdGRyUXILf?@DNA}LFF(f1ZLwrUWICE8e@|~tOpCZCEsSnYCdI< z{>XBaUsIW$a^;>pzxPg7y$`&*9m+I9cX{&sX25VbtZ}12>5biv57#_BYVCNQiYC#i z-Ycy1p56L(yVBC!FsY||e=FL(?8P@A$DiAY4O;q5=)U1G4}0&a=<3#0fjmZalq7>Y@0 z_nt0lo)$+Hh{1&N_B|Swqd&Y*dme&d-AS}|M;?yJJEtyQ+4GV43%T4JxVZT2@I5S; zx)o)#8UK1SbZ}cMOf?HoFd4%D&R~qtMEvpG_G4Y3ATdF{oNmwEFl2+eRvT-wpPywUKptuGm! z&Zl(EhqJetl*LW`V-Fht?!c`C(FqZQRZ=<1>*v6ZC#s=Pcda4WD9wmq2`H;?c7=zw zqxBc{Fa-lwkTB9yC6zk&wVGF$>k-CuG#!`bIVc~wHx|5rlp&gQpD6o$-AIWK9HtYk z2LM>l$Yenj<`>;yz<_VvW!(NLJijel@{>76n7D8KsM!Hd6A4JvN59xTH!eN~cEZvHlKb9gI#V4m(BFJBa?_Qgc{_5D|-Rd z*}YBq#yf+yehgf;PY;!ppr<{A7Iu3PU-KsgXfhF1h6#|+RTG*pXo_uD2F8n3ud)Am zsm*K-yCFr!%L&%X`7E0mE(}F9Sae4#W>}aK<;ttz<#sk_*#c2Ys~?kjELhl<-H{MD z;4F}IU0Vv8df=XF;_+k7>?Zkypi=Q;K&Y5p0-SO8Qh*}J8sB0vDPRl5KHOnFT$-3` z)*j`m3D7b;D(Vv^HM)8nyXt|g_%nAlWlZJe%FD`rL$6pAqY+%_$Tyf)t1!_uKk*;R z9ak0Zf4kguy4tIkdL&Gw>jh(1oW_XMLKQhG?!Ax|TxL3qSq>t*?RDh3655_FPjo%1$e$kU%C(8gn?y&g&A_aRIq_k?-#~*=6dsxCO#u3Z2Z0BC%@WBmM zmk{WA{mEZMWWPd8L)#7)O(4}?M~&18GzF-=9i+7)9P@xkUPD^fz@v8xQoJQ*SyPQf zs7DM<#&X=0>ETcjajDG$Rt}$w8zeP8CdAd&8lQJT2mBk9@}eL1VKfjegkr!H$53hM ze-^|RRw}2exrpA_0ZJKc5Pco`FxHF6ZbB1ihr4rQhQ z5=|{UhCwxEOkrvIdSYW>)Nk)0fH%~=@i7=W7a^exyE}S->}G{nRdaN!5;XH&8dLpq zpJ;0&aCf{BM=z-i{U9X`gb)dQ!g!#IE3e-e|KjRRABp(1m*RcodTP1xW9%t0FRs0S zP(K26OaLa;lgs<9BRwwD!-q#VK6|K!u1hKl`>jGFPgqxIKKj=1=`K*A>@pg_%J9KM z)x!9xBw&zR0x?(v6cz^T~2)-^-QM}0R=eu$A3QZVi`oKq#XfV(R{_VF)s&J@VoIbl6Av&xO@W@zJy3Ff-HFu zQQ86Z!=nDD!ka7#3vD_u%-A=(UJ8t#|$0& z$S^YA!<)O2p-ajZPe=HikY1#-#r!9DWjMHq8Pu$Lj#HK5f+_jr;>5tm{Ol0LSBy>u zNEs&oi99;6kpzLwe#BYQaQPUK)&;mL0q&~{ZezRMa_TVM8qCeK-m1QiSQ)+YRW`N2 z0g=g4XBXy<=f)CH+{4lGoPWq5eIR#-$>-zYF)>YTmbI4#uYE#1a08#Antp1g&(crBk#u090Gyw=Projgs1M!&y}cfF#MRR{d>jyCw*nsK-~gLl9T^#~K9JE; z-T{c>N*m!_wgDhy$6T0{703*+rXq-J>>OFsgDqKeV{@t){d$euWVr+G)3&*exoLk% z6Op!$#tLYOCWJYQj5UDrWm^38{U3)Kdd7~!QQZi{xUKls+2$6sG&u0MWpJ-vLgg&; z01o5!jYQzI=&pw{dY z_PKrwy7m};4>~7J{9bB$M}V59>L4>D{v?%-85jgIEgrqwm#|?9;vh=sZ&uM6ek_@Y zN%w$V{KeO3Yr~>#c6|AMhZe9Bq7ug5RD<02rtugE?gyy_``@Y~Q26WMVIhKPY##}W z6z+~I!tGSpVf=|xAaU-9|8N%5d|s)uS(d(7VzMttOsVM&OTHgyf;hvyZ`prm*{G9G|5B?tr8 zX~WD)b2Iap%PUDw6{+6EzRZ_HQdmBNV6nAhlBWm*h%+}sWnvv(e#CK%+OA&Nc4lOK zd>(G9H*(Q^sIHZHyx zxc~mgRxrvL^U>ofc%qVhF;4w7*|>s0da%>Z-~GXfN#_QL0i}GszrE|a;Yf{jSKJT^ z5H@Wg7fmct=vv~JIR?5tlQ-{v(BRK& zOcq(y1O{w82E}IM+N&P!0_#UN;p8vE zJT5oNh?}ADC25F?t{*yR?9N=R?^}3pOTNV_>hlAWz9u2~5UQq>Up~ZT+9liPC3G24 zlhP8kOh@+3%)-FqE3-&ev!zz|!ln0ni2edW=3jDqxLB1gd;t{|E6q}^w)n~gmY-QG zr|s;tGBgm5eS31U4Cw$-X)3^K@H%AOd42-knNL7m3T|Ng?bWJur~)2qb>xo6wnRsj zD_A^VN@;SA30f>98b7g6^wN!y@((V^D=pw#@(deh-PI z0v$tH$jmX2Vs_gaqdX*! zCY833=fXAFE#9%3ZWZGqUK~iGFe9jHFew*5Hr=0%Iin#HOx*ADHIXL4__;+_c$>r! z&3~!+w~MCqWi?ElJciSn12u_7=5X+#tC+Ynjp0Lk6h)|)ur+CJ_;G1o6h;rb2sW!E zsxagZ<9H-YQiJ5L_pv|pH)t&csp;VI#f@tj2L>P;8BH|C+>bUsL%mZi_!@%ltG^t2 zE6&&Gh7_{{qZ5t2BbZwkF>5qcz|b}qP6|kI-rk^nQ5am$0_3#hwmCaOFRK7o;sYzx z_vME35zyR!5r7|Py;`zzQ;i0_WF<8c39%3psi$t0 zfcA`-HxC=q!xEA;>z0QId0sVdKp-YlO*r4(d>uqkc#^c7%wes6PB*_6-cBuU)wilY zFy<%WLL|MA@8D1?K$`1^PGAU*{!Y9pDIEkSzPa*pf~IauDvoY6<~2yn#z;~qMrklS zn-7`1!KeD7#6Mq^n$7RY0O%DAFhy9$yi$xy+v>LhQ5bnp`dq$+n#8FJtF@)jwE7G!Asrw_l_ zNGc*%W;~s_ni>p;lajv^lSQbJo&q83-qX5$kT38>);2Kqy}RqQA5v*;P>7!64)T6)0-O-7OLfmWA6gAA%*bf#!^Z(RXyG2~B0)Uk%;<|~ zq-!6ye#WQtLh~bt8(mTb-a`Ur8c!_voCyBB|Lq>B5}bk}9m>|zO43k@OSyzVbk%L7 zaAa?gst}OYMPKt@<^M$NzO^JX6W(K7|(&c|d10pn?!VKorE=_GoL| zQm80UVB8QzPzWHRXxf#nh>C!MV3Z}wrVut+YCflmGM(w}Cz-j={qN?nyKOX8zvX?; zIp5`+7lPvK{j-}pa+e>kzbZqh1*&tlO0%`&zuoUo`{>;t0(BWSU!T`cztv75z1uV} zE_y??-U~nq@L#9?FHFIc`Srjor7M#k{NjUKU!En@W<%HQoBnRKz2>F+uZm{~;7@h; zZKT;bcJ8#;xmlb@vDdVXd3oojw584 z9Z9t*1(cg+N;d6r-=ujm^ht=)6&fymj5n6+{+6C!M1^#<;ZQiHZkq5c;^zM@`wGkT zVou|Tc3T$Sj zySBGq59zoLv@bszws4w|xljs>V3nMa&^sOa-L&3r@(QQml6xj=ool8SlRv8}QEFD!6&KVL&TPM&ahwOHDD|FE`Wei~jU`(K>_a7*VAq!ExN?EV zk7e68KVR6fC8TvrZG3WVSNz4U=iz5$GbLBXli?@N%8%3;fG1A+IZMlKFI*6?fPoCV z`LN*hk(y^Fny)$brwR~}jfpMF)QUA3YRYV`nWu`_2V*fvua!x00L8#mpL;3IIN;~& zYV+*j>BFe27vcvAh2C=IC0POQR)!~O7o#8j1Y{= ztyuv-vC^Vo%$2UwBdmXgjEK0|FXJsc&*A`e%4nShefe^IjX7d0t6;|d58nx!@1roA zv41zv*qs$17t!#@L^E!15I?Ghv8_eSnRzX4?OEsG$ zDq-<{mV5C%;cxKmeiOIoqOFJug&EDs!yqo@=XgagzS{4@w~>nT0$?npX2sf*!(%>R z!We+!1uaYr^+W=Rq-SQdROfkS!AJH6!EjTwuC}lvOYS7Mc@5*w=yxM^CHwOC6;@N_8Yck0{zTf@fEm>ni zk}smA#+|Ees~8b-fWFfA6mTkGuq8~+eOn<|K@yW<_K>|kG#8o$YF-W|X~iZtpI&m= z2Zp#Ht}|NG7TwmA5Te@jy0y7t6gX)6zzNo=B|g(hSNkTtZefF)9+?qEe1Cxkca;oRjwC#7RJHSR5=0wHer?D7L-q7|}DW zVxLQc9F6iAXm6`&%Znk+29lf`{$oVYHy^bm#K${`baBXbSKlnK&a(0wUk6e!B~na= zKifOh=@|HjQpTBBO?i5%KCag}9EOebcO|RWPU>>2dD8NbgnEm64=+=y{4(DQlX_Dh zQO&pta>-U2}_#AGjBez zIr$gN#ohO8qibH1(9M{+WjLR0g6{oT>PcRqYIhk9gI?layb1z=SLp+etH3C#rdz1& z?e!Cb8``zs1tC%ULdtL7h=g1L5tAc;xSlZr6%H{AQU54wj*;}!0EkAeyJR-JkfGvy z?KayL9ex4HYX%7?GVF`fZ;Q8&3vsGj^CWj$-=PgpP9{`xUXfVB4PAFh#N2G;b%O&3 zzJI$~_Yi9Sszl`ixF}!~p(XA1pM!64fst|)(h8Ib;csMZ3(xoy2KMio zWf1j*?#nX&%B;dcm$5enmx)Zp#!W0)q5F}+80#oKZPNXdf20XM`Bm^8`rZv{g0@b|9>I>m8|-I^F+qH|AK2OmJ^;1KCM`2~jc zh_n(Z>(7+vUgyDg_Q0`bskE`fz+j?MNJJ}+UB;n(o8r%NtW02$l1&`SGHG)CxJkNy z^|(`#g`T$CagDfen<#xAhS;QkA@OAxwF+RoY+zP5J8F2PrdE?MLd#r0*Kt(EyD}nP z%Dv0`5i2VWeKq`6wp$Fu(Rn?=8_iQx?14F2^3}k=&>_}*+o2Lg z_i_#TUP1}Z{NVILc$BaC-GrmFSM+l4ZnA6gN*Vm(lGWJ0ZgH2^kB}2{ufDY?t~Xff z1kI}#V<$JoCy)~9RmPNT20gK_9Ham@b|Izxt=rn|v5x~)8+J8)%1(#p!Ox5gL z6>@7Bge~(je4)g`#*WnejpKGn6Mp_|x#Oift;~>DV;KT4^1AWi7k9Mt=R2a+?-SCU za7|EIJ~6sTZO{}ymr}jXwEN3b+#%G3O;)<{-%{Be&|l^{i@#@hIcOtG^}F`7j5P?e z`9t%puClY*kC1 zT0ZXPVfC@{>05dN(xB;Bh^EVma7jeglo3xuT@w;AV`HMiO@V>-2S(rJSjf$Rn);*q zxK(lN#S_Xm^z}8--Cxk`zWPMceZvO-oe;Y*Smrrn#)w9Gd6znXU-a7rkqG7 zb%w8px^Zq?_`%+3R!@!}7NBbFYisN@WUmxXqg=~QtH(Xsj&)^5)c7=Y^2@!=T!9VC zZs@3rgB$b@aB=h)Neb_m^^}!~a^R}4# zXGD%0$pH{*$ZQk$JX@kcbkqRp&dlU z5XZ@c{W?qD#LipYS^kpkW85n94jRf;LJfYiW#GyOIl50bd=YT6WNvsa*Bb$( z952kH9P+AtZmA*dsn$Ez{T8Nm;MxcO$5bJ$&(!*iRCZ&Y1_c*`rY8w5WyA3cF)Kej zy|xM5?vC9+wh#29Ry3;$>2mMl+?Gm=0%D4|C9W4kiy;F2_j+(Zl30pD9jxD{Qj@Q_ zg&#tyexaeZ;;DPIvNjMA82iZhXIJJu;@z#--B{MQcz4mXp58ZhL3w&_v&*9ExX zv60u7AD2|yG5zT5a{={H=Xuo4Wkx=?%_z?>=AE$m?(yRL){&wpWtzmzQ1w zgZn0O60yo|;{XmHQ^cQrxJ|flzCPC>m%`RjSq`<-ex+R(Eca~EhtsT;$OUbSG}R%1 z5wA=fQ(7g27VSJZ+XHj}7h0@l2|D7M@|A>quJBb zu^;N?C}-w!=Z;$b->P!|QXeMr;LgInlJUc~rz35HhT9mLU_uc38Des%c=UQZj{o|V z;b#w;Z76PIFD(PR^k-tU06UR8kPOrm^+N29Z_1yePy);EvsYo zxWr>91dt9VQ%B$XOk%6@2o^mPBNxo!;)k5D?x!0(IUl&2VAqbi4WHY_Z%`y+HTtQ# zaD*T%*zj=Da21DGd?tr<({t{Q%9QSFY{3}Me?<_VPSq=o6P?96FPU5f2#NEk{A%GP z#0-}FP<*HO5I*=7msnv*7w00_a>Csj>9%@f&=jrZ2?5uKIi+L}TM3)O&=@CltDB+> zZ~bd;T3qjRHlO(SES|9gwJV1~Rqhz{UJI`xVtW`GWG|!UQz(ItwR3}TJC0@#%amH0 zIn|8&|Mqgx{m!_W8J*gPK$Rs7W+SuyMk1v-F!7^-V@$?Oo>lWxXpht?#(rkw3XLQj zuL!G@u^ysC&d^nY&6eG?lY#k3(FtV8N8{dvp!az9*$jpVGi}?YY25`cbkK~cpmo!g zk^c8qBv*=LB)bQts1Y;!9S<+=Z1ugAsfNOLeY!`VYqP!eTX ziD8%n=v-s!S48}hoc1dD1vx#&|K~>}AU=%?7Vs_QxL{`4J>gT1ng$YJl6YleCX>ji zvS8Rtq^YPY7b*+zAI#IpKvM!+7=5<|hGoc+iRAEkOJNwbNe3`1Bnr8LU&6d7O|i8_ zSJwnEaHtBuaHgD#Mfc>GzJ1phMmO4a%sofx{+>dWq)@`|dI#)46n;+uU2S*A*MCR0 zxR*^?O4-A6jcoiqMf{@$(w3MM>)RO`B%8Llp!A%d2NaG|V^nFgjE4v_4PH zp`#(}qR6v8xcg$vw}}I|tuEkVM0w}n-Q+ZRds&c`)p2KZe73!(dyD6Ck%EOhmXybE z5j9(4PM^tM8EuuOidlX9Dm(DLWQm=Gv=>zCu_zlp#&CR|k275e{&|aCe9KbYE|zyz zX0fXZw=U3`;(9lA9_cp4eXlje8T%J4Ndqo5is7ap`FU4d(AwI6%8@5)elY1;lJ2o8 z{UQ@bGu&#}Tx(9H0nD)K=~bJ*4_wJusKtJyJi;;%qE37NbB9z=bez~~BW(7Of-lf2 zt}=byAH#yS0;T>pUCJz{z(ql&_9kO|R#vEeT$t5TM38n4z zCd5LL`p>!@+Jn=Xd;aMSD4 z$cbL3E~KYi7@MNfar~D`_2Rg}vH+O7a%#+Mk#OufA3LT!J{CbTrT5~C-i@ccgNJT0 z_L(YqOlT-)T=2p%i-gD%5eb%kbbd~IFeg*zGP+UpQa4hG7LVcZDlG1lCIc~Pi@Ui# zsLDoiyx3!TuA^vg?^S(8raxI#$0cDE$?v$csPnVeZCfA6$yUNct7#`7bsa7B@fgO! z3WL_R77)aKk>-c_Yi>>!7duw7&xiW|Ywo(NXYl-Bj9B~WQOJoHoA6Qnv%}qfy7bO( zuL-M2v0Z%Oa~@>vsr%H|a$LHahprS0EG}*_JY;Y}h*XRs1=)A}Q|4O7H5x4T)_WE= zCStLO@c{-`iML#eR^!!I-U!6{AjdOQ5Ut|3R`dQV^P;0E5Z|IqtThLWIL_i=N&~*9IfMornwT6sd?p;yJ^atNUPD3$T+7=NxG=O3Yf{{gRgnv zgB6nOe?nj-M2Vi;0B=_zD_X4QaK>&JDp?fMMXnY(04qUh?~0=MTGeBo)VG%#rz!a! z(Qy<)(F%*3T!0?t=LKDjrA*^1K|svH;*pTSIzd0YvgmkUo4|(h?P$!Jh7lU27;7-p zs6{Un5eXGu_|gxTd~Dyb^GUir6*zU^tUgU4U)aR{DzVL6?)3W>LLUd=)ju^lBPn|C z{n$m&_6@RmwTluBU0Voao@qp%9M5F9iE3!cd1)ffkkr*5^&If+^eW%q%7H)7BnMP| zH*a5)=2F?%cefc&>=E|+Lx(4Y_8+o)_w@bSwi(3-{@WXoX77#a+yCl+{O#z*X-lX1 z^jB;)oAcDbD>imc{6~vtZhf48_QB?1>n6VW#-56{&YNM4jcaE*tAAJ>c)=~oE~+{s zzPd5ZuBEf1DaT#g-m@`p+o8GYka%4JX#JbHwrim&Jjgs6Wz00QJTo*qQn5fli@m+Q zcsuLn8s=1<*N~9yc^m>`UWlFHTVlxu_pJ(=vCnoAPn6I3Eo*@C&uW|OMAQG`uOxfP=ruj&LVhHLVu%wIQ zdgvS>8}t6CXO#?=3G5Q{od}O4?9c1g80Ih>RSe7H8EpV`^4!ypjg*V*IttW2<*tt1 zSnQ#%VGTU{vd~dMn6Th4Fr7k?RUT$@DzO-t+sH9-XQN52y!&PEfa=kV3DnA}y} zTwKsQV?NN+ikHGJvuZh)=X+tbwf{uF@9^LE>iq-#skp5-1zvjVIUSoiASp~U zdCpmpnPHn+G>z9s>)@B|E87SRL-a&hP#3g&T^|F>uP)|lFKXkc@EU#7x#0{pi_k1S zG2dxoPn?*h6tX4fK+vLb!o|3vTk;)MfL z0t>1aq(9s?lpMNXbDZuj44IFq`(2jAH^C6TwBnQl7V|J8H8MiT0xxkc1OHObt`J9w z70pNDrWL+dx=U_R@b<_Wm{LObQ7AF>C}gOtbV~IY2reRSQuA|g{*zNKcHTU1DO({S zsU4G(Z+p)bKZ*>|+I7JeX!xp;JI~QitwFQ!8 zm`JT+kr&(4@ql1n!gMZBjASrjXI|~UFAp$2%Js%>V90}|RRYSyS|!vG2zJ%gntynX z4|#Tu${O?^qw^cC^>_DNyGXCC!CWvxdkyd4f9;2x$ zFeMjd@wIeFQ8Dc$a|b_^0}QLAbpt=Ml8!3RqyPA|e*zBMD?89vOCK~ztAmAwg-f5M z=-Dpc4m6xjlB5^H2M75v(2|Kwy_EFyBr#{RfkI&!Z_H(6c0)fm9lWhrK@Gr|*d#m0|^jnF*6#GiuZJd_Sn6EQp3kVIbv@05FO0 zgQ77c`-(QkQWou0af`>x??rXi#VbzCnk)@|hs-I{#HR0F`#g`MHTMC;q&H92kC>~p z9R(a~Eku*>DI(nS%;bKo)8cV><94wkR!So&yT={xPxk(iOP`c@VBLRmr3O7jS$_QR z&J&|Ei1{DHw_hvTZ@A0YD$z25d(Yp=AqAI{A0g|`scnt96WrNETO3PWDhS+7uEI?X z@Gp8t`!-da<~%AKp71JLc!D^Ev~wj!nvPtzK!FjtISX^;F$ zZ{hfc8*g6MnNZDp>T}2*Fy~|;Utkp{2)D3v+{3@h04vz|Jh8q}-QRIZqQn$8v-o~_ zI0TYV>Cm&OIX!77AG_UX>~MvTwB~^zXgP3D>deINiz$J0K=-EBh+OSbhRI2MP9QGJ zv&~Y$$QG4VF6JOHLMExLhl=eJf_Ib{nKADQKO`L_)@`;t?8mgXt)qWdrg{ZZ-8ayC zW5>jz)#6RO7bs+lgcxv!^y>8oQ|dq>gGcs@(~cy2eL#R`YtJ(WEC$*Jtz9+1t_FI* zo~wGPr}0epj@wT%y4ErCNSv)wSNFH_aTV_mQZOi}cC2Ca#G26N9nu;ldiI6Gc~uy)M_TYiXOG-x5>I(RyLqtEw(d9@ z@G;C3V)Kw%#U_E*(2wP!?+**BKwpG=-0e~X6gnSDTYYP3pXR~5_v>q38Ua!543EUSYdtPjaS_| zC-kTJwtL~a(k`g`$ULKrZ z{D=ms9EMyDK$1$F;;?tBy5z40TZ>qwDU%k};g z-W^xfm^NmUO@J|8UzYN)n50$M#)qd5R;XH@6ASEdNl6uK?K^bn(AzvCda^Y)usM!> z9#ya&4#<~W@5YqaCI|PDe!Tk5B3;X#K~RA{M?V;Sm_RSOkdTAY4KC~w?hmCYljb(i z9~v&%j>aR^#Xix_~@?A;tQPpG0%(N`_3?-_5qi&VoK~UZ4?*d4UKlkK>;A}}F zTKFR^)}f~2w!5&Fvutlj3=sNI%DhlBm--PGeD1U!mJs{e&UzF_g%XDuZhu5 z>B@tS_|}V>Tp}^?Hcce9rg-nn(H%d={#opt%6l#AI!lFU;XfW_RZY=Chbfd2kV5O; zS4hnwnic(tYgH3^l8{W(kTN{3FJw~Sy6QqK&SV{LpZVIPxiRl|F9P#bK*b|=4+C85Rm%kOFPi<%-YJf{>kXD`8Ip|z)%%vu|Mi9w8eg;^LOOB z*j3WbWvYmsdm^a=BbM0>&5c8kwDPJKg(r|2sDU*}>aqLH0#L`x9kopqt%^MHn%7pPFK3kys_V>{n_ z;NIySFeeiKsZohXXD5R~4*A!Jk6e{ZX5!LLoa*Lcs&>36FzL0g5TiQWz2(|qNDYOO zg0*0$iYh~)Jl0T?4;3NM#!RQyB&U5k73d;{BkpEw4*uo;{7A*TTNwI@f2s1 z+NH^mL>a&8Lzgt4iXMgMc?lxwh&oUqT?g_>*a)p)JpDISG_9~qz9#Vx1;p9Cj-JH^ z5|sCsnjNw2NI2qqvtBAQ-I$Vho<@>1htW<;uap@!lSWN5Wjh3}BC(2?DCC()+81c> zv}rpocn+#udiS3!NC!nF(ID;0Qi@1!shp?jC@j?VBtB^TnVs^ZJe001tb_|?e6Z98 zGU`DFDM|*BR?i{!M7emS9WCt;cdK~XBw@Awkh;|!KYnVL z1)7s#9Rg&kD~S=cO|D0wo8L(Z#fSyRf3nygAiFEk``Z) zKBbfsAz93@c=Gp3L5T};N7sDIlxx+}(;!HaKILc%HUCVRMKGVpCASTyP3bL4sN<>j zEsXLm7jqxOQbVPF6n>4z9xZ==WkZWDiaz9Kei}v~FOJ~^t@V-qn6T06afcm-OKHG{l)}gUL|(5APd9M^_}@(x@q_|?4>g!ls!hva zI~OSp?6>LG##856dkovlbb-nsqmNc#^}AqZk`;phsu%??H_AQnnZWPx@Nn9kQ%hn! zmAQc$GH*CU-O+&hQls(rpEY{n29zW$V>m=y+wt#9X$KTg(+XHrpB`Fb{w^S zynJ3=x2eoPM#=!1_Sw9qgULltBK1s}?gs|{Bbz3f1nW`vmqdrqa3D$m%3hZ0j~aLO znL$yUgwY+|-6wh}EKL9B z-4|*enrWY<(yg5C9~lHW>r0>RpZpeYX1V62EBBo}M&z#4o|B`P?C?qa$BX~`pH\n", "**Date created:** 2023/09/14
\n", - "**Last modified:** 2023/09/14
\n", + "**Last modified:** 2024/01/06
\n", "**Description:** Use pre-trained nlp models for multiplechoice task." ] }, @@ -45,9 +45,20 @@ }, "outputs": [], "source": [ - "import keras_nlp\n", + "!pip install -q keras-nlp --upgrade" + ] + }, + { + "cell_type": "code", + "execution_count": 0, + "metadata": { + "colab_type": "code" + }, + "outputs": [], + "source": [ "import keras\n", - "import tensorflow as tf # For tf.data only.\n", + "import keras_nlp\n", + "import tensorflow as tf\n", "\n", "import numpy as np\n", "import pandas as pd\n", @@ -856,9 +867,9 @@ " question = row.startphrase\n", " pred_answer = f\"ending{pred_answers[i]}\"\n", " true_answer = f\"ending{true_answers[i]}\"\n", - " print(f\"\u2753 Sentence {i+1}:\\n{question}\\n\")\n", - " print(f\"\u2705 True Ending: {true_answer}\\n >> {row[true_answer]}\\n\")\n", - " print(f\"\ud83e\udd16 Predicted Ending: {pred_answer}\\n >> {row[pred_answer]}\\n\")\n", + " print(f\"\u2753 Sentence {i+1}:\\n{question}\\n\")\n", + " print(f\"\u2705 True Ending: {true_answer}\\n >> {row[true_answer]}\\n\")\n", + " print(f\"\ud83e\udd16 Predicted Ending: {pred_answer}\\n >> {row[pred_answer]}\\n\")\n", " print(\"-\" * 90, \"\\n\")" ] }, diff --git a/examples/nlp/md/multiple_choice_task_with_transfer_learning.md b/examples/nlp/md/multiple_choice_task_with_transfer_learning.md index c682d6fade..a68d80cac5 100644 --- a/examples/nlp/md/multiple_choice_task_with_transfer_learning.md +++ b/examples/nlp/md/multiple_choice_task_with_transfer_learning.md @@ -2,7 +2,7 @@ **Author:** Md Awsafur Rahman
**Date created:** 2023/09/14
-**Last modified:** 2023/09/14
+**Last modified:** 2024/01/06
**Description:** Use pre-trained nlp models for multiplechoice task. @@ -23,9 +23,14 @@ unlike question answering. We will use SWAG dataset to demonstrate this example. ```python -import keras_nlp +!pip install -q keras-nlp --upgrade +``` + + +```python import keras -import tensorflow as tf # For tf.data only. +import keras_nlp +import tensorflow as tf import numpy as np import pandas as pd @@ -33,6 +38,12 @@ import pandas as pd import matplotlib.pyplot as plt ``` +
+``` +Using TensorFlow backend + +``` +
--- ## Dataset In this example we'll use **SWAG** dataset for multiplechoice task. @@ -45,29 +56,55 @@ In this example we'll use **SWAG** dataset for multiplechoice task.
``` ---2023-11-13 20:05:24-- https://github.com/rowanz/swagaf/archive/refs/heads/master.zip -Resolving github.com (github.com)... 192.30.255.113 -Connecting to github.com (github.com)|192.30.255.113|:443... connected. -HTTP request sent, awaiting response... 302 Found +--2024-01-07 05:21:33-- https://github.com/rowanz/swagaf/archive/refs/heads/master.zip +Resolving github.com (github.com)... 140.82.112.3 +Connecting to github.com (github.com)|140.82.112.3|:443... + +connected. + +HTTP request sent, awaiting response... + +302 Found Location: https://codeload.github.com/rowanz/swagaf/zip/refs/heads/master [following] ---2023-11-13 20:05:25-- https://codeload.github.com/rowanz/swagaf/zip/refs/heads/master -Resolving codeload.github.com (codeload.github.com)... 20.29.134.24 -Connecting to codeload.github.com (codeload.github.com)|20.29.134.24|:443... connected. -HTTP request sent, awaiting response... 200 OK +--2024-01-07 05:21:33-- https://codeload.github.com/rowanz/swagaf/zip/refs/heads/master +Resolving codeload.github.com (codeload.github.com)... 140.82.112.9 +Connecting to codeload.github.com (codeload.github.com)|140.82.112.9|:443... + +connected. + +HTTP request sent, awaiting response... + +200 OK Length: unspecified [application/zip] Saving to: ‘swag.zip’ ```
-
-``` -swag.zip [ <=> ] 19.94M 4.25MB/s in 4.7s -``` -
+ +swag.zip [<=> ] 0 --.-KB/s + + +swag.zip [ <=> ] 84.24K 229KB/s + + +swag.zip [ <=> ] 1.46M 2.44MB/s + + +swag.zip [ <=> ] 2.20M 1.48MB/s + + +swag.zip [ <=> ] 8.59M 3.16MB/s + + +swag.zip [ <=> ] 15.40M 4.96MB/s + + +swag.zip [ <=> ] 17.54M 5.05MB/s +swag.zip [ <=> ] 19.94M 5.71MB/s in 3.5s
``` -2023-11-13 20:05:30 (4.25 MB/s) - ‘swag.zip’ saved [20905751] +2024-01-07 05:21:37 (5.71 MB/s) - ‘swag.zip’ saved [20905751] ```
@@ -209,6 +246,37 @@ preprocessor = keras_nlp.models.DebertaV3Preprocessor.from_preset( ) ``` +
+``` +Downloading from https://www.kaggle.com/api/v1/models/keras/deberta_v3/keras/deberta_v3_extra_small_en/2/download/tokenizer.json... + +``` +
+ + 0%| | 0.00/424 [00:00 +``` +Downloading from https://www.kaggle.com/api/v1/models/keras/deberta_v3/keras/deberta_v3_extra_small_en/2/download/assets/tokenizer/vocabulary.spm... + +``` + + + 0%| | 0.00/2.35M [00:00 ``` -CUDA backend failed to initialize: Found CUDA version 12010, but JAX was built against version 12020, which is newer. The copy of CUDA that is installed must be at least as new as the version against which JAX was built. (Set TF_CPP_MIN_LOG_LEVEL=0 and rerun for more info.) - token_ids : (4, 200) padding_mask : (4, 200) @@ -418,7 +484,7 @@ _ = get_lr_callback(CFG.batch_size, plot=True) -![png](/img/examples/nlp/multiple_choice_task_with_transfer_learning/multiple_choice_task_with_transfer_learning_32_0.png) +![png](/img/examples/nlp/multiple_choice_task_with_transfer_learning/multiple_choice_task_with_transfer_learning_33_0.png) @@ -572,6 +638,205 @@ def build_model(): model = build_model() ``` +
+``` +Downloading from https://www.kaggle.com/api/v1/models/keras/deberta_v3/keras/deberta_v3_extra_small_en/2/download/config.json... + +``` +
+ + 0%| | 0.00/539 [00:00 +``` +Downloading from https://www.kaggle.com/api/v1/models/keras/deberta_v3/keras/deberta_v3_extra_small_en/2/download/model.weights.h5... + +``` + + + 0%| | 0.00/270M [00:00 +``` +/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/backbone.py:37: UserWarning: `Model.state_updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. + return id(getattr(self, attr)) not in self._functional_layer_ids +/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/backbone.py:37: UserWarning: `layer.updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. + return id(getattr(self, attr)) not in self._functional_layer_ids + +``` + Let's checkout the model summary to have a better insight on the model. @@ -579,84 +844,112 @@ Let's checkout the model summary to have a better insight on the model. model.summary() ``` +
+``` +Model: "model" + +__________________________________________________________________________________________________ + + Layer (type) Output Shape Param # Connected to + +================================================================================================== + + padding_mask (InputLayer) [(None, 4, None)] 0 [] + + + + token_ids (InputLayer) [(None, 4, None)] 0 [] + + + + padding_mask_0 (SelectOpti (None, None) 0 ['padding_mask[0][0]'] + + on) + + + + token_ids_0 (SelectOption) (None, None) 0 ['token_ids[0][0]'] + + + + padding_mask_1 (SelectOpti (None, None) 0 ['padding_mask[0][0]'] + + on) + + + + token_ids_1 (SelectOption) (None, None) 0 ['token_ids[0][0]'] + + + + padding_mask_2 (SelectOpti (None, None) 0 ['padding_mask[0][0]'] + + on) + + + + token_ids_2 (SelectOption) (None, None) 0 ['token_ids[0][0]'] + + + + padding_mask_3 (SelectOpti (None, None) 0 ['padding_mask[0][0]'] + + on) + + + + token_ids_3 (SelectOption) (None, None) 0 ['token_ids[0][0]'] + + + + deberta_v3_classifier (Deb (None, 1) 7083033 ['padding_mask_0[0][0]', -
Model: "functional_1"
-
+ ertaV3Classifier) 7 'token_ids_0[0][0]', + 'padding_mask_1[0][0]', + 'token_ids_1[0][0]', + 'padding_mask_2[0][0]', -
┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┓
-┃ Layer (type)        ┃ Output Shape      ┃ Param # ┃ Connected to         ┃
-┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━┩
-│ padding_mask        │ (None, 4, None)   │       0 │ -                    │
-│ (InputLayer)        │                   │         │                      │
-├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
-│ token_ids           │ (None, 4, None)   │       0 │ -                    │
-│ (InputLayer)        │                   │         │                      │
-├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
-│ padding_mask_0      │ (None, None)      │       0 │ padding_mask[0][0]   │
-│ (SelectOption)      │                   │         │                      │
-├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
-│ token_ids_0         │ (None, None)      │       0 │ token_ids[0][0]      │
-│ (SelectOption)      │                   │         │                      │
-├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
-│ padding_mask_1      │ (None, None)      │       0 │ padding_mask[0][0]   │
-│ (SelectOption)      │                   │         │                      │
-├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
-│ token_ids_1         │ (None, None)      │       0 │ token_ids[0][0]      │
-│ (SelectOption)      │                   │         │                      │
-├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
-│ padding_mask_2      │ (None, None)      │       0 │ padding_mask[0][0]   │
-│ (SelectOption)      │                   │         │                      │
-├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
-│ token_ids_2         │ (None, None)      │       0 │ token_ids[0][0]      │
-│ (SelectOption)      │                   │         │                      │
-├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
-│ padding_mask_3      │ (None, None)      │       0 │ padding_mask[0][0]   │
-│ (SelectOption)      │                   │         │                      │
-├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
-│ token_ids_3         │ (None, None)      │       0 │ token_ids[0][0]      │
-│ (SelectOption)      │                   │         │                      │
-├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
-│ deberta_v3_classif… │ (None, 1)         │ 70,830… │ padding_mask_0[0][0… │
-│ (DebertaV3Classifi… │                   │         │ token_ids_0[0][0],   │
-│                     │                   │         │ padding_mask_1[0][0… │
-│                     │                   │         │ token_ids_1[0][0],   │
-│                     │                   │         │ padding_mask_2[0][0… │
-│                     │                   │         │ token_ids_2[0][0],   │
-│                     │                   │         │ padding_mask_3[0][0… │
-│                     │                   │         │ token_ids_3[0][0]    │
-├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
-│ concatenate         │ (None, 4)         │       0 │ deberta_v3_classifi… │
-│ (Concatenate)       │                   │         │ deberta_v3_classifi… │
-│                     │                   │         │ deberta_v3_classifi… │
-│                     │                   │         │ deberta_v3_classifi… │
-├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
-│ softmax (Softmax)   │ (None, 4)         │       0 │ concatenate[0][0]    │
-└─────────────────────┴───────────────────┴─────────┴──────────────────────┘
-
+ 'token_ids_2[0][0]', + 'padding_mask_3[0][0]', + 'token_ids_3[0][0]'] + -
 Total params: 70,830,337 (270.20 MB)
-
+ concatenate (Concatenate) (None, 4) 0 ['deberta_v3_classifier[0][0]' + , 'deberta_v3_classifier[1][0] + ', + 'deberta_v3_classifier[2][0]' -
 Trainable params: 70,830,337 (270.20 MB)
-
+ , 'deberta_v3_classifier[3][0] + '] + + softmax (Softmax) (None, 4) 0 ['concatenate[0][0]'] -
 Non-trainable params: 0 (0.00 B)
-
+ +================================================================================================== +Total params: 70830337 (270.20 MB) +Trainable params: 70830337 (270.20 MB) + +Non-trainable params: 0 (0.00 Byte) + +__________________________________________________________________________________________________ + +``` +
Finally, let's check the model structure visually if everything is in place. @@ -668,7 +961,7 @@ keras.utils.plot_model(model, show_shapes=True) -![png](/img/examples/nlp/multiple_choice_task_with_transfer_learning/multiple_choice_task_with_transfer_learning_42_0.png) +![png](/img/examples/nlp/multiple_choice_task_with_transfer_learning/multiple_choice_task_with_transfer_learning_43_0.png) @@ -692,33 +985,6485 @@ history = model.fit(
``` Epoch 1/5 - 183/183 ━━━━━━━━━━━━━━━━━━━━ 5087s 25s/step - accuracy: 0.2563 - loss: 1.3884 - val_accuracy: 0.5150 - val_loss: 1.3742 - learning_rate: 1.0000e-06 -Epoch 2/5 - 183/183 ━━━━━━━━━━━━━━━━━━━━ 4529s 25s/step - accuracy: 0.3825 - loss: 1.3364 - val_accuracy: 0.7125 - val_loss: 0.9071 - learning_rate: 2.9000e-06 -Epoch 3/5 - 183/183 ━━━━━━━━━━━━━━━━━━━━ 4524s 25s/step - accuracy: 0.6144 - loss: 1.0118 - val_accuracy: 0.7425 - val_loss: 0.8017 - learning_rate: 4.8000e-06 -Epoch 4/5 - 183/183 ━━━━━━━━━━━━━━━━━━━━ 4522s 25s/step - accuracy: 0.6744 - loss: 0.8460 - val_accuracy: 0.7625 - val_loss: 0.7323 - learning_rate: 4.7230e-06 -Epoch 5/5 - 183/183 ━━━━━━━━━━━━━━━━━━━━ 4517s 25s/step - accuracy: 0.7200 - loss: 0.7458 - val_accuracy: 0.7750 - val_loss: 0.7022 - learning_rate: 4.4984e-06 + +WARNING: All log messages before absl::InitializeLog() is called are written to STDERR +I0000 00:00:1704605251.846942 12962 device_compiler.h:186] Compiled cluster using XLA! This line is logged at most once for the lifetime of the process. ```
---- -## Inference - + + 1/183 [..............................] - ETA: 16:51:51 - loss: 1.3865 - accuracy: 0.3750 -```python -# Make predictions using the trained model on last validation data -predictions = model.predict( - valid_ds, - batch_size=CFG.batch_size, # max batch size = valid size - verbose=1, -) +
+``` + +``` +
+ 2/183 [..............................] - ETA: 44:52 - loss: 1.3652 - accuracy: 0.3750 -# Format predictions and true answers -pred_answers = np.arange(4)[np.argsort(-predictions)][:, 0] -true_answers = valid_df.label.values +
+``` + +``` +
+ 3/183 [..............................] - ETA: 44:29 - loss: 1.3851 - accuracy: 0.2500 + +
+``` + +``` +
+ 4/183 [..............................] - ETA: 44:12 - loss: 1.3875 - accuracy: 0.2188 + +
+``` + +``` +
+ 5/183 [..............................] - ETA: 43:54 - loss: 1.3896 - accuracy: 0.2000 + +
+``` + +``` +
+ 6/183 [..............................] - ETA: 43:41 - loss: 1.3942 - accuracy: 0.1875 + +
+``` + +``` +
+ 7/183 [>.............................] - ETA: 43:25 - loss: 1.3928 - accuracy: 0.2143 + +
+``` + +``` +
+ 8/183 [>.............................] - ETA: 43:22 - loss: 1.3933 - accuracy: 0.2031 + +
+``` + +``` +
+ 9/183 [>.............................] - ETA: 42:54 - loss: 1.3934 - accuracy: 0.2083 + +
+``` + +``` +
+ 10/183 [>.............................] - ETA: 42:27 - loss: 1.3901 - accuracy: 0.2375 + +
+``` + +``` +
+ 11/183 [>.............................] - ETA: 42:04 - loss: 1.3898 - accuracy: 0.2500 + +
+``` + +``` +
+ 12/183 [>.............................] - ETA: 41:42 - loss: 1.3903 - accuracy: 0.2396 + +
+``` + +``` +
+ 13/183 [=>............................] - ETA: 41:21 - loss: 1.3900 - accuracy: 0.2500 + +
+``` + +``` +
+ 14/183 [=>............................] - ETA: 41:02 - loss: 1.3908 - accuracy: 0.2321 + +
+``` + +``` +
+ 15/183 [=>............................] - ETA: 40:45 - loss: 1.3919 - accuracy: 0.2167 + +
+``` + +``` +
+ 16/183 [=>............................] - ETA: 40:26 - loss: 1.3927 - accuracy: 0.2109 + +
+``` + +``` +
+ 17/183 [=>............................] - ETA: 40:08 - loss: 1.3935 - accuracy: 0.2132 + +
+``` + +``` +
+ 18/183 [=>............................] - ETA: 39:51 - loss: 1.3920 - accuracy: 0.2153 + +
+``` + +``` +
+ 19/183 [==>...........................] - ETA: 39:34 - loss: 1.3905 - accuracy: 0.2171 + +
+``` + +``` +
+ 20/183 [==>...........................] - ETA: 39:16 - loss: 1.3900 - accuracy: 0.2188 + +
+``` + +``` +
+ 21/183 [==>...........................] - ETA: 39:01 - loss: 1.3908 - accuracy: 0.2202 + +
+``` + +``` +
+ 22/183 [==>...........................] - ETA: 38:44 - loss: 1.3915 - accuracy: 0.2159 + +
+``` + +``` +
+ 23/183 [==>...........................] - ETA: 38:28 - loss: 1.3892 - accuracy: 0.2391 + +
+``` + +``` +
+ 24/183 [==>...........................] - ETA: 38:12 - loss: 1.3891 - accuracy: 0.2396 + +
+``` + +``` +
+ 25/183 [===>..........................] - ETA: 37:56 - loss: 1.3893 - accuracy: 0.2350 + +
+``` + +``` +
+ 26/183 [===>..........................] - ETA: 37:40 - loss: 1.3893 - accuracy: 0.2404 + +
+``` + +``` +
+ 27/183 [===>..........................] - ETA: 37:25 - loss: 1.3886 - accuracy: 0.2454 + +
+``` + +``` +
+ 28/183 [===>..........................] - ETA: 37:09 - loss: 1.3880 - accuracy: 0.2455 + +
+``` + +``` +
+ 29/183 [===>..........................] - ETA: 36:55 - loss: 1.3874 - accuracy: 0.2457 + +
+``` + +``` +
+ 30/183 [===>..........................] - ETA: 36:39 - loss: 1.3877 - accuracy: 0.2458 + +
+``` + +``` +
+ 31/183 [====>.........................] - ETA: 36:23 - loss: 1.3870 - accuracy: 0.2540 + +
+``` + +``` +
+ 32/183 [====>.........................] - ETA: 36:08 - loss: 1.3870 - accuracy: 0.2578 + +
+``` + +``` +
+ 33/183 [====>.........................] - ETA: 35:53 - loss: 1.3870 - accuracy: 0.2538 + +
+``` + +``` +
+ 34/183 [====>.........................] - ETA: 35:38 - loss: 1.3882 - accuracy: 0.2500 + +
+``` + +``` +
+ 35/183 [====>.........................] - ETA: 35:23 - loss: 1.3876 - accuracy: 0.2536 + +
+``` + +``` +
+ 36/183 [====>.........................] - ETA: 35:07 - loss: 1.3878 - accuracy: 0.2500 + +
+``` + +``` +
+ 37/183 [=====>........................] - ETA: 34:53 - loss: 1.3871 - accuracy: 0.2568 + +
+``` + +``` +
+ 38/183 [=====>........................] - ETA: 34:38 - loss: 1.3875 - accuracy: 0.2566 + +
+``` + +``` +
+ 39/183 [=====>........................] - ETA: 34:22 - loss: 1.3875 - accuracy: 0.2564 + +
+``` + +``` +
+ 40/183 [=====>........................] - ETA: 34:07 - loss: 1.3875 - accuracy: 0.2531 + +
+``` + +``` +
+ 41/183 [=====>........................] - ETA: 33:52 - loss: 1.3874 - accuracy: 0.2530 + +
+``` + +``` +
+ 42/183 [=====>........................] - ETA: 33:38 - loss: 1.3886 - accuracy: 0.2500 + +
+``` + +``` +
+ 43/183 [======>.......................] - ETA: 33:23 - loss: 1.3876 - accuracy: 0.2529 + +
+``` + +``` +
+ 44/183 [======>.......................] - ETA: 33:08 - loss: 1.3876 - accuracy: 0.2557 + +
+``` + +``` +
+ 45/183 [======>.......................] - ETA: 32:54 - loss: 1.3875 - accuracy: 0.2583 + +
+``` + +``` +
+ 46/183 [======>.......................] - ETA: 32:39 - loss: 1.3875 - accuracy: 0.2582 + +
+``` + +``` +
+ 47/183 [======>.......................] - ETA: 32:24 - loss: 1.3873 - accuracy: 0.2553 + +
+``` + +``` +
+ 48/183 [======>.......................] - ETA: 32:09 - loss: 1.3866 - accuracy: 0.2604 + +
+``` + +``` +
+ 49/183 [=======>......................] - ETA: 31:54 - loss: 1.3870 - accuracy: 0.2602 + +
+``` + +``` +
+ 50/183 [=======>......................] - ETA: 31:40 - loss: 1.3869 - accuracy: 0.2600 + +
+``` + +``` +
+ 51/183 [=======>......................] - ETA: 31:25 - loss: 1.3862 - accuracy: 0.2647 + +
+``` + +``` +
+ 52/183 [=======>......................] - ETA: 31:10 - loss: 1.3865 - accuracy: 0.2596 + +
+``` + +``` +
+ 53/183 [=======>......................] - ETA: 30:56 - loss: 1.3869 - accuracy: 0.2571 + +
+``` + +``` +
+ 54/183 [=======>......................] - ETA: 30:41 - loss: 1.3869 - accuracy: 0.2546 + +
+``` + +``` +
+ 55/183 [========>.....................] - ETA: 30:27 - loss: 1.3866 - accuracy: 0.2591 + +
+``` + +``` +
+ 56/183 [========>.....................] - ETA: 30:12 - loss: 1.3869 - accuracy: 0.2589 + +
+``` + +``` +
+ 57/183 [========>.....................] - ETA: 29:58 - loss: 1.3861 - accuracy: 0.2632 + +
+``` + +``` +
+ 58/183 [========>.....................] - ETA: 29:43 - loss: 1.3857 - accuracy: 0.2651 + +
+``` + +``` +
+ 59/183 [========>.....................] - ETA: 29:29 - loss: 1.3854 - accuracy: 0.2669 + +
+``` + +``` +
+ 60/183 [========>.....................] - ETA: 29:14 - loss: 1.3854 - accuracy: 0.2688 + +
+``` + +``` +
+ 61/183 [=========>....................] - ETA: 29:00 - loss: 1.3852 - accuracy: 0.2705 + +
+``` + +``` +
+ 62/183 [=========>....................] - ETA: 28:45 - loss: 1.3851 - accuracy: 0.2702 + +
+``` + +``` +
+ 63/183 [=========>....................] - ETA: 28:31 - loss: 1.3855 - accuracy: 0.2679 + +
+``` + +``` +
+ 64/183 [=========>....................] - ETA: 28:17 - loss: 1.3857 - accuracy: 0.2656 + +
+``` + +``` +
+ 65/183 [=========>....................] - ETA: 28:02 - loss: 1.3867 - accuracy: 0.2615 + +
+``` + +``` +
+ 66/183 [=========>....................] - ETA: 27:48 - loss: 1.3868 - accuracy: 0.2614 + +
+``` + +``` +
+ 67/183 [=========>....................] - ETA: 27:34 - loss: 1.3868 - accuracy: 0.2631 + +
+``` + +``` +
+ 68/183 [==========>...................] - ETA: 27:19 - loss: 1.3864 - accuracy: 0.2610 + +
+``` + +``` +
+ 69/183 [==========>...................] - ETA: 27:05 - loss: 1.3864 - accuracy: 0.2591 + +
+``` + +``` +
+ 70/183 [==========>...................] - ETA: 26:51 - loss: 1.3860 - accuracy: 0.2607 + +
+``` + +``` +
+ 71/183 [==========>...................] - ETA: 26:36 - loss: 1.3866 - accuracy: 0.2570 + +
+``` + +``` +
+ 72/183 [==========>...................] - ETA: 26:22 - loss: 1.3858 - accuracy: 0.2622 + +
+``` + +``` +
+ 73/183 [==========>...................] - ETA: 26:07 - loss: 1.3854 - accuracy: 0.2637 + +
+``` + +``` +
+ 74/183 [===========>..................] - ETA: 25:53 - loss: 1.3858 - accuracy: 0.2601 + +
+``` + +``` +
+ 75/183 [===========>..................] - ETA: 25:39 - loss: 1.3859 - accuracy: 0.2583 + +
+``` + +``` +
+ 76/183 [===========>..................] - ETA: 25:24 - loss: 1.3859 - accuracy: 0.2599 + +
+``` + +``` +
+ 77/183 [===========>..................] - ETA: 25:10 - loss: 1.3860 - accuracy: 0.2597 + +
+``` + +``` +
+ 78/183 [===========>..................] - ETA: 24:55 - loss: 1.3862 - accuracy: 0.2580 + +
+``` + +``` +
+ 79/183 [===========>..................] - ETA: 24:41 - loss: 1.3855 - accuracy: 0.2611 + +
+``` + +``` +
+ 80/183 [============>.................] - ETA: 24:27 - loss: 1.3857 - accuracy: 0.2625 + +
+``` + +``` +
+ 81/183 [============>.................] - ETA: 24:12 - loss: 1.3853 - accuracy: 0.2639 + +
+``` + +``` +
+ 82/183 [============>.................] - ETA: 23:58 - loss: 1.3854 - accuracy: 0.2622 + +
+``` + +``` +
+ 83/183 [============>.................] - ETA: 23:43 - loss: 1.3854 - accuracy: 0.2636 + +
+``` + +``` +
+ 84/183 [============>.................] - ETA: 23:29 - loss: 1.3857 - accuracy: 0.2634 + +
+``` + +``` +
+ 85/183 [============>.................] - ETA: 23:15 - loss: 1.3853 - accuracy: 0.2647 + +
+``` + +``` +
+ 86/183 [=============>................] - ETA: 23:00 - loss: 1.3852 - accuracy: 0.2689 + +
+``` + +``` +
+ 87/183 [=============>................] - ETA: 22:46 - loss: 1.3852 - accuracy: 0.2687 + +
+``` + +``` +
+ 88/183 [=============>................] - ETA: 22:32 - loss: 1.3852 - accuracy: 0.2685 + +
+``` + +``` +
+ 89/183 [=============>................] - ETA: 22:17 - loss: 1.3852 - accuracy: 0.2711 + +
+``` + +``` +
+ 90/183 [=============>................] - ETA: 22:03 - loss: 1.3852 - accuracy: 0.2694 + +
+``` + +``` +
+ 91/183 [=============>................] - ETA: 21:49 - loss: 1.3851 - accuracy: 0.2720 + +
+``` + +``` +
+ 92/183 [==============>...............] - ETA: 21:35 - loss: 1.3851 - accuracy: 0.2717 + +
+``` + +``` +
+ 93/183 [==============>...............] - ETA: 21:20 - loss: 1.3853 - accuracy: 0.2702 + +
+``` + +``` +
+ 94/183 [==============>...............] - ETA: 21:06 - loss: 1.3856 - accuracy: 0.2699 + +
+``` + +``` +
+ 95/183 [==============>...............] - ETA: 20:52 - loss: 1.3855 - accuracy: 0.2711 + +
+``` + +``` +
+ 96/183 [==============>...............] - ETA: 20:37 - loss: 1.3856 - accuracy: 0.2695 + +
+``` + +``` +
+ 97/183 [==============>...............] - ETA: 20:23 - loss: 1.3855 - accuracy: 0.2706 + +
+``` + +``` +
+ 98/183 [===============>..............] - ETA: 20:09 - loss: 1.3852 - accuracy: 0.2730 + +
+``` + +``` +
+ 99/183 [===============>..............] - ETA: 19:54 - loss: 1.3853 - accuracy: 0.2715 + +
+``` + +``` +
+100/183 [===============>..............] - ETA: 19:40 - loss: 1.3854 - accuracy: 0.2713 + +
+``` + +``` +
+101/183 [===============>..............] - ETA: 19:26 - loss: 1.3856 - accuracy: 0.2698 + +
+``` + +``` +
+102/183 [===============>..............] - ETA: 19:12 - loss: 1.3856 - accuracy: 0.2684 + +
+``` + +``` +
+103/183 [===============>..............] - ETA: 18:57 - loss: 1.3854 - accuracy: 0.2694 + +
+``` + +``` +
+104/183 [================>.............] - ETA: 18:43 - loss: 1.3852 - accuracy: 0.2716 + +
+``` + +``` +
+105/183 [================>.............] - ETA: 18:29 - loss: 1.3854 - accuracy: 0.2714 + +
+``` + +``` +
+106/183 [================>.............] - ETA: 18:15 - loss: 1.3851 - accuracy: 0.2748 + +
+``` + +``` +
+107/183 [================>.............] - ETA: 18:00 - loss: 1.3852 - accuracy: 0.2745 + +
+``` + +``` +
+108/183 [================>.............] - ETA: 17:46 - loss: 1.3853 - accuracy: 0.2720 + +
+``` + +``` +
+109/183 [================>.............] - ETA: 17:32 - loss: 1.3854 - accuracy: 0.2718 + +
+``` + +``` +
+110/183 [=================>............] - ETA: 17:18 - loss: 1.3855 - accuracy: 0.2716 + +
+``` + +``` +
+111/183 [=================>............] - ETA: 17:03 - loss: 1.3856 - accuracy: 0.2703 + +
+``` + +``` +
+112/183 [=================>............] - ETA: 16:49 - loss: 1.3859 - accuracy: 0.2701 + +
+``` + +``` +
+113/183 [=================>............] - ETA: 16:35 - loss: 1.3859 - accuracy: 0.2699 + +
+``` + +``` +
+114/183 [=================>............] - ETA: 16:21 - loss: 1.3859 - accuracy: 0.2697 + +
+``` + +``` +
+115/183 [=================>............] - ETA: 16:06 - loss: 1.3862 - accuracy: 0.2707 + +
+``` + +``` +
+116/183 [==================>...........] - ETA: 15:52 - loss: 1.3858 - accuracy: 0.2737 + +
+``` + +``` +
+117/183 [==================>...........] - ETA: 15:38 - loss: 1.3857 - accuracy: 0.2746 + +
+``` + +``` +
+118/183 [==================>...........] - ETA: 15:24 - loss: 1.3856 - accuracy: 0.2744 + +
+``` + +``` +
+119/183 [==================>...........] - ETA: 15:09 - loss: 1.3858 - accuracy: 0.2731 + +
+``` + +``` +
+120/183 [==================>...........] - ETA: 14:55 - loss: 1.3861 - accuracy: 0.2719 + +
+``` + +``` +
+121/183 [==================>...........] - ETA: 14:41 - loss: 1.3862 - accuracy: 0.2707 + +
+``` + +``` +
+122/183 [===================>..........] - ETA: 14:27 - loss: 1.3862 - accuracy: 0.2705 + +
+``` + +``` +
+123/183 [===================>..........] - ETA: 14:12 - loss: 1.3861 - accuracy: 0.2703 + +
+``` + +``` +
+124/183 [===================>..........] - ETA: 13:58 - loss: 1.3860 - accuracy: 0.2692 + +
+``` + +``` +
+125/183 [===================>..........] - ETA: 13:44 - loss: 1.3861 - accuracy: 0.2670 + +
+``` + +``` +
+126/183 [===================>..........] - ETA: 13:30 - loss: 1.3860 - accuracy: 0.2679 + +
+``` + +``` +
+127/183 [===================>..........] - ETA: 13:15 - loss: 1.3858 - accuracy: 0.2677 + +
+``` + +``` +
+128/183 [===================>..........] - ETA: 13:01 - loss: 1.3856 - accuracy: 0.2715 + +
+``` + +``` +
+129/183 [====================>.........] - ETA: 12:47 - loss: 1.3855 - accuracy: 0.2723 + +
+``` + +``` +
+130/183 [====================>.........] - ETA: 12:33 - loss: 1.3854 - accuracy: 0.2731 + +
+``` + +``` +
+131/183 [====================>.........] - ETA: 12:19 - loss: 1.3854 - accuracy: 0.2719 + +
+``` + +``` +
+132/183 [====================>.........] - ETA: 12:04 - loss: 1.3854 - accuracy: 0.2718 + +
+``` + +``` +
+133/183 [====================>.........] - ETA: 11:50 - loss: 1.3854 - accuracy: 0.2707 + +
+``` + +``` +
+134/183 [====================>.........] - ETA: 11:36 - loss: 1.3854 - accuracy: 0.2705 + +
+``` + +``` +
+135/183 [=====================>........] - ETA: 11:22 - loss: 1.3853 - accuracy: 0.2694 + +
+``` + +``` +
+136/183 [=====================>........] - ETA: 11:07 - loss: 1.3854 - accuracy: 0.2693 + +
+``` + +``` +
+137/183 [=====================>........] - ETA: 10:53 - loss: 1.3854 - accuracy: 0.2710 + +
+``` + +``` +
+138/183 [=====================>........] - ETA: 10:39 - loss: 1.3856 - accuracy: 0.2717 + +
+``` + +``` +
+139/183 [=====================>........] - ETA: 10:25 - loss: 1.3855 - accuracy: 0.2743 + +
+``` + +``` +
+140/183 [=====================>........] - ETA: 10:10 - loss: 1.3853 - accuracy: 0.2741 + +
+``` + +``` +
+141/183 [======================>.......] - ETA: 9:56 - loss: 1.3854 - accuracy: 0.2730 + +
+``` + +``` +
+142/183 [======================>.......] - ETA: 9:42 - loss: 1.3854 - accuracy: 0.2720 + +
+``` + +``` +
+143/183 [======================>.......] - ETA: 9:28 - loss: 1.3852 - accuracy: 0.2719 + +
+``` + +``` +
+144/183 [======================>.......] - ETA: 9:14 - loss: 1.3852 - accuracy: 0.2717 + +
+``` + +``` +
+145/183 [======================>.......] - ETA: 8:59 - loss: 1.3852 - accuracy: 0.2724 + +
+``` + +``` +
+146/183 [======================>.......] - ETA: 8:45 - loss: 1.3853 - accuracy: 0.2723 + +
+``` + +``` +
+147/183 [=======================>......] - ETA: 8:31 - loss: 1.3852 - accuracy: 0.2730 + +
+``` + +``` +
+148/183 [=======================>......] - ETA: 8:17 - loss: 1.3852 - accuracy: 0.2736 + +
+``` + +``` +
+149/183 [=======================>......] - ETA: 8:03 - loss: 1.3851 - accuracy: 0.2743 + +
+``` + +``` +
+150/183 [=======================>......] - ETA: 7:48 - loss: 1.3848 - accuracy: 0.2758 + +
+``` + +``` +
+151/183 [=======================>......] - ETA: 7:34 - loss: 1.3847 - accuracy: 0.2757 + +
+``` + +``` +
+152/183 [=======================>......] - ETA: 7:20 - loss: 1.3847 - accuracy: 0.2755 + +
+``` + +``` +
+153/183 [========================>.....] - ETA: 7:06 - loss: 1.3847 - accuracy: 0.2753 + +
+``` + +``` +
+154/183 [========================>.....] - ETA: 6:52 - loss: 1.3848 - accuracy: 0.2744 + +
+``` + +``` +
+155/183 [========================>.....] - ETA: 6:37 - loss: 1.3847 - accuracy: 0.2742 + +
+``` + +``` +
+156/183 [========================>.....] - ETA: 6:23 - loss: 1.3848 - accuracy: 0.2740 + +
+``` + +``` +
+157/183 [========================>.....] - ETA: 6:09 - loss: 1.3848 - accuracy: 0.2731 + +
+``` + +``` +
+158/183 [========================>.....] - ETA: 5:55 - loss: 1.3848 - accuracy: 0.2737 + +
+``` + +``` +
+159/183 [=========================>....] - ETA: 5:40 - loss: 1.3848 - accuracy: 0.2752 + +
+``` + +``` +
+160/183 [=========================>....] - ETA: 5:26 - loss: 1.3849 - accuracy: 0.2742 + +
+``` + +``` +
+161/183 [=========================>....] - ETA: 5:12 - loss: 1.3845 - accuracy: 0.2772 + +
+``` + +``` +
+162/183 [=========================>....] - ETA: 4:58 - loss: 1.3847 - accuracy: 0.2770 + +
+``` + +``` +
+163/183 [=========================>....] - ETA: 4:44 - loss: 1.3849 - accuracy: 0.2768 + +
+``` + +``` +
+164/183 [=========================>....] - ETA: 4:29 - loss: 1.3848 - accuracy: 0.2774 + +
+``` + +``` +
+165/183 [==========================>...] - ETA: 4:15 - loss: 1.3848 - accuracy: 0.2780 + +
+``` + +``` +
+166/183 [==========================>...] - ETA: 4:01 - loss: 1.3848 - accuracy: 0.2764 + +
+``` + +``` +
+167/183 [==========================>...] - ETA: 3:47 - loss: 1.3847 - accuracy: 0.2762 + +
+``` + +``` +
+168/183 [==========================>...] - ETA: 3:33 - loss: 1.3848 - accuracy: 0.2753 + +
+``` + +``` +
+169/183 [==========================>...] - ETA: 3:18 - loss: 1.3848 - accuracy: 0.2759 + +
+``` + +``` +
+170/183 [==========================>...] - ETA: 3:04 - loss: 1.3846 - accuracy: 0.2779 + +
+``` + +``` +
+171/183 [===========================>..] - ETA: 2:50 - loss: 1.3849 - accuracy: 0.2770 + +
+``` + +``` +
+172/183 [===========================>..] - ETA: 2:36 - loss: 1.3850 - accuracy: 0.2754 + +
+``` + +``` +
+173/183 [===========================>..] - ETA: 2:22 - loss: 1.3849 - accuracy: 0.2760 + +
+``` + +``` +
+174/183 [===========================>..] - ETA: 2:07 - loss: 1.3849 - accuracy: 0.2766 + +
+``` + +``` +
+175/183 [===========================>..] - ETA: 1:53 - loss: 1.3849 - accuracy: 0.2779 + +
+``` + +``` +
+176/183 [===========================>..] - ETA: 1:39 - loss: 1.3846 - accuracy: 0.2784 + +
+``` + +``` +
+177/183 [============================>.] - ETA: 1:25 - loss: 1.3846 - accuracy: 0.2797 + +
+``` + +``` +
+178/183 [============================>.] - ETA: 1:11 - loss: 1.3844 - accuracy: 0.2809 + +
+``` + +``` +
+179/183 [============================>.] - ETA: 56s - loss: 1.3844 - accuracy: 0.2807 + +
+``` + +``` +
+180/183 [============================>.] - ETA: 42s - loss: 1.3843 - accuracy: 0.2806 + +
+``` + +``` +
+181/183 [============================>.] - ETA: 28s - loss: 1.3843 - accuracy: 0.2818 + +
+``` + +``` +
+182/183 [============================>.] - ETA: 14s - loss: 1.3843 - accuracy: 0.2823 + +
+``` + +``` +
+183/183 [==============================] - ETA: 0s - loss: 1.3842 - accuracy: 0.2828 + +
+``` +/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/task.py:47: UserWarning: `Model.state_updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. + return id(getattr(self, attr)) not in self._functional_layer_ids +/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/task.py:47: UserWarning: `layer.updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. + return id(getattr(self, attr)) not in self._functional_layer_ids +/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/backbone.py:37: UserWarning: `Model.state_updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. + return id(getattr(self, attr)) not in self._functional_layer_ids +/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/backbone.py:37: UserWarning: `layer.updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. + return id(getattr(self, attr)) not in self._functional_layer_ids + + +``` +
+183/183 [==============================] - 3111s 15s/step - loss: 1.3842 - accuracy: 0.2828 - val_loss: 1.3755 - val_accuracy: 0.5225 - lr: 1.0000e-06 + + +
+``` +Epoch 2/5 + +``` +
+ + 1/183 [..............................] - ETA: 46:52 - loss: 1.3583 - accuracy: 0.5000 + +
+``` + +``` +
+ 2/183 [..............................] - ETA: 43:21 - loss: 1.3603 - accuracy: 0.3750 + +
+``` + +``` +
+ 3/183 [..............................] - ETA: 43:12 - loss: 1.3608 - accuracy: 0.3750 + +
+``` + +``` +
+ 4/183 [..............................] - ETA: 42:59 - loss: 1.3601 - accuracy: 0.4062 + +
+``` + +``` +
+ 5/183 [..............................] - ETA: 42:33 - loss: 1.3611 - accuracy: 0.3750 + +
+``` + +``` +
+ 6/183 [..............................] - ETA: 42:14 - loss: 1.3652 - accuracy: 0.3333 + +
+``` + +``` +
+ 7/183 [>.............................] - ETA: 41:54 - loss: 1.3719 - accuracy: 0.2857 + +
+``` + +``` +
+ 8/183 [>.............................] - ETA: 41:38 - loss: 1.3726 - accuracy: 0.2969 + +
+``` + +``` +
+ 9/183 [>.............................] - ETA: 41:22 - loss: 1.3738 - accuracy: 0.2917 + +
+``` + +``` +
+ 10/183 [>.............................] - ETA: 41:05 - loss: 1.3772 - accuracy: 0.2875 + +
+``` + +``` +
+ 11/183 [>.............................] - ETA: 40:54 - loss: 1.3764 - accuracy: 0.2955 + +
+``` + +``` +
+ 12/183 [>.............................] - ETA: 40:37 - loss: 1.3753 - accuracy: 0.3021 + +
+``` + +``` +
+ 13/183 [=>............................] - ETA: 40:22 - loss: 1.3747 - accuracy: 0.3173 + +
+``` + +``` +
+ 14/183 [=>............................] - ETA: 40:06 - loss: 1.3742 - accuracy: 0.3214 + +
+``` + +``` +
+ 15/183 [=>............................] - ETA: 39:50 - loss: 1.3715 - accuracy: 0.3333 + +
+``` + +``` +
+ 16/183 [=>............................] - ETA: 39:34 - loss: 1.3716 - accuracy: 0.3359 + +
+``` + +``` +
+ 17/183 [=>............................] - ETA: 39:19 - loss: 1.3721 - accuracy: 0.3382 + +
+``` + +``` +
+ 18/183 [=>............................] - ETA: 39:03 - loss: 1.3735 - accuracy: 0.3194 + +
+``` + +``` +
+ 19/183 [==>...........................] - ETA: 38:48 - loss: 1.3746 - accuracy: 0.3158 + +
+``` + +``` +
+ 20/183 [==>...........................] - ETA: 38:33 - loss: 1.3740 - accuracy: 0.3250 + +
+``` + +``` +
+ 21/183 [==>...........................] - ETA: 38:18 - loss: 1.3744 - accuracy: 0.3274 + +
+``` + +``` +
+ 22/183 [==>...........................] - ETA: 38:04 - loss: 1.3718 - accuracy: 0.3352 + +
+``` + +``` +
+ 23/183 [==>...........................] - ETA: 37:49 - loss: 1.3711 - accuracy: 0.3424 + +
+``` + +``` +
+ 24/183 [==>...........................] - ETA: 37:34 - loss: 1.3712 - accuracy: 0.3333 + +
+``` + +``` +
+ 25/183 [===>..........................] - ETA: 37:20 - loss: 1.3700 - accuracy: 0.3400 + +
+``` + +``` +
+ 26/183 [===>..........................] - ETA: 37:05 - loss: 1.3709 - accuracy: 0.3365 + +
+``` + +``` +
+ 27/183 [===>..........................] - ETA: 36:51 - loss: 1.3708 - accuracy: 0.3380 + +
+``` + +``` +
+ 28/183 [===>..........................] - ETA: 36:36 - loss: 1.3709 - accuracy: 0.3348 + +
+``` + +``` +
+ 29/183 [===>..........................] - ETA: 36:22 - loss: 1.3708 - accuracy: 0.3362 + +
+``` + +``` +
+ 30/183 [===>..........................] - ETA: 36:07 - loss: 1.3706 - accuracy: 0.3375 + +
+``` + +``` +
+ 31/183 [====>.........................] - ETA: 35:53 - loss: 1.3708 - accuracy: 0.3387 + +
+``` + +``` +
+ 32/183 [====>.........................] - ETA: 35:38 - loss: 1.3699 - accuracy: 0.3359 + +
+``` + +``` +
+ 33/183 [====>.........................] - ETA: 35:24 - loss: 1.3704 - accuracy: 0.3295 + +
+``` + +``` +
+ 34/183 [====>.........................] - ETA: 35:10 - loss: 1.3712 - accuracy: 0.3199 + +
+``` + +``` +
+ 35/183 [====>.........................] - ETA: 34:55 - loss: 1.3718 - accuracy: 0.3214 + +
+``` + +``` +
+ 36/183 [====>.........................] - ETA: 34:41 - loss: 1.3712 - accuracy: 0.3264 + +
+``` + +``` +
+ 37/183 [=====>........................] - ETA: 34:27 - loss: 1.3713 - accuracy: 0.3243 + +
+``` + +``` +
+ 38/183 [=====>........................] - ETA: 34:13 - loss: 1.3701 - accuracy: 0.3289 + +
+``` + +``` +
+ 39/183 [=====>........................] - ETA: 33:58 - loss: 1.3701 - accuracy: 0.3237 + +
+``` + +``` +
+ 40/183 [=====>........................] - ETA: 33:44 - loss: 1.3697 - accuracy: 0.3250 + +
+``` + +``` +
+ 41/183 [=====>........................] - ETA: 33:30 - loss: 1.3700 - accuracy: 0.3201 + +
+``` + +``` +
+ 42/183 [=====>........................] - ETA: 33:16 - loss: 1.3699 - accuracy: 0.3214 + +
+``` + +``` +
+ 43/183 [======>.......................] - ETA: 33:01 - loss: 1.3695 - accuracy: 0.3227 + +
+``` + +``` +
+ 44/183 [======>.......................] - ETA: 32:48 - loss: 1.3689 - accuracy: 0.3210 + +
+``` + +``` +
+ 45/183 [======>.......................] - ETA: 32:33 - loss: 1.3685 - accuracy: 0.3222 + +
+``` + +``` +
+ 46/183 [======>.......................] - ETA: 32:19 - loss: 1.3692 - accuracy: 0.3207 + +
+``` + +``` +
+ 47/183 [======>.......................] - ETA: 32:05 - loss: 1.3682 - accuracy: 0.3271 + +
+``` + +``` +
+ 48/183 [======>.......................] - ETA: 31:50 - loss: 1.3682 - accuracy: 0.3281 + +
+``` + +``` +
+ 49/183 [=======>......................] - ETA: 31:36 - loss: 1.3685 - accuracy: 0.3291 + +
+``` + +``` +
+ 50/183 [=======>......................] - ETA: 31:22 - loss: 1.3682 - accuracy: 0.3250 + +
+``` + +``` +
+ 51/183 [=======>......................] - ETA: 31:08 - loss: 1.3690 - accuracy: 0.3235 + +
+``` + +``` +
+ 52/183 [=======>......................] - ETA: 30:53 - loss: 1.3690 - accuracy: 0.3221 + +
+``` + +``` +
+ 53/183 [=======>......................] - ETA: 30:39 - loss: 1.3692 - accuracy: 0.3231 + +
+``` + +``` +
+ 54/183 [=======>......................] - ETA: 30:25 - loss: 1.3690 - accuracy: 0.3241 + +
+``` + +``` +
+ 55/183 [========>.....................] - ETA: 30:11 - loss: 1.3688 - accuracy: 0.3273 + +
+``` + +``` +
+ 56/183 [========>.....................] - ETA: 29:56 - loss: 1.3685 - accuracy: 0.3281 + +
+``` + +``` +
+ 57/183 [========>.....................] - ETA: 29:42 - loss: 1.3679 - accuracy: 0.3311 + +
+``` + +``` +
+ 58/183 [========>.....................] - ETA: 29:28 - loss: 1.3671 - accuracy: 0.3319 + +
+``` + +``` +
+ 59/183 [========>.....................] - ETA: 29:14 - loss: 1.3670 - accuracy: 0.3326 + +
+``` + +``` +
+ 60/183 [========>.....................] - ETA: 29:00 - loss: 1.3672 - accuracy: 0.3313 + +
+``` + +``` +
+ 61/183 [=========>....................] - ETA: 28:45 - loss: 1.3673 - accuracy: 0.3279 + +
+``` + +``` +
+ 62/183 [=========>....................] - ETA: 28:31 - loss: 1.3669 - accuracy: 0.3286 + +
+``` + +``` +
+ 63/183 [=========>....................] - ETA: 28:17 - loss: 1.3667 - accuracy: 0.3234 + +
+``` + +``` +
+ 64/183 [=========>....................] - ETA: 28:03 - loss: 1.3669 - accuracy: 0.3223 + +
+``` + +``` +
+ 65/183 [=========>....................] - ETA: 27:49 - loss: 1.3662 - accuracy: 0.3231 + +
+``` + +``` +
+ 66/183 [=========>....................] - ETA: 27:35 - loss: 1.3663 - accuracy: 0.3239 + +
+``` + +``` +
+ 67/183 [=========>....................] - ETA: 27:20 - loss: 1.3659 - accuracy: 0.3265 + +
+``` + +``` +
+ 68/183 [==========>...................] - ETA: 27:06 - loss: 1.3657 - accuracy: 0.3272 + +
+``` + +``` +
+ 69/183 [==========>...................] - ETA: 26:52 - loss: 1.3648 - accuracy: 0.3315 + +
+``` + +``` +
+ 70/183 [==========>...................] - ETA: 26:38 - loss: 1.3654 - accuracy: 0.3286 + +
+``` + +``` +
+ 71/183 [==========>...................] - ETA: 26:24 - loss: 1.3644 - accuracy: 0.3327 + +
+``` + +``` +
+ 72/183 [==========>...................] - ETA: 26:10 - loss: 1.3645 - accuracy: 0.3316 + +
+``` + +``` +
+ 73/183 [==========>...................] - ETA: 25:56 - loss: 1.3645 - accuracy: 0.3305 + +
+``` + +``` +
+ 74/183 [===========>..................] - ETA: 25:41 - loss: 1.3641 - accuracy: 0.3311 + +
+``` + +``` +
+ 75/183 [===========>..................] - ETA: 25:27 - loss: 1.3628 - accuracy: 0.3367 + +
+``` + +``` +
+ 76/183 [===========>..................] - ETA: 25:13 - loss: 1.3616 - accuracy: 0.3421 + +
+``` + +``` +
+ 77/183 [===========>..................] - ETA: 24:59 - loss: 1.3614 - accuracy: 0.3425 + +
+``` + +``` +
+ 78/183 [===========>..................] - ETA: 24:45 - loss: 1.3616 - accuracy: 0.3397 + +
+``` + +``` +
+ 79/183 [===========>..................] - ETA: 24:31 - loss: 1.3610 - accuracy: 0.3418 + +
+``` + +``` +
+ 80/183 [============>.................] - ETA: 24:17 - loss: 1.3608 - accuracy: 0.3438 + +
+``` + +``` +
+ 81/183 [============>.................] - ETA: 24:03 - loss: 1.3599 - accuracy: 0.3441 + +
+``` + +``` +
+ 82/183 [============>.................] - ETA: 23:49 - loss: 1.3591 - accuracy: 0.3460 + +
+``` + +``` +
+ 83/183 [============>.................] - ETA: 23:35 - loss: 1.3589 - accuracy: 0.3479 + +
+``` + +``` +
+ 84/183 [============>.................] - ETA: 23:21 - loss: 1.3583 - accuracy: 0.3482 + +
+``` + +``` +
+ 85/183 [============>.................] - ETA: 23:07 - loss: 1.3575 - accuracy: 0.3515 + +
+``` + +``` +
+ 86/183 [=============>................] - ETA: 22:53 - loss: 1.3558 - accuracy: 0.3561 + +
+``` + +``` +
+ 87/183 [=============>................] - ETA: 22:39 - loss: 1.3560 - accuracy: 0.3549 + +
+``` + +``` +
+ 88/183 [=============>................] - ETA: 22:25 - loss: 1.3535 - accuracy: 0.3594 + +
+``` + +``` +
+ 89/183 [=============>................] - ETA: 22:10 - loss: 1.3529 - accuracy: 0.3596 + +
+``` + +``` +
+ 90/183 [=============>................] - ETA: 21:56 - loss: 1.3529 - accuracy: 0.3597 + +
+``` + +``` +
+ 91/183 [=============>................] - ETA: 21:42 - loss: 1.3510 - accuracy: 0.3613 + +
+``` + +``` +
+ 92/183 [==============>...............] - ETA: 21:28 - loss: 1.3498 - accuracy: 0.3614 + +
+``` + +``` +
+ 93/183 [==============>...............] - ETA: 21:14 - loss: 1.3492 - accuracy: 0.3629 + +
+``` + +``` +
+ 94/183 [==============>...............] - ETA: 21:00 - loss: 1.3485 - accuracy: 0.3644 + +
+``` + +``` +
+ 95/183 [==============>...............] - ETA: 20:45 - loss: 1.3484 - accuracy: 0.3658 + +
+``` + +``` +
+ 96/183 [==============>...............] - ETA: 20:31 - loss: 1.3486 - accuracy: 0.3672 + +
+``` + +``` +
+ 97/183 [==============>...............] - ETA: 20:17 - loss: 1.3488 - accuracy: 0.3647 + +
+``` + +``` +
+ 98/183 [===============>..............] - ETA: 20:03 - loss: 1.3484 - accuracy: 0.3648 + +
+``` + +``` +
+ 99/183 [===============>..............] - ETA: 19:49 - loss: 1.3478 - accuracy: 0.3662 + +
+``` + +``` +
+100/183 [===============>..............] - ETA: 19:34 - loss: 1.3469 - accuracy: 0.3650 + +
+``` + +``` +
+101/183 [===============>..............] - ETA: 19:20 - loss: 1.3474 - accuracy: 0.3651 + +
+``` + +``` +
+102/183 [===============>..............] - ETA: 19:06 - loss: 1.3457 - accuracy: 0.3689 + +
+``` + +``` +
+103/183 [===============>..............] - ETA: 18:52 - loss: 1.3453 - accuracy: 0.3689 + +
+``` + +``` +
+104/183 [================>.............] - ETA: 18:38 - loss: 1.3444 - accuracy: 0.3714 + +
+``` + +``` +
+105/183 [================>.............] - ETA: 18:24 - loss: 1.3441 - accuracy: 0.3726 + +
+``` + +``` +
+106/183 [================>.............] - ETA: 18:10 - loss: 1.3431 - accuracy: 0.3750 + +
+``` + +``` +
+107/183 [================>.............] - ETA: 17:55 - loss: 1.3425 - accuracy: 0.3738 + +
+``` + +``` +
+108/183 [================>.............] - ETA: 17:41 - loss: 1.3421 - accuracy: 0.3738 + +
+``` + +``` +
+109/183 [================>.............] - ETA: 17:27 - loss: 1.3419 - accuracy: 0.3739 + +
+``` + +``` +
+110/183 [=================>............] - ETA: 17:13 - loss: 1.3412 - accuracy: 0.3750 + +
+``` + +``` +
+111/183 [=================>............] - ETA: 16:59 - loss: 1.3400 - accuracy: 0.3773 + +
+``` + +``` +
+112/183 [=================>............] - ETA: 16:45 - loss: 1.3393 - accuracy: 0.3795 + +
+``` + +``` +
+113/183 [=================>............] - ETA: 16:30 - loss: 1.3380 - accuracy: 0.3827 + +
+``` + +``` +
+114/183 [=================>............] - ETA: 16:16 - loss: 1.3366 - accuracy: 0.3860 + +
+``` + +``` +
+115/183 [=================>............] - ETA: 16:02 - loss: 1.3350 - accuracy: 0.3870 + +
+``` + +``` +
+116/183 [==================>...........] - ETA: 15:48 - loss: 1.3334 - accuracy: 0.3901 + +
+``` + +``` +
+117/183 [==================>...........] - ETA: 15:34 - loss: 1.3331 - accuracy: 0.3900 + +
+``` + +``` +
+118/183 [==================>...........] - ETA: 15:20 - loss: 1.3324 - accuracy: 0.3909 + +
+``` + +``` +
+119/183 [==================>...........] - ETA: 15:06 - loss: 1.3308 - accuracy: 0.3929 + +
+``` + +``` +
+120/183 [==================>...........] - ETA: 14:51 - loss: 1.3316 - accuracy: 0.3906 + +
+``` + +``` +
+121/183 [==================>...........] - ETA: 14:37 - loss: 1.3312 - accuracy: 0.3895 + +
+``` + +``` +
+122/183 [===================>..........] - ETA: 14:23 - loss: 1.3294 - accuracy: 0.3924 + +
+``` + +``` +
+123/183 [===================>..........] - ETA: 14:09 - loss: 1.3284 - accuracy: 0.3953 + +
+``` + +``` +
+124/183 [===================>..........] - ETA: 13:55 - loss: 1.3269 - accuracy: 0.3972 + +
+``` + +``` +
+125/183 [===================>..........] - ETA: 13:40 - loss: 1.3249 - accuracy: 0.4000 + +
+``` + +``` +
+126/183 [===================>..........] - ETA: 13:26 - loss: 1.3245 - accuracy: 0.3988 + +
+``` + +``` +
+127/183 [===================>..........] - ETA: 13:12 - loss: 1.3231 - accuracy: 0.4006 + +
+``` + +``` +
+128/183 [===================>..........] - ETA: 12:58 - loss: 1.3233 - accuracy: 0.3994 + +
+``` + +``` +
+129/183 [====================>.........] - ETA: 12:44 - loss: 1.3212 - accuracy: 0.4021 + +
+``` + +``` +
+130/183 [====================>.........] - ETA: 12:30 - loss: 1.3206 - accuracy: 0.4029 + +
+``` + +``` +
+131/183 [====================>.........] - ETA: 12:16 - loss: 1.3187 - accuracy: 0.4065 + +
+``` + +``` +
+132/183 [====================>.........] - ETA: 12:01 - loss: 1.3173 - accuracy: 0.4091 + +
+``` + +``` +
+133/183 [====================>.........] - ETA: 11:47 - loss: 1.3162 - accuracy: 0.4098 + +
+``` + +``` +
+134/183 [====================>.........] - ETA: 11:33 - loss: 1.3148 - accuracy: 0.4123 + +
+``` + +``` +
+135/183 [=====================>........] - ETA: 11:19 - loss: 1.3149 - accuracy: 0.4120 + +
+``` + +``` +
+136/183 [=====================>........] - ETA: 11:05 - loss: 1.3150 - accuracy: 0.4118 + +
+``` + +``` +
+137/183 [=====================>........] - ETA: 10:51 - loss: 1.3143 - accuracy: 0.4106 + +
+``` + +``` +
+138/183 [=====================>........] - ETA: 10:36 - loss: 1.3133 - accuracy: 0.4130 + +
+``` + +``` +
+139/183 [=====================>........] - ETA: 10:22 - loss: 1.3127 - accuracy: 0.4128 + +
+``` + +``` +
+140/183 [=====================>........] - ETA: 10:08 - loss: 1.3136 - accuracy: 0.4125 + +
+``` + +``` +
+141/183 [======================>.......] - ETA: 9:54 - loss: 1.3125 - accuracy: 0.4131 + +
+``` + +``` +
+142/183 [======================>.......] - ETA: 9:40 - loss: 1.3115 - accuracy: 0.4155 + +
+``` + +``` +
+143/183 [======================>.......] - ETA: 9:26 - loss: 1.3108 - accuracy: 0.4161 + +
+``` + +``` +
+144/183 [======================>.......] - ETA: 9:11 - loss: 1.3098 - accuracy: 0.4167 + +
+``` + +``` +
+145/183 [======================>.......] - ETA: 8:57 - loss: 1.3086 - accuracy: 0.4172 + +
+``` + +``` +
+146/183 [======================>.......] - ETA: 8:43 - loss: 1.3083 - accuracy: 0.4161 + +
+``` + +``` +
+147/183 [=======================>......] - ETA: 8:29 - loss: 1.3067 - accuracy: 0.4184 + +
+``` + +``` +
+148/183 [=======================>......] - ETA: 8:15 - loss: 1.3047 - accuracy: 0.4215 + +
+``` + +``` +
+149/183 [=======================>......] - ETA: 8:01 - loss: 1.3037 - accuracy: 0.4211 + +
+``` + +``` +
+150/183 [=======================>......] - ETA: 7:47 - loss: 1.3029 - accuracy: 0.4217 + +
+``` + +``` +
+151/183 [=======================>......] - ETA: 7:32 - loss: 1.3021 - accuracy: 0.4222 + +
+``` + +``` +
+152/183 [=======================>......] - ETA: 7:18 - loss: 1.3007 - accuracy: 0.4243 + +
+``` + +``` +
+153/183 [========================>.....] - ETA: 7:04 - loss: 1.3017 - accuracy: 0.4240 + +
+``` + +``` +
+154/183 [========================>.....] - ETA: 6:50 - loss: 1.3006 - accuracy: 0.4253 + +
+``` + +``` +
+155/183 [========================>.....] - ETA: 6:36 - loss: 1.2986 - accuracy: 0.4282 + +
+``` + +``` +
+156/183 [========================>.....] - ETA: 6:22 - loss: 1.2965 - accuracy: 0.4303 + +
+``` + +``` +
+157/183 [========================>.....] - ETA: 6:08 - loss: 1.2964 - accuracy: 0.4283 + +
+``` + +``` +
+158/183 [========================>.....] - ETA: 5:53 - loss: 1.2953 - accuracy: 0.4288 + +
+``` + +``` +
+159/183 [=========================>....] - ETA: 5:39 - loss: 1.2931 - accuracy: 0.4316 + +
+``` + +``` +
+160/183 [=========================>....] - ETA: 5:25 - loss: 1.2923 - accuracy: 0.4320 + +
+``` + +``` +
+161/183 [=========================>....] - ETA: 5:11 - loss: 1.2916 - accuracy: 0.4332 + +
+``` + +``` +
+162/183 [=========================>....] - ETA: 4:57 - loss: 1.2905 - accuracy: 0.4344 + +
+``` + +``` +
+163/183 [=========================>....] - ETA: 4:43 - loss: 1.2901 - accuracy: 0.4348 + +
+``` + +``` +
+164/183 [=========================>....] - ETA: 4:28 - loss: 1.2891 - accuracy: 0.4360 + +
+``` + +``` +
+165/183 [==========================>...] - ETA: 4:14 - loss: 1.2881 - accuracy: 0.4356 + +
+``` + +``` +
+166/183 [==========================>...] - ETA: 4:00 - loss: 1.2860 - accuracy: 0.4375 + +
+``` + +``` +
+167/183 [==========================>...] - ETA: 3:46 - loss: 1.2835 - accuracy: 0.4386 + +
+``` + +``` +
+168/183 [==========================>...] - ETA: 3:32 - loss: 1.2838 - accuracy: 0.4375 + +
+``` + +``` +
+169/183 [==========================>...] - ETA: 3:18 - loss: 1.2829 - accuracy: 0.4379 + +
+``` + +``` +
+170/183 [==========================>...] - ETA: 3:03 - loss: 1.2830 - accuracy: 0.4390 + +
+``` + +``` +
+171/183 [===========================>..] - ETA: 2:49 - loss: 1.2800 - accuracy: 0.4415 + +
+``` + +``` +
+172/183 [===========================>..] - ETA: 2:35 - loss: 1.2784 - accuracy: 0.4419 + +
+``` + +``` +
+173/183 [===========================>..] - ETA: 2:21 - loss: 1.2765 - accuracy: 0.4429 + +
+``` + +``` +
+174/183 [===========================>..] - ETA: 2:07 - loss: 1.2746 - accuracy: 0.4447 + +
+``` + +``` +
+175/183 [===========================>..] - ETA: 1:53 - loss: 1.2730 - accuracy: 0.4457 + +
+``` + +``` +
+176/183 [===========================>..] - ETA: 1:39 - loss: 1.2705 - accuracy: 0.4489 + +
+``` + +``` +
+177/183 [============================>.] - ETA: 1:24 - loss: 1.2696 - accuracy: 0.4492 + +
+``` + +``` +
+178/183 [============================>.] - ETA: 1:10 - loss: 1.2686 - accuracy: 0.4501 + +
+``` + +``` +
+179/183 [============================>.] - ETA: 56s - loss: 1.2679 - accuracy: 0.4511 + +
+``` + +``` +
+180/183 [============================>.] - ETA: 42s - loss: 1.2671 - accuracy: 0.4521 + +
+``` + +``` +
+181/183 [============================>.] - ETA: 28s - loss: 1.2666 - accuracy: 0.4523 + +
+``` + +``` +
+182/183 [============================>.] - ETA: 14s - loss: 1.2642 - accuracy: 0.4547 + +
+``` + +``` +
+183/183 [==============================] - ETA: 0s - loss: 1.2631 - accuracy: 0.4556 + +
+``` + +``` +
+183/183 [==============================] - 2748s 15s/step - loss: 1.2631 - accuracy: 0.4556 - val_loss: 0.9210 - val_accuracy: 0.7075 - lr: 2.9000e-06 + + +
+``` +Epoch 3/5 + +``` +
+ + 1/183 [..............................] - ETA: 46:11 - loss: 1.1680 - accuracy: 0.3750 + +
+``` + +``` +
+ 2/183 [..............................] - ETA: 43:28 - loss: 1.0826 - accuracy: 0.5625 + +
+``` + +``` +
+ 3/183 [..............................] - ETA: 43:21 - loss: 1.1881 - accuracy: 0.5417 + +
+``` + +``` +
+ 4/183 [..............................] - ETA: 43:06 - loss: 1.1313 - accuracy: 0.5625 + +
+``` + +``` +
+ 5/183 [..............................] - ETA: 42:50 - loss: 1.1148 - accuracy: 0.6000 + +
+``` + +``` +
+ 6/183 [..............................] - ETA: 42:32 - loss: 1.0660 - accuracy: 0.6458 + +
+``` + +``` +
+ 7/183 [>.............................] - ETA: 42:14 - loss: 1.0620 - accuracy: 0.6429 + +
+``` + +``` +
+ 8/183 [>.............................] - ETA: 41:56 - loss: 1.0516 - accuracy: 0.6562 + +
+``` + +``` +
+ 9/183 [>.............................] - ETA: 41:40 - loss: 1.0623 - accuracy: 0.6250 + +
+``` + +``` +
+ 10/183 [>.............................] - ETA: 41:28 - loss: 1.0573 - accuracy: 0.6250 + +
+``` + +``` +
+ 11/183 [>.............................] - ETA: 41:12 - loss: 1.0500 - accuracy: 0.6364 + +
+``` + +``` +
+ 12/183 [>.............................] - ETA: 40:55 - loss: 1.0126 - accuracy: 0.6667 + +
+``` + +``` +
+ 13/183 [=>............................] - ETA: 40:39 - loss: 1.0203 - accuracy: 0.6538 + +
+``` + +``` +
+ 14/183 [=>............................] - ETA: 40:22 - loss: 1.0258 - accuracy: 0.6518 + +
+``` + +``` +
+ 15/183 [=>............................] - ETA: 40:06 - loss: 1.0312 - accuracy: 0.6583 + +
+``` + +``` +
+ 16/183 [=>............................] - ETA: 39:50 - loss: 1.0269 - accuracy: 0.6562 + +
+``` + +``` +
+ 17/183 [=>............................] - ETA: 39:33 - loss: 1.0329 - accuracy: 0.6618 + +
+``` + +``` +
+ 18/183 [=>............................] - ETA: 39:18 - loss: 1.0382 - accuracy: 0.6667 + +
+``` + +``` +
+ 19/183 [==>...........................] - ETA: 39:03 - loss: 1.0372 - accuracy: 0.6579 + +
+``` + +``` +
+ 20/183 [==>...........................] - ETA: 38:48 - loss: 1.0363 - accuracy: 0.6500 + +
+``` + +``` +
+ 21/183 [==>...........................] - ETA: 38:33 - loss: 1.0430 - accuracy: 0.6369 + +
+``` + +``` +
+ 22/183 [==>...........................] - ETA: 38:18 - loss: 1.0392 - accuracy: 0.6420 + +
+``` + +``` +
+ 23/183 [==>...........................] - ETA: 38:03 - loss: 1.0438 - accuracy: 0.6250 + +
+``` + +``` +
+ 24/183 [==>...........................] - ETA: 37:49 - loss: 1.0405 - accuracy: 0.6302 + +
+``` + +``` +
+ 25/183 [===>..........................] - ETA: 37:34 - loss: 1.0383 - accuracy: 0.6250 + +
+``` + +``` +
+ 26/183 [===>..........................] - ETA: 37:20 - loss: 1.0392 - accuracy: 0.6250 + +
+``` + +``` +
+ 27/183 [===>..........................] - ETA: 37:05 - loss: 1.0422 - accuracy: 0.6204 + +
+``` + +``` +
+ 28/183 [===>..........................] - ETA: 36:50 - loss: 1.0441 - accuracy: 0.6205 + +
+``` + +``` +
+ 29/183 [===>..........................] - ETA: 36:35 - loss: 1.0482 - accuracy: 0.6164 + +
+``` + +``` +
+ 30/183 [===>..........................] - ETA: 36:21 - loss: 1.0541 - accuracy: 0.6042 + +
+``` + +``` +
+ 31/183 [====>.........................] - ETA: 36:06 - loss: 1.0507 - accuracy: 0.6089 + +
+``` + +``` +
+ 32/183 [====>.........................] - ETA: 35:52 - loss: 1.0431 - accuracy: 0.6211 + +
+``` + +``` +
+ 33/183 [====>.........................] - ETA: 35:37 - loss: 1.0418 - accuracy: 0.6250 + +
+``` + +``` +
+ 34/183 [====>.........................] - ETA: 35:22 - loss: 1.0382 - accuracy: 0.6250 + +
+``` + +``` +
+ 35/183 [====>.........................] - ETA: 35:08 - loss: 1.0369 - accuracy: 0.6250 + +
+``` + +``` +
+ 36/183 [====>.........................] - ETA: 34:53 - loss: 1.0396 - accuracy: 0.6250 + +
+``` + +``` +
+ 37/183 [=====>........................] - ETA: 34:38 - loss: 1.0396 - accuracy: 0.6216 + +
+``` + +``` +
+ 38/183 [=====>........................] - ETA: 34:24 - loss: 1.0478 - accuracy: 0.6118 + +
+``` + +``` +
+ 39/183 [=====>........................] - ETA: 34:09 - loss: 1.0412 - accuracy: 0.6154 + +
+``` + +``` +
+ 40/183 [=====>........................] - ETA: 33:55 - loss: 1.0397 - accuracy: 0.6156 + +
+``` + +``` +
+ 41/183 [=====>........................] - ETA: 33:41 - loss: 1.0378 - accuracy: 0.6159 + +
+``` + +``` +
+ 42/183 [=====>........................] - ETA: 33:26 - loss: 1.0331 - accuracy: 0.6190 + +
+``` + +``` +
+ 43/183 [======>.......................] - ETA: 33:13 - loss: 1.0287 - accuracy: 0.6192 + +
+``` + +``` +
+ 44/183 [======>.......................] - ETA: 32:58 - loss: 1.0366 - accuracy: 0.6136 + +
+``` + +``` +
+ 45/183 [======>.......................] - ETA: 32:43 - loss: 1.0337 - accuracy: 0.6167 + +
+``` + +``` +
+ 46/183 [======>.......................] - ETA: 32:29 - loss: 1.0309 - accuracy: 0.6196 + +
+``` + +``` +
+ 47/183 [======>.......................] - ETA: 32:15 - loss: 1.0355 - accuracy: 0.6144 + +
+``` + +``` +
+ 48/183 [======>.......................] - ETA: 32:00 - loss: 1.0365 - accuracy: 0.6146 + +
+``` + +``` +
+ 49/183 [=======>......................] - ETA: 31:46 - loss: 1.0344 - accuracy: 0.6173 + +
+``` + +``` +
+ 50/183 [=======>......................] - ETA: 31:32 - loss: 1.0364 - accuracy: 0.6175 + +
+``` + +``` +
+ 51/183 [=======>......................] - ETA: 31:17 - loss: 1.0385 - accuracy: 0.6152 + +
+``` + +``` +
+ 52/183 [=======>......................] - ETA: 31:03 - loss: 1.0415 - accuracy: 0.6106 + +
+``` + +``` +
+ 53/183 [=======>......................] - ETA: 30:50 - loss: 1.0360 - accuracy: 0.6156 + +
+``` + +``` +
+ 54/183 [=======>......................] - ETA: 30:36 - loss: 1.0329 - accuracy: 0.6181 + +
+``` + +``` +
+ 55/183 [========>.....................] - ETA: 30:21 - loss: 1.0340 - accuracy: 0.6136 + +
+``` + +``` +
+ 56/183 [========>.....................] - ETA: 30:07 - loss: 1.0357 - accuracy: 0.6094 + +
+``` + +``` +
+ 57/183 [========>.....................] - ETA: 29:53 - loss: 1.0389 - accuracy: 0.6096 + +
+``` + +``` +
+ 58/183 [========>.....................] - ETA: 29:38 - loss: 1.0403 - accuracy: 0.6099 + +
+``` + +``` +
+ 59/183 [========>.....................] - ETA: 29:24 - loss: 1.0437 - accuracy: 0.6038 + +
+``` + +``` +
+ 60/183 [========>.....................] - ETA: 29:09 - loss: 1.0459 - accuracy: 0.6042 + +
+``` + +``` +
+ 61/183 [=========>....................] - ETA: 28:55 - loss: 1.0509 - accuracy: 0.6025 + +
+``` + +``` +
+ 62/183 [=========>....................] - ETA: 28:41 - loss: 1.0511 - accuracy: 0.5988 + +
+``` + +``` +
+ 63/183 [=========>....................] - ETA: 28:27 - loss: 1.0479 - accuracy: 0.5992 + +
+``` + +``` +
+ 64/183 [=========>....................] - ETA: 28:12 - loss: 1.0548 - accuracy: 0.5977 + +
+``` + +``` +
+ 65/183 [=========>....................] - ETA: 27:58 - loss: 1.0570 - accuracy: 0.5962 + +
+``` + +``` +
+ 66/183 [=========>....................] - ETA: 27:44 - loss: 1.0555 - accuracy: 0.5966 + +
+``` + +``` +
+ 67/183 [=========>....................] - ETA: 27:29 - loss: 1.0566 - accuracy: 0.5951 + +
+``` + +``` +
+ 68/183 [==========>...................] - ETA: 27:15 - loss: 1.0571 - accuracy: 0.5938 + +
+``` + +``` +
+ 69/183 [==========>...................] - ETA: 27:01 - loss: 1.0523 - accuracy: 0.5978 + +
+``` + +``` +
+ 70/183 [==========>...................] - ETA: 26:47 - loss: 1.0483 - accuracy: 0.6000 + +
+``` + +``` +
+ 71/183 [==========>...................] - ETA: 26:32 - loss: 1.0489 - accuracy: 0.5968 + +
+``` + +``` +
+ 72/183 [==========>...................] - ETA: 26:18 - loss: 1.0491 - accuracy: 0.5955 + +
+``` + +``` +
+ 73/183 [==========>...................] - ETA: 26:04 - loss: 1.0486 - accuracy: 0.5959 + +
+``` + +``` +
+ 74/183 [===========>..................] - ETA: 25:49 - loss: 1.0532 - accuracy: 0.5912 + +
+``` + +``` +
+ 75/183 [===========>..................] - ETA: 25:35 - loss: 1.0535 - accuracy: 0.5917 + +
+``` + +``` +
+ 76/183 [===========>..................] - ETA: 25:21 - loss: 1.0568 - accuracy: 0.5888 + +
+``` + +``` +
+ 77/183 [===========>..................] - ETA: 25:06 - loss: 1.0600 - accuracy: 0.5844 + +
+``` + +``` +
+ 78/183 [===========>..................] - ETA: 24:52 - loss: 1.0557 - accuracy: 0.5865 + +
+``` + +``` +
+ 79/183 [===========>..................] - ETA: 24:38 - loss: 1.0538 - accuracy: 0.5870 + +
+``` + +``` +
+ 80/183 [============>.................] - ETA: 24:23 - loss: 1.0543 - accuracy: 0.5844 + +
+``` + +``` +
+ 81/183 [============>.................] - ETA: 24:09 - loss: 1.0528 - accuracy: 0.5864 + +
+``` + +``` +
+ 82/183 [============>.................] - ETA: 23:55 - loss: 1.0547 - accuracy: 0.5838 + +
+``` + +``` +
+ 83/183 [============>.................] - ETA: 23:41 - loss: 1.0558 - accuracy: 0.5798 + +
+``` + +``` +
+ 84/183 [============>.................] - ETA: 23:26 - loss: 1.0564 - accuracy: 0.5804 + +
+``` + +``` +
+ 85/183 [============>.................] - ETA: 23:12 - loss: 1.0548 - accuracy: 0.5794 + +
+``` + +``` +
+ 86/183 [=============>................] - ETA: 22:58 - loss: 1.0542 - accuracy: 0.5770 + +
+``` + +``` +
+ 87/183 [=============>................] - ETA: 22:44 - loss: 1.0569 - accuracy: 0.5761 + +
+``` + +``` +
+ 88/183 [=============>................] - ETA: 22:29 - loss: 1.0551 - accuracy: 0.5781 + +
+``` + +``` +
+ 89/183 [=============>................] - ETA: 22:15 - loss: 1.0525 - accuracy: 0.5815 + +
+``` + +``` +
+ 90/183 [=============>................] - ETA: 22:01 - loss: 1.0552 - accuracy: 0.5778 + +
+``` + +``` +
+ 91/183 [=============>................] - ETA: 21:47 - loss: 1.0529 - accuracy: 0.5797 + +
+``` + +``` +
+ 92/183 [==============>...............] - ETA: 21:32 - loss: 1.0501 - accuracy: 0.5802 + +
+``` + +``` +
+ 93/183 [==============>...............] - ETA: 21:18 - loss: 1.0496 - accuracy: 0.5793 + +
+``` + +``` +
+ 94/183 [==============>...............] - ETA: 21:04 - loss: 1.0512 - accuracy: 0.5798 + +
+``` + +``` +
+ 95/183 [==============>...............] - ETA: 20:49 - loss: 1.0518 - accuracy: 0.5803 + +
+``` + +``` +
+ 96/183 [==============>...............] - ETA: 20:35 - loss: 1.0520 - accuracy: 0.5807 + +
+``` + +``` +
+ 97/183 [==============>...............] - ETA: 20:21 - loss: 1.0550 - accuracy: 0.5812 + +
+``` + +``` +
+ 98/183 [===============>..............] - ETA: 20:07 - loss: 1.0576 - accuracy: 0.5791 + +
+``` + +``` +
+ 99/183 [===============>..............] - ETA: 19:53 - loss: 1.0571 - accuracy: 0.5770 + +
+``` + +``` +
+100/183 [===============>..............] - ETA: 19:38 - loss: 1.0547 - accuracy: 0.5775 + +
+``` + +``` +
+101/183 [===============>..............] - ETA: 19:24 - loss: 1.0547 - accuracy: 0.5767 + +
+``` + +``` +
+102/183 [===============>..............] - ETA: 19:10 - loss: 1.0536 - accuracy: 0.5748 + +
+``` + +``` +
+103/183 [===============>..............] - ETA: 18:56 - loss: 1.0514 - accuracy: 0.5752 + +
+``` + +``` +
+104/183 [================>.............] - ETA: 18:41 - loss: 1.0495 - accuracy: 0.5769 + +
+``` + +``` +
+105/183 [================>.............] - ETA: 18:27 - loss: 1.0462 - accuracy: 0.5774 + +
+``` + +``` +
+106/183 [================>.............] - ETA: 18:13 - loss: 1.0451 - accuracy: 0.5790 + +
+``` + +``` +
+107/183 [================>.............] - ETA: 17:59 - loss: 1.0434 - accuracy: 0.5818 + +
+``` + +``` +
+108/183 [================>.............] - ETA: 17:44 - loss: 1.0424 - accuracy: 0.5833 + +
+``` + +``` +
+109/183 [================>.............] - ETA: 17:30 - loss: 1.0421 - accuracy: 0.5826 + +
+``` + +``` +
+110/183 [=================>............] - ETA: 17:16 - loss: 1.0409 - accuracy: 0.5830 + +
+``` + +``` +
+111/183 [=================>............] - ETA: 17:02 - loss: 1.0415 - accuracy: 0.5833 + +
+``` + +``` +
+112/183 [=================>............] - ETA: 16:47 - loss: 1.0403 - accuracy: 0.5837 + +
+``` + +``` +
+113/183 [=================>............] - ETA: 16:33 - loss: 1.0377 - accuracy: 0.5852 + +
+``` + +``` +
+114/183 [=================>............] - ETA: 16:19 - loss: 1.0367 - accuracy: 0.5866 + +
+``` + +``` +
+115/183 [=================>............] - ETA: 16:05 - loss: 1.0357 - accuracy: 0.5880 + +
+``` + +``` +
+116/183 [==================>...........] - ETA: 15:50 - loss: 1.0347 - accuracy: 0.5884 + +
+``` + +``` +
+117/183 [==================>...........] - ETA: 15:36 - loss: 1.0329 - accuracy: 0.5897 + +
+``` + +``` +
+118/183 [==================>...........] - ETA: 15:22 - loss: 1.0314 - accuracy: 0.5900 + +
+``` + +``` +
+119/183 [==================>...........] - ETA: 15:08 - loss: 1.0309 - accuracy: 0.5903 + +
+``` + +``` +
+120/183 [==================>...........] - ETA: 14:54 - loss: 1.0273 - accuracy: 0.5927 + +
+``` + +``` +
+121/183 [==================>...........] - ETA: 14:39 - loss: 1.0271 - accuracy: 0.5919 + +
+``` + +``` +
+122/183 [===================>..........] - ETA: 14:25 - loss: 1.0277 - accuracy: 0.5922 + +
+``` + +``` +
+123/183 [===================>..........] - ETA: 14:11 - loss: 1.0252 - accuracy: 0.5925 + +
+``` + +``` +
+124/183 [===================>..........] - ETA: 13:57 - loss: 1.0260 - accuracy: 0.5927 + +
+``` + +``` +
+125/183 [===================>..........] - ETA: 13:42 - loss: 1.0269 - accuracy: 0.5930 + +
+``` + +``` +
+126/183 [===================>..........] - ETA: 13:28 - loss: 1.0241 - accuracy: 0.5942 + +
+``` + +``` +
+127/183 [===================>..........] - ETA: 13:14 - loss: 1.0223 - accuracy: 0.5965 + +
+``` + +``` +
+128/183 [===================>..........] - ETA: 13:00 - loss: 1.0215 - accuracy: 0.5947 + +
+``` + +``` +
+129/183 [====================>.........] - ETA: 12:46 - loss: 1.0225 - accuracy: 0.5940 + +
+``` + +``` +
+130/183 [====================>.........] - ETA: 12:31 - loss: 1.0200 - accuracy: 0.5962 + +
+``` + +``` +
+131/183 [====================>.........] - ETA: 12:17 - loss: 1.0190 - accuracy: 0.5964 + +
+``` + +``` +
+132/183 [====================>.........] - ETA: 12:03 - loss: 1.0178 - accuracy: 0.5975 + +
+``` + +``` +
+133/183 [====================>.........] - ETA: 11:49 - loss: 1.0159 - accuracy: 0.5987 + +
+``` + +``` +
+134/183 [====================>.........] - ETA: 11:35 - loss: 1.0160 - accuracy: 0.5989 + +
+``` + +``` +
+135/183 [=====================>........] - ETA: 11:20 - loss: 1.0147 - accuracy: 0.5991 + +
+``` + +``` +
+136/183 [=====================>........] - ETA: 11:06 - loss: 1.0153 - accuracy: 0.5993 + +
+``` + +``` +
+137/183 [=====================>........] - ETA: 10:52 - loss: 1.0184 - accuracy: 0.5976 + +
+``` + +``` +
+138/183 [=====================>........] - ETA: 10:38 - loss: 1.0174 - accuracy: 0.5978 + +
+``` + +``` +
+139/183 [=====================>........] - ETA: 10:24 - loss: 1.0192 - accuracy: 0.5980 + +
+``` + +``` +
+140/183 [=====================>........] - ETA: 10:09 - loss: 1.0221 - accuracy: 0.5955 + +
+``` + +``` +
+141/183 [======================>.......] - ETA: 9:55 - loss: 1.0244 - accuracy: 0.5931 + +
+``` + +``` +
+142/183 [======================>.......] - ETA: 9:41 - loss: 1.0228 - accuracy: 0.5951 + +
+``` + +``` +
+143/183 [======================>.......] - ETA: 9:27 - loss: 1.0211 - accuracy: 0.5970 + +
+``` + +``` +
+144/183 [======================>.......] - ETA: 9:13 - loss: 1.0235 - accuracy: 0.5946 + +
+``` + +``` +
+145/183 [======================>.......] - ETA: 8:59 - loss: 1.0241 - accuracy: 0.5940 + +
+``` + +``` +
+146/183 [======================>.......] - ETA: 8:44 - loss: 1.0228 - accuracy: 0.5950 + +
+``` + +``` +
+147/183 [=======================>......] - ETA: 8:30 - loss: 1.0229 - accuracy: 0.5961 + +
+``` + +``` +
+148/183 [=======================>......] - ETA: 8:16 - loss: 1.0204 - accuracy: 0.5980 + +
+``` + +``` +
+149/183 [=======================>......] - ETA: 8:02 - loss: 1.0193 - accuracy: 0.5990 + +
+``` + +``` +
+150/183 [=======================>......] - ETA: 7:48 - loss: 1.0173 - accuracy: 0.6000 + +
+``` + +``` +
+151/183 [=======================>......] - ETA: 7:33 - loss: 1.0190 - accuracy: 0.5993 + +
+``` + +``` +
+152/183 [=======================>......] - ETA: 7:19 - loss: 1.0233 - accuracy: 0.5979 + +
+``` + +``` +
+153/183 [========================>.....] - ETA: 7:05 - loss: 1.0230 - accuracy: 0.5972 + +
+``` + +``` +
+154/183 [========================>.....] - ETA: 6:51 - loss: 1.0230 - accuracy: 0.5974 + +
+``` + +``` +
+155/183 [========================>.....] - ETA: 6:37 - loss: 1.0223 - accuracy: 0.5992 + +
+``` + +``` +
+156/183 [========================>.....] - ETA: 6:22 - loss: 1.0204 - accuracy: 0.5994 + +
+``` + +``` +
+157/183 [========================>.....] - ETA: 6:08 - loss: 1.0204 - accuracy: 0.5987 + +
+``` + +``` +
+158/183 [========================>.....] - ETA: 5:54 - loss: 1.0201 - accuracy: 0.5965 + +
+``` + +``` +
+159/183 [=========================>....] - ETA: 5:40 - loss: 1.0199 - accuracy: 0.5975 + +
+``` + +``` +
+160/183 [=========================>....] - ETA: 5:26 - loss: 1.0168 - accuracy: 0.5992 + +
+``` + +``` +
+161/183 [=========================>....] - ETA: 5:12 - loss: 1.0155 - accuracy: 0.6009 + +
+``` + +``` +
+162/183 [=========================>....] - ETA: 4:57 - loss: 1.0131 - accuracy: 0.6019 + +
+``` + +``` +
+163/183 [=========================>....] - ETA: 4:43 - loss: 1.0144 - accuracy: 0.6020 + +
+``` + +``` +
+164/183 [=========================>....] - ETA: 4:29 - loss: 1.0145 - accuracy: 0.6021 + +
+``` + +``` +
+165/183 [==========================>...] - ETA: 4:15 - loss: 1.0138 - accuracy: 0.6030 + +
+``` + +``` +
+166/183 [==========================>...] - ETA: 4:01 - loss: 1.0127 - accuracy: 0.6032 + +
+``` + +``` +
+167/183 [==========================>...] - ETA: 3:46 - loss: 1.0127 - accuracy: 0.6018 + +
+``` + +``` +
+168/183 [==========================>...] - ETA: 3:32 - loss: 1.0102 - accuracy: 0.6027 + +
+``` + +``` +
+169/183 [==========================>...] - ETA: 3:18 - loss: 1.0119 - accuracy: 0.6013 + +
+``` + +``` +
+170/183 [==========================>...] - ETA: 3:04 - loss: 1.0113 - accuracy: 0.6007 + +
+``` + +``` +
+171/183 [===========================>..] - ETA: 2:50 - loss: 1.0134 - accuracy: 0.6001 + +
+``` + +``` +
+172/183 [===========================>..] - ETA: 2:36 - loss: 1.0117 - accuracy: 0.6010 + +
+``` + +``` +
+173/183 [===========================>..] - ETA: 2:21 - loss: 1.0100 - accuracy: 0.6012 + +
+``` + +``` +
+174/183 [===========================>..] - ETA: 2:07 - loss: 1.0084 - accuracy: 0.6020 + +
+``` + +``` +
+175/183 [===========================>..] - ETA: 1:53 - loss: 1.0060 - accuracy: 0.6043 + +
+``` + +``` +
+176/183 [===========================>..] - ETA: 1:39 - loss: 1.0041 - accuracy: 0.6044 + +
+``` + +``` +
+177/183 [============================>.] - ETA: 1:25 - loss: 1.0025 - accuracy: 0.6059 + +
+``` + +``` +
+178/183 [============================>.] - ETA: 1:10 - loss: 1.0034 - accuracy: 0.6053 + +
+``` + +``` +
+179/183 [============================>.] - ETA: 56s - loss: 1.0040 - accuracy: 0.6054 + +
+``` + +``` +
+180/183 [============================>.] - ETA: 42s - loss: 1.0036 - accuracy: 0.6049 + +
+``` + +``` +
+181/183 [============================>.] - ETA: 28s - loss: 1.0028 - accuracy: 0.6050 + +
+``` + +``` +
+182/183 [============================>.] - ETA: 14s - loss: 1.0028 - accuracy: 0.6051 + +
+``` + +``` +
+183/183 [==============================] - ETA: 0s - loss: 1.0013 - accuracy: 0.6052 + +
+``` + +``` +
+183/183 [==============================] - 2755s 15s/step - loss: 1.0013 - accuracy: 0.6052 - val_loss: 0.7730 - val_accuracy: 0.7475 - lr: 4.8000e-06 + + +
+``` +Epoch 4/5 + +``` +
+ + 1/183 [..............................] - ETA: 45:34 - loss: 0.7885 - accuracy: 0.7500 + +
+``` + +``` +
+ 2/183 [..............................] - ETA: 43:17 - loss: 0.8742 - accuracy: 0.6875 + +
+``` + +``` +
+ 3/183 [..............................] - ETA: 43:02 - loss: 0.7851 - accuracy: 0.7083 + +
+``` + +``` +
+ 4/183 [..............................] - ETA: 42:51 - loss: 0.9176 - accuracy: 0.6562 + +
+``` + +``` +
+ 5/183 [..............................] - ETA: 42:39 - loss: 0.8677 - accuracy: 0.7000 + +
+``` + +``` +
+ 6/183 [..............................] - ETA: 42:25 - loss: 0.8238 - accuracy: 0.7292 + +
+``` + +``` +
+ 7/183 [>.............................] - ETA: 42:09 - loss: 0.8209 - accuracy: 0.7143 + +
+``` + +``` +
+ 8/183 [>.............................] - ETA: 41:54 - loss: 0.8494 - accuracy: 0.6875 + +
+``` + +``` +
+ 9/183 [>.............................] - ETA: 41:40 - loss: 0.8458 - accuracy: 0.6944 + +
+``` + +``` +
+ 10/183 [>.............................] - ETA: 41:25 - loss: 0.8841 - accuracy: 0.6625 + +
+``` + +``` +
+ 11/183 [>.............................] - ETA: 41:10 - loss: 0.8833 - accuracy: 0.6705 + +
+``` + +``` +
+ 12/183 [>.............................] - ETA: 40:54 - loss: 0.8520 - accuracy: 0.6979 + +
+``` + +``` +
+ 13/183 [=>............................] - ETA: 40:38 - loss: 0.8262 - accuracy: 0.7115 + +
+``` + +``` +
+ 14/183 [=>............................] - ETA: 40:23 - loss: 0.8389 - accuracy: 0.7054 + +
+``` + +``` +
+ 15/183 [=>............................] - ETA: 40:08 - loss: 0.8262 - accuracy: 0.7250 + +
+``` + +``` +
+ 16/183 [=>............................] - ETA: 39:53 - loss: 0.8368 - accuracy: 0.7188 + +
+``` + +``` +
+ 17/183 [=>............................] - ETA: 39:39 - loss: 0.8293 - accuracy: 0.7279 + +
+``` + +``` +
+ 18/183 [=>............................] - ETA: 39:25 - loss: 0.8353 - accuracy: 0.7222 + +
+``` + +``` +
+ 19/183 [==>...........................] - ETA: 39:09 - loss: 0.8331 - accuracy: 0.7237 + +
+``` + +``` +
+ 20/183 [==>...........................] - ETA: 38:54 - loss: 0.8452 - accuracy: 0.7063 + +
+``` + +``` +
+ 21/183 [==>...........................] - ETA: 38:38 - loss: 0.8396 - accuracy: 0.7083 + +
+``` + +``` +
+ 22/183 [==>...........................] - ETA: 38:23 - loss: 0.8370 - accuracy: 0.7102 + +
+``` + +``` +
+ 23/183 [==>...........................] - ETA: 38:08 - loss: 0.8350 - accuracy: 0.7120 + +
+``` + +``` +
+ 24/183 [==>...........................] - ETA: 37:53 - loss: 0.8551 - accuracy: 0.7031 + +
+``` + +``` +
+ 25/183 [===>..........................] - ETA: 37:38 - loss: 0.8385 - accuracy: 0.7150 + +
+``` + +``` +
+ 26/183 [===>..........................] - ETA: 37:23 - loss: 0.8379 - accuracy: 0.7163 + +
+``` + +``` +
+ 27/183 [===>..........................] - ETA: 37:09 - loss: 0.8418 - accuracy: 0.7130 + +
+``` + +``` +
+ 28/183 [===>..........................] - ETA: 36:54 - loss: 0.8280 - accuracy: 0.7232 + +
+``` + +``` +
+ 29/183 [===>..........................] - ETA: 36:39 - loss: 0.8371 - accuracy: 0.7069 + +
+``` + +``` +
+ 30/183 [===>..........................] - ETA: 36:24 - loss: 0.8461 - accuracy: 0.7042 + +
+``` + +``` +
+ 31/183 [====>.........................] - ETA: 36:10 - loss: 0.8476 - accuracy: 0.7056 + +
+``` + +``` +
+ 32/183 [====>.........................] - ETA: 35:55 - loss: 0.8437 - accuracy: 0.7031 + +
+``` + +``` +
+ 33/183 [====>.........................] - ETA: 35:40 - loss: 0.8428 - accuracy: 0.7045 + +
+``` + +``` +
+ 34/183 [====>.........................] - ETA: 35:25 - loss: 0.8396 - accuracy: 0.7096 + +
+``` + +``` +
+ 35/183 [====>.........................] - ETA: 35:11 - loss: 0.8330 - accuracy: 0.7107 + +
+``` + +``` +
+ 36/183 [====>.........................] - ETA: 34:56 - loss: 0.8283 - accuracy: 0.7118 + +
+``` + +``` +
+ 37/183 [=====>........................] - ETA: 34:41 - loss: 0.8235 - accuracy: 0.7162 + +
+``` + +``` +
+ 38/183 [=====>........................] - ETA: 34:27 - loss: 0.8247 - accuracy: 0.7171 + +
+``` + +``` +
+ 39/183 [=====>........................] - ETA: 34:12 - loss: 0.8305 - accuracy: 0.7147 + +
+``` + +``` +
+ 40/183 [=====>........................] - ETA: 33:58 - loss: 0.8233 - accuracy: 0.7219 + +
+``` + +``` +
+ 41/183 [=====>........................] - ETA: 33:43 - loss: 0.8217 - accuracy: 0.7195 + +
+``` + +``` +
+ 42/183 [=====>........................] - ETA: 33:28 - loss: 0.8180 - accuracy: 0.7202 + +
+``` + +``` +
+ 43/183 [======>.......................] - ETA: 33:15 - loss: 0.8268 - accuracy: 0.7209 + +
+``` + +``` +
+ 44/183 [======>.......................] - ETA: 33:00 - loss: 0.8309 - accuracy: 0.7131 + +
+``` + +``` +
+ 45/183 [======>.......................] - ETA: 32:46 - loss: 0.8377 - accuracy: 0.7111 + +
+``` + +``` +
+ 46/183 [======>.......................] - ETA: 32:31 - loss: 0.8367 - accuracy: 0.7120 + +
+``` + +``` +
+ 47/183 [======>.......................] - ETA: 32:17 - loss: 0.8331 - accuracy: 0.7154 + +
+``` + +``` +
+ 48/183 [======>.......................] - ETA: 32:02 - loss: 0.8366 - accuracy: 0.7109 + +
+``` + +``` +
+ 49/183 [=======>......................] - ETA: 31:48 - loss: 0.8383 - accuracy: 0.7117 + +
+``` + +``` +
+ 50/183 [=======>......................] - ETA: 31:34 - loss: 0.8408 - accuracy: 0.7075 + +
+``` + +``` +
+ 51/183 [=======>......................] - ETA: 31:19 - loss: 0.8529 - accuracy: 0.7010 + +
+``` + +``` +
+ 52/183 [=======>......................] - ETA: 31:05 - loss: 0.8545 - accuracy: 0.7019 + +
+``` + +``` +
+ 53/183 [=======>......................] - ETA: 30:50 - loss: 0.8502 - accuracy: 0.7075 + +
+``` + +``` +
+ 54/183 [=======>......................] - ETA: 30:36 - loss: 0.8479 - accuracy: 0.7083 + +
+``` + +``` +
+ 55/183 [========>.....................] - ETA: 30:21 - loss: 0.8517 - accuracy: 0.7068 + +
+``` + +``` +
+ 56/183 [========>.....................] - ETA: 30:07 - loss: 0.8541 - accuracy: 0.7009 + +
+``` + +``` +
+ 57/183 [========>.....................] - ETA: 29:53 - loss: 0.8560 - accuracy: 0.6996 + +
+``` + +``` +
+ 58/183 [========>.....................] - ETA: 29:38 - loss: 0.8572 - accuracy: 0.6983 + +
+``` + +``` +
+ 59/183 [========>.....................] - ETA: 29:24 - loss: 0.8588 - accuracy: 0.6928 + +
+``` + +``` +
+ 60/183 [========>.....................] - ETA: 29:10 - loss: 0.8648 - accuracy: 0.6896 + +
+``` + +``` +
+ 61/183 [=========>....................] - ETA: 28:55 - loss: 0.8662 - accuracy: 0.6885 + +
+``` + +``` +
+ 62/183 [=========>....................] - ETA: 28:41 - loss: 0.8701 - accuracy: 0.6855 + +
+``` + +``` +
+ 63/183 [=========>....................] - ETA: 28:27 - loss: 0.8699 - accuracy: 0.6845 + +
+``` + +``` +
+ 64/183 [=========>....................] - ETA: 28:13 - loss: 0.8668 - accuracy: 0.6875 + +
+``` + +``` +
+ 65/183 [=========>....................] - ETA: 27:58 - loss: 0.8760 - accuracy: 0.6846 + +
+``` + +``` +
+ 66/183 [=========>....................] - ETA: 27:44 - loss: 0.8789 - accuracy: 0.6799 + +
+``` + +``` +
+ 67/183 [=========>....................] - ETA: 27:30 - loss: 0.8779 - accuracy: 0.6791 + +
+``` + +``` +
+ 68/183 [==========>...................] - ETA: 27:15 - loss: 0.8763 - accuracy: 0.6783 + +
+``` + +``` +
+ 69/183 [==========>...................] - ETA: 27:01 - loss: 0.8751 - accuracy: 0.6775 + +
+``` + +``` +
+ 70/183 [==========>...................] - ETA: 26:47 - loss: 0.8755 - accuracy: 0.6750 + +
+``` + +``` +
+ 71/183 [==========>...................] - ETA: 26:32 - loss: 0.8697 - accuracy: 0.6778 + +
+``` + +``` +
+ 72/183 [==========>...................] - ETA: 26:18 - loss: 0.8729 - accuracy: 0.6736 + +
+``` + +``` +
+ 73/183 [==========>...................] - ETA: 26:04 - loss: 0.8713 - accuracy: 0.6747 + +
+``` + +``` +
+ 74/183 [===========>..................] - ETA: 25:50 - loss: 0.8721 - accuracy: 0.6740 + +
+``` + +``` +
+ 75/183 [===========>..................] - ETA: 25:35 - loss: 0.8787 - accuracy: 0.6700 + +
+``` + +``` +
+ 76/183 [===========>..................] - ETA: 25:21 - loss: 0.8769 - accuracy: 0.6694 + +
+``` + +``` +
+ 77/183 [===========>..................] - ETA: 25:07 - loss: 0.8743 - accuracy: 0.6705 + +
+``` + +``` +
+ 78/183 [===========>..................] - ETA: 24:53 - loss: 0.8794 - accuracy: 0.6683 + +
+``` + +``` +
+ 79/183 [===========>..................] - ETA: 24:39 - loss: 0.8800 - accuracy: 0.6677 + +
+``` + +``` +
+ 80/183 [============>.................] - ETA: 24:24 - loss: 0.8773 - accuracy: 0.6687 + +
+``` + +``` +
+ 81/183 [============>.................] - ETA: 24:10 - loss: 0.8769 - accuracy: 0.6682 + +
+``` + +``` +
+ 82/183 [============>.................] - ETA: 23:56 - loss: 0.8788 - accuracy: 0.6677 + +
+``` + +``` +
+ 83/183 [============>.................] - ETA: 23:42 - loss: 0.8773 - accuracy: 0.6672 + +
+``` + +``` +
+ 84/183 [============>.................] - ETA: 23:27 - loss: 0.8800 - accuracy: 0.6652 + +
+``` + +``` +
+ 85/183 [============>.................] - ETA: 23:13 - loss: 0.8819 - accuracy: 0.6632 + +
+``` + +``` +
+ 86/183 [=============>................] - ETA: 22:59 - loss: 0.8789 - accuracy: 0.6657 + +
+``` + +``` +
+ 87/183 [=============>................] - ETA: 22:45 - loss: 0.8813 - accuracy: 0.6667 + +
+``` + +``` +
+ 88/183 [=============>................] - ETA: 22:31 - loss: 0.8872 - accuracy: 0.6619 + +
+``` + +``` +
+ 89/183 [=============>................] - ETA: 22:16 - loss: 0.8847 - accuracy: 0.6629 + +
+``` + +``` +
+ 90/183 [=============>................] - ETA: 22:02 - loss: 0.8823 - accuracy: 0.6639 + +
+``` + +``` +
+ 91/183 [=============>................] - ETA: 21:48 - loss: 0.8859 - accuracy: 0.6621 + +
+``` + +``` +
+ 92/183 [==============>...............] - ETA: 21:34 - loss: 0.8902 - accuracy: 0.6617 + +
+``` + +``` +
+ 93/183 [==============>...............] - ETA: 21:20 - loss: 0.8896 - accuracy: 0.6626 + +
+``` + +``` +
+ 94/183 [==============>...............] - ETA: 21:05 - loss: 0.8932 - accuracy: 0.6622 + +
+``` + +``` +
+ 95/183 [==============>...............] - ETA: 20:51 - loss: 0.8946 - accuracy: 0.6618 + +
+``` + +``` +
+ 96/183 [==============>...............] - ETA: 20:37 - loss: 0.8960 - accuracy: 0.6628 + +
+``` + +``` +
+ 97/183 [==============>...............] - ETA: 20:23 - loss: 0.8934 - accuracy: 0.6649 + +
+``` + +``` +
+ 98/183 [===============>..............] - ETA: 20:08 - loss: 0.8942 - accuracy: 0.6658 + +
+``` + +``` +
+ 99/183 [===============>..............] - ETA: 19:54 - loss: 0.9002 - accuracy: 0.6629 + +
+``` + +``` +
+100/183 [===============>..............] - ETA: 19:40 - loss: 0.8975 - accuracy: 0.6637 + +
+``` + +``` +
+101/183 [===============>..............] - ETA: 19:26 - loss: 0.8965 - accuracy: 0.6646 + +
+``` + +``` +
+102/183 [===============>..............] - ETA: 19:11 - loss: 0.8963 - accuracy: 0.6642 + +
+``` + +``` +
+103/183 [===============>..............] - ETA: 18:57 - loss: 0.8950 - accuracy: 0.6650 + +
+``` + +``` +
+104/183 [================>.............] - ETA: 18:43 - loss: 0.8935 - accuracy: 0.6659 + +
+``` + +``` +
+105/183 [================>.............] - ETA: 18:29 - loss: 0.8912 - accuracy: 0.6667 + +
+``` + +``` +
+106/183 [================>.............] - ETA: 18:14 - loss: 0.8940 - accuracy: 0.6663 + +
+``` + +``` +
+107/183 [================>.............] - ETA: 18:00 - loss: 0.8913 - accuracy: 0.6671 + +
+``` + +``` +
+108/183 [================>.............] - ETA: 17:46 - loss: 0.8920 - accuracy: 0.6667 + +
+``` + +``` +
+109/183 [================>.............] - ETA: 17:32 - loss: 0.8915 - accuracy: 0.6674 + +
+``` + +``` +
+110/183 [=================>............] - ETA: 17:18 - loss: 0.8893 - accuracy: 0.6682 + +
+``` + +``` +
+111/183 [=================>............] - ETA: 17:03 - loss: 0.8909 - accuracy: 0.6667 + +
+``` + +``` +
+112/183 [=================>............] - ETA: 16:49 - loss: 0.8894 - accuracy: 0.6674 + +
+``` + +``` +
+113/183 [=================>............] - ETA: 16:35 - loss: 0.8909 - accuracy: 0.6659 + +
+``` + +``` +
+114/183 [=================>............] - ETA: 16:21 - loss: 0.8908 - accuracy: 0.6667 + +
+``` + +``` +
+115/183 [=================>............] - ETA: 16:07 - loss: 0.8943 - accuracy: 0.6652 + +
+``` + +``` +
+116/183 [==================>...........] - ETA: 15:53 - loss: 0.8956 - accuracy: 0.6659 + +
+``` + +``` +
+117/183 [==================>...........] - ETA: 15:40 - loss: 0.8949 - accuracy: 0.6656 + +
+``` + +``` +
+118/183 [==================>...........] - ETA: 15:26 - loss: 0.8907 - accuracy: 0.6684 + +
+``` + +``` +
+119/183 [==================>...........] - ETA: 15:11 - loss: 0.8892 - accuracy: 0.6691 + +
+``` + +``` +
+120/183 [==================>...........] - ETA: 14:57 - loss: 0.8889 - accuracy: 0.6677 + +
+``` + +``` +
+121/183 [==================>...........] - ETA: 14:43 - loss: 0.8853 - accuracy: 0.6694 + +
+``` + +``` +
+122/183 [===================>..........] - ETA: 14:29 - loss: 0.8860 - accuracy: 0.6691 + +
+``` + +``` +
+123/183 [===================>..........] - ETA: 14:14 - loss: 0.8832 - accuracy: 0.6707 + +
+``` + +``` +
+124/183 [===================>..........] - ETA: 14:00 - loss: 0.8812 - accuracy: 0.6724 + +
+``` + +``` +
+125/183 [===================>..........] - ETA: 13:46 - loss: 0.8806 - accuracy: 0.6720 + +
+``` + +``` +
+126/183 [===================>..........] - ETA: 13:32 - loss: 0.8807 - accuracy: 0.6696 + +
+``` + +``` +
+127/183 [===================>..........] - ETA: 13:17 - loss: 0.8778 - accuracy: 0.6713 + +
+``` + +``` +
+128/183 [===================>..........] - ETA: 13:03 - loss: 0.8790 - accuracy: 0.6719 + +
+``` + +``` +
+129/183 [====================>.........] - ETA: 12:49 - loss: 0.8775 - accuracy: 0.6725 + +
+``` + +``` +
+130/183 [====================>.........] - ETA: 12:35 - loss: 0.8775 - accuracy: 0.6731 + +
+``` + +``` +
+131/183 [====================>.........] - ETA: 12:21 - loss: 0.8785 - accuracy: 0.6718 + +
+``` + +``` +
+132/183 [====================>.........] - ETA: 12:07 - loss: 0.8759 - accuracy: 0.6733 + +
+``` + +``` +
+133/183 [====================>.........] - ETA: 11:52 - loss: 0.8739 - accuracy: 0.6739 + +
+``` + +``` +
+134/183 [====================>.........] - ETA: 11:38 - loss: 0.8749 - accuracy: 0.6735 + +
+``` + +``` +
+135/183 [=====================>........] - ETA: 11:24 - loss: 0.8742 - accuracy: 0.6741 + +
+``` + +``` +
+136/183 [=====================>........] - ETA: 11:10 - loss: 0.8738 - accuracy: 0.6728 + +
+``` + +``` +
+137/183 [=====================>........] - ETA: 10:56 - loss: 0.8752 - accuracy: 0.6715 + +
+``` + +``` +
+138/183 [=====================>........] - ETA: 10:41 - loss: 0.8792 - accuracy: 0.6694 + +
+``` + +``` +
+139/183 [=====================>........] - ETA: 10:27 - loss: 0.8795 - accuracy: 0.6691 + +
+``` + +``` +
+140/183 [=====================>........] - ETA: 10:13 - loss: 0.8808 - accuracy: 0.6670 + +
+``` + +``` +
+141/183 [======================>.......] - ETA: 9:59 - loss: 0.8836 - accuracy: 0.6667 + +
+``` + +``` +
+142/183 [======================>.......] - ETA: 9:44 - loss: 0.8848 - accuracy: 0.6664 + +
+``` + +``` +
+143/183 [======================>.......] - ETA: 9:30 - loss: 0.8833 - accuracy: 0.6661 + +
+``` + +``` +
+144/183 [======================>.......] - ETA: 9:16 - loss: 0.8850 - accuracy: 0.6641 + +
+``` + +``` +
+145/183 [======================>.......] - ETA: 9:02 - loss: 0.8841 - accuracy: 0.6647 + +
+``` + +``` +
+146/183 [======================>.......] - ETA: 8:47 - loss: 0.8825 - accuracy: 0.6661 + +
+``` + +``` +
+147/183 [=======================>......] - ETA: 8:33 - loss: 0.8814 - accuracy: 0.6675 + +
+``` + +``` +
+148/183 [=======================>......] - ETA: 8:19 - loss: 0.8801 - accuracy: 0.6698 + +
+``` + +``` +
+149/183 [=======================>......] - ETA: 8:05 - loss: 0.8782 - accuracy: 0.6703 + +
+``` + +``` +
+150/183 [=======================>......] - ETA: 7:51 - loss: 0.8789 - accuracy: 0.6700 + +
+``` + +``` +
+151/183 [=======================>......] - ETA: 7:36 - loss: 0.8776 - accuracy: 0.6705 + +
+``` + +``` +
+152/183 [=======================>......] - ETA: 7:22 - loss: 0.8797 - accuracy: 0.6694 + +
+``` + +``` +
+153/183 [========================>.....] - ETA: 7:08 - loss: 0.8804 - accuracy: 0.6691 + +
+``` + +``` +
+154/183 [========================>.....] - ETA: 6:53 - loss: 0.8793 - accuracy: 0.6688 + +
+``` + +``` +
+155/183 [========================>.....] - ETA: 6:39 - loss: 0.8793 - accuracy: 0.6685 + +
+``` + +``` +
+156/183 [========================>.....] - ETA: 6:25 - loss: 0.8776 - accuracy: 0.6691 + +
+``` + +``` +
+157/183 [========================>.....] - ETA: 6:11 - loss: 0.8755 - accuracy: 0.6704 + +
+``` + +``` +
+158/183 [========================>.....] - ETA: 5:57 - loss: 0.8768 - accuracy: 0.6701 + +
+``` + +``` +
+159/183 [=========================>....] - ETA: 5:42 - loss: 0.8771 - accuracy: 0.6698 + +
+``` + +``` +
+160/183 [=========================>....] - ETA: 5:28 - loss: 0.8761 - accuracy: 0.6703 + +
+``` + +``` +
+161/183 [=========================>....] - ETA: 5:14 - loss: 0.8734 - accuracy: 0.6716 + +
+``` + +``` +
+162/183 [=========================>....] - ETA: 4:59 - loss: 0.8730 - accuracy: 0.6713 + +
+``` + +``` +
+163/183 [=========================>....] - ETA: 4:45 - loss: 0.8722 - accuracy: 0.6710 + +
+``` + +``` +
+164/183 [=========================>....] - ETA: 4:31 - loss: 0.8728 - accuracy: 0.6707 + +
+``` + +``` +
+165/183 [==========================>...] - ETA: 4:17 - loss: 0.8743 - accuracy: 0.6697 + +
+``` + +``` +
+166/183 [==========================>...] - ETA: 4:02 - loss: 0.8745 - accuracy: 0.6702 + +
+``` + +``` +
+167/183 [==========================>...] - ETA: 3:48 - loss: 0.8753 - accuracy: 0.6684 + +
+``` + +``` +
+168/183 [==========================>...] - ETA: 3:34 - loss: 0.8738 - accuracy: 0.6696 + +
+``` + +``` +
+169/183 [==========================>...] - ETA: 3:20 - loss: 0.8724 - accuracy: 0.6694 + +
+``` + +``` +
+170/183 [==========================>...] - ETA: 3:05 - loss: 0.8757 - accuracy: 0.6676 + +
+``` + +``` +
+171/183 [===========================>..] - ETA: 2:51 - loss: 0.8752 - accuracy: 0.6674 + +
+``` + +``` +
+172/183 [===========================>..] - ETA: 2:37 - loss: 0.8768 - accuracy: 0.6672 + +
+``` + +``` +
+173/183 [===========================>..] - ETA: 2:22 - loss: 0.8750 - accuracy: 0.6676 + +
+``` + +``` +
+174/183 [===========================>..] - ETA: 2:08 - loss: 0.8753 - accuracy: 0.6681 + +
+``` + +``` +
+175/183 [===========================>..] - ETA: 1:54 - loss: 0.8749 - accuracy: 0.6679 + +
+``` + +``` +
+176/183 [===========================>..] - ETA: 1:40 - loss: 0.8739 - accuracy: 0.6683 + +
+``` + +``` +
+177/183 [============================>.] - ETA: 1:25 - loss: 0.8720 - accuracy: 0.6688 + +
+``` + +``` +
+178/183 [============================>.] - ETA: 1:11 - loss: 0.8719 - accuracy: 0.6692 + +
+``` + +``` +
+179/183 [============================>.] - ETA: 57s - loss: 0.8739 - accuracy: 0.6669 + +
+``` + +``` +
+180/183 [============================>.] - ETA: 42s - loss: 0.8729 - accuracy: 0.6674 + +
+``` + +``` +
+181/183 [============================>.] - ETA: 28s - loss: 0.8722 - accuracy: 0.6678 + +
+``` + +``` +
+182/183 [============================>.] - ETA: 14s - loss: 0.8715 - accuracy: 0.6683 + +
+``` + +``` +
+183/183 [==============================] - ETA: 0s - loss: 0.8728 - accuracy: 0.6680 + +
+``` + +``` +
+183/183 [==============================] - 2778s 15s/step - loss: 0.8728 - accuracy: 0.6680 - val_loss: 0.7296 - val_accuracy: 0.7525 - lr: 4.7230e-06 + + +
+``` +Epoch 5/5 + +``` +
+ + 1/183 [..............................] - ETA: 45:36 - loss: 0.7472 - accuracy: 0.6250 + +
+``` + +``` +
+ 2/183 [..............................] - ETA: 44:02 - loss: 0.7747 - accuracy: 0.6875 + +
+``` + +``` +
+ 3/183 [..............................] - ETA: 43:51 - loss: 0.7801 - accuracy: 0.6667 + +
+``` + +``` +
+ 4/183 [..............................] - ETA: 43:41 - loss: 0.7945 - accuracy: 0.6250 + +
+``` + +``` +
+ 5/183 [..............................] - ETA: 43:26 - loss: 0.8398 - accuracy: 0.6500 + +
+``` + +``` +
+ 6/183 [..............................] - ETA: 43:07 - loss: 0.7811 - accuracy: 0.6875 + +
+``` + +``` +
+ 7/183 [>.............................] - ETA: 42:47 - loss: 0.8120 - accuracy: 0.6964 + +
+``` + +``` +
+ 8/183 [>.............................] - ETA: 42:30 - loss: 0.7819 - accuracy: 0.6875 + +
+``` + +``` +
+ 9/183 [>.............................] - ETA: 42:09 - loss: 0.7870 - accuracy: 0.6944 + +
+``` + +``` +
+ 10/183 [>.............................] - ETA: 41:50 - loss: 0.7538 - accuracy: 0.7125 + +
+``` + +``` +
+ 11/183 [>.............................] - ETA: 41:33 - loss: 0.7518 - accuracy: 0.7159 + +
+``` + +``` +
+ 12/183 [>.............................] - ETA: 41:17 - loss: 0.7440 - accuracy: 0.7188 + +
+``` + +``` +
+ 13/183 [=>............................] - ETA: 41:00 - loss: 0.7263 - accuracy: 0.7404 + +
+``` + +``` +
+ 14/183 [=>............................] - ETA: 40:44 - loss: 0.7001 - accuracy: 0.7589 + +
+``` + +``` +
+ 15/183 [=>............................] - ETA: 40:28 - loss: 0.7132 - accuracy: 0.7583 + +
+``` + +``` +
+ 16/183 [=>............................] - ETA: 40:11 - loss: 0.7123 - accuracy: 0.7500 + +
+``` + +``` +
+ 17/183 [=>............................] - ETA: 39:55 - loss: 0.7370 - accuracy: 0.7426 + +
+``` + +``` +
+ 18/183 [=>............................] - ETA: 39:38 - loss: 0.7365 - accuracy: 0.7431 + +
+``` + +``` +
+ 19/183 [==>...........................] - ETA: 39:22 - loss: 0.7469 - accuracy: 0.7303 + +
+``` + +``` +
+ 20/183 [==>...........................] - ETA: 39:07 - loss: 0.7500 - accuracy: 0.7375 + +
+``` + +``` +
+ 21/183 [==>...........................] - ETA: 38:52 - loss: 0.7459 - accuracy: 0.7440 + +
+``` + +``` +
+ 22/183 [==>...........................] - ETA: 38:37 - loss: 0.7396 - accuracy: 0.7557 + +
+``` + +``` +
+ 23/183 [==>...........................] - ETA: 38:21 - loss: 0.7387 - accuracy: 0.7500 + +
+``` + +``` +
+ 24/183 [==>...........................] - ETA: 38:06 - loss: 0.7266 - accuracy: 0.7552 + +
+``` + +``` +
+ 25/183 [===>..........................] - ETA: 37:51 - loss: 0.7416 - accuracy: 0.7400 + +
+``` + +``` +
+ 26/183 [===>..........................] - ETA: 37:37 - loss: 0.7411 - accuracy: 0.7404 + +
+``` + +``` +
+ 27/183 [===>..........................] - ETA: 37:23 - loss: 0.7337 - accuracy: 0.7454 + +
+``` + +``` +
+ 28/183 [===>..........................] - ETA: 37:09 - loss: 0.7336 - accuracy: 0.7411 + +
+``` + +``` +
+ 29/183 [===>..........................] - ETA: 36:54 - loss: 0.7294 - accuracy: 0.7457 + +
+``` + +``` +
+ 30/183 [===>..........................] - ETA: 36:40 - loss: 0.7293 - accuracy: 0.7417 + +
+``` + +``` +
+ 31/183 [====>.........................] - ETA: 36:26 - loss: 0.7399 - accuracy: 0.7379 + +
+``` + +``` +
+ 32/183 [====>.........................] - ETA: 36:11 - loss: 0.7355 - accuracy: 0.7422 + +
+``` + +``` +
+ 33/183 [====>.........................] - ETA: 35:57 - loss: 0.7283 - accuracy: 0.7462 + +
+``` + +``` +
+ 34/183 [====>.........................] - ETA: 35:43 - loss: 0.7330 - accuracy: 0.7426 + +
+``` + +``` +
+ 35/183 [====>.........................] - ETA: 35:28 - loss: 0.7390 - accuracy: 0.7321 + +
+``` + +``` +
+ 36/183 [====>.........................] - ETA: 35:14 - loss: 0.7381 - accuracy: 0.7292 + +
+``` + +``` +
+ 37/183 [=====>........................] - ETA: 34:59 - loss: 0.7374 - accuracy: 0.7264 + +
+``` + +``` +
+ 38/183 [=====>........................] - ETA: 34:45 - loss: 0.7359 - accuracy: 0.7303 + +
+``` + +``` +
+ 39/183 [=====>........................] - ETA: 34:31 - loss: 0.7345 - accuracy: 0.7340 + +
+``` + +``` +
+ 40/183 [=====>........................] - ETA: 34:16 - loss: 0.7355 - accuracy: 0.7344 + +
+``` + +``` +
+ 41/183 [=====>........................] - ETA: 34:01 - loss: 0.7277 - accuracy: 0.7378 + +
+``` + +``` +
+ 42/183 [=====>........................] - ETA: 33:48 - loss: 0.7305 - accuracy: 0.7381 + +
+``` + +``` +
+ 43/183 [======>.......................] - ETA: 33:33 - loss: 0.7320 - accuracy: 0.7355 + +
+``` + +``` +
+ 44/183 [======>.......................] - ETA: 33:18 - loss: 0.7283 - accuracy: 0.7386 + +
+``` + +``` +
+ 45/183 [======>.......................] - ETA: 33:03 - loss: 0.7341 - accuracy: 0.7333 + +
+``` + +``` +
+ 46/183 [======>.......................] - ETA: 32:48 - loss: 0.7445 - accuracy: 0.7255 + +
+``` + +``` +
+ 47/183 [======>.......................] - ETA: 32:33 - loss: 0.7413 - accuracy: 0.7287 + +
+``` + +``` +
+ 48/183 [======>.......................] - ETA: 32:18 - loss: 0.7428 - accuracy: 0.7292 + +
+``` + +``` +
+ 49/183 [=======>......................] - ETA: 32:03 - loss: 0.7457 - accuracy: 0.7270 + +
+``` + +``` +
+ 50/183 [=======>......................] - ETA: 31:49 - loss: 0.7504 - accuracy: 0.7250 + +
+``` + +``` +
+ 51/183 [=======>......................] - ETA: 31:34 - loss: 0.7524 - accuracy: 0.7181 + +
+``` + +``` +
+ 52/183 [=======>......................] - ETA: 31:19 - loss: 0.7636 - accuracy: 0.7163 + +
+``` + +``` +
+ 53/183 [=======>......................] - ETA: 31:04 - loss: 0.7691 - accuracy: 0.7123 + +
+``` + +``` +
+ 54/183 [=======>......................] - ETA: 30:50 - loss: 0.7681 - accuracy: 0.7130 + +
+``` + +``` +
+ 55/183 [========>.....................] - ETA: 30:35 - loss: 0.7717 - accuracy: 0.7091 + +
+``` + +``` +
+ 56/183 [========>.....................] - ETA: 30:20 - loss: 0.7725 - accuracy: 0.7098 + +
+``` + +``` +
+ 57/183 [========>.....................] - ETA: 30:05 - loss: 0.7781 - accuracy: 0.7105 + +
+``` + +``` +
+ 58/183 [========>.....................] - ETA: 29:51 - loss: 0.7811 - accuracy: 0.7091 + +
+``` + +``` +
+ 59/183 [========>.....................] - ETA: 29:36 - loss: 0.7856 - accuracy: 0.7097 + +
+``` + +``` +
+ 60/183 [========>.....................] - ETA: 29:22 - loss: 0.7853 - accuracy: 0.7083 + +
+``` + +``` +
+ 61/183 [=========>....................] - ETA: 29:07 - loss: 0.7866 - accuracy: 0.7111 + +
+``` + +``` +
+ 62/183 [=========>....................] - ETA: 28:53 - loss: 0.7861 - accuracy: 0.7117 + +
+``` + +``` +
+ 63/183 [=========>....................] - ETA: 28:38 - loss: 0.7909 - accuracy: 0.7083 + +
+``` + +``` +
+ 64/183 [=========>....................] - ETA: 28:24 - loss: 0.7890 - accuracy: 0.7070 + +
+``` + +``` +
+ 65/183 [=========>....................] - ETA: 28:09 - loss: 0.7919 - accuracy: 0.7058 + +
+``` + +``` +
+ 66/183 [=========>....................] - ETA: 27:54 - loss: 0.7981 - accuracy: 0.7027 + +
+``` + +``` +
+ 67/183 [=========>....................] - ETA: 27:40 - loss: 0.7995 - accuracy: 0.7015 + +
+``` + +``` +
+ 68/183 [==========>...................] - ETA: 27:25 - loss: 0.7972 - accuracy: 0.7022 + +
+``` + +``` +
+ 69/183 [==========>...................] - ETA: 27:11 - loss: 0.7957 - accuracy: 0.7029 + +
+``` + +``` +
+ 70/183 [==========>...................] - ETA: 26:57 - loss: 0.7951 - accuracy: 0.7036 + +
+``` + +``` +
+ 71/183 [==========>...................] - ETA: 26:43 - loss: 0.7939 - accuracy: 0.7042 + +
+``` + +``` +
+ 72/183 [==========>...................] - ETA: 26:28 - loss: 0.7897 - accuracy: 0.7049 + +
+``` + +``` +
+ 73/183 [==========>...................] - ETA: 26:13 - loss: 0.7879 - accuracy: 0.7055 + +
+``` + +``` +
+ 74/183 [===========>..................] - ETA: 25:59 - loss: 0.7864 - accuracy: 0.7044 + +
+``` + +``` +
+ 75/183 [===========>..................] - ETA: 25:44 - loss: 0.7859 - accuracy: 0.7050 + +
+``` + +``` +
+ 76/183 [===========>..................] - ETA: 25:30 - loss: 0.7883 - accuracy: 0.7056 + +
+``` + +``` +
+ 77/183 [===========>..................] - ETA: 25:16 - loss: 0.7881 - accuracy: 0.7062 + +
+``` + +``` +
+ 78/183 [===========>..................] - ETA: 25:01 - loss: 0.7931 - accuracy: 0.7035 + +
+``` + +``` +
+ 79/183 [===========>..................] - ETA: 24:47 - loss: 0.7971 - accuracy: 0.7009 + +
+``` + +``` +
+ 80/183 [============>.................] - ETA: 24:32 - loss: 0.7980 - accuracy: 0.7000 + +
+``` + +``` +
+ 81/183 [============>.................] - ETA: 24:18 - loss: 0.7948 - accuracy: 0.7022 + +
+``` + +``` +
+ 82/183 [============>.................] - ETA: 24:03 - loss: 0.7942 - accuracy: 0.7027 + +
+``` + +``` +
+ 83/183 [============>.................] - ETA: 23:49 - loss: 0.7900 - accuracy: 0.7048 + +
+``` + +``` +
+ 84/183 [============>.................] - ETA: 23:35 - loss: 0.7926 - accuracy: 0.7024 + +
+``` + +``` +
+ 85/183 [============>.................] - ETA: 23:20 - loss: 0.7966 - accuracy: 0.7000 + +
+``` + +``` +
+ 86/183 [=============>................] - ETA: 23:06 - loss: 0.7997 - accuracy: 0.6977 + +
+``` + +``` +
+ 87/183 [=============>................] - ETA: 22:52 - loss: 0.7973 - accuracy: 0.6997 + +
+``` + +``` +
+ 88/183 [=============>................] - ETA: 22:38 - loss: 0.8052 - accuracy: 0.6960 + +
+``` + +``` +
+ 89/183 [=============>................] - ETA: 22:23 - loss: 0.8064 - accuracy: 0.6952 + +
+``` + +``` +
+ 90/183 [=============>................] - ETA: 22:09 - loss: 0.8023 - accuracy: 0.6972 + +
+``` + +``` +
+ 91/183 [=============>................] - ETA: 21:54 - loss: 0.8045 - accuracy: 0.6978 + +
+``` + +``` +
+ 92/183 [==============>...............] - ETA: 21:40 - loss: 0.8056 - accuracy: 0.6984 + +
+``` + +``` +
+ 93/183 [==============>...............] - ETA: 21:26 - loss: 0.8058 - accuracy: 0.6976 + +
+``` + +``` +
+ 94/183 [==============>...............] - ETA: 21:11 - loss: 0.8039 - accuracy: 0.6981 + +
+``` + +``` +
+ 95/183 [==============>...............] - ETA: 20:57 - loss: 0.8073 - accuracy: 0.6987 + +
+``` + +``` +
+ 96/183 [==============>...............] - ETA: 20:42 - loss: 0.8063 - accuracy: 0.6992 + +
+``` + +``` +
+ 97/183 [==============>...............] - ETA: 20:28 - loss: 0.8076 - accuracy: 0.6972 + +
+``` + +``` +
+ 98/183 [===============>..............] - ETA: 20:14 - loss: 0.8061 - accuracy: 0.6977 + +
+``` + +``` +
+ 99/183 [===============>..............] - ETA: 19:59 - loss: 0.8094 - accuracy: 0.6944 + +
+``` + +``` +
+100/183 [===============>..............] - ETA: 19:45 - loss: 0.8154 - accuracy: 0.6925 + +
+``` + +``` +
+101/183 [===============>..............] - ETA: 19:31 - loss: 0.8130 - accuracy: 0.6943 + +
+``` + +``` +
+102/183 [===============>..............] - ETA: 19:16 - loss: 0.8113 - accuracy: 0.6949 + +
+``` + +``` +
+103/183 [===============>..............] - ETA: 19:02 - loss: 0.8098 - accuracy: 0.6966 + +
+``` + +``` +
+104/183 [================>.............] - ETA: 18:48 - loss: 0.8088 - accuracy: 0.6971 + +
+``` + +``` +
+105/183 [================>.............] - ETA: 18:33 - loss: 0.8074 - accuracy: 0.6976 + +
+``` + +``` +
+106/183 [================>.............] - ETA: 18:19 - loss: 0.8061 - accuracy: 0.6981 + +
+``` + +``` +
+107/183 [================>.............] - ETA: 18:05 - loss: 0.8043 - accuracy: 0.6986 + +
+``` + +``` +
+108/183 [================>.............] - ETA: 17:50 - loss: 0.8021 - accuracy: 0.7002 + +
+``` + +``` +
+109/183 [================>.............] - ETA: 17:36 - loss: 0.8002 - accuracy: 0.7018 + +
+``` + +``` +
+110/183 [=================>............] - ETA: 17:22 - loss: 0.7979 - accuracy: 0.7045 + +
+``` + +``` +
+111/183 [=================>............] - ETA: 17:07 - loss: 0.7951 - accuracy: 0.7050 + +
+``` + +``` +
+112/183 [=================>............] - ETA: 16:53 - loss: 0.7978 - accuracy: 0.7009 + +
+``` + +``` +
+113/183 [=================>............] - ETA: 16:39 - loss: 0.7977 - accuracy: 0.7013 + +
+``` + +``` +
+114/183 [=================>............] - ETA: 16:24 - loss: 0.8027 - accuracy: 0.6974 + +
+``` + +``` +
+115/183 [=================>............] - ETA: 16:10 - loss: 0.7983 - accuracy: 0.7000 + +
+``` + +``` +
+116/183 [==================>...........] - ETA: 15:56 - loss: 0.8009 - accuracy: 0.6983 + +
+``` + +``` +
+117/183 [==================>...........] - ETA: 15:41 - loss: 0.8030 - accuracy: 0.6976 + +
+``` + +``` +
+118/183 [==================>...........] - ETA: 15:27 - loss: 0.8015 - accuracy: 0.6981 + +
+``` + +``` +
+119/183 [==================>...........] - ETA: 15:13 - loss: 0.7986 - accuracy: 0.6996 + +
+``` + +``` +
+120/183 [==================>...........] - ETA: 14:59 - loss: 0.7966 - accuracy: 0.7010 + +
+``` + +``` +
+121/183 [==================>...........] - ETA: 14:44 - loss: 0.7946 - accuracy: 0.7025 + +
+``` + +``` +
+122/183 [===================>..........] - ETA: 14:30 - loss: 0.7923 - accuracy: 0.7049 + +
+``` + +``` +
+123/183 [===================>..........] - ETA: 14:16 - loss: 0.7925 - accuracy: 0.7043 + +
+``` + +``` +
+124/183 [===================>..........] - ETA: 14:01 - loss: 0.7932 - accuracy: 0.7046 + +
+``` + +``` +
+125/183 [===================>..........] - ETA: 13:47 - loss: 0.7914 - accuracy: 0.7070 + +
+``` + +``` +
+126/183 [===================>..........] - ETA: 13:33 - loss: 0.7918 - accuracy: 0.7054 + +
+``` + +``` +
+127/183 [===================>..........] - ETA: 13:19 - loss: 0.7911 - accuracy: 0.7057 + +
+``` + +``` +
+128/183 [===================>..........] - ETA: 13:04 - loss: 0.7901 - accuracy: 0.7061 + +
+``` + +``` +
+129/183 [====================>.........] - ETA: 12:50 - loss: 0.7908 - accuracy: 0.7054 + +
+``` + +``` +
+130/183 [====================>.........] - ETA: 12:36 - loss: 0.7887 - accuracy: 0.7067 + +
+``` + +``` +
+131/183 [====================>.........] - ETA: 12:21 - loss: 0.7877 - accuracy: 0.7080 + +
+``` + +``` +
+132/183 [====================>.........] - ETA: 12:07 - loss: 0.7871 - accuracy: 0.7083 + +
+``` + +``` +
+133/183 [====================>.........] - ETA: 11:53 - loss: 0.7852 - accuracy: 0.7096 + +
+``` + +``` +
+134/183 [====================>.........] - ETA: 11:39 - loss: 0.7828 - accuracy: 0.7118 + +
+``` + +``` +
+135/183 [=====================>........] - ETA: 11:24 - loss: 0.7804 - accuracy: 0.7139 + +
+``` + +``` +
+136/183 [=====================>........] - ETA: 11:10 - loss: 0.7790 - accuracy: 0.7151 + +
+``` + +``` +
+137/183 [=====================>........] - ETA: 10:56 - loss: 0.7804 - accuracy: 0.7144 + +
+``` + +``` +
+138/183 [=====================>........] - ETA: 10:41 - loss: 0.7795 - accuracy: 0.7156 + +
+``` + +``` +
+139/183 [=====================>........] - ETA: 10:27 - loss: 0.7800 - accuracy: 0.7149 + +
+``` + +``` +
+140/183 [=====================>........] - ETA: 10:13 - loss: 0.7802 - accuracy: 0.7143 + +
+``` + +``` +
+141/183 [======================>.......] - ETA: 9:59 - loss: 0.7813 - accuracy: 0.7137 + +
+``` + +``` +
+142/183 [======================>.......] - ETA: 9:44 - loss: 0.7843 - accuracy: 0.7130 + +
+``` + +``` +
+143/183 [======================>.......] - ETA: 9:30 - loss: 0.7841 - accuracy: 0.7133 + +
+``` + +``` +
+144/183 [======================>.......] - ETA: 9:16 - loss: 0.7848 - accuracy: 0.7135 + +
+``` + +``` +
+145/183 [======================>.......] - ETA: 9:01 - loss: 0.7835 - accuracy: 0.7138 + +
+``` + +``` +
+146/183 [======================>.......] - ETA: 8:47 - loss: 0.7817 - accuracy: 0.7149 + +
+``` + +``` +
+147/183 [=======================>......] - ETA: 8:33 - loss: 0.7827 - accuracy: 0.7143 + +
+``` + +``` +
+148/183 [=======================>......] - ETA: 8:19 - loss: 0.7813 - accuracy: 0.7145 + +
+``` + +``` +
+149/183 [=======================>......] - ETA: 8:04 - loss: 0.7820 - accuracy: 0.7148 + +
+``` + +``` +
+150/183 [=======================>......] - ETA: 7:50 - loss: 0.7804 - accuracy: 0.7158 + +
+``` + +``` +
+151/183 [=======================>......] - ETA: 7:36 - loss: 0.7809 - accuracy: 0.7169 + +
+``` + +``` +
+152/183 [=======================>......] - ETA: 7:22 - loss: 0.7802 - accuracy: 0.7171 + +
+``` + +``` +
+153/183 [========================>.....] - ETA: 7:07 - loss: 0.7851 - accuracy: 0.7141 + +
+``` + +``` +
+154/183 [========================>.....] - ETA: 6:53 - loss: 0.7865 - accuracy: 0.7135 + +
+``` + +``` +
+155/183 [========================>.....] - ETA: 6:39 - loss: 0.7845 - accuracy: 0.7145 + +
+``` + +``` +
+156/183 [========================>.....] - ETA: 6:24 - loss: 0.7830 - accuracy: 0.7155 + +
+``` + +``` +
+157/183 [========================>.....] - ETA: 6:10 - loss: 0.7830 - accuracy: 0.7150 + +
+``` + +``` +
+158/183 [========================>.....] - ETA: 5:56 - loss: 0.7843 - accuracy: 0.7152 + +
+``` + +``` +
+159/183 [=========================>....] - ETA: 5:42 - loss: 0.7841 - accuracy: 0.7146 + +
+``` + +``` +
+160/183 [=========================>....] - ETA: 5:27 - loss: 0.7842 - accuracy: 0.7148 + +
+``` + +``` +
+161/183 [=========================>....] - ETA: 5:13 - loss: 0.7826 - accuracy: 0.7151 + +
+``` + +``` +
+162/183 [=========================>....] - ETA: 4:59 - loss: 0.7822 - accuracy: 0.7160 + +
+``` + +``` +
+163/183 [=========================>....] - ETA: 4:45 - loss: 0.7811 - accuracy: 0.7163 + +
+``` + +``` +
+164/183 [=========================>....] - ETA: 4:30 - loss: 0.7808 - accuracy: 0.7157 + +
+``` + +``` +
+165/183 [==========================>...] - ETA: 4:16 - loss: 0.7798 - accuracy: 0.7167 + +
+``` + +``` +
+166/183 [==========================>...] - ETA: 4:02 - loss: 0.7796 - accuracy: 0.7169 + +
+``` + +``` +
+167/183 [==========================>...] - ETA: 3:48 - loss: 0.7798 - accuracy: 0.7171 + +
+``` + +``` +
+168/183 [==========================>...] - ETA: 3:33 - loss: 0.7794 - accuracy: 0.7173 + +
+``` + +``` +
+169/183 [==========================>...] - ETA: 3:19 - loss: 0.7796 - accuracy: 0.7167 + +
+``` + +``` +
+170/183 [==========================>...] - ETA: 3:05 - loss: 0.7789 - accuracy: 0.7162 + +
+``` + +``` +
+171/183 [===========================>..] - ETA: 2:51 - loss: 0.7807 - accuracy: 0.7142 + +
+``` + +``` +
+172/183 [===========================>..] - ETA: 2:36 - loss: 0.7788 - accuracy: 0.7151 + +
+``` + +``` +
+173/183 [===========================>..] - ETA: 2:22 - loss: 0.7807 - accuracy: 0.7139 + +
+``` + +``` +
+174/183 [===========================>..] - ETA: 2:08 - loss: 0.7793 - accuracy: 0.7148 + +
+``` + +``` +
+175/183 [===========================>..] - ETA: 1:54 - loss: 0.7791 - accuracy: 0.7157 + +
+``` + +``` +
+176/183 [===========================>..] - ETA: 1:39 - loss: 0.7799 - accuracy: 0.7138 + +
+``` + +``` +
+177/183 [============================>.] - ETA: 1:25 - loss: 0.7768 - accuracy: 0.7154 + +
+``` + +``` +
+178/183 [============================>.] - ETA: 1:11 - loss: 0.7748 - accuracy: 0.7156 + +
+``` + +``` +
+179/183 [============================>.] - ETA: 57s - loss: 0.7741 - accuracy: 0.7158 + +
+``` + +``` +
+180/183 [============================>.] - ETA: 42s - loss: 0.7740 - accuracy: 0.7153 + +
+``` + +``` +
+181/183 [============================>.] - ETA: 28s - loss: 0.7727 - accuracy: 0.7162 + +
+``` + +``` +
+182/183 [============================>.] - ETA: 14s - loss: 0.7719 - accuracy: 0.7163 + +
+``` + +``` +
+183/183 [==============================] - ETA: 0s - loss: 0.7714 - accuracy: 0.7158 + +
+``` + +``` +
+183/183 [==============================] - 2764s 15s/step - loss: 0.7714 - accuracy: 0.7158 - val_loss: 0.7098 - val_accuracy: 0.7500 - lr: 4.4984e-06 + + +--- +## Inference + + +```python +# Make predictions using the trained model on last validation data +predictions = model.predict( + valid_ds, + batch_size=CFG.batch_size, # max batch size = valid size + verbose=1, +) + +# Format predictions and true answers +pred_answers = np.arange(4)[np.argsort(-predictions)][:, 0] +true_answers = valid_df.label.values # Check 5 Predictions print("# Predictions\n") @@ -727,36 +7472,389 @@ for i in range(0, 50, 10): question = row.startphrase pred_answer = f"ending{pred_answers[i]}" true_answer = f"ending{true_answers[i]}" - print(f"❓ Sentence {i+1}:\n{question}\n") - print(f"✅ True Ending: {true_answer}\n >> {row[true_answer]}\n") - print(f"🤖 Predicted Ending: {pred_answer}\n >> {row[pred_answer]}\n") + print(f"❓ Sentence {i+1}:\n{question}\n") + print(f"✅ True Ending: {true_answer}\n >> {row[true_answer]}\n") + print(f"🤖 Predicted Ending: {pred_answer}\n >> {row[pred_answer]}\n") print("-" * 90, "\n") ``` + + 1/50 [..............................] - ETA: 32:35 + +
+``` + +``` +
+ 2/50 [>.............................] - ETA: 2:26 + +
+``` + +``` +
+ 3/50 [>.............................] - ETA: 2:25 + +
+``` + +``` +
+ 4/50 [=>............................] - ETA: 2:22 + +
+``` + +``` +
+ 5/50 [==>...........................] - ETA: 2:19 + +
+``` + +``` +
+ 6/50 [==>...........................] - ETA: 2:16 + +
+``` + +``` +
+ 7/50 [===>..........................] - ETA: 2:13 + +
+``` + +``` +
+ 8/50 [===>..........................] - ETA: 2:10 + +
+``` + +``` +
+ 9/50 [====>.........................] - ETA: 2:07 + +
+``` + +``` +
+10/50 [=====>........................] - ETA: 2:04 + +
+``` + +``` +
+11/50 [=====>........................] - ETA: 2:01 + +
+``` + +``` +
+12/50 [======>.......................] - ETA: 1:58 + +
+``` + +``` +
+13/50 [======>.......................] - ETA: 1:55 + +
+``` + +``` +
+14/50 [=======>......................] - ETA: 1:51 + +
+``` + +``` +
+15/50 [========>.....................] - ETA: 1:48 + +
+``` + +``` +
+16/50 [========>.....................] - ETA: 1:45 + +
+``` + +``` +
+17/50 [=========>....................] - ETA: 1:42 + +
+``` + +``` +
+18/50 [=========>....................] - ETA: 1:39 + +
+``` + +``` +
+19/50 [==========>...................] - ETA: 1:36 + +
+``` + +``` +
+20/50 [===========>..................] - ETA: 1:33 + +
+``` + +``` +
+21/50 [===========>..................] - ETA: 1:30 + +
+``` + +``` +
+22/50 [============>.................] - ETA: 1:26 + +
+``` + +``` +
+23/50 [============>.................] - ETA: 1:23 + +
+``` + +``` +
+24/50 [=============>................] - ETA: 1:20 + +
+``` + +``` +
+25/50 [==============>...............] - ETA: 1:17 + +
+``` + +``` +
+26/50 [==============>...............] - ETA: 1:14 + +
+``` + +``` +
+27/50 [===============>..............] - ETA: 1:11 + +
+``` + +``` +
+28/50 [===============>..............] - ETA: 1:08 + +
+``` + +``` +
+29/50 [================>.............] - ETA: 1:05 + +
+``` + +``` +
+30/50 [=================>............] - ETA: 1:02 + +
+``` + +``` +
+31/50 [=================>............] - ETA: 58s + +
+``` + +``` +
+32/50 [==================>...........] - ETA: 55s + +
+``` + +``` +
+33/50 [==================>...........] - ETA: 52s + +
+``` + +``` +
+34/50 [===================>..........] - ETA: 49s + +
+``` + +``` +
+35/50 [====================>.........] - ETA: 46s + +
+``` + +``` +
+36/50 [====================>.........] - ETA: 43s + +
+``` + +``` +
+37/50 [=====================>........] - ETA: 40s + +
+``` + +``` +
+38/50 [=====================>........] - ETA: 37s + +
+``` + +``` +
+39/50 [======================>.......] - ETA: 34s + +
+``` + +``` +
+40/50 [=======================>......] - ETA: 31s + +
+``` + +``` +
+41/50 [=======================>......] - ETA: 27s + +
+``` + +``` +
+42/50 [========================>.....] - ETA: 24s + +
+``` + +``` +
+43/50 [========================>.....] - ETA: 21s + +
+``` + +``` +
+44/50 [=========================>....] - ETA: 18s + +
+``` + +``` +
+45/50 [==========================>...] - ETA: 15s + +
+``` + +``` +
+46/50 [==========================>...] - ETA: 12s + +
+``` + +``` +
+47/50 [===========================>..] - ETA: 9s + +
+``` + +``` +
+48/50 [===========================>..] - ETA: 6s + +
+``` + +``` +
+49/50 [============================>.] - ETA: 3s + +
+``` + +``` +
+50/50 [==============================] - ETA: 0s + +
+``` + +``` +
+50/50 [==============================] - 192s 3s/step + +
``` - 50/50 ━━━━━━━━━━━━━━━━━━━━ 274s 5s/step # Predictions ```
``` -❓ Sentence 1: +❓ Sentence 1: The man shows the teens how to move the oars. The teens ```
``` -✅ True Ending: ending3 +✅ True Ending: ending3 >> follow the instructions of the man and row the oars. ```
``` -🤖 Predicted Ending: ending3 +🤖 Predicted Ending: ending3 >> follow the instructions of the man and row the oars. ```
@@ -769,21 +7867,21 @@ The man shows the teens how to move the oars. The teens
``` -❓ Sentence 11: +❓ Sentence 11: A lake reflects the mountains and the sky. Someone ```
``` -✅ True Ending: ending2 +✅ True Ending: ending2 >> runs along a desert highway. ```
``` -🤖 Predicted Ending: ending1 +🤖 Predicted Ending: ending1 >> remains by the door. ```
@@ -796,21 +7894,21 @@ A lake reflects the mountains and the sky. Someone
``` -❓ Sentence 21: +❓ Sentence 21: On screen, she smiles as someone holds up a present. He watches somberly as on screen, his mother ```
``` -✅ True Ending: ending1 +✅ True Ending: ending1 >> picks him up and plays with him in the garden. ```
``` -🤖 Predicted Ending: ending0 +🤖 Predicted Ending: ending0 >> comes out of her apartment, glowers at her laptop. ```
@@ -823,21 +7921,21 @@ On screen, she smiles as someone holds up a present. He watches somberly as on s
``` -❓ Sentence 31: +❓ Sentence 31: A woman in a black shirt is sitting on a bench. A man ```
``` -✅ True Ending: ending2 +✅ True Ending: ending2 >> sits behind a desk. ```
``` -🤖 Predicted Ending: ending0 +🤖 Predicted Ending: ending0 >> is dancing on a stage. ```
@@ -850,21 +7948,21 @@ A woman in a black shirt is sitting on a bench. A man
``` -❓ Sentence 41: +❓ Sentence 41: People are standing on sand wearing red shirts. They ```
``` -✅ True Ending: ending3 +✅ True Ending: ending3 >> are playing a game of soccer in the sand. ```
``` -🤖 Predicted Ending: ending3 +🤖 Predicted Ending: ending3 >> are playing a game of soccer in the sand. ```
diff --git a/examples/nlp/multiple_choice_task_with_transfer_learning.py b/examples/nlp/multiple_choice_task_with_transfer_learning.py index dc3f254867..5c90ecb666 100644 --- a/examples/nlp/multiple_choice_task_with_transfer_learning.py +++ b/examples/nlp/multiple_choice_task_with_transfer_learning.py @@ -2,7 +2,7 @@ Title: MultipleChoice Task with Transfer Learning Author: Md Awsafur Rahman Date created: 2023/09/14 -Last modified: 2023/09/14 +Last modified: 2024/01/06 Description: Use pre-trained nlp models for multiplechoice task. Accelerator: GPU """ @@ -21,11 +21,12 @@ """ """shell +pip install -q keras-nlp --upgrade """ -import keras_nlp import keras -import tensorflow as tf # For tf.data only. +import keras_nlp +import tensorflow as tf import numpy as np import pandas as pd @@ -542,9 +543,9 @@ def build_model(): question = row.startphrase pred_answer = f"ending{pred_answers[i]}" true_answer = f"ending{true_answers[i]}" - print(f"❓ Sentence {i+1}:\n{question}\n") - print(f"✅ True Ending: {true_answer}\n >> {row[true_answer]}\n") - print(f"🤖 Predicted Ending: {pred_answer}\n >> {row[pred_answer]}\n") + print(f"❓ Sentence {i+1}:\n{question}\n") + print(f"✅ True Ending: {true_answer}\n >> {row[true_answer]}\n") + print(f"🤖 Predicted Ending: {pred_answer}\n >> {row[pred_answer]}\n") print("-" * 90, "\n") """ From 248c461171a083ec23edd4dc1aac3c723f1ce79c Mon Sep 17 00:00:00 2001 From: Sachin Prasad Date: Sun, 7 Jan 2024 01:55:23 -0800 Subject: [PATCH 2/3] Keras 3 migration --- ...iple_choice_task_with_transfer_learning.md | 6662 +---------------- 1 file changed, 10 insertions(+), 6652 deletions(-) diff --git a/examples/nlp/md/multiple_choice_task_with_transfer_learning.md b/examples/nlp/md/multiple_choice_task_with_transfer_learning.md index a68d80cac5..d8793702f9 100644 --- a/examples/nlp/md/multiple_choice_task_with_transfer_learning.md +++ b/examples/nlp/md/multiple_choice_task_with_transfer_learning.md @@ -80,26 +80,7 @@ Saving to: ‘swag.zip’ ``` - -swag.zip [<=> ] 0 --.-KB/s - - -swag.zip [ <=> ] 84.24K 229KB/s - - -swag.zip [ <=> ] 1.46M 2.44MB/s - - -swag.zip [ <=> ] 2.20M 1.48MB/s - - -swag.zip [ <=> ] 8.59M 3.16MB/s - - -swag.zip [ <=> ] 15.40M 4.96MB/s - - -swag.zip [ <=> ] 17.54M 5.05MB/s + swag.zip [ <=> ] 19.94M 5.71MB/s in 3.5s
@@ -663,180 +644,9 @@ Downloading from https://www.kaggle.com/api/v1/models/keras/deberta_v3/keras/deb 0%| | 0.00/270M [00:00 -``` -/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/backbone.py:37: UserWarning: `Model.state_updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. - return id(getattr(self, attr)) not in self._functional_layer_ids -/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/backbone.py:37: UserWarning: `layer.updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. - return id(getattr(self, attr)) not in self._functional_layer_ids -``` -
Let's checkout the model summary to have a better insight on the model. @@ -985,6470 +795,18 @@ history = model.fit(
``` Epoch 1/5 +183/183 [==============================] - 3111s 15s/step - loss: 1.3842 - accuracy: 0.2828 - val_loss: 1.3755 - val_accuracy: 0.5225 - lr: 1.0000e-06 +Epoch 2/5 +183/183 [==============================] - 2748s 15s/step - loss: 1.2631 - accuracy: 0.4556 - val_loss: 0.9210 - val_accuracy: 0.7075 - lr: 2.9000e-06 +Epoch 3/5 +183/183 [==============================] - 2755s 15s/step - loss: 1.0013 - accuracy: 0.6052 - val_loss: 0.7730 - val_accuracy: 0.7475 - lr: 4.8000e-06 +Epoch 4/5 +183/183 [==============================] - 2778s 15s/step - loss: 0.8728 - accuracy: 0.6680 - val_loss: 0.7296 - val_accuracy: 0.7525 - lr: 4.7230e-06 +Epoch 5/5 +183/183 [==============================] - 2764s 15s/step - loss: 0.7714 - accuracy: 0.7158 - val_loss: 0.7098 - val_accuracy: 0.7500 - lr: 4.4984e-06 -WARNING: All log messages before absl::InitializeLog() is called are written to STDERR -I0000 00:00:1704605251.846942 12962 device_compiler.h:186] Compiled cluster using XLA! This line is logged at most once for the lifetime of the process. - -``` -
- - 1/183 [..............................] - ETA: 16:51:51 - loss: 1.3865 - accuracy: 0.3750 - -
-``` - -``` -
- 2/183 [..............................] - ETA: 44:52 - loss: 1.3652 - accuracy: 0.3750 - -
-``` - -``` -
- 3/183 [..............................] - ETA: 44:29 - loss: 1.3851 - accuracy: 0.2500 - -
-``` - -``` -
- 4/183 [..............................] - ETA: 44:12 - loss: 1.3875 - accuracy: 0.2188 - -
-``` - -``` -
- 5/183 [..............................] - ETA: 43:54 - loss: 1.3896 - accuracy: 0.2000 - -
-``` - -``` -
- 6/183 [..............................] - ETA: 43:41 - loss: 1.3942 - accuracy: 0.1875 - -
-``` - -``` -
- 7/183 [>.............................] - ETA: 43:25 - loss: 1.3928 - accuracy: 0.2143 - -
-``` - -``` -
- 8/183 [>.............................] - ETA: 43:22 - loss: 1.3933 - accuracy: 0.2031 - -
-``` - -``` -
- 9/183 [>.............................] - ETA: 42:54 - loss: 1.3934 - accuracy: 0.2083 - -
-``` - -``` -
- 10/183 [>.............................] - ETA: 42:27 - loss: 1.3901 - accuracy: 0.2375 - -
-``` - -``` -
- 11/183 [>.............................] - ETA: 42:04 - loss: 1.3898 - accuracy: 0.2500 - -
-``` - -``` -
- 12/183 [>.............................] - ETA: 41:42 - loss: 1.3903 - accuracy: 0.2396 - -
-``` - -``` -
- 13/183 [=>............................] - ETA: 41:21 - loss: 1.3900 - accuracy: 0.2500 - -
-``` - -``` -
- 14/183 [=>............................] - ETA: 41:02 - loss: 1.3908 - accuracy: 0.2321 - -
-``` - -``` -
- 15/183 [=>............................] - ETA: 40:45 - loss: 1.3919 - accuracy: 0.2167 - -
-``` - -``` -
- 16/183 [=>............................] - ETA: 40:26 - loss: 1.3927 - accuracy: 0.2109 - -
-``` - -``` -
- 17/183 [=>............................] - ETA: 40:08 - loss: 1.3935 - accuracy: 0.2132 - -
-``` - -``` -
- 18/183 [=>............................] - ETA: 39:51 - loss: 1.3920 - accuracy: 0.2153 - -
-``` - -``` -
- 19/183 [==>...........................] - ETA: 39:34 - loss: 1.3905 - accuracy: 0.2171 - -
-``` - -``` -
- 20/183 [==>...........................] - ETA: 39:16 - loss: 1.3900 - accuracy: 0.2188 - -
-``` - -``` -
- 21/183 [==>...........................] - ETA: 39:01 - loss: 1.3908 - accuracy: 0.2202 - -
-``` - -``` -
- 22/183 [==>...........................] - ETA: 38:44 - loss: 1.3915 - accuracy: 0.2159 - -
-``` - -``` -
- 23/183 [==>...........................] - ETA: 38:28 - loss: 1.3892 - accuracy: 0.2391 - -
-``` - ```
- 24/183 [==>...........................] - ETA: 38:12 - loss: 1.3891 - accuracy: 0.2396 - -
-``` - -``` -
- 25/183 [===>..........................] - ETA: 37:56 - loss: 1.3893 - accuracy: 0.2350 - -
-``` - -``` -
- 26/183 [===>..........................] - ETA: 37:40 - loss: 1.3893 - accuracy: 0.2404 - -
-``` - -``` -
- 27/183 [===>..........................] - ETA: 37:25 - loss: 1.3886 - accuracy: 0.2454 - -
-``` - -``` -
- 28/183 [===>..........................] - ETA: 37:09 - loss: 1.3880 - accuracy: 0.2455 - -
-``` - -``` -
- 29/183 [===>..........................] - ETA: 36:55 - loss: 1.3874 - accuracy: 0.2457 - -
-``` - -``` -
- 30/183 [===>..........................] - ETA: 36:39 - loss: 1.3877 - accuracy: 0.2458 - -
-``` - -``` -
- 31/183 [====>.........................] - ETA: 36:23 - loss: 1.3870 - accuracy: 0.2540 - -
-``` - -``` -
- 32/183 [====>.........................] - ETA: 36:08 - loss: 1.3870 - accuracy: 0.2578 - -
-``` - -``` -
- 33/183 [====>.........................] - ETA: 35:53 - loss: 1.3870 - accuracy: 0.2538 - -
-``` - -``` -
- 34/183 [====>.........................] - ETA: 35:38 - loss: 1.3882 - accuracy: 0.2500 - -
-``` - -``` -
- 35/183 [====>.........................] - ETA: 35:23 - loss: 1.3876 - accuracy: 0.2536 - -
-``` - -``` -
- 36/183 [====>.........................] - ETA: 35:07 - loss: 1.3878 - accuracy: 0.2500 - -
-``` - -``` -
- 37/183 [=====>........................] - ETA: 34:53 - loss: 1.3871 - accuracy: 0.2568 - -
-``` - -``` -
- 38/183 [=====>........................] - ETA: 34:38 - loss: 1.3875 - accuracy: 0.2566 - -
-``` - -``` -
- 39/183 [=====>........................] - ETA: 34:22 - loss: 1.3875 - accuracy: 0.2564 - -
-``` - -``` -
- 40/183 [=====>........................] - ETA: 34:07 - loss: 1.3875 - accuracy: 0.2531 - -
-``` - -``` -
- 41/183 [=====>........................] - ETA: 33:52 - loss: 1.3874 - accuracy: 0.2530 - -
-``` - -``` -
- 42/183 [=====>........................] - ETA: 33:38 - loss: 1.3886 - accuracy: 0.2500 - -
-``` - -``` -
- 43/183 [======>.......................] - ETA: 33:23 - loss: 1.3876 - accuracy: 0.2529 - -
-``` - -``` -
- 44/183 [======>.......................] - ETA: 33:08 - loss: 1.3876 - accuracy: 0.2557 - -
-``` - -``` -
- 45/183 [======>.......................] - ETA: 32:54 - loss: 1.3875 - accuracy: 0.2583 - -
-``` - -``` -
- 46/183 [======>.......................] - ETA: 32:39 - loss: 1.3875 - accuracy: 0.2582 - -
-``` - -``` -
- 47/183 [======>.......................] - ETA: 32:24 - loss: 1.3873 - accuracy: 0.2553 - -
-``` - -``` -
- 48/183 [======>.......................] - ETA: 32:09 - loss: 1.3866 - accuracy: 0.2604 - -
-``` - -``` -
- 49/183 [=======>......................] - ETA: 31:54 - loss: 1.3870 - accuracy: 0.2602 - -
-``` - -``` -
- 50/183 [=======>......................] - ETA: 31:40 - loss: 1.3869 - accuracy: 0.2600 - -
-``` - -``` -
- 51/183 [=======>......................] - ETA: 31:25 - loss: 1.3862 - accuracy: 0.2647 - -
-``` - -``` -
- 52/183 [=======>......................] - ETA: 31:10 - loss: 1.3865 - accuracy: 0.2596 - -
-``` - -``` -
- 53/183 [=======>......................] - ETA: 30:56 - loss: 1.3869 - accuracy: 0.2571 - -
-``` - -``` -
- 54/183 [=======>......................] - ETA: 30:41 - loss: 1.3869 - accuracy: 0.2546 - -
-``` - -``` -
- 55/183 [========>.....................] - ETA: 30:27 - loss: 1.3866 - accuracy: 0.2591 - -
-``` - -``` -
- 56/183 [========>.....................] - ETA: 30:12 - loss: 1.3869 - accuracy: 0.2589 - -
-``` - -``` -
- 57/183 [========>.....................] - ETA: 29:58 - loss: 1.3861 - accuracy: 0.2632 - -
-``` - -``` -
- 58/183 [========>.....................] - ETA: 29:43 - loss: 1.3857 - accuracy: 0.2651 - -
-``` - -``` -
- 59/183 [========>.....................] - ETA: 29:29 - loss: 1.3854 - accuracy: 0.2669 - -
-``` - -``` -
- 60/183 [========>.....................] - ETA: 29:14 - loss: 1.3854 - accuracy: 0.2688 - -
-``` - -``` -
- 61/183 [=========>....................] - ETA: 29:00 - loss: 1.3852 - accuracy: 0.2705 - -
-``` - -``` -
- 62/183 [=========>....................] - ETA: 28:45 - loss: 1.3851 - accuracy: 0.2702 - -
-``` - -``` -
- 63/183 [=========>....................] - ETA: 28:31 - loss: 1.3855 - accuracy: 0.2679 - -
-``` - -``` -
- 64/183 [=========>....................] - ETA: 28:17 - loss: 1.3857 - accuracy: 0.2656 - -
-``` - -``` -
- 65/183 [=========>....................] - ETA: 28:02 - loss: 1.3867 - accuracy: 0.2615 - -
-``` - -``` -
- 66/183 [=========>....................] - ETA: 27:48 - loss: 1.3868 - accuracy: 0.2614 - -
-``` - -``` -
- 67/183 [=========>....................] - ETA: 27:34 - loss: 1.3868 - accuracy: 0.2631 - -
-``` - -``` -
- 68/183 [==========>...................] - ETA: 27:19 - loss: 1.3864 - accuracy: 0.2610 - -
-``` - -``` -
- 69/183 [==========>...................] - ETA: 27:05 - loss: 1.3864 - accuracy: 0.2591 - -
-``` - -``` -
- 70/183 [==========>...................] - ETA: 26:51 - loss: 1.3860 - accuracy: 0.2607 - -
-``` - -``` -
- 71/183 [==========>...................] - ETA: 26:36 - loss: 1.3866 - accuracy: 0.2570 - -
-``` - -``` -
- 72/183 [==========>...................] - ETA: 26:22 - loss: 1.3858 - accuracy: 0.2622 - -
-``` - -``` -
- 73/183 [==========>...................] - ETA: 26:07 - loss: 1.3854 - accuracy: 0.2637 - -
-``` - -``` -
- 74/183 [===========>..................] - ETA: 25:53 - loss: 1.3858 - accuracy: 0.2601 - -
-``` - -``` -
- 75/183 [===========>..................] - ETA: 25:39 - loss: 1.3859 - accuracy: 0.2583 - -
-``` - -``` -
- 76/183 [===========>..................] - ETA: 25:24 - loss: 1.3859 - accuracy: 0.2599 - -
-``` - -``` -
- 77/183 [===========>..................] - ETA: 25:10 - loss: 1.3860 - accuracy: 0.2597 - -
-``` - -``` -
- 78/183 [===========>..................] - ETA: 24:55 - loss: 1.3862 - accuracy: 0.2580 - -
-``` - -``` -
- 79/183 [===========>..................] - ETA: 24:41 - loss: 1.3855 - accuracy: 0.2611 - -
-``` - -``` -
- 80/183 [============>.................] - ETA: 24:27 - loss: 1.3857 - accuracy: 0.2625 - -
-``` - -``` -
- 81/183 [============>.................] - ETA: 24:12 - loss: 1.3853 - accuracy: 0.2639 - -
-``` - -``` -
- 82/183 [============>.................] - ETA: 23:58 - loss: 1.3854 - accuracy: 0.2622 - -
-``` - -``` -
- 83/183 [============>.................] - ETA: 23:43 - loss: 1.3854 - accuracy: 0.2636 - -
-``` - -``` -
- 84/183 [============>.................] - ETA: 23:29 - loss: 1.3857 - accuracy: 0.2634 - -
-``` - -``` -
- 85/183 [============>.................] - ETA: 23:15 - loss: 1.3853 - accuracy: 0.2647 - -
-``` - -``` -
- 86/183 [=============>................] - ETA: 23:00 - loss: 1.3852 - accuracy: 0.2689 - -
-``` - -``` -
- 87/183 [=============>................] - ETA: 22:46 - loss: 1.3852 - accuracy: 0.2687 - -
-``` - -``` -
- 88/183 [=============>................] - ETA: 22:32 - loss: 1.3852 - accuracy: 0.2685 - -
-``` - -``` -
- 89/183 [=============>................] - ETA: 22:17 - loss: 1.3852 - accuracy: 0.2711 - -
-``` - -``` -
- 90/183 [=============>................] - ETA: 22:03 - loss: 1.3852 - accuracy: 0.2694 - -
-``` - -``` -
- 91/183 [=============>................] - ETA: 21:49 - loss: 1.3851 - accuracy: 0.2720 - -
-``` - -``` -
- 92/183 [==============>...............] - ETA: 21:35 - loss: 1.3851 - accuracy: 0.2717 - -
-``` - -``` -
- 93/183 [==============>...............] - ETA: 21:20 - loss: 1.3853 - accuracy: 0.2702 - -
-``` - -``` -
- 94/183 [==============>...............] - ETA: 21:06 - loss: 1.3856 - accuracy: 0.2699 - -
-``` - -``` -
- 95/183 [==============>...............] - ETA: 20:52 - loss: 1.3855 - accuracy: 0.2711 - -
-``` - -``` -
- 96/183 [==============>...............] - ETA: 20:37 - loss: 1.3856 - accuracy: 0.2695 - -
-``` - -``` -
- 97/183 [==============>...............] - ETA: 20:23 - loss: 1.3855 - accuracy: 0.2706 - -
-``` - -``` -
- 98/183 [===============>..............] - ETA: 20:09 - loss: 1.3852 - accuracy: 0.2730 - -
-``` - -``` -
- 99/183 [===============>..............] - ETA: 19:54 - loss: 1.3853 - accuracy: 0.2715 - -
-``` - -``` -
-100/183 [===============>..............] - ETA: 19:40 - loss: 1.3854 - accuracy: 0.2713 - -
-``` - -``` -
-101/183 [===============>..............] - ETA: 19:26 - loss: 1.3856 - accuracy: 0.2698 - -
-``` - -``` -
-102/183 [===============>..............] - ETA: 19:12 - loss: 1.3856 - accuracy: 0.2684 - -
-``` - -``` -
-103/183 [===============>..............] - ETA: 18:57 - loss: 1.3854 - accuracy: 0.2694 - -
-``` - -``` -
-104/183 [================>.............] - ETA: 18:43 - loss: 1.3852 - accuracy: 0.2716 - -
-``` - -``` -
-105/183 [================>.............] - ETA: 18:29 - loss: 1.3854 - accuracy: 0.2714 - -
-``` - -``` -
-106/183 [================>.............] - ETA: 18:15 - loss: 1.3851 - accuracy: 0.2748 - -
-``` - -``` -
-107/183 [================>.............] - ETA: 18:00 - loss: 1.3852 - accuracy: 0.2745 - -
-``` - -``` -
-108/183 [================>.............] - ETA: 17:46 - loss: 1.3853 - accuracy: 0.2720 - -
-``` - -``` -
-109/183 [================>.............] - ETA: 17:32 - loss: 1.3854 - accuracy: 0.2718 - -
-``` - -``` -
-110/183 [=================>............] - ETA: 17:18 - loss: 1.3855 - accuracy: 0.2716 - -
-``` - -``` -
-111/183 [=================>............] - ETA: 17:03 - loss: 1.3856 - accuracy: 0.2703 - -
-``` - -``` -
-112/183 [=================>............] - ETA: 16:49 - loss: 1.3859 - accuracy: 0.2701 - -
-``` - -``` -
-113/183 [=================>............] - ETA: 16:35 - loss: 1.3859 - accuracy: 0.2699 - -
-``` - -``` -
-114/183 [=================>............] - ETA: 16:21 - loss: 1.3859 - accuracy: 0.2697 - -
-``` - -``` -
-115/183 [=================>............] - ETA: 16:06 - loss: 1.3862 - accuracy: 0.2707 - -
-``` - -``` -
-116/183 [==================>...........] - ETA: 15:52 - loss: 1.3858 - accuracy: 0.2737 - -
-``` - -``` -
-117/183 [==================>...........] - ETA: 15:38 - loss: 1.3857 - accuracy: 0.2746 - -
-``` - -``` -
-118/183 [==================>...........] - ETA: 15:24 - loss: 1.3856 - accuracy: 0.2744 - -
-``` - -``` -
-119/183 [==================>...........] - ETA: 15:09 - loss: 1.3858 - accuracy: 0.2731 - -
-``` - -``` -
-120/183 [==================>...........] - ETA: 14:55 - loss: 1.3861 - accuracy: 0.2719 - -
-``` - -``` -
-121/183 [==================>...........] - ETA: 14:41 - loss: 1.3862 - accuracy: 0.2707 - -
-``` - -``` -
-122/183 [===================>..........] - ETA: 14:27 - loss: 1.3862 - accuracy: 0.2705 - -
-``` - -``` -
-123/183 [===================>..........] - ETA: 14:12 - loss: 1.3861 - accuracy: 0.2703 - -
-``` - -``` -
-124/183 [===================>..........] - ETA: 13:58 - loss: 1.3860 - accuracy: 0.2692 - -
-``` - -``` -
-125/183 [===================>..........] - ETA: 13:44 - loss: 1.3861 - accuracy: 0.2670 - -
-``` - -``` -
-126/183 [===================>..........] - ETA: 13:30 - loss: 1.3860 - accuracy: 0.2679 - -
-``` - -``` -
-127/183 [===================>..........] - ETA: 13:15 - loss: 1.3858 - accuracy: 0.2677 - -
-``` - -``` -
-128/183 [===================>..........] - ETA: 13:01 - loss: 1.3856 - accuracy: 0.2715 - -
-``` - -``` -
-129/183 [====================>.........] - ETA: 12:47 - loss: 1.3855 - accuracy: 0.2723 - -
-``` - -``` -
-130/183 [====================>.........] - ETA: 12:33 - loss: 1.3854 - accuracy: 0.2731 - -
-``` - -``` -
-131/183 [====================>.........] - ETA: 12:19 - loss: 1.3854 - accuracy: 0.2719 - -
-``` - -``` -
-132/183 [====================>.........] - ETA: 12:04 - loss: 1.3854 - accuracy: 0.2718 - -
-``` - -``` -
-133/183 [====================>.........] - ETA: 11:50 - loss: 1.3854 - accuracy: 0.2707 - -
-``` - -``` -
-134/183 [====================>.........] - ETA: 11:36 - loss: 1.3854 - accuracy: 0.2705 - -
-``` - -``` -
-135/183 [=====================>........] - ETA: 11:22 - loss: 1.3853 - accuracy: 0.2694 - -
-``` - -``` -
-136/183 [=====================>........] - ETA: 11:07 - loss: 1.3854 - accuracy: 0.2693 - -
-``` - -``` -
-137/183 [=====================>........] - ETA: 10:53 - loss: 1.3854 - accuracy: 0.2710 - -
-``` - -``` -
-138/183 [=====================>........] - ETA: 10:39 - loss: 1.3856 - accuracy: 0.2717 - -
-``` - -``` -
-139/183 [=====================>........] - ETA: 10:25 - loss: 1.3855 - accuracy: 0.2743 - -
-``` - -``` -
-140/183 [=====================>........] - ETA: 10:10 - loss: 1.3853 - accuracy: 0.2741 - -
-``` - -``` -
-141/183 [======================>.......] - ETA: 9:56 - loss: 1.3854 - accuracy: 0.2730 - -
-``` - -``` -
-142/183 [======================>.......] - ETA: 9:42 - loss: 1.3854 - accuracy: 0.2720 - -
-``` - -``` -
-143/183 [======================>.......] - ETA: 9:28 - loss: 1.3852 - accuracy: 0.2719 - -
-``` - -``` -
-144/183 [======================>.......] - ETA: 9:14 - loss: 1.3852 - accuracy: 0.2717 - -
-``` - -``` -
-145/183 [======================>.......] - ETA: 8:59 - loss: 1.3852 - accuracy: 0.2724 - -
-``` - -``` -
-146/183 [======================>.......] - ETA: 8:45 - loss: 1.3853 - accuracy: 0.2723 - -
-``` - -``` -
-147/183 [=======================>......] - ETA: 8:31 - loss: 1.3852 - accuracy: 0.2730 - -
-``` - -``` -
-148/183 [=======================>......] - ETA: 8:17 - loss: 1.3852 - accuracy: 0.2736 - -
-``` - -``` -
-149/183 [=======================>......] - ETA: 8:03 - loss: 1.3851 - accuracy: 0.2743 - -
-``` - -``` -
-150/183 [=======================>......] - ETA: 7:48 - loss: 1.3848 - accuracy: 0.2758 - -
-``` - -``` -
-151/183 [=======================>......] - ETA: 7:34 - loss: 1.3847 - accuracy: 0.2757 - -
-``` - -``` -
-152/183 [=======================>......] - ETA: 7:20 - loss: 1.3847 - accuracy: 0.2755 - -
-``` - -``` -
-153/183 [========================>.....] - ETA: 7:06 - loss: 1.3847 - accuracy: 0.2753 - -
-``` - -``` -
-154/183 [========================>.....] - ETA: 6:52 - loss: 1.3848 - accuracy: 0.2744 - -
-``` - -``` -
-155/183 [========================>.....] - ETA: 6:37 - loss: 1.3847 - accuracy: 0.2742 - -
-``` - -``` -
-156/183 [========================>.....] - ETA: 6:23 - loss: 1.3848 - accuracy: 0.2740 - -
-``` - -``` -
-157/183 [========================>.....] - ETA: 6:09 - loss: 1.3848 - accuracy: 0.2731 - -
-``` - -``` -
-158/183 [========================>.....] - ETA: 5:55 - loss: 1.3848 - accuracy: 0.2737 - -
-``` - -``` -
-159/183 [=========================>....] - ETA: 5:40 - loss: 1.3848 - accuracy: 0.2752 - -
-``` - -``` -
-160/183 [=========================>....] - ETA: 5:26 - loss: 1.3849 - accuracy: 0.2742 - -
-``` - -``` -
-161/183 [=========================>....] - ETA: 5:12 - loss: 1.3845 - accuracy: 0.2772 - -
-``` - -``` -
-162/183 [=========================>....] - ETA: 4:58 - loss: 1.3847 - accuracy: 0.2770 - -
-``` - -``` -
-163/183 [=========================>....] - ETA: 4:44 - loss: 1.3849 - accuracy: 0.2768 - -
-``` - -``` -
-164/183 [=========================>....] - ETA: 4:29 - loss: 1.3848 - accuracy: 0.2774 - -
-``` - -``` -
-165/183 [==========================>...] - ETA: 4:15 - loss: 1.3848 - accuracy: 0.2780 - -
-``` - -``` -
-166/183 [==========================>...] - ETA: 4:01 - loss: 1.3848 - accuracy: 0.2764 - -
-``` - -``` -
-167/183 [==========================>...] - ETA: 3:47 - loss: 1.3847 - accuracy: 0.2762 - -
-``` - -``` -
-168/183 [==========================>...] - ETA: 3:33 - loss: 1.3848 - accuracy: 0.2753 - -
-``` - -``` -
-169/183 [==========================>...] - ETA: 3:18 - loss: 1.3848 - accuracy: 0.2759 - -
-``` - -``` -
-170/183 [==========================>...] - ETA: 3:04 - loss: 1.3846 - accuracy: 0.2779 - -
-``` - -``` -
-171/183 [===========================>..] - ETA: 2:50 - loss: 1.3849 - accuracy: 0.2770 - -
-``` - -``` -
-172/183 [===========================>..] - ETA: 2:36 - loss: 1.3850 - accuracy: 0.2754 - -
-``` - -``` -
-173/183 [===========================>..] - ETA: 2:22 - loss: 1.3849 - accuracy: 0.2760 - -
-``` - -``` -
-174/183 [===========================>..] - ETA: 2:07 - loss: 1.3849 - accuracy: 0.2766 - -
-``` - -``` -
-175/183 [===========================>..] - ETA: 1:53 - loss: 1.3849 - accuracy: 0.2779 - -
-``` - -``` -
-176/183 [===========================>..] - ETA: 1:39 - loss: 1.3846 - accuracy: 0.2784 - -
-``` - -``` -
-177/183 [============================>.] - ETA: 1:25 - loss: 1.3846 - accuracy: 0.2797 - -
-``` - -``` -
-178/183 [============================>.] - ETA: 1:11 - loss: 1.3844 - accuracy: 0.2809 - -
-``` - -``` -
-179/183 [============================>.] - ETA: 56s - loss: 1.3844 - accuracy: 0.2807 - -
-``` - -``` -
-180/183 [============================>.] - ETA: 42s - loss: 1.3843 - accuracy: 0.2806 - -
-``` - -``` -
-181/183 [============================>.] - ETA: 28s - loss: 1.3843 - accuracy: 0.2818 - -
-``` - -``` -
-182/183 [============================>.] - ETA: 14s - loss: 1.3843 - accuracy: 0.2823 - -
-``` - -``` -
-183/183 [==============================] - ETA: 0s - loss: 1.3842 - accuracy: 0.2828 - -
-``` -/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/task.py:47: UserWarning: `Model.state_updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. - return id(getattr(self, attr)) not in self._functional_layer_ids -/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/task.py:47: UserWarning: `layer.updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. - return id(getattr(self, attr)) not in self._functional_layer_ids -/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/backbone.py:37: UserWarning: `Model.state_updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. - return id(getattr(self, attr)) not in self._functional_layer_ids -/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/backbone.py:37: UserWarning: `layer.updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. - return id(getattr(self, attr)) not in self._functional_layer_ids - - -``` -
-183/183 [==============================] - 3111s 15s/step - loss: 1.3842 - accuracy: 0.2828 - val_loss: 1.3755 - val_accuracy: 0.5225 - lr: 1.0000e-06 - - -
-``` -Epoch 2/5 - -``` -
- - 1/183 [..............................] - ETA: 46:52 - loss: 1.3583 - accuracy: 0.5000 - -
-``` - -``` -
- 2/183 [..............................] - ETA: 43:21 - loss: 1.3603 - accuracy: 0.3750 - -
-``` - -``` -
- 3/183 [..............................] - ETA: 43:12 - loss: 1.3608 - accuracy: 0.3750 - -
-``` - -``` -
- 4/183 [..............................] - ETA: 42:59 - loss: 1.3601 - accuracy: 0.4062 - -
-``` - -``` -
- 5/183 [..............................] - ETA: 42:33 - loss: 1.3611 - accuracy: 0.3750 - -
-``` - -``` -
- 6/183 [..............................] - ETA: 42:14 - loss: 1.3652 - accuracy: 0.3333 - -
-``` - -``` -
- 7/183 [>.............................] - ETA: 41:54 - loss: 1.3719 - accuracy: 0.2857 - -
-``` - -``` -
- 8/183 [>.............................] - ETA: 41:38 - loss: 1.3726 - accuracy: 0.2969 - -
-``` - -``` -
- 9/183 [>.............................] - ETA: 41:22 - loss: 1.3738 - accuracy: 0.2917 - -
-``` - -``` -
- 10/183 [>.............................] - ETA: 41:05 - loss: 1.3772 - accuracy: 0.2875 - -
-``` - -``` -
- 11/183 [>.............................] - ETA: 40:54 - loss: 1.3764 - accuracy: 0.2955 - -
-``` - -``` -
- 12/183 [>.............................] - ETA: 40:37 - loss: 1.3753 - accuracy: 0.3021 - -
-``` - -``` -
- 13/183 [=>............................] - ETA: 40:22 - loss: 1.3747 - accuracy: 0.3173 - -
-``` - -``` -
- 14/183 [=>............................] - ETA: 40:06 - loss: 1.3742 - accuracy: 0.3214 - -
-``` - -``` -
- 15/183 [=>............................] - ETA: 39:50 - loss: 1.3715 - accuracy: 0.3333 - -
-``` - -``` -
- 16/183 [=>............................] - ETA: 39:34 - loss: 1.3716 - accuracy: 0.3359 - -
-``` - -``` -
- 17/183 [=>............................] - ETA: 39:19 - loss: 1.3721 - accuracy: 0.3382 - -
-``` - -``` -
- 18/183 [=>............................] - ETA: 39:03 - loss: 1.3735 - accuracy: 0.3194 - -
-``` - -``` -
- 19/183 [==>...........................] - ETA: 38:48 - loss: 1.3746 - accuracy: 0.3158 - -
-``` - -``` -
- 20/183 [==>...........................] - ETA: 38:33 - loss: 1.3740 - accuracy: 0.3250 - -
-``` - -``` -
- 21/183 [==>...........................] - ETA: 38:18 - loss: 1.3744 - accuracy: 0.3274 - -
-``` - -``` -
- 22/183 [==>...........................] - ETA: 38:04 - loss: 1.3718 - accuracy: 0.3352 - -
-``` - -``` -
- 23/183 [==>...........................] - ETA: 37:49 - loss: 1.3711 - accuracy: 0.3424 - -
-``` - -``` -
- 24/183 [==>...........................] - ETA: 37:34 - loss: 1.3712 - accuracy: 0.3333 - -
-``` - -``` -
- 25/183 [===>..........................] - ETA: 37:20 - loss: 1.3700 - accuracy: 0.3400 - -
-``` - -``` -
- 26/183 [===>..........................] - ETA: 37:05 - loss: 1.3709 - accuracy: 0.3365 - -
-``` - -``` -
- 27/183 [===>..........................] - ETA: 36:51 - loss: 1.3708 - accuracy: 0.3380 - -
-``` - -``` -
- 28/183 [===>..........................] - ETA: 36:36 - loss: 1.3709 - accuracy: 0.3348 - -
-``` - -``` -
- 29/183 [===>..........................] - ETA: 36:22 - loss: 1.3708 - accuracy: 0.3362 - -
-``` - -``` -
- 30/183 [===>..........................] - ETA: 36:07 - loss: 1.3706 - accuracy: 0.3375 - -
-``` - -``` -
- 31/183 [====>.........................] - ETA: 35:53 - loss: 1.3708 - accuracy: 0.3387 - -
-``` - -``` -
- 32/183 [====>.........................] - ETA: 35:38 - loss: 1.3699 - accuracy: 0.3359 - -
-``` - -``` -
- 33/183 [====>.........................] - ETA: 35:24 - loss: 1.3704 - accuracy: 0.3295 - -
-``` - -``` -
- 34/183 [====>.........................] - ETA: 35:10 - loss: 1.3712 - accuracy: 0.3199 - -
-``` - -``` -
- 35/183 [====>.........................] - ETA: 34:55 - loss: 1.3718 - accuracy: 0.3214 - -
-``` - -``` -
- 36/183 [====>.........................] - ETA: 34:41 - loss: 1.3712 - accuracy: 0.3264 - -
-``` - -``` -
- 37/183 [=====>........................] - ETA: 34:27 - loss: 1.3713 - accuracy: 0.3243 - -
-``` - -``` -
- 38/183 [=====>........................] - ETA: 34:13 - loss: 1.3701 - accuracy: 0.3289 - -
-``` - -``` -
- 39/183 [=====>........................] - ETA: 33:58 - loss: 1.3701 - accuracy: 0.3237 - -
-``` - -``` -
- 40/183 [=====>........................] - ETA: 33:44 - loss: 1.3697 - accuracy: 0.3250 - -
-``` - -``` -
- 41/183 [=====>........................] - ETA: 33:30 - loss: 1.3700 - accuracy: 0.3201 - -
-``` - -``` -
- 42/183 [=====>........................] - ETA: 33:16 - loss: 1.3699 - accuracy: 0.3214 - -
-``` - -``` -
- 43/183 [======>.......................] - ETA: 33:01 - loss: 1.3695 - accuracy: 0.3227 - -
-``` - -``` -
- 44/183 [======>.......................] - ETA: 32:48 - loss: 1.3689 - accuracy: 0.3210 - -
-``` - -``` -
- 45/183 [======>.......................] - ETA: 32:33 - loss: 1.3685 - accuracy: 0.3222 - -
-``` - -``` -
- 46/183 [======>.......................] - ETA: 32:19 - loss: 1.3692 - accuracy: 0.3207 - -
-``` - -``` -
- 47/183 [======>.......................] - ETA: 32:05 - loss: 1.3682 - accuracy: 0.3271 - -
-``` - -``` -
- 48/183 [======>.......................] - ETA: 31:50 - loss: 1.3682 - accuracy: 0.3281 - -
-``` - -``` -
- 49/183 [=======>......................] - ETA: 31:36 - loss: 1.3685 - accuracy: 0.3291 - -
-``` - -``` -
- 50/183 [=======>......................] - ETA: 31:22 - loss: 1.3682 - accuracy: 0.3250 - -
-``` - -``` -
- 51/183 [=======>......................] - ETA: 31:08 - loss: 1.3690 - accuracy: 0.3235 - -
-``` - -``` -
- 52/183 [=======>......................] - ETA: 30:53 - loss: 1.3690 - accuracy: 0.3221 - -
-``` - -``` -
- 53/183 [=======>......................] - ETA: 30:39 - loss: 1.3692 - accuracy: 0.3231 - -
-``` - -``` -
- 54/183 [=======>......................] - ETA: 30:25 - loss: 1.3690 - accuracy: 0.3241 - -
-``` - -``` -
- 55/183 [========>.....................] - ETA: 30:11 - loss: 1.3688 - accuracy: 0.3273 - -
-``` - -``` -
- 56/183 [========>.....................] - ETA: 29:56 - loss: 1.3685 - accuracy: 0.3281 - -
-``` - -``` -
- 57/183 [========>.....................] - ETA: 29:42 - loss: 1.3679 - accuracy: 0.3311 - -
-``` - -``` -
- 58/183 [========>.....................] - ETA: 29:28 - loss: 1.3671 - accuracy: 0.3319 - -
-``` - -``` -
- 59/183 [========>.....................] - ETA: 29:14 - loss: 1.3670 - accuracy: 0.3326 - -
-``` - -``` -
- 60/183 [========>.....................] - ETA: 29:00 - loss: 1.3672 - accuracy: 0.3313 - -
-``` - -``` -
- 61/183 [=========>....................] - ETA: 28:45 - loss: 1.3673 - accuracy: 0.3279 - -
-``` - -``` -
- 62/183 [=========>....................] - ETA: 28:31 - loss: 1.3669 - accuracy: 0.3286 - -
-``` - -``` -
- 63/183 [=========>....................] - ETA: 28:17 - loss: 1.3667 - accuracy: 0.3234 - -
-``` - -``` -
- 64/183 [=========>....................] - ETA: 28:03 - loss: 1.3669 - accuracy: 0.3223 - -
-``` - -``` -
- 65/183 [=========>....................] - ETA: 27:49 - loss: 1.3662 - accuracy: 0.3231 - -
-``` - -``` -
- 66/183 [=========>....................] - ETA: 27:35 - loss: 1.3663 - accuracy: 0.3239 - -
-``` - -``` -
- 67/183 [=========>....................] - ETA: 27:20 - loss: 1.3659 - accuracy: 0.3265 - -
-``` - -``` -
- 68/183 [==========>...................] - ETA: 27:06 - loss: 1.3657 - accuracy: 0.3272 - -
-``` - -``` -
- 69/183 [==========>...................] - ETA: 26:52 - loss: 1.3648 - accuracy: 0.3315 - -
-``` - -``` -
- 70/183 [==========>...................] - ETA: 26:38 - loss: 1.3654 - accuracy: 0.3286 - -
-``` - -``` -
- 71/183 [==========>...................] - ETA: 26:24 - loss: 1.3644 - accuracy: 0.3327 - -
-``` - -``` -
- 72/183 [==========>...................] - ETA: 26:10 - loss: 1.3645 - accuracy: 0.3316 - -
-``` - -``` -
- 73/183 [==========>...................] - ETA: 25:56 - loss: 1.3645 - accuracy: 0.3305 - -
-``` - -``` -
- 74/183 [===========>..................] - ETA: 25:41 - loss: 1.3641 - accuracy: 0.3311 - -
-``` - -``` -
- 75/183 [===========>..................] - ETA: 25:27 - loss: 1.3628 - accuracy: 0.3367 - -
-``` - -``` -
- 76/183 [===========>..................] - ETA: 25:13 - loss: 1.3616 - accuracy: 0.3421 - -
-``` - -``` -
- 77/183 [===========>..................] - ETA: 24:59 - loss: 1.3614 - accuracy: 0.3425 - -
-``` - -``` -
- 78/183 [===========>..................] - ETA: 24:45 - loss: 1.3616 - accuracy: 0.3397 - -
-``` - -``` -
- 79/183 [===========>..................] - ETA: 24:31 - loss: 1.3610 - accuracy: 0.3418 - -
-``` - -``` -
- 80/183 [============>.................] - ETA: 24:17 - loss: 1.3608 - accuracy: 0.3438 - -
-``` - -``` -
- 81/183 [============>.................] - ETA: 24:03 - loss: 1.3599 - accuracy: 0.3441 - -
-``` - -``` -
- 82/183 [============>.................] - ETA: 23:49 - loss: 1.3591 - accuracy: 0.3460 - -
-``` - -``` -
- 83/183 [============>.................] - ETA: 23:35 - loss: 1.3589 - accuracy: 0.3479 - -
-``` - -``` -
- 84/183 [============>.................] - ETA: 23:21 - loss: 1.3583 - accuracy: 0.3482 - -
-``` - -``` -
- 85/183 [============>.................] - ETA: 23:07 - loss: 1.3575 - accuracy: 0.3515 - -
-``` - -``` -
- 86/183 [=============>................] - ETA: 22:53 - loss: 1.3558 - accuracy: 0.3561 - -
-``` - -``` -
- 87/183 [=============>................] - ETA: 22:39 - loss: 1.3560 - accuracy: 0.3549 - -
-``` - -``` -
- 88/183 [=============>................] - ETA: 22:25 - loss: 1.3535 - accuracy: 0.3594 - -
-``` - -``` -
- 89/183 [=============>................] - ETA: 22:10 - loss: 1.3529 - accuracy: 0.3596 - -
-``` - -``` -
- 90/183 [=============>................] - ETA: 21:56 - loss: 1.3529 - accuracy: 0.3597 - -
-``` - -``` -
- 91/183 [=============>................] - ETA: 21:42 - loss: 1.3510 - accuracy: 0.3613 - -
-``` - -``` -
- 92/183 [==============>...............] - ETA: 21:28 - loss: 1.3498 - accuracy: 0.3614 - -
-``` - -``` -
- 93/183 [==============>...............] - ETA: 21:14 - loss: 1.3492 - accuracy: 0.3629 - -
-``` - -``` -
- 94/183 [==============>...............] - ETA: 21:00 - loss: 1.3485 - accuracy: 0.3644 - -
-``` - -``` -
- 95/183 [==============>...............] - ETA: 20:45 - loss: 1.3484 - accuracy: 0.3658 - -
-``` - -``` -
- 96/183 [==============>...............] - ETA: 20:31 - loss: 1.3486 - accuracy: 0.3672 - -
-``` - -``` -
- 97/183 [==============>...............] - ETA: 20:17 - loss: 1.3488 - accuracy: 0.3647 - -
-``` - -``` -
- 98/183 [===============>..............] - ETA: 20:03 - loss: 1.3484 - accuracy: 0.3648 - -
-``` - -``` -
- 99/183 [===============>..............] - ETA: 19:49 - loss: 1.3478 - accuracy: 0.3662 - -
-``` - -``` -
-100/183 [===============>..............] - ETA: 19:34 - loss: 1.3469 - accuracy: 0.3650 - -
-``` - -``` -
-101/183 [===============>..............] - ETA: 19:20 - loss: 1.3474 - accuracy: 0.3651 - -
-``` - -``` -
-102/183 [===============>..............] - ETA: 19:06 - loss: 1.3457 - accuracy: 0.3689 - -
-``` - -``` -
-103/183 [===============>..............] - ETA: 18:52 - loss: 1.3453 - accuracy: 0.3689 - -
-``` - -``` -
-104/183 [================>.............] - ETA: 18:38 - loss: 1.3444 - accuracy: 0.3714 - -
-``` - -``` -
-105/183 [================>.............] - ETA: 18:24 - loss: 1.3441 - accuracy: 0.3726 - -
-``` - -``` -
-106/183 [================>.............] - ETA: 18:10 - loss: 1.3431 - accuracy: 0.3750 - -
-``` - -``` -
-107/183 [================>.............] - ETA: 17:55 - loss: 1.3425 - accuracy: 0.3738 - -
-``` - -``` -
-108/183 [================>.............] - ETA: 17:41 - loss: 1.3421 - accuracy: 0.3738 - -
-``` - -``` -
-109/183 [================>.............] - ETA: 17:27 - loss: 1.3419 - accuracy: 0.3739 - -
-``` - -``` -
-110/183 [=================>............] - ETA: 17:13 - loss: 1.3412 - accuracy: 0.3750 - -
-``` - -``` -
-111/183 [=================>............] - ETA: 16:59 - loss: 1.3400 - accuracy: 0.3773 - -
-``` - -``` -
-112/183 [=================>............] - ETA: 16:45 - loss: 1.3393 - accuracy: 0.3795 - -
-``` - -``` -
-113/183 [=================>............] - ETA: 16:30 - loss: 1.3380 - accuracy: 0.3827 - -
-``` - -``` -
-114/183 [=================>............] - ETA: 16:16 - loss: 1.3366 - accuracy: 0.3860 - -
-``` - -``` -
-115/183 [=================>............] - ETA: 16:02 - loss: 1.3350 - accuracy: 0.3870 - -
-``` - -``` -
-116/183 [==================>...........] - ETA: 15:48 - loss: 1.3334 - accuracy: 0.3901 - -
-``` - -``` -
-117/183 [==================>...........] - ETA: 15:34 - loss: 1.3331 - accuracy: 0.3900 - -
-``` - -``` -
-118/183 [==================>...........] - ETA: 15:20 - loss: 1.3324 - accuracy: 0.3909 - -
-``` - -``` -
-119/183 [==================>...........] - ETA: 15:06 - loss: 1.3308 - accuracy: 0.3929 - -
-``` - -``` -
-120/183 [==================>...........] - ETA: 14:51 - loss: 1.3316 - accuracy: 0.3906 - -
-``` - -``` -
-121/183 [==================>...........] - ETA: 14:37 - loss: 1.3312 - accuracy: 0.3895 - -
-``` - -``` -
-122/183 [===================>..........] - ETA: 14:23 - loss: 1.3294 - accuracy: 0.3924 - -
-``` - -``` -
-123/183 [===================>..........] - ETA: 14:09 - loss: 1.3284 - accuracy: 0.3953 - -
-``` - -``` -
-124/183 [===================>..........] - ETA: 13:55 - loss: 1.3269 - accuracy: 0.3972 - -
-``` - -``` -
-125/183 [===================>..........] - ETA: 13:40 - loss: 1.3249 - accuracy: 0.4000 - -
-``` - -``` -
-126/183 [===================>..........] - ETA: 13:26 - loss: 1.3245 - accuracy: 0.3988 - -
-``` - -``` -
-127/183 [===================>..........] - ETA: 13:12 - loss: 1.3231 - accuracy: 0.4006 - -
-``` - -``` -
-128/183 [===================>..........] - ETA: 12:58 - loss: 1.3233 - accuracy: 0.3994 - -
-``` - -``` -
-129/183 [====================>.........] - ETA: 12:44 - loss: 1.3212 - accuracy: 0.4021 - -
-``` - -``` -
-130/183 [====================>.........] - ETA: 12:30 - loss: 1.3206 - accuracy: 0.4029 - -
-``` - -``` -
-131/183 [====================>.........] - ETA: 12:16 - loss: 1.3187 - accuracy: 0.4065 - -
-``` - -``` -
-132/183 [====================>.........] - ETA: 12:01 - loss: 1.3173 - accuracy: 0.4091 - -
-``` - -``` -
-133/183 [====================>.........] - ETA: 11:47 - loss: 1.3162 - accuracy: 0.4098 - -
-``` - -``` -
-134/183 [====================>.........] - ETA: 11:33 - loss: 1.3148 - accuracy: 0.4123 - -
-``` - -``` -
-135/183 [=====================>........] - ETA: 11:19 - loss: 1.3149 - accuracy: 0.4120 - -
-``` - -``` -
-136/183 [=====================>........] - ETA: 11:05 - loss: 1.3150 - accuracy: 0.4118 - -
-``` - -``` -
-137/183 [=====================>........] - ETA: 10:51 - loss: 1.3143 - accuracy: 0.4106 - -
-``` - -``` -
-138/183 [=====================>........] - ETA: 10:36 - loss: 1.3133 - accuracy: 0.4130 - -
-``` - -``` -
-139/183 [=====================>........] - ETA: 10:22 - loss: 1.3127 - accuracy: 0.4128 - -
-``` - -``` -
-140/183 [=====================>........] - ETA: 10:08 - loss: 1.3136 - accuracy: 0.4125 - -
-``` - -``` -
-141/183 [======================>.......] - ETA: 9:54 - loss: 1.3125 - accuracy: 0.4131 - -
-``` - -``` -
-142/183 [======================>.......] - ETA: 9:40 - loss: 1.3115 - accuracy: 0.4155 - -
-``` - -``` -
-143/183 [======================>.......] - ETA: 9:26 - loss: 1.3108 - accuracy: 0.4161 - -
-``` - -``` -
-144/183 [======================>.......] - ETA: 9:11 - loss: 1.3098 - accuracy: 0.4167 - -
-``` - -``` -
-145/183 [======================>.......] - ETA: 8:57 - loss: 1.3086 - accuracy: 0.4172 - -
-``` - -``` -
-146/183 [======================>.......] - ETA: 8:43 - loss: 1.3083 - accuracy: 0.4161 - -
-``` - -``` -
-147/183 [=======================>......] - ETA: 8:29 - loss: 1.3067 - accuracy: 0.4184 - -
-``` - -``` -
-148/183 [=======================>......] - ETA: 8:15 - loss: 1.3047 - accuracy: 0.4215 - -
-``` - -``` -
-149/183 [=======================>......] - ETA: 8:01 - loss: 1.3037 - accuracy: 0.4211 - -
-``` - -``` -
-150/183 [=======================>......] - ETA: 7:47 - loss: 1.3029 - accuracy: 0.4217 - -
-``` - -``` -
-151/183 [=======================>......] - ETA: 7:32 - loss: 1.3021 - accuracy: 0.4222 - -
-``` - -``` -
-152/183 [=======================>......] - ETA: 7:18 - loss: 1.3007 - accuracy: 0.4243 - -
-``` - -``` -
-153/183 [========================>.....] - ETA: 7:04 - loss: 1.3017 - accuracy: 0.4240 - -
-``` - -``` -
-154/183 [========================>.....] - ETA: 6:50 - loss: 1.3006 - accuracy: 0.4253 - -
-``` - -``` -
-155/183 [========================>.....] - ETA: 6:36 - loss: 1.2986 - accuracy: 0.4282 - -
-``` - -``` -
-156/183 [========================>.....] - ETA: 6:22 - loss: 1.2965 - accuracy: 0.4303 - -
-``` - -``` -
-157/183 [========================>.....] - ETA: 6:08 - loss: 1.2964 - accuracy: 0.4283 - -
-``` - -``` -
-158/183 [========================>.....] - ETA: 5:53 - loss: 1.2953 - accuracy: 0.4288 - -
-``` - -``` -
-159/183 [=========================>....] - ETA: 5:39 - loss: 1.2931 - accuracy: 0.4316 - -
-``` - -``` -
-160/183 [=========================>....] - ETA: 5:25 - loss: 1.2923 - accuracy: 0.4320 - -
-``` - -``` -
-161/183 [=========================>....] - ETA: 5:11 - loss: 1.2916 - accuracy: 0.4332 - -
-``` - -``` -
-162/183 [=========================>....] - ETA: 4:57 - loss: 1.2905 - accuracy: 0.4344 - -
-``` - -``` -
-163/183 [=========================>....] - ETA: 4:43 - loss: 1.2901 - accuracy: 0.4348 - -
-``` - -``` -
-164/183 [=========================>....] - ETA: 4:28 - loss: 1.2891 - accuracy: 0.4360 - -
-``` - -``` -
-165/183 [==========================>...] - ETA: 4:14 - loss: 1.2881 - accuracy: 0.4356 - -
-``` - -``` -
-166/183 [==========================>...] - ETA: 4:00 - loss: 1.2860 - accuracy: 0.4375 - -
-``` - -``` -
-167/183 [==========================>...] - ETA: 3:46 - loss: 1.2835 - accuracy: 0.4386 - -
-``` - -``` -
-168/183 [==========================>...] - ETA: 3:32 - loss: 1.2838 - accuracy: 0.4375 - -
-``` - -``` -
-169/183 [==========================>...] - ETA: 3:18 - loss: 1.2829 - accuracy: 0.4379 - -
-``` - -``` -
-170/183 [==========================>...] - ETA: 3:03 - loss: 1.2830 - accuracy: 0.4390 - -
-``` - -``` -
-171/183 [===========================>..] - ETA: 2:49 - loss: 1.2800 - accuracy: 0.4415 - -
-``` - -``` -
-172/183 [===========================>..] - ETA: 2:35 - loss: 1.2784 - accuracy: 0.4419 - -
-``` - -``` -
-173/183 [===========================>..] - ETA: 2:21 - loss: 1.2765 - accuracy: 0.4429 - -
-``` - -``` -
-174/183 [===========================>..] - ETA: 2:07 - loss: 1.2746 - accuracy: 0.4447 - -
-``` - -``` -
-175/183 [===========================>..] - ETA: 1:53 - loss: 1.2730 - accuracy: 0.4457 - -
-``` - -``` -
-176/183 [===========================>..] - ETA: 1:39 - loss: 1.2705 - accuracy: 0.4489 - -
-``` - -``` -
-177/183 [============================>.] - ETA: 1:24 - loss: 1.2696 - accuracy: 0.4492 - -
-``` - -``` -
-178/183 [============================>.] - ETA: 1:10 - loss: 1.2686 - accuracy: 0.4501 - -
-``` - -``` -
-179/183 [============================>.] - ETA: 56s - loss: 1.2679 - accuracy: 0.4511 - -
-``` - -``` -
-180/183 [============================>.] - ETA: 42s - loss: 1.2671 - accuracy: 0.4521 - -
-``` - -``` -
-181/183 [============================>.] - ETA: 28s - loss: 1.2666 - accuracy: 0.4523 - -
-``` - -``` -
-182/183 [============================>.] - ETA: 14s - loss: 1.2642 - accuracy: 0.4547 - -
-``` - -``` -
-183/183 [==============================] - ETA: 0s - loss: 1.2631 - accuracy: 0.4556 - -
-``` - -``` -
-183/183 [==============================] - 2748s 15s/step - loss: 1.2631 - accuracy: 0.4556 - val_loss: 0.9210 - val_accuracy: 0.7075 - lr: 2.9000e-06 - - -
-``` -Epoch 3/5 - -``` -
- - 1/183 [..............................] - ETA: 46:11 - loss: 1.1680 - accuracy: 0.3750 - -
-``` - -``` -
- 2/183 [..............................] - ETA: 43:28 - loss: 1.0826 - accuracy: 0.5625 - -
-``` - -``` -
- 3/183 [..............................] - ETA: 43:21 - loss: 1.1881 - accuracy: 0.5417 - -
-``` - -``` -
- 4/183 [..............................] - ETA: 43:06 - loss: 1.1313 - accuracy: 0.5625 - -
-``` - -``` -
- 5/183 [..............................] - ETA: 42:50 - loss: 1.1148 - accuracy: 0.6000 - -
-``` - -``` -
- 6/183 [..............................] - ETA: 42:32 - loss: 1.0660 - accuracy: 0.6458 - -
-``` - -``` -
- 7/183 [>.............................] - ETA: 42:14 - loss: 1.0620 - accuracy: 0.6429 - -
-``` - -``` -
- 8/183 [>.............................] - ETA: 41:56 - loss: 1.0516 - accuracy: 0.6562 - -
-``` - -``` -
- 9/183 [>.............................] - ETA: 41:40 - loss: 1.0623 - accuracy: 0.6250 - -
-``` - -``` -
- 10/183 [>.............................] - ETA: 41:28 - loss: 1.0573 - accuracy: 0.6250 - -
-``` - -``` -
- 11/183 [>.............................] - ETA: 41:12 - loss: 1.0500 - accuracy: 0.6364 - -
-``` - -``` -
- 12/183 [>.............................] - ETA: 40:55 - loss: 1.0126 - accuracy: 0.6667 - -
-``` - -``` -
- 13/183 [=>............................] - ETA: 40:39 - loss: 1.0203 - accuracy: 0.6538 - -
-``` - -``` -
- 14/183 [=>............................] - ETA: 40:22 - loss: 1.0258 - accuracy: 0.6518 - -
-``` - -``` -
- 15/183 [=>............................] - ETA: 40:06 - loss: 1.0312 - accuracy: 0.6583 - -
-``` - -``` -
- 16/183 [=>............................] - ETA: 39:50 - loss: 1.0269 - accuracy: 0.6562 - -
-``` - -``` -
- 17/183 [=>............................] - ETA: 39:33 - loss: 1.0329 - accuracy: 0.6618 - -
-``` - -``` -
- 18/183 [=>............................] - ETA: 39:18 - loss: 1.0382 - accuracy: 0.6667 - -
-``` - -``` -
- 19/183 [==>...........................] - ETA: 39:03 - loss: 1.0372 - accuracy: 0.6579 - -
-``` - -``` -
- 20/183 [==>...........................] - ETA: 38:48 - loss: 1.0363 - accuracy: 0.6500 - -
-``` - -``` -
- 21/183 [==>...........................] - ETA: 38:33 - loss: 1.0430 - accuracy: 0.6369 - -
-``` - -``` -
- 22/183 [==>...........................] - ETA: 38:18 - loss: 1.0392 - accuracy: 0.6420 - -
-``` - -``` -
- 23/183 [==>...........................] - ETA: 38:03 - loss: 1.0438 - accuracy: 0.6250 - -
-``` - -``` -
- 24/183 [==>...........................] - ETA: 37:49 - loss: 1.0405 - accuracy: 0.6302 - -
-``` - -``` -
- 25/183 [===>..........................] - ETA: 37:34 - loss: 1.0383 - accuracy: 0.6250 - -
-``` - -``` -
- 26/183 [===>..........................] - ETA: 37:20 - loss: 1.0392 - accuracy: 0.6250 - -
-``` - -``` -
- 27/183 [===>..........................] - ETA: 37:05 - loss: 1.0422 - accuracy: 0.6204 - -
-``` - -``` -
- 28/183 [===>..........................] - ETA: 36:50 - loss: 1.0441 - accuracy: 0.6205 - -
-``` - -``` -
- 29/183 [===>..........................] - ETA: 36:35 - loss: 1.0482 - accuracy: 0.6164 - -
-``` - -``` -
- 30/183 [===>..........................] - ETA: 36:21 - loss: 1.0541 - accuracy: 0.6042 - -
-``` - -``` -
- 31/183 [====>.........................] - ETA: 36:06 - loss: 1.0507 - accuracy: 0.6089 - -
-``` - -``` -
- 32/183 [====>.........................] - ETA: 35:52 - loss: 1.0431 - accuracy: 0.6211 - -
-``` - -``` -
- 33/183 [====>.........................] - ETA: 35:37 - loss: 1.0418 - accuracy: 0.6250 - -
-``` - -``` -
- 34/183 [====>.........................] - ETA: 35:22 - loss: 1.0382 - accuracy: 0.6250 - -
-``` - -``` -
- 35/183 [====>.........................] - ETA: 35:08 - loss: 1.0369 - accuracy: 0.6250 - -
-``` - -``` -
- 36/183 [====>.........................] - ETA: 34:53 - loss: 1.0396 - accuracy: 0.6250 - -
-``` - -``` -
- 37/183 [=====>........................] - ETA: 34:38 - loss: 1.0396 - accuracy: 0.6216 - -
-``` - -``` -
- 38/183 [=====>........................] - ETA: 34:24 - loss: 1.0478 - accuracy: 0.6118 - -
-``` - -``` -
- 39/183 [=====>........................] - ETA: 34:09 - loss: 1.0412 - accuracy: 0.6154 - -
-``` - -``` -
- 40/183 [=====>........................] - ETA: 33:55 - loss: 1.0397 - accuracy: 0.6156 - -
-``` - -``` -
- 41/183 [=====>........................] - ETA: 33:41 - loss: 1.0378 - accuracy: 0.6159 - -
-``` - -``` -
- 42/183 [=====>........................] - ETA: 33:26 - loss: 1.0331 - accuracy: 0.6190 - -
-``` - -``` -
- 43/183 [======>.......................] - ETA: 33:13 - loss: 1.0287 - accuracy: 0.6192 - -
-``` - -``` -
- 44/183 [======>.......................] - ETA: 32:58 - loss: 1.0366 - accuracy: 0.6136 - -
-``` - -``` -
- 45/183 [======>.......................] - ETA: 32:43 - loss: 1.0337 - accuracy: 0.6167 - -
-``` - -``` -
- 46/183 [======>.......................] - ETA: 32:29 - loss: 1.0309 - accuracy: 0.6196 - -
-``` - -``` -
- 47/183 [======>.......................] - ETA: 32:15 - loss: 1.0355 - accuracy: 0.6144 - -
-``` - -``` -
- 48/183 [======>.......................] - ETA: 32:00 - loss: 1.0365 - accuracy: 0.6146 - -
-``` - -``` -
- 49/183 [=======>......................] - ETA: 31:46 - loss: 1.0344 - accuracy: 0.6173 - -
-``` - -``` -
- 50/183 [=======>......................] - ETA: 31:32 - loss: 1.0364 - accuracy: 0.6175 - -
-``` - -``` -
- 51/183 [=======>......................] - ETA: 31:17 - loss: 1.0385 - accuracy: 0.6152 - -
-``` - -``` -
- 52/183 [=======>......................] - ETA: 31:03 - loss: 1.0415 - accuracy: 0.6106 - -
-``` - -``` -
- 53/183 [=======>......................] - ETA: 30:50 - loss: 1.0360 - accuracy: 0.6156 - -
-``` - -``` -
- 54/183 [=======>......................] - ETA: 30:36 - loss: 1.0329 - accuracy: 0.6181 - -
-``` - -``` -
- 55/183 [========>.....................] - ETA: 30:21 - loss: 1.0340 - accuracy: 0.6136 - -
-``` - -``` -
- 56/183 [========>.....................] - ETA: 30:07 - loss: 1.0357 - accuracy: 0.6094 - -
-``` - -``` -
- 57/183 [========>.....................] - ETA: 29:53 - loss: 1.0389 - accuracy: 0.6096 - -
-``` - -``` -
- 58/183 [========>.....................] - ETA: 29:38 - loss: 1.0403 - accuracy: 0.6099 - -
-``` - -``` -
- 59/183 [========>.....................] - ETA: 29:24 - loss: 1.0437 - accuracy: 0.6038 - -
-``` - -``` -
- 60/183 [========>.....................] - ETA: 29:09 - loss: 1.0459 - accuracy: 0.6042 - -
-``` - -``` -
- 61/183 [=========>....................] - ETA: 28:55 - loss: 1.0509 - accuracy: 0.6025 - -
-``` - -``` -
- 62/183 [=========>....................] - ETA: 28:41 - loss: 1.0511 - accuracy: 0.5988 - -
-``` - -``` -
- 63/183 [=========>....................] - ETA: 28:27 - loss: 1.0479 - accuracy: 0.5992 - -
-``` - -``` -
- 64/183 [=========>....................] - ETA: 28:12 - loss: 1.0548 - accuracy: 0.5977 - -
-``` - -``` -
- 65/183 [=========>....................] - ETA: 27:58 - loss: 1.0570 - accuracy: 0.5962 - -
-``` - -``` -
- 66/183 [=========>....................] - ETA: 27:44 - loss: 1.0555 - accuracy: 0.5966 - -
-``` - -``` -
- 67/183 [=========>....................] - ETA: 27:29 - loss: 1.0566 - accuracy: 0.5951 - -
-``` - -``` -
- 68/183 [==========>...................] - ETA: 27:15 - loss: 1.0571 - accuracy: 0.5938 - -
-``` - -``` -
- 69/183 [==========>...................] - ETA: 27:01 - loss: 1.0523 - accuracy: 0.5978 - -
-``` - -``` -
- 70/183 [==========>...................] - ETA: 26:47 - loss: 1.0483 - accuracy: 0.6000 - -
-``` - -``` -
- 71/183 [==========>...................] - ETA: 26:32 - loss: 1.0489 - accuracy: 0.5968 - -
-``` - -``` -
- 72/183 [==========>...................] - ETA: 26:18 - loss: 1.0491 - accuracy: 0.5955 - -
-``` - -``` -
- 73/183 [==========>...................] - ETA: 26:04 - loss: 1.0486 - accuracy: 0.5959 - -
-``` - -``` -
- 74/183 [===========>..................] - ETA: 25:49 - loss: 1.0532 - accuracy: 0.5912 - -
-``` - -``` -
- 75/183 [===========>..................] - ETA: 25:35 - loss: 1.0535 - accuracy: 0.5917 - -
-``` - -``` -
- 76/183 [===========>..................] - ETA: 25:21 - loss: 1.0568 - accuracy: 0.5888 - -
-``` - -``` -
- 77/183 [===========>..................] - ETA: 25:06 - loss: 1.0600 - accuracy: 0.5844 - -
-``` - -``` -
- 78/183 [===========>..................] - ETA: 24:52 - loss: 1.0557 - accuracy: 0.5865 - -
-``` - -``` -
- 79/183 [===========>..................] - ETA: 24:38 - loss: 1.0538 - accuracy: 0.5870 - -
-``` - -``` -
- 80/183 [============>.................] - ETA: 24:23 - loss: 1.0543 - accuracy: 0.5844 - -
-``` - -``` -
- 81/183 [============>.................] - ETA: 24:09 - loss: 1.0528 - accuracy: 0.5864 - -
-``` - -``` -
- 82/183 [============>.................] - ETA: 23:55 - loss: 1.0547 - accuracy: 0.5838 - -
-``` - -``` -
- 83/183 [============>.................] - ETA: 23:41 - loss: 1.0558 - accuracy: 0.5798 - -
-``` - -``` -
- 84/183 [============>.................] - ETA: 23:26 - loss: 1.0564 - accuracy: 0.5804 - -
-``` - -``` -
- 85/183 [============>.................] - ETA: 23:12 - loss: 1.0548 - accuracy: 0.5794 - -
-``` - -``` -
- 86/183 [=============>................] - ETA: 22:58 - loss: 1.0542 - accuracy: 0.5770 - -
-``` - -``` -
- 87/183 [=============>................] - ETA: 22:44 - loss: 1.0569 - accuracy: 0.5761 - -
-``` - -``` -
- 88/183 [=============>................] - ETA: 22:29 - loss: 1.0551 - accuracy: 0.5781 - -
-``` - -``` -
- 89/183 [=============>................] - ETA: 22:15 - loss: 1.0525 - accuracy: 0.5815 - -
-``` - -``` -
- 90/183 [=============>................] - ETA: 22:01 - loss: 1.0552 - accuracy: 0.5778 - -
-``` - -``` -
- 91/183 [=============>................] - ETA: 21:47 - loss: 1.0529 - accuracy: 0.5797 - -
-``` - -``` -
- 92/183 [==============>...............] - ETA: 21:32 - loss: 1.0501 - accuracy: 0.5802 - -
-``` - -``` -
- 93/183 [==============>...............] - ETA: 21:18 - loss: 1.0496 - accuracy: 0.5793 - -
-``` - -``` -
- 94/183 [==============>...............] - ETA: 21:04 - loss: 1.0512 - accuracy: 0.5798 - -
-``` - -``` -
- 95/183 [==============>...............] - ETA: 20:49 - loss: 1.0518 - accuracy: 0.5803 - -
-``` - -``` -
- 96/183 [==============>...............] - ETA: 20:35 - loss: 1.0520 - accuracy: 0.5807 - -
-``` - -``` -
- 97/183 [==============>...............] - ETA: 20:21 - loss: 1.0550 - accuracy: 0.5812 - -
-``` - -``` -
- 98/183 [===============>..............] - ETA: 20:07 - loss: 1.0576 - accuracy: 0.5791 - -
-``` - -``` -
- 99/183 [===============>..............] - ETA: 19:53 - loss: 1.0571 - accuracy: 0.5770 - -
-``` - -``` -
-100/183 [===============>..............] - ETA: 19:38 - loss: 1.0547 - accuracy: 0.5775 - -
-``` - -``` -
-101/183 [===============>..............] - ETA: 19:24 - loss: 1.0547 - accuracy: 0.5767 - -
-``` - -``` -
-102/183 [===============>..............] - ETA: 19:10 - loss: 1.0536 - accuracy: 0.5748 - -
-``` - -``` -
-103/183 [===============>..............] - ETA: 18:56 - loss: 1.0514 - accuracy: 0.5752 - -
-``` - -``` -
-104/183 [================>.............] - ETA: 18:41 - loss: 1.0495 - accuracy: 0.5769 - -
-``` - -``` -
-105/183 [================>.............] - ETA: 18:27 - loss: 1.0462 - accuracy: 0.5774 - -
-``` - -``` -
-106/183 [================>.............] - ETA: 18:13 - loss: 1.0451 - accuracy: 0.5790 - -
-``` - -``` -
-107/183 [================>.............] - ETA: 17:59 - loss: 1.0434 - accuracy: 0.5818 - -
-``` - -``` -
-108/183 [================>.............] - ETA: 17:44 - loss: 1.0424 - accuracy: 0.5833 - -
-``` - -``` -
-109/183 [================>.............] - ETA: 17:30 - loss: 1.0421 - accuracy: 0.5826 - -
-``` - -``` -
-110/183 [=================>............] - ETA: 17:16 - loss: 1.0409 - accuracy: 0.5830 - -
-``` - -``` -
-111/183 [=================>............] - ETA: 17:02 - loss: 1.0415 - accuracy: 0.5833 - -
-``` - -``` -
-112/183 [=================>............] - ETA: 16:47 - loss: 1.0403 - accuracy: 0.5837 - -
-``` - -``` -
-113/183 [=================>............] - ETA: 16:33 - loss: 1.0377 - accuracy: 0.5852 - -
-``` - -``` -
-114/183 [=================>............] - ETA: 16:19 - loss: 1.0367 - accuracy: 0.5866 - -
-``` - -``` -
-115/183 [=================>............] - ETA: 16:05 - loss: 1.0357 - accuracy: 0.5880 - -
-``` - -``` -
-116/183 [==================>...........] - ETA: 15:50 - loss: 1.0347 - accuracy: 0.5884 - -
-``` - -``` -
-117/183 [==================>...........] - ETA: 15:36 - loss: 1.0329 - accuracy: 0.5897 - -
-``` - -``` -
-118/183 [==================>...........] - ETA: 15:22 - loss: 1.0314 - accuracy: 0.5900 - -
-``` - -``` -
-119/183 [==================>...........] - ETA: 15:08 - loss: 1.0309 - accuracy: 0.5903 - -
-``` - -``` -
-120/183 [==================>...........] - ETA: 14:54 - loss: 1.0273 - accuracy: 0.5927 - -
-``` - -``` -
-121/183 [==================>...........] - ETA: 14:39 - loss: 1.0271 - accuracy: 0.5919 - -
-``` - -``` -
-122/183 [===================>..........] - ETA: 14:25 - loss: 1.0277 - accuracy: 0.5922 - -
-``` - -``` -
-123/183 [===================>..........] - ETA: 14:11 - loss: 1.0252 - accuracy: 0.5925 - -
-``` - -``` -
-124/183 [===================>..........] - ETA: 13:57 - loss: 1.0260 - accuracy: 0.5927 - -
-``` - -``` -
-125/183 [===================>..........] - ETA: 13:42 - loss: 1.0269 - accuracy: 0.5930 - -
-``` - -``` -
-126/183 [===================>..........] - ETA: 13:28 - loss: 1.0241 - accuracy: 0.5942 - -
-``` - -``` -
-127/183 [===================>..........] - ETA: 13:14 - loss: 1.0223 - accuracy: 0.5965 - -
-``` - -``` -
-128/183 [===================>..........] - ETA: 13:00 - loss: 1.0215 - accuracy: 0.5947 - -
-``` - -``` -
-129/183 [====================>.........] - ETA: 12:46 - loss: 1.0225 - accuracy: 0.5940 - -
-``` - -``` -
-130/183 [====================>.........] - ETA: 12:31 - loss: 1.0200 - accuracy: 0.5962 - -
-``` - -``` -
-131/183 [====================>.........] - ETA: 12:17 - loss: 1.0190 - accuracy: 0.5964 - -
-``` - -``` -
-132/183 [====================>.........] - ETA: 12:03 - loss: 1.0178 - accuracy: 0.5975 - -
-``` - -``` -
-133/183 [====================>.........] - ETA: 11:49 - loss: 1.0159 - accuracy: 0.5987 - -
-``` - -``` -
-134/183 [====================>.........] - ETA: 11:35 - loss: 1.0160 - accuracy: 0.5989 - -
-``` - -``` -
-135/183 [=====================>........] - ETA: 11:20 - loss: 1.0147 - accuracy: 0.5991 - -
-``` - -``` -
-136/183 [=====================>........] - ETA: 11:06 - loss: 1.0153 - accuracy: 0.5993 - -
-``` - -``` -
-137/183 [=====================>........] - ETA: 10:52 - loss: 1.0184 - accuracy: 0.5976 - -
-``` - -``` -
-138/183 [=====================>........] - ETA: 10:38 - loss: 1.0174 - accuracy: 0.5978 - -
-``` - -``` -
-139/183 [=====================>........] - ETA: 10:24 - loss: 1.0192 - accuracy: 0.5980 - -
-``` - -``` -
-140/183 [=====================>........] - ETA: 10:09 - loss: 1.0221 - accuracy: 0.5955 - -
-``` - -``` -
-141/183 [======================>.......] - ETA: 9:55 - loss: 1.0244 - accuracy: 0.5931 - -
-``` - -``` -
-142/183 [======================>.......] - ETA: 9:41 - loss: 1.0228 - accuracy: 0.5951 - -
-``` - -``` -
-143/183 [======================>.......] - ETA: 9:27 - loss: 1.0211 - accuracy: 0.5970 - -
-``` - -``` -
-144/183 [======================>.......] - ETA: 9:13 - loss: 1.0235 - accuracy: 0.5946 - -
-``` - -``` -
-145/183 [======================>.......] - ETA: 8:59 - loss: 1.0241 - accuracy: 0.5940 - -
-``` - -``` -
-146/183 [======================>.......] - ETA: 8:44 - loss: 1.0228 - accuracy: 0.5950 - -
-``` - -``` -
-147/183 [=======================>......] - ETA: 8:30 - loss: 1.0229 - accuracy: 0.5961 - -
-``` - -``` -
-148/183 [=======================>......] - ETA: 8:16 - loss: 1.0204 - accuracy: 0.5980 - -
-``` - -``` -
-149/183 [=======================>......] - ETA: 8:02 - loss: 1.0193 - accuracy: 0.5990 - -
-``` - -``` -
-150/183 [=======================>......] - ETA: 7:48 - loss: 1.0173 - accuracy: 0.6000 - -
-``` - -``` -
-151/183 [=======================>......] - ETA: 7:33 - loss: 1.0190 - accuracy: 0.5993 - -
-``` - -``` -
-152/183 [=======================>......] - ETA: 7:19 - loss: 1.0233 - accuracy: 0.5979 - -
-``` - -``` -
-153/183 [========================>.....] - ETA: 7:05 - loss: 1.0230 - accuracy: 0.5972 - -
-``` - -``` -
-154/183 [========================>.....] - ETA: 6:51 - loss: 1.0230 - accuracy: 0.5974 - -
-``` - -``` -
-155/183 [========================>.....] - ETA: 6:37 - loss: 1.0223 - accuracy: 0.5992 - -
-``` - -``` -
-156/183 [========================>.....] - ETA: 6:22 - loss: 1.0204 - accuracy: 0.5994 - -
-``` - -``` -
-157/183 [========================>.....] - ETA: 6:08 - loss: 1.0204 - accuracy: 0.5987 - -
-``` - -``` -
-158/183 [========================>.....] - ETA: 5:54 - loss: 1.0201 - accuracy: 0.5965 - -
-``` - -``` -
-159/183 [=========================>....] - ETA: 5:40 - loss: 1.0199 - accuracy: 0.5975 - -
-``` - -``` -
-160/183 [=========================>....] - ETA: 5:26 - loss: 1.0168 - accuracy: 0.5992 - -
-``` - -``` -
-161/183 [=========================>....] - ETA: 5:12 - loss: 1.0155 - accuracy: 0.6009 - -
-``` - -``` -
-162/183 [=========================>....] - ETA: 4:57 - loss: 1.0131 - accuracy: 0.6019 - -
-``` - -``` -
-163/183 [=========================>....] - ETA: 4:43 - loss: 1.0144 - accuracy: 0.6020 - -
-``` - -``` -
-164/183 [=========================>....] - ETA: 4:29 - loss: 1.0145 - accuracy: 0.6021 - -
-``` - -``` -
-165/183 [==========================>...] - ETA: 4:15 - loss: 1.0138 - accuracy: 0.6030 - -
-``` - -``` -
-166/183 [==========================>...] - ETA: 4:01 - loss: 1.0127 - accuracy: 0.6032 - -
-``` - -``` -
-167/183 [==========================>...] - ETA: 3:46 - loss: 1.0127 - accuracy: 0.6018 - -
-``` - -``` -
-168/183 [==========================>...] - ETA: 3:32 - loss: 1.0102 - accuracy: 0.6027 - -
-``` - -``` -
-169/183 [==========================>...] - ETA: 3:18 - loss: 1.0119 - accuracy: 0.6013 - -
-``` - -``` -
-170/183 [==========================>...] - ETA: 3:04 - loss: 1.0113 - accuracy: 0.6007 - -
-``` - -``` -
-171/183 [===========================>..] - ETA: 2:50 - loss: 1.0134 - accuracy: 0.6001 - -
-``` - -``` -
-172/183 [===========================>..] - ETA: 2:36 - loss: 1.0117 - accuracy: 0.6010 - -
-``` - -``` -
-173/183 [===========================>..] - ETA: 2:21 - loss: 1.0100 - accuracy: 0.6012 - -
-``` - -``` -
-174/183 [===========================>..] - ETA: 2:07 - loss: 1.0084 - accuracy: 0.6020 - -
-``` - -``` -
-175/183 [===========================>..] - ETA: 1:53 - loss: 1.0060 - accuracy: 0.6043 - -
-``` - -``` -
-176/183 [===========================>..] - ETA: 1:39 - loss: 1.0041 - accuracy: 0.6044 - -
-``` - -``` -
-177/183 [============================>.] - ETA: 1:25 - loss: 1.0025 - accuracy: 0.6059 - -
-``` - -``` -
-178/183 [============================>.] - ETA: 1:10 - loss: 1.0034 - accuracy: 0.6053 - -
-``` - -``` -
-179/183 [============================>.] - ETA: 56s - loss: 1.0040 - accuracy: 0.6054 - -
-``` - -``` -
-180/183 [============================>.] - ETA: 42s - loss: 1.0036 - accuracy: 0.6049 - -
-``` - -``` -
-181/183 [============================>.] - ETA: 28s - loss: 1.0028 - accuracy: 0.6050 - -
-``` - -``` -
-182/183 [============================>.] - ETA: 14s - loss: 1.0028 - accuracy: 0.6051 - -
-``` - -``` -
-183/183 [==============================] - ETA: 0s - loss: 1.0013 - accuracy: 0.6052 - -
-``` - -``` -
-183/183 [==============================] - 2755s 15s/step - loss: 1.0013 - accuracy: 0.6052 - val_loss: 0.7730 - val_accuracy: 0.7475 - lr: 4.8000e-06 - - -
-``` -Epoch 4/5 - -``` -
- - 1/183 [..............................] - ETA: 45:34 - loss: 0.7885 - accuracy: 0.7500 - -
-``` - -``` -
- 2/183 [..............................] - ETA: 43:17 - loss: 0.8742 - accuracy: 0.6875 - -
-``` - -``` -
- 3/183 [..............................] - ETA: 43:02 - loss: 0.7851 - accuracy: 0.7083 - -
-``` - -``` -
- 4/183 [..............................] - ETA: 42:51 - loss: 0.9176 - accuracy: 0.6562 - -
-``` - -``` -
- 5/183 [..............................] - ETA: 42:39 - loss: 0.8677 - accuracy: 0.7000 - -
-``` - -``` -
- 6/183 [..............................] - ETA: 42:25 - loss: 0.8238 - accuracy: 0.7292 - -
-``` - -``` -
- 7/183 [>.............................] - ETA: 42:09 - loss: 0.8209 - accuracy: 0.7143 - -
-``` - -``` -
- 8/183 [>.............................] - ETA: 41:54 - loss: 0.8494 - accuracy: 0.6875 - -
-``` - -``` -
- 9/183 [>.............................] - ETA: 41:40 - loss: 0.8458 - accuracy: 0.6944 - -
-``` - -``` -
- 10/183 [>.............................] - ETA: 41:25 - loss: 0.8841 - accuracy: 0.6625 - -
-``` - -``` -
- 11/183 [>.............................] - ETA: 41:10 - loss: 0.8833 - accuracy: 0.6705 - -
-``` - -``` -
- 12/183 [>.............................] - ETA: 40:54 - loss: 0.8520 - accuracy: 0.6979 - -
-``` - -``` -
- 13/183 [=>............................] - ETA: 40:38 - loss: 0.8262 - accuracy: 0.7115 - -
-``` - -``` -
- 14/183 [=>............................] - ETA: 40:23 - loss: 0.8389 - accuracy: 0.7054 - -
-``` - -``` -
- 15/183 [=>............................] - ETA: 40:08 - loss: 0.8262 - accuracy: 0.7250 - -
-``` - -``` -
- 16/183 [=>............................] - ETA: 39:53 - loss: 0.8368 - accuracy: 0.7188 - -
-``` - -``` -
- 17/183 [=>............................] - ETA: 39:39 - loss: 0.8293 - accuracy: 0.7279 - -
-``` - -``` -
- 18/183 [=>............................] - ETA: 39:25 - loss: 0.8353 - accuracy: 0.7222 - -
-``` - -``` -
- 19/183 [==>...........................] - ETA: 39:09 - loss: 0.8331 - accuracy: 0.7237 - -
-``` - -``` -
- 20/183 [==>...........................] - ETA: 38:54 - loss: 0.8452 - accuracy: 0.7063 - -
-``` - -``` -
- 21/183 [==>...........................] - ETA: 38:38 - loss: 0.8396 - accuracy: 0.7083 - -
-``` - -``` -
- 22/183 [==>...........................] - ETA: 38:23 - loss: 0.8370 - accuracy: 0.7102 - -
-``` - -``` -
- 23/183 [==>...........................] - ETA: 38:08 - loss: 0.8350 - accuracy: 0.7120 - -
-``` - -``` -
- 24/183 [==>...........................] - ETA: 37:53 - loss: 0.8551 - accuracy: 0.7031 - -
-``` - -``` -
- 25/183 [===>..........................] - ETA: 37:38 - loss: 0.8385 - accuracy: 0.7150 - -
-``` - -``` -
- 26/183 [===>..........................] - ETA: 37:23 - loss: 0.8379 - accuracy: 0.7163 - -
-``` - -``` -
- 27/183 [===>..........................] - ETA: 37:09 - loss: 0.8418 - accuracy: 0.7130 - -
-``` - -``` -
- 28/183 [===>..........................] - ETA: 36:54 - loss: 0.8280 - accuracy: 0.7232 - -
-``` - -``` -
- 29/183 [===>..........................] - ETA: 36:39 - loss: 0.8371 - accuracy: 0.7069 - -
-``` - -``` -
- 30/183 [===>..........................] - ETA: 36:24 - loss: 0.8461 - accuracy: 0.7042 - -
-``` - -``` -
- 31/183 [====>.........................] - ETA: 36:10 - loss: 0.8476 - accuracy: 0.7056 - -
-``` - -``` -
- 32/183 [====>.........................] - ETA: 35:55 - loss: 0.8437 - accuracy: 0.7031 - -
-``` - -``` -
- 33/183 [====>.........................] - ETA: 35:40 - loss: 0.8428 - accuracy: 0.7045 - -
-``` - -``` -
- 34/183 [====>.........................] - ETA: 35:25 - loss: 0.8396 - accuracy: 0.7096 - -
-``` - -``` -
- 35/183 [====>.........................] - ETA: 35:11 - loss: 0.8330 - accuracy: 0.7107 - -
-``` - -``` -
- 36/183 [====>.........................] - ETA: 34:56 - loss: 0.8283 - accuracy: 0.7118 - -
-``` - -``` -
- 37/183 [=====>........................] - ETA: 34:41 - loss: 0.8235 - accuracy: 0.7162 - -
-``` - -``` -
- 38/183 [=====>........................] - ETA: 34:27 - loss: 0.8247 - accuracy: 0.7171 - -
-``` - -``` -
- 39/183 [=====>........................] - ETA: 34:12 - loss: 0.8305 - accuracy: 0.7147 - -
-``` - -``` -
- 40/183 [=====>........................] - ETA: 33:58 - loss: 0.8233 - accuracy: 0.7219 - -
-``` - -``` -
- 41/183 [=====>........................] - ETA: 33:43 - loss: 0.8217 - accuracy: 0.7195 - -
-``` - -``` -
- 42/183 [=====>........................] - ETA: 33:28 - loss: 0.8180 - accuracy: 0.7202 - -
-``` - -``` -
- 43/183 [======>.......................] - ETA: 33:15 - loss: 0.8268 - accuracy: 0.7209 - -
-``` - -``` -
- 44/183 [======>.......................] - ETA: 33:00 - loss: 0.8309 - accuracy: 0.7131 - -
-``` - -``` -
- 45/183 [======>.......................] - ETA: 32:46 - loss: 0.8377 - accuracy: 0.7111 - -
-``` - -``` -
- 46/183 [======>.......................] - ETA: 32:31 - loss: 0.8367 - accuracy: 0.7120 - -
-``` - -``` -
- 47/183 [======>.......................] - ETA: 32:17 - loss: 0.8331 - accuracy: 0.7154 - -
-``` - -``` -
- 48/183 [======>.......................] - ETA: 32:02 - loss: 0.8366 - accuracy: 0.7109 - -
-``` - -``` -
- 49/183 [=======>......................] - ETA: 31:48 - loss: 0.8383 - accuracy: 0.7117 - -
-``` - -``` -
- 50/183 [=======>......................] - ETA: 31:34 - loss: 0.8408 - accuracy: 0.7075 - -
-``` - -``` -
- 51/183 [=======>......................] - ETA: 31:19 - loss: 0.8529 - accuracy: 0.7010 - -
-``` - -``` -
- 52/183 [=======>......................] - ETA: 31:05 - loss: 0.8545 - accuracy: 0.7019 - -
-``` - -``` -
- 53/183 [=======>......................] - ETA: 30:50 - loss: 0.8502 - accuracy: 0.7075 - -
-``` - -``` -
- 54/183 [=======>......................] - ETA: 30:36 - loss: 0.8479 - accuracy: 0.7083 - -
-``` - -``` -
- 55/183 [========>.....................] - ETA: 30:21 - loss: 0.8517 - accuracy: 0.7068 - -
-``` - -``` -
- 56/183 [========>.....................] - ETA: 30:07 - loss: 0.8541 - accuracy: 0.7009 - -
-``` - -``` -
- 57/183 [========>.....................] - ETA: 29:53 - loss: 0.8560 - accuracy: 0.6996 - -
-``` - -``` -
- 58/183 [========>.....................] - ETA: 29:38 - loss: 0.8572 - accuracy: 0.6983 - -
-``` - -``` -
- 59/183 [========>.....................] - ETA: 29:24 - loss: 0.8588 - accuracy: 0.6928 - -
-``` - -``` -
- 60/183 [========>.....................] - ETA: 29:10 - loss: 0.8648 - accuracy: 0.6896 - -
-``` - -``` -
- 61/183 [=========>....................] - ETA: 28:55 - loss: 0.8662 - accuracy: 0.6885 - -
-``` - -``` -
- 62/183 [=========>....................] - ETA: 28:41 - loss: 0.8701 - accuracy: 0.6855 - -
-``` - -``` -
- 63/183 [=========>....................] - ETA: 28:27 - loss: 0.8699 - accuracy: 0.6845 - -
-``` - -``` -
- 64/183 [=========>....................] - ETA: 28:13 - loss: 0.8668 - accuracy: 0.6875 - -
-``` - -``` -
- 65/183 [=========>....................] - ETA: 27:58 - loss: 0.8760 - accuracy: 0.6846 - -
-``` - -``` -
- 66/183 [=========>....................] - ETA: 27:44 - loss: 0.8789 - accuracy: 0.6799 - -
-``` - -``` -
- 67/183 [=========>....................] - ETA: 27:30 - loss: 0.8779 - accuracy: 0.6791 - -
-``` - -``` -
- 68/183 [==========>...................] - ETA: 27:15 - loss: 0.8763 - accuracy: 0.6783 - -
-``` - -``` -
- 69/183 [==========>...................] - ETA: 27:01 - loss: 0.8751 - accuracy: 0.6775 - -
-``` - -``` -
- 70/183 [==========>...................] - ETA: 26:47 - loss: 0.8755 - accuracy: 0.6750 - -
-``` - -``` -
- 71/183 [==========>...................] - ETA: 26:32 - loss: 0.8697 - accuracy: 0.6778 - -
-``` - -``` -
- 72/183 [==========>...................] - ETA: 26:18 - loss: 0.8729 - accuracy: 0.6736 - -
-``` - -``` -
- 73/183 [==========>...................] - ETA: 26:04 - loss: 0.8713 - accuracy: 0.6747 - -
-``` - -``` -
- 74/183 [===========>..................] - ETA: 25:50 - loss: 0.8721 - accuracy: 0.6740 - -
-``` - -``` -
- 75/183 [===========>..................] - ETA: 25:35 - loss: 0.8787 - accuracy: 0.6700 - -
-``` - -``` -
- 76/183 [===========>..................] - ETA: 25:21 - loss: 0.8769 - accuracy: 0.6694 - -
-``` - -``` -
- 77/183 [===========>..................] - ETA: 25:07 - loss: 0.8743 - accuracy: 0.6705 - -
-``` - -``` -
- 78/183 [===========>..................] - ETA: 24:53 - loss: 0.8794 - accuracy: 0.6683 - -
-``` - -``` -
- 79/183 [===========>..................] - ETA: 24:39 - loss: 0.8800 - accuracy: 0.6677 - -
-``` - -``` -
- 80/183 [============>.................] - ETA: 24:24 - loss: 0.8773 - accuracy: 0.6687 - -
-``` - -``` -
- 81/183 [============>.................] - ETA: 24:10 - loss: 0.8769 - accuracy: 0.6682 - -
-``` - -``` -
- 82/183 [============>.................] - ETA: 23:56 - loss: 0.8788 - accuracy: 0.6677 - -
-``` - -``` -
- 83/183 [============>.................] - ETA: 23:42 - loss: 0.8773 - accuracy: 0.6672 - -
-``` - -``` -
- 84/183 [============>.................] - ETA: 23:27 - loss: 0.8800 - accuracy: 0.6652 - -
-``` - -``` -
- 85/183 [============>.................] - ETA: 23:13 - loss: 0.8819 - accuracy: 0.6632 - -
-``` - -``` -
- 86/183 [=============>................] - ETA: 22:59 - loss: 0.8789 - accuracy: 0.6657 - -
-``` - -``` -
- 87/183 [=============>................] - ETA: 22:45 - loss: 0.8813 - accuracy: 0.6667 - -
-``` - -``` -
- 88/183 [=============>................] - ETA: 22:31 - loss: 0.8872 - accuracy: 0.6619 - -
-``` - -``` -
- 89/183 [=============>................] - ETA: 22:16 - loss: 0.8847 - accuracy: 0.6629 - -
-``` - -``` -
- 90/183 [=============>................] - ETA: 22:02 - loss: 0.8823 - accuracy: 0.6639 - -
-``` - -``` -
- 91/183 [=============>................] - ETA: 21:48 - loss: 0.8859 - accuracy: 0.6621 - -
-``` - -``` -
- 92/183 [==============>...............] - ETA: 21:34 - loss: 0.8902 - accuracy: 0.6617 - -
-``` - -``` -
- 93/183 [==============>...............] - ETA: 21:20 - loss: 0.8896 - accuracy: 0.6626 - -
-``` - -``` -
- 94/183 [==============>...............] - ETA: 21:05 - loss: 0.8932 - accuracy: 0.6622 - -
-``` - -``` -
- 95/183 [==============>...............] - ETA: 20:51 - loss: 0.8946 - accuracy: 0.6618 - -
-``` - -``` -
- 96/183 [==============>...............] - ETA: 20:37 - loss: 0.8960 - accuracy: 0.6628 - -
-``` - -``` -
- 97/183 [==============>...............] - ETA: 20:23 - loss: 0.8934 - accuracy: 0.6649 - -
-``` - -``` -
- 98/183 [===============>..............] - ETA: 20:08 - loss: 0.8942 - accuracy: 0.6658 - -
-``` - -``` -
- 99/183 [===============>..............] - ETA: 19:54 - loss: 0.9002 - accuracy: 0.6629 - -
-``` - -``` -
-100/183 [===============>..............] - ETA: 19:40 - loss: 0.8975 - accuracy: 0.6637 - -
-``` - -``` -
-101/183 [===============>..............] - ETA: 19:26 - loss: 0.8965 - accuracy: 0.6646 - -
-``` - -``` -
-102/183 [===============>..............] - ETA: 19:11 - loss: 0.8963 - accuracy: 0.6642 - -
-``` - -``` -
-103/183 [===============>..............] - ETA: 18:57 - loss: 0.8950 - accuracy: 0.6650 - -
-``` - -``` -
-104/183 [================>.............] - ETA: 18:43 - loss: 0.8935 - accuracy: 0.6659 - -
-``` - -``` -
-105/183 [================>.............] - ETA: 18:29 - loss: 0.8912 - accuracy: 0.6667 - -
-``` - -``` -
-106/183 [================>.............] - ETA: 18:14 - loss: 0.8940 - accuracy: 0.6663 - -
-``` - -``` -
-107/183 [================>.............] - ETA: 18:00 - loss: 0.8913 - accuracy: 0.6671 - -
-``` - -``` -
-108/183 [================>.............] - ETA: 17:46 - loss: 0.8920 - accuracy: 0.6667 - -
-``` - -``` -
-109/183 [================>.............] - ETA: 17:32 - loss: 0.8915 - accuracy: 0.6674 - -
-``` - -``` -
-110/183 [=================>............] - ETA: 17:18 - loss: 0.8893 - accuracy: 0.6682 - -
-``` - -``` -
-111/183 [=================>............] - ETA: 17:03 - loss: 0.8909 - accuracy: 0.6667 - -
-``` - -``` -
-112/183 [=================>............] - ETA: 16:49 - loss: 0.8894 - accuracy: 0.6674 - -
-``` - -``` -
-113/183 [=================>............] - ETA: 16:35 - loss: 0.8909 - accuracy: 0.6659 - -
-``` - -``` -
-114/183 [=================>............] - ETA: 16:21 - loss: 0.8908 - accuracy: 0.6667 - -
-``` - -``` -
-115/183 [=================>............] - ETA: 16:07 - loss: 0.8943 - accuracy: 0.6652 - -
-``` - -``` -
-116/183 [==================>...........] - ETA: 15:53 - loss: 0.8956 - accuracy: 0.6659 - -
-``` - -``` -
-117/183 [==================>...........] - ETA: 15:40 - loss: 0.8949 - accuracy: 0.6656 - -
-``` - -``` -
-118/183 [==================>...........] - ETA: 15:26 - loss: 0.8907 - accuracy: 0.6684 - -
-``` - -``` -
-119/183 [==================>...........] - ETA: 15:11 - loss: 0.8892 - accuracy: 0.6691 - -
-``` - -``` -
-120/183 [==================>...........] - ETA: 14:57 - loss: 0.8889 - accuracy: 0.6677 - -
-``` - -``` -
-121/183 [==================>...........] - ETA: 14:43 - loss: 0.8853 - accuracy: 0.6694 - -
-``` - -``` -
-122/183 [===================>..........] - ETA: 14:29 - loss: 0.8860 - accuracy: 0.6691 - -
-``` - -``` -
-123/183 [===================>..........] - ETA: 14:14 - loss: 0.8832 - accuracy: 0.6707 - -
-``` - -``` -
-124/183 [===================>..........] - ETA: 14:00 - loss: 0.8812 - accuracy: 0.6724 - -
-``` - -``` -
-125/183 [===================>..........] - ETA: 13:46 - loss: 0.8806 - accuracy: 0.6720 - -
-``` - -``` -
-126/183 [===================>..........] - ETA: 13:32 - loss: 0.8807 - accuracy: 0.6696 - -
-``` - -``` -
-127/183 [===================>..........] - ETA: 13:17 - loss: 0.8778 - accuracy: 0.6713 - -
-``` - -``` -
-128/183 [===================>..........] - ETA: 13:03 - loss: 0.8790 - accuracy: 0.6719 - -
-``` - -``` -
-129/183 [====================>.........] - ETA: 12:49 - loss: 0.8775 - accuracy: 0.6725 - -
-``` - -``` -
-130/183 [====================>.........] - ETA: 12:35 - loss: 0.8775 - accuracy: 0.6731 - -
-``` - -``` -
-131/183 [====================>.........] - ETA: 12:21 - loss: 0.8785 - accuracy: 0.6718 - -
-``` - -``` -
-132/183 [====================>.........] - ETA: 12:07 - loss: 0.8759 - accuracy: 0.6733 - -
-``` - -``` -
-133/183 [====================>.........] - ETA: 11:52 - loss: 0.8739 - accuracy: 0.6739 - -
-``` - -``` -
-134/183 [====================>.........] - ETA: 11:38 - loss: 0.8749 - accuracy: 0.6735 - -
-``` - -``` -
-135/183 [=====================>........] - ETA: 11:24 - loss: 0.8742 - accuracy: 0.6741 - -
-``` - -``` -
-136/183 [=====================>........] - ETA: 11:10 - loss: 0.8738 - accuracy: 0.6728 - -
-``` - -``` -
-137/183 [=====================>........] - ETA: 10:56 - loss: 0.8752 - accuracy: 0.6715 - -
-``` - -``` -
-138/183 [=====================>........] - ETA: 10:41 - loss: 0.8792 - accuracy: 0.6694 - -
-``` - -``` -
-139/183 [=====================>........] - ETA: 10:27 - loss: 0.8795 - accuracy: 0.6691 - -
-``` - -``` -
-140/183 [=====================>........] - ETA: 10:13 - loss: 0.8808 - accuracy: 0.6670 - -
-``` - -``` -
-141/183 [======================>.......] - ETA: 9:59 - loss: 0.8836 - accuracy: 0.6667 - -
-``` - -``` -
-142/183 [======================>.......] - ETA: 9:44 - loss: 0.8848 - accuracy: 0.6664 - -
-``` - -``` -
-143/183 [======================>.......] - ETA: 9:30 - loss: 0.8833 - accuracy: 0.6661 - -
-``` - -``` -
-144/183 [======================>.......] - ETA: 9:16 - loss: 0.8850 - accuracy: 0.6641 - -
-``` - -``` -
-145/183 [======================>.......] - ETA: 9:02 - loss: 0.8841 - accuracy: 0.6647 - -
-``` - -``` -
-146/183 [======================>.......] - ETA: 8:47 - loss: 0.8825 - accuracy: 0.6661 - -
-``` - -``` -
-147/183 [=======================>......] - ETA: 8:33 - loss: 0.8814 - accuracy: 0.6675 - -
-``` - -``` -
-148/183 [=======================>......] - ETA: 8:19 - loss: 0.8801 - accuracy: 0.6698 - -
-``` - -``` -
-149/183 [=======================>......] - ETA: 8:05 - loss: 0.8782 - accuracy: 0.6703 - -
-``` - -``` -
-150/183 [=======================>......] - ETA: 7:51 - loss: 0.8789 - accuracy: 0.6700 - -
-``` - -``` -
-151/183 [=======================>......] - ETA: 7:36 - loss: 0.8776 - accuracy: 0.6705 - -
-``` - -``` -
-152/183 [=======================>......] - ETA: 7:22 - loss: 0.8797 - accuracy: 0.6694 - -
-``` - -``` -
-153/183 [========================>.....] - ETA: 7:08 - loss: 0.8804 - accuracy: 0.6691 - -
-``` - -``` -
-154/183 [========================>.....] - ETA: 6:53 - loss: 0.8793 - accuracy: 0.6688 - -
-``` - -``` -
-155/183 [========================>.....] - ETA: 6:39 - loss: 0.8793 - accuracy: 0.6685 - -
-``` - -``` -
-156/183 [========================>.....] - ETA: 6:25 - loss: 0.8776 - accuracy: 0.6691 - -
-``` - -``` -
-157/183 [========================>.....] - ETA: 6:11 - loss: 0.8755 - accuracy: 0.6704 - -
-``` - -``` -
-158/183 [========================>.....] - ETA: 5:57 - loss: 0.8768 - accuracy: 0.6701 - -
-``` - -``` -
-159/183 [=========================>....] - ETA: 5:42 - loss: 0.8771 - accuracy: 0.6698 - -
-``` - -``` -
-160/183 [=========================>....] - ETA: 5:28 - loss: 0.8761 - accuracy: 0.6703 - -
-``` - -``` -
-161/183 [=========================>....] - ETA: 5:14 - loss: 0.8734 - accuracy: 0.6716 - -
-``` - -``` -
-162/183 [=========================>....] - ETA: 4:59 - loss: 0.8730 - accuracy: 0.6713 - -
-``` - -``` -
-163/183 [=========================>....] - ETA: 4:45 - loss: 0.8722 - accuracy: 0.6710 - -
-``` - -``` -
-164/183 [=========================>....] - ETA: 4:31 - loss: 0.8728 - accuracy: 0.6707 - -
-``` - -``` -
-165/183 [==========================>...] - ETA: 4:17 - loss: 0.8743 - accuracy: 0.6697 - -
-``` - -``` -
-166/183 [==========================>...] - ETA: 4:02 - loss: 0.8745 - accuracy: 0.6702 - -
-``` - -``` -
-167/183 [==========================>...] - ETA: 3:48 - loss: 0.8753 - accuracy: 0.6684 - -
-``` - -``` -
-168/183 [==========================>...] - ETA: 3:34 - loss: 0.8738 - accuracy: 0.6696 - -
-``` - -``` -
-169/183 [==========================>...] - ETA: 3:20 - loss: 0.8724 - accuracy: 0.6694 - -
-``` - -``` -
-170/183 [==========================>...] - ETA: 3:05 - loss: 0.8757 - accuracy: 0.6676 - -
-``` - -``` -
-171/183 [===========================>..] - ETA: 2:51 - loss: 0.8752 - accuracy: 0.6674 - -
-``` - -``` -
-172/183 [===========================>..] - ETA: 2:37 - loss: 0.8768 - accuracy: 0.6672 - -
-``` - -``` -
-173/183 [===========================>..] - ETA: 2:22 - loss: 0.8750 - accuracy: 0.6676 - -
-``` - -``` -
-174/183 [===========================>..] - ETA: 2:08 - loss: 0.8753 - accuracy: 0.6681 - -
-``` - -``` -
-175/183 [===========================>..] - ETA: 1:54 - loss: 0.8749 - accuracy: 0.6679 - -
-``` - -``` -
-176/183 [===========================>..] - ETA: 1:40 - loss: 0.8739 - accuracy: 0.6683 - -
-``` - -``` -
-177/183 [============================>.] - ETA: 1:25 - loss: 0.8720 - accuracy: 0.6688 - -
-``` - -``` -
-178/183 [============================>.] - ETA: 1:11 - loss: 0.8719 - accuracy: 0.6692 - -
-``` - -``` -
-179/183 [============================>.] - ETA: 57s - loss: 0.8739 - accuracy: 0.6669 - -
-``` - -``` -
-180/183 [============================>.] - ETA: 42s - loss: 0.8729 - accuracy: 0.6674 - -
-``` - -``` -
-181/183 [============================>.] - ETA: 28s - loss: 0.8722 - accuracy: 0.6678 - -
-``` - -``` -
-182/183 [============================>.] - ETA: 14s - loss: 0.8715 - accuracy: 0.6683 - -
-``` - -``` -
-183/183 [==============================] - ETA: 0s - loss: 0.8728 - accuracy: 0.6680 - -
-``` - -``` -
-183/183 [==============================] - 2778s 15s/step - loss: 0.8728 - accuracy: 0.6680 - val_loss: 0.7296 - val_accuracy: 0.7525 - lr: 4.7230e-06 - - -
-``` -Epoch 5/5 - -``` -
- - 1/183 [..............................] - ETA: 45:36 - loss: 0.7472 - accuracy: 0.6250 - -
-``` - -``` -
- 2/183 [..............................] - ETA: 44:02 - loss: 0.7747 - accuracy: 0.6875 - -
-``` - -``` -
- 3/183 [..............................] - ETA: 43:51 - loss: 0.7801 - accuracy: 0.6667 - -
-``` - -``` -
- 4/183 [..............................] - ETA: 43:41 - loss: 0.7945 - accuracy: 0.6250 - -
-``` - -``` -
- 5/183 [..............................] - ETA: 43:26 - loss: 0.8398 - accuracy: 0.6500 - -
-``` - -``` -
- 6/183 [..............................] - ETA: 43:07 - loss: 0.7811 - accuracy: 0.6875 - -
-``` - -``` -
- 7/183 [>.............................] - ETA: 42:47 - loss: 0.8120 - accuracy: 0.6964 - -
-``` - -``` -
- 8/183 [>.............................] - ETA: 42:30 - loss: 0.7819 - accuracy: 0.6875 - -
-``` - -``` -
- 9/183 [>.............................] - ETA: 42:09 - loss: 0.7870 - accuracy: 0.6944 - -
-``` - -``` -
- 10/183 [>.............................] - ETA: 41:50 - loss: 0.7538 - accuracy: 0.7125 - -
-``` - -``` -
- 11/183 [>.............................] - ETA: 41:33 - loss: 0.7518 - accuracy: 0.7159 - -
-``` - -``` -
- 12/183 [>.............................] - ETA: 41:17 - loss: 0.7440 - accuracy: 0.7188 - -
-``` - -``` -
- 13/183 [=>............................] - ETA: 41:00 - loss: 0.7263 - accuracy: 0.7404 - -
-``` - -``` -
- 14/183 [=>............................] - ETA: 40:44 - loss: 0.7001 - accuracy: 0.7589 - -
-``` - -``` -
- 15/183 [=>............................] - ETA: 40:28 - loss: 0.7132 - accuracy: 0.7583 - -
-``` - -``` -
- 16/183 [=>............................] - ETA: 40:11 - loss: 0.7123 - accuracy: 0.7500 - -
-``` - -``` -
- 17/183 [=>............................] - ETA: 39:55 - loss: 0.7370 - accuracy: 0.7426 - -
-``` - -``` -
- 18/183 [=>............................] - ETA: 39:38 - loss: 0.7365 - accuracy: 0.7431 - -
-``` - -``` -
- 19/183 [==>...........................] - ETA: 39:22 - loss: 0.7469 - accuracy: 0.7303 - -
-``` - -``` -
- 20/183 [==>...........................] - ETA: 39:07 - loss: 0.7500 - accuracy: 0.7375 - -
-``` - -``` -
- 21/183 [==>...........................] - ETA: 38:52 - loss: 0.7459 - accuracy: 0.7440 - -
-``` - -``` -
- 22/183 [==>...........................] - ETA: 38:37 - loss: 0.7396 - accuracy: 0.7557 - -
-``` - -``` -
- 23/183 [==>...........................] - ETA: 38:21 - loss: 0.7387 - accuracy: 0.7500 - -
-``` - -``` -
- 24/183 [==>...........................] - ETA: 38:06 - loss: 0.7266 - accuracy: 0.7552 - -
-``` - -``` -
- 25/183 [===>..........................] - ETA: 37:51 - loss: 0.7416 - accuracy: 0.7400 - -
-``` - -``` -
- 26/183 [===>..........................] - ETA: 37:37 - loss: 0.7411 - accuracy: 0.7404 - -
-``` - -``` -
- 27/183 [===>..........................] - ETA: 37:23 - loss: 0.7337 - accuracy: 0.7454 - -
-``` - -``` -
- 28/183 [===>..........................] - ETA: 37:09 - loss: 0.7336 - accuracy: 0.7411 - -
-``` - -``` -
- 29/183 [===>..........................] - ETA: 36:54 - loss: 0.7294 - accuracy: 0.7457 - -
-``` - -``` -
- 30/183 [===>..........................] - ETA: 36:40 - loss: 0.7293 - accuracy: 0.7417 - -
-``` - -``` -
- 31/183 [====>.........................] - ETA: 36:26 - loss: 0.7399 - accuracy: 0.7379 - -
-``` - -``` -
- 32/183 [====>.........................] - ETA: 36:11 - loss: 0.7355 - accuracy: 0.7422 - -
-``` - -``` -
- 33/183 [====>.........................] - ETA: 35:57 - loss: 0.7283 - accuracy: 0.7462 - -
-``` - -``` -
- 34/183 [====>.........................] - ETA: 35:43 - loss: 0.7330 - accuracy: 0.7426 - -
-``` - -``` -
- 35/183 [====>.........................] - ETA: 35:28 - loss: 0.7390 - accuracy: 0.7321 - -
-``` - -``` -
- 36/183 [====>.........................] - ETA: 35:14 - loss: 0.7381 - accuracy: 0.7292 - -
-``` - -``` -
- 37/183 [=====>........................] - ETA: 34:59 - loss: 0.7374 - accuracy: 0.7264 - -
-``` - -``` -
- 38/183 [=====>........................] - ETA: 34:45 - loss: 0.7359 - accuracy: 0.7303 - -
-``` - -``` -
- 39/183 [=====>........................] - ETA: 34:31 - loss: 0.7345 - accuracy: 0.7340 - -
-``` - -``` -
- 40/183 [=====>........................] - ETA: 34:16 - loss: 0.7355 - accuracy: 0.7344 - -
-``` - -``` -
- 41/183 [=====>........................] - ETA: 34:01 - loss: 0.7277 - accuracy: 0.7378 - -
-``` - -``` -
- 42/183 [=====>........................] - ETA: 33:48 - loss: 0.7305 - accuracy: 0.7381 - -
-``` - -``` -
- 43/183 [======>.......................] - ETA: 33:33 - loss: 0.7320 - accuracy: 0.7355 - -
-``` - -``` -
- 44/183 [======>.......................] - ETA: 33:18 - loss: 0.7283 - accuracy: 0.7386 - -
-``` - -``` -
- 45/183 [======>.......................] - ETA: 33:03 - loss: 0.7341 - accuracy: 0.7333 - -
-``` - -``` -
- 46/183 [======>.......................] - ETA: 32:48 - loss: 0.7445 - accuracy: 0.7255 - -
-``` - -``` -
- 47/183 [======>.......................] - ETA: 32:33 - loss: 0.7413 - accuracy: 0.7287 - -
-``` - -``` -
- 48/183 [======>.......................] - ETA: 32:18 - loss: 0.7428 - accuracy: 0.7292 - -
-``` - -``` -
- 49/183 [=======>......................] - ETA: 32:03 - loss: 0.7457 - accuracy: 0.7270 - -
-``` - -``` -
- 50/183 [=======>......................] - ETA: 31:49 - loss: 0.7504 - accuracy: 0.7250 - -
-``` - -``` -
- 51/183 [=======>......................] - ETA: 31:34 - loss: 0.7524 - accuracy: 0.7181 - -
-``` - -``` -
- 52/183 [=======>......................] - ETA: 31:19 - loss: 0.7636 - accuracy: 0.7163 - -
-``` - -``` -
- 53/183 [=======>......................] - ETA: 31:04 - loss: 0.7691 - accuracy: 0.7123 - -
-``` - -``` -
- 54/183 [=======>......................] - ETA: 30:50 - loss: 0.7681 - accuracy: 0.7130 - -
-``` - -``` -
- 55/183 [========>.....................] - ETA: 30:35 - loss: 0.7717 - accuracy: 0.7091 - -
-``` - -``` -
- 56/183 [========>.....................] - ETA: 30:20 - loss: 0.7725 - accuracy: 0.7098 - -
-``` - -``` -
- 57/183 [========>.....................] - ETA: 30:05 - loss: 0.7781 - accuracy: 0.7105 - -
-``` - -``` -
- 58/183 [========>.....................] - ETA: 29:51 - loss: 0.7811 - accuracy: 0.7091 - -
-``` - -``` -
- 59/183 [========>.....................] - ETA: 29:36 - loss: 0.7856 - accuracy: 0.7097 - -
-``` - -``` -
- 60/183 [========>.....................] - ETA: 29:22 - loss: 0.7853 - accuracy: 0.7083 - -
-``` - -``` -
- 61/183 [=========>....................] - ETA: 29:07 - loss: 0.7866 - accuracy: 0.7111 - -
-``` - -``` -
- 62/183 [=========>....................] - ETA: 28:53 - loss: 0.7861 - accuracy: 0.7117 - -
-``` - -``` -
- 63/183 [=========>....................] - ETA: 28:38 - loss: 0.7909 - accuracy: 0.7083 - -
-``` - -``` -
- 64/183 [=========>....................] - ETA: 28:24 - loss: 0.7890 - accuracy: 0.7070 - -
-``` - -``` -
- 65/183 [=========>....................] - ETA: 28:09 - loss: 0.7919 - accuracy: 0.7058 - -
-``` - -``` -
- 66/183 [=========>....................] - ETA: 27:54 - loss: 0.7981 - accuracy: 0.7027 - -
-``` - -``` -
- 67/183 [=========>....................] - ETA: 27:40 - loss: 0.7995 - accuracy: 0.7015 - -
-``` - -``` -
- 68/183 [==========>...................] - ETA: 27:25 - loss: 0.7972 - accuracy: 0.7022 - -
-``` - -``` -
- 69/183 [==========>...................] - ETA: 27:11 - loss: 0.7957 - accuracy: 0.7029 - -
-``` - -``` -
- 70/183 [==========>...................] - ETA: 26:57 - loss: 0.7951 - accuracy: 0.7036 - -
-``` - -``` -
- 71/183 [==========>...................] - ETA: 26:43 - loss: 0.7939 - accuracy: 0.7042 - -
-``` - -``` -
- 72/183 [==========>...................] - ETA: 26:28 - loss: 0.7897 - accuracy: 0.7049 - -
-``` - -``` -
- 73/183 [==========>...................] - ETA: 26:13 - loss: 0.7879 - accuracy: 0.7055 - -
-``` - -``` -
- 74/183 [===========>..................] - ETA: 25:59 - loss: 0.7864 - accuracy: 0.7044 - -
-``` - -``` -
- 75/183 [===========>..................] - ETA: 25:44 - loss: 0.7859 - accuracy: 0.7050 - -
-``` - -``` -
- 76/183 [===========>..................] - ETA: 25:30 - loss: 0.7883 - accuracy: 0.7056 - -
-``` - -``` -
- 77/183 [===========>..................] - ETA: 25:16 - loss: 0.7881 - accuracy: 0.7062 - -
-``` - -``` -
- 78/183 [===========>..................] - ETA: 25:01 - loss: 0.7931 - accuracy: 0.7035 - -
-``` - -``` -
- 79/183 [===========>..................] - ETA: 24:47 - loss: 0.7971 - accuracy: 0.7009 - -
-``` - -``` -
- 80/183 [============>.................] - ETA: 24:32 - loss: 0.7980 - accuracy: 0.7000 - -
-``` - -``` -
- 81/183 [============>.................] - ETA: 24:18 - loss: 0.7948 - accuracy: 0.7022 - -
-``` - -``` -
- 82/183 [============>.................] - ETA: 24:03 - loss: 0.7942 - accuracy: 0.7027 - -
-``` - -``` -
- 83/183 [============>.................] - ETA: 23:49 - loss: 0.7900 - accuracy: 0.7048 - -
-``` - -``` -
- 84/183 [============>.................] - ETA: 23:35 - loss: 0.7926 - accuracy: 0.7024 - -
-``` - -``` -
- 85/183 [============>.................] - ETA: 23:20 - loss: 0.7966 - accuracy: 0.7000 - -
-``` - -``` -
- 86/183 [=============>................] - ETA: 23:06 - loss: 0.7997 - accuracy: 0.6977 - -
-``` - -``` -
- 87/183 [=============>................] - ETA: 22:52 - loss: 0.7973 - accuracy: 0.6997 - -
-``` - -``` -
- 88/183 [=============>................] - ETA: 22:38 - loss: 0.8052 - accuracy: 0.6960 - -
-``` - -``` -
- 89/183 [=============>................] - ETA: 22:23 - loss: 0.8064 - accuracy: 0.6952 - -
-``` - -``` -
- 90/183 [=============>................] - ETA: 22:09 - loss: 0.8023 - accuracy: 0.6972 - -
-``` - -``` -
- 91/183 [=============>................] - ETA: 21:54 - loss: 0.8045 - accuracy: 0.6978 - -
-``` - -``` -
- 92/183 [==============>...............] - ETA: 21:40 - loss: 0.8056 - accuracy: 0.6984 - -
-``` - -``` -
- 93/183 [==============>...............] - ETA: 21:26 - loss: 0.8058 - accuracy: 0.6976 - -
-``` - -``` -
- 94/183 [==============>...............] - ETA: 21:11 - loss: 0.8039 - accuracy: 0.6981 - -
-``` - -``` -
- 95/183 [==============>...............] - ETA: 20:57 - loss: 0.8073 - accuracy: 0.6987 - -
-``` - -``` -
- 96/183 [==============>...............] - ETA: 20:42 - loss: 0.8063 - accuracy: 0.6992 - -
-``` - -``` -
- 97/183 [==============>...............] - ETA: 20:28 - loss: 0.8076 - accuracy: 0.6972 - -
-``` - -``` -
- 98/183 [===============>..............] - ETA: 20:14 - loss: 0.8061 - accuracy: 0.6977 - -
-``` - -``` -
- 99/183 [===============>..............] - ETA: 19:59 - loss: 0.8094 - accuracy: 0.6944 - -
-``` - -``` -
-100/183 [===============>..............] - ETA: 19:45 - loss: 0.8154 - accuracy: 0.6925 - -
-``` - -``` -
-101/183 [===============>..............] - ETA: 19:31 - loss: 0.8130 - accuracy: 0.6943 - -
-``` - -``` -
-102/183 [===============>..............] - ETA: 19:16 - loss: 0.8113 - accuracy: 0.6949 - -
-``` - -``` -
-103/183 [===============>..............] - ETA: 19:02 - loss: 0.8098 - accuracy: 0.6966 - -
-``` - -``` -
-104/183 [================>.............] - ETA: 18:48 - loss: 0.8088 - accuracy: 0.6971 - -
-``` - -``` -
-105/183 [================>.............] - ETA: 18:33 - loss: 0.8074 - accuracy: 0.6976 - -
-``` - -``` -
-106/183 [================>.............] - ETA: 18:19 - loss: 0.8061 - accuracy: 0.6981 - -
-``` - -``` -
-107/183 [================>.............] - ETA: 18:05 - loss: 0.8043 - accuracy: 0.6986 - -
-``` - -``` -
-108/183 [================>.............] - ETA: 17:50 - loss: 0.8021 - accuracy: 0.7002 - -
-``` - -``` -
-109/183 [================>.............] - ETA: 17:36 - loss: 0.8002 - accuracy: 0.7018 - -
-``` - -``` -
-110/183 [=================>............] - ETA: 17:22 - loss: 0.7979 - accuracy: 0.7045 - -
-``` - -``` -
-111/183 [=================>............] - ETA: 17:07 - loss: 0.7951 - accuracy: 0.7050 - -
-``` - -``` -
-112/183 [=================>............] - ETA: 16:53 - loss: 0.7978 - accuracy: 0.7009 - -
-``` - -``` -
-113/183 [=================>............] - ETA: 16:39 - loss: 0.7977 - accuracy: 0.7013 - -
-``` - -``` -
-114/183 [=================>............] - ETA: 16:24 - loss: 0.8027 - accuracy: 0.6974 - -
-``` - -``` -
-115/183 [=================>............] - ETA: 16:10 - loss: 0.7983 - accuracy: 0.7000 - -
-``` - -``` -
-116/183 [==================>...........] - ETA: 15:56 - loss: 0.8009 - accuracy: 0.6983 - -
-``` - -``` -
-117/183 [==================>...........] - ETA: 15:41 - loss: 0.8030 - accuracy: 0.6976 - -
-``` - -``` -
-118/183 [==================>...........] - ETA: 15:27 - loss: 0.8015 - accuracy: 0.6981 - -
-``` - -``` -
-119/183 [==================>...........] - ETA: 15:13 - loss: 0.7986 - accuracy: 0.6996 - -
-``` - -``` -
-120/183 [==================>...........] - ETA: 14:59 - loss: 0.7966 - accuracy: 0.7010 - -
-``` - -``` -
-121/183 [==================>...........] - ETA: 14:44 - loss: 0.7946 - accuracy: 0.7025 - -
-``` - -``` -
-122/183 [===================>..........] - ETA: 14:30 - loss: 0.7923 - accuracy: 0.7049 - -
-``` - -``` -
-123/183 [===================>..........] - ETA: 14:16 - loss: 0.7925 - accuracy: 0.7043 - -
-``` - -``` -
-124/183 [===================>..........] - ETA: 14:01 - loss: 0.7932 - accuracy: 0.7046 - -
-``` - -``` -
-125/183 [===================>..........] - ETA: 13:47 - loss: 0.7914 - accuracy: 0.7070 - -
-``` - -``` -
-126/183 [===================>..........] - ETA: 13:33 - loss: 0.7918 - accuracy: 0.7054 - -
-``` - -``` -
-127/183 [===================>..........] - ETA: 13:19 - loss: 0.7911 - accuracy: 0.7057 - -
-``` - -``` -
-128/183 [===================>..........] - ETA: 13:04 - loss: 0.7901 - accuracy: 0.7061 - -
-``` - -``` -
-129/183 [====================>.........] - ETA: 12:50 - loss: 0.7908 - accuracy: 0.7054 - -
-``` - -``` -
-130/183 [====================>.........] - ETA: 12:36 - loss: 0.7887 - accuracy: 0.7067 - -
-``` - -``` -
-131/183 [====================>.........] - ETA: 12:21 - loss: 0.7877 - accuracy: 0.7080 - -
-``` - -``` -
-132/183 [====================>.........] - ETA: 12:07 - loss: 0.7871 - accuracy: 0.7083 - -
-``` - -``` -
-133/183 [====================>.........] - ETA: 11:53 - loss: 0.7852 - accuracy: 0.7096 - -
-``` - -``` -
-134/183 [====================>.........] - ETA: 11:39 - loss: 0.7828 - accuracy: 0.7118 - -
-``` - -``` -
-135/183 [=====================>........] - ETA: 11:24 - loss: 0.7804 - accuracy: 0.7139 - -
-``` - -``` -
-136/183 [=====================>........] - ETA: 11:10 - loss: 0.7790 - accuracy: 0.7151 - -
-``` - -``` -
-137/183 [=====================>........] - ETA: 10:56 - loss: 0.7804 - accuracy: 0.7144 - -
-``` - -``` -
-138/183 [=====================>........] - ETA: 10:41 - loss: 0.7795 - accuracy: 0.7156 - -
-``` - -``` -
-139/183 [=====================>........] - ETA: 10:27 - loss: 0.7800 - accuracy: 0.7149 - -
-``` - -``` -
-140/183 [=====================>........] - ETA: 10:13 - loss: 0.7802 - accuracy: 0.7143 - -
-``` - -``` -
-141/183 [======================>.......] - ETA: 9:59 - loss: 0.7813 - accuracy: 0.7137 - -
-``` - -``` -
-142/183 [======================>.......] - ETA: 9:44 - loss: 0.7843 - accuracy: 0.7130 - -
-``` - -``` -
-143/183 [======================>.......] - ETA: 9:30 - loss: 0.7841 - accuracy: 0.7133 - -
-``` - -``` -
-144/183 [======================>.......] - ETA: 9:16 - loss: 0.7848 - accuracy: 0.7135 - -
-``` - -``` -
-145/183 [======================>.......] - ETA: 9:01 - loss: 0.7835 - accuracy: 0.7138 - -
-``` - -``` -
-146/183 [======================>.......] - ETA: 8:47 - loss: 0.7817 - accuracy: 0.7149 - -
-``` - -``` -
-147/183 [=======================>......] - ETA: 8:33 - loss: 0.7827 - accuracy: 0.7143 - -
-``` - -``` -
-148/183 [=======================>......] - ETA: 8:19 - loss: 0.7813 - accuracy: 0.7145 - -
-``` - -``` -
-149/183 [=======================>......] - ETA: 8:04 - loss: 0.7820 - accuracy: 0.7148 - -
-``` - -``` -
-150/183 [=======================>......] - ETA: 7:50 - loss: 0.7804 - accuracy: 0.7158 - -
-``` - -``` -
-151/183 [=======================>......] - ETA: 7:36 - loss: 0.7809 - accuracy: 0.7169 - -
-``` - -``` -
-152/183 [=======================>......] - ETA: 7:22 - loss: 0.7802 - accuracy: 0.7171 - -
-``` - -``` -
-153/183 [========================>.....] - ETA: 7:07 - loss: 0.7851 - accuracy: 0.7141 - -
-``` - -``` -
-154/183 [========================>.....] - ETA: 6:53 - loss: 0.7865 - accuracy: 0.7135 - -
-``` - -``` -
-155/183 [========================>.....] - ETA: 6:39 - loss: 0.7845 - accuracy: 0.7145 - -
-``` - -``` -
-156/183 [========================>.....] - ETA: 6:24 - loss: 0.7830 - accuracy: 0.7155 - -
-``` - -``` -
-157/183 [========================>.....] - ETA: 6:10 - loss: 0.7830 - accuracy: 0.7150 - -
-``` - -``` -
-158/183 [========================>.....] - ETA: 5:56 - loss: 0.7843 - accuracy: 0.7152 - -
-``` - -``` -
-159/183 [=========================>....] - ETA: 5:42 - loss: 0.7841 - accuracy: 0.7146 - -
-``` - -``` -
-160/183 [=========================>....] - ETA: 5:27 - loss: 0.7842 - accuracy: 0.7148 - -
-``` - -``` -
-161/183 [=========================>....] - ETA: 5:13 - loss: 0.7826 - accuracy: 0.7151 - -
-``` - -``` -
-162/183 [=========================>....] - ETA: 4:59 - loss: 0.7822 - accuracy: 0.7160 - -
-``` - -``` -
-163/183 [=========================>....] - ETA: 4:45 - loss: 0.7811 - accuracy: 0.7163 - -
-``` - -``` -
-164/183 [=========================>....] - ETA: 4:30 - loss: 0.7808 - accuracy: 0.7157 - -
-``` - -``` -
-165/183 [==========================>...] - ETA: 4:16 - loss: 0.7798 - accuracy: 0.7167 - -
-``` - -``` -
-166/183 [==========================>...] - ETA: 4:02 - loss: 0.7796 - accuracy: 0.7169 - -
-``` - -``` -
-167/183 [==========================>...] - ETA: 3:48 - loss: 0.7798 - accuracy: 0.7171 - -
-``` - -``` -
-168/183 [==========================>...] - ETA: 3:33 - loss: 0.7794 - accuracy: 0.7173 - -
-``` - -``` -
-169/183 [==========================>...] - ETA: 3:19 - loss: 0.7796 - accuracy: 0.7167 - -
-``` - -``` -
-170/183 [==========================>...] - ETA: 3:05 - loss: 0.7789 - accuracy: 0.7162 - -
-``` - -``` -
-171/183 [===========================>..] - ETA: 2:51 - loss: 0.7807 - accuracy: 0.7142 - -
-``` - -``` -
-172/183 [===========================>..] - ETA: 2:36 - loss: 0.7788 - accuracy: 0.7151 - -
-``` - -``` -
-173/183 [===========================>..] - ETA: 2:22 - loss: 0.7807 - accuracy: 0.7139 - -
-``` - -``` -
-174/183 [===========================>..] - ETA: 2:08 - loss: 0.7793 - accuracy: 0.7148 - -
-``` - -``` -
-175/183 [===========================>..] - ETA: 1:54 - loss: 0.7791 - accuracy: 0.7157 - -
-``` - -``` -
-176/183 [===========================>..] - ETA: 1:39 - loss: 0.7799 - accuracy: 0.7138 - -
-``` - -``` -
-177/183 [============================>.] - ETA: 1:25 - loss: 0.7768 - accuracy: 0.7154 - -
-``` - -``` -
-178/183 [============================>.] - ETA: 1:11 - loss: 0.7748 - accuracy: 0.7156 - -
-``` - -``` -
-179/183 [============================>.] - ETA: 57s - loss: 0.7741 - accuracy: 0.7158 - -
-``` - -``` -
-180/183 [============================>.] - ETA: 42s - loss: 0.7740 - accuracy: 0.7153 - -
-``` - -``` -
-181/183 [============================>.] - ETA: 28s - loss: 0.7727 - accuracy: 0.7162 - -
-``` - -``` -
-182/183 [============================>.] - ETA: 14s - loss: 0.7719 - accuracy: 0.7163 - -
-``` - -``` -
-183/183 [==============================] - ETA: 0s - loss: 0.7714 - accuracy: 0.7158 - -
-``` - -``` -
-183/183 [==============================] - 2764s 15s/step - loss: 0.7714 - accuracy: 0.7158 - val_loss: 0.7098 - val_accuracy: 0.7500 - lr: 4.4984e-06 - - --- ## Inference From 1bb935605dff8f86b72b3bceaa675a37450b0490 Mon Sep 17 00:00:00 2001 From: Sachin Prasad Date: Thu, 11 Jan 2024 05:40:39 +0000 Subject: [PATCH 3/3] Keras 3 transfer learning --- ...hoice_task_with_transfer_learning_32_0.png | Bin 27005 -> 27005 bytes ...e_choice_task_with_transfer_learning.ipynb | 14 +- ...iple_choice_task_with_transfer_learning.md | 4301 ++++++++--------- ...iple_choice_task_with_transfer_learning.py | 5 +- 4 files changed, 2015 insertions(+), 2305 deletions(-) diff --git a/examples/nlp/img/multiple_choice_task_with_transfer_learning/multiple_choice_task_with_transfer_learning_32_0.png b/examples/nlp/img/multiple_choice_task_with_transfer_learning/multiple_choice_task_with_transfer_learning_32_0.png index ceb8f833622cc7dc5d6b1ca41c9da8cc8fee27b9..f4623bfb37540e3cac61e24e8fd37824d303b3ec 100644 GIT binary patch delta 43 zcmex+iSh3x#t9yBMmh=^B_##LR{Hw6i6sR&`6W4-NqYH3>G}%4{~g(wCY}iZjd2n& delta 43 zcmex+iSh3x#t9yBhB^uvB_##LR{Hw6i6sR&`6W4-NqYH3>H3$}2-|E-6VC(yh>Q^+ diff --git a/examples/nlp/ipynb/multiple_choice_task_with_transfer_learning.ipynb b/examples/nlp/ipynb/multiple_choice_task_with_transfer_learning.ipynb index ddd96147b6..bd2c851f55 100644 --- a/examples/nlp/ipynb/multiple_choice_task_with_transfer_learning.ipynb +++ b/examples/nlp/ipynb/multiple_choice_task_with_transfer_learning.ipynb @@ -10,7 +10,7 @@ "\n", "**Author:** Md Awsafur Rahman
\n", "**Date created:** 2023/09/14
\n", - "**Last modified:** 2024/01/06
\n", + "**Last modified:** 2024/01/10
\n", "**Description:** Use pre-trained nlp models for multiplechoice task." ] }, @@ -45,17 +45,7 @@ }, "outputs": [], "source": [ - "!pip install -q keras-nlp --upgrade" - ] - }, - { - "cell_type": "code", - "execution_count": 0, - "metadata": { - "colab_type": "code" - }, - "outputs": [], - "source": [ + "\n", "import keras\n", "import keras_nlp\n", "import tensorflow as tf\n", diff --git a/examples/nlp/md/multiple_choice_task_with_transfer_learning.md b/examples/nlp/md/multiple_choice_task_with_transfer_learning.md index a68d80cac5..4c849819e6 100644 --- a/examples/nlp/md/multiple_choice_task_with_transfer_learning.md +++ b/examples/nlp/md/multiple_choice_task_with_transfer_learning.md @@ -2,7 +2,7 @@ **Author:** Md Awsafur Rahman
**Date created:** 2023/09/14
-**Last modified:** 2024/01/06
+**Last modified:** 2024/01/10
**Description:** Use pre-trained nlp models for multiplechoice task. @@ -23,11 +23,7 @@ unlike question answering. We will use SWAG dataset to demonstrate this example. ```python -!pip install -q keras-nlp --upgrade -``` - -```python import keras import keras_nlp import tensorflow as tf @@ -38,12 +34,6 @@ import pandas as pd import matplotlib.pyplot as plt ``` -
-``` -Using TensorFlow backend - -``` -
--- ## Dataset In this example we'll use **SWAG** dataset for multiplechoice task. @@ -56,9 +46,9 @@ In this example we'll use **SWAG** dataset for multiplechoice task.
``` ---2024-01-07 05:21:33-- https://github.com/rowanz/swagaf/archive/refs/heads/master.zip -Resolving github.com (github.com)... 140.82.112.3 -Connecting to github.com (github.com)|140.82.112.3|:443... +--2024-01-11 01:43:38-- https://github.com/rowanz/swagaf/archive/refs/heads/master.zip +Resolving github.com (github.com)... 140.82.112.4 +Connecting to github.com (github.com)|140.82.112.4|:443... connected. @@ -66,9 +56,9 @@ HTTP request sent, awaiting response... 302 Found Location: https://codeload.github.com/rowanz/swagaf/zip/refs/heads/master [following] ---2024-01-07 05:21:33-- https://codeload.github.com/rowanz/swagaf/zip/refs/heads/master -Resolving codeload.github.com (codeload.github.com)... 140.82.112.9 -Connecting to codeload.github.com (codeload.github.com)|140.82.112.9|:443... +--2024-01-11 01:43:38-- https://codeload.github.com/rowanz/swagaf/zip/refs/heads/master +Resolving codeload.github.com (codeload.github.com)... 140.82.113.9 +Connecting to codeload.github.com (codeload.github.com)|140.82.113.9|:443... connected. @@ -84,27 +74,27 @@ Saving to: ‘swag.zip’ swag.zip [<=> ] 0 --.-KB/s -swag.zip [ <=> ] 84.24K 229KB/s +swag.zip [ <=> ] 84.24K 206KB/s -swag.zip [ <=> ] 1.46M 2.44MB/s +swag.zip [ <=> ] 1.49M 2.39MB/s -swag.zip [ <=> ] 2.20M 1.48MB/s +swag.zip [ <=> ] 2.19M 1.32MB/s -swag.zip [ <=> ] 8.59M 3.16MB/s +swag.zip [ <=> ] 8.59M 2.79MB/s -swag.zip [ <=> ] 15.40M 4.96MB/s +swag.zip [ <=> ] 15.41M 4.38MB/s -swag.zip [ <=> ] 17.54M 5.05MB/s -swag.zip [ <=> ] 19.94M 5.71MB/s in 3.5s +swag.zip [ <=> ] 17.54M 4.47MB/s +swag.zip [ <=> ] 19.94M 5.06MB/s in 3.9s
``` -2024-01-07 05:21:37 (5.71 MB/s) - ‘swag.zip’ saved [20905751] +2024-01-11 01:43:42 (5.06 MB/s) - ‘swag.zip’ saved [20905751] ```
@@ -246,37 +236,6 @@ preprocessor = keras_nlp.models.DebertaV3Preprocessor.from_preset( ) ``` -
-``` -Downloading from https://www.kaggle.com/api/v1/models/keras/deberta_v3/keras/deberta_v3_extra_small_en/2/download/tokenizer.json... - -``` -
- - 0%| | 0.00/424 [00:00 -``` -Downloading from https://www.kaggle.com/api/v1/models/keras/deberta_v3/keras/deberta_v3_extra_small_en/2/download/assets/tokenizer/vocabulary.spm... - -``` -
- - 0%| | 0.00/2.35M [00:00 -``` -Downloading from https://www.kaggle.com/api/v1/models/keras/deberta_v3/keras/deberta_v3_extra_small_en/2/download/config.json... - -``` - - - 0%| | 0.00/539 [00:00 -``` -Downloading from https://www.kaggle.com/api/v1/models/keras/deberta_v3/keras/deberta_v3_extra_small_en/2/download/model.weights.h5... - -``` - - - 0%| | 0.00/270M [00:00 -``` -/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/backbone.py:37: UserWarning: `Model.state_updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. - return id(getattr(self, attr)) not in self._functional_layer_ids -/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/backbone.py:37: UserWarning: `layer.updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. - return id(getattr(self, attr)) not in self._functional_layer_ids - -``` - Let's checkout the model summary to have a better insight on the model. @@ -844,112 +604,84 @@ Let's checkout the model summary to have a better insight on the model. model.summary() ``` -
-``` -Model: "model" - -__________________________________________________________________________________________________ - - Layer (type) Output Shape Param # Connected to - -================================================================================================== - - padding_mask (InputLayer) [(None, 4, None)] 0 [] - - - - token_ids (InputLayer) [(None, 4, None)] 0 [] - - - - padding_mask_0 (SelectOpti (None, None) 0 ['padding_mask[0][0]'] - - on) - +
Model: "functional_1"
+
- token_ids_0 (SelectOption) (None, None) 0 ['token_ids[0][0]'] - - padding_mask_1 (SelectOpti (None, None) 0 ['padding_mask[0][0]'] - on) +
┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┓
+┃ Layer (type)        ┃ Output Shape      ┃ Param # ┃ Connected to         ┃
+┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━┩
+│ padding_mask        │ (None, 4, None)   │       0 │ -                    │
+│ (InputLayer)        │                   │         │                      │
+├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
+│ token_ids           │ (None, 4, None)   │       0 │ -                    │
+│ (InputLayer)        │                   │         │                      │
+├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
+│ padding_mask_0      │ (None, None)      │       0 │ padding_mask[0][0]   │
+│ (SelectOption)      │                   │         │                      │
+├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
+│ token_ids_0         │ (None, None)      │       0 │ token_ids[0][0]      │
+│ (SelectOption)      │                   │         │                      │
+├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
+│ padding_mask_1      │ (None, None)      │       0 │ padding_mask[0][0]   │
+│ (SelectOption)      │                   │         │                      │
+├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
+│ token_ids_1         │ (None, None)      │       0 │ token_ids[0][0]      │
+│ (SelectOption)      │                   │         │                      │
+├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
+│ padding_mask_2      │ (None, None)      │       0 │ padding_mask[0][0]   │
+│ (SelectOption)      │                   │         │                      │
+├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
+│ token_ids_2         │ (None, None)      │       0 │ token_ids[0][0]      │
+│ (SelectOption)      │                   │         │                      │
+├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
+│ padding_mask_3      │ (None, None)      │       0 │ padding_mask[0][0]   │
+│ (SelectOption)      │                   │         │                      │
+├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
+│ token_ids_3         │ (None, None)      │       0 │ token_ids[0][0]      │
+│ (SelectOption)      │                   │         │                      │
+├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
+│ deberta_v3_classif… │ (None, 1)         │ 70,830… │ padding_mask_0[0][0… │
+│ (DebertaV3Classifi… │                   │         │ token_ids_0[0][0],   │
+│                     │                   │         │ padding_mask_1[0][0… │
+│                     │                   │         │ token_ids_1[0][0],   │
+│                     │                   │         │ padding_mask_2[0][0… │
+│                     │                   │         │ token_ids_2[0][0],   │
+│                     │                   │         │ padding_mask_3[0][0… │
+│                     │                   │         │ token_ids_3[0][0]    │
+├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
+│ concatenate         │ (None, 4)         │       0 │ deberta_v3_classifi… │
+│ (Concatenate)       │                   │         │ deberta_v3_classifi… │
+│                     │                   │         │ deberta_v3_classifi… │
+│                     │                   │         │ deberta_v3_classifi… │
+├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
+│ softmax (Softmax)   │ (None, 4)         │       0 │ concatenate[0][0]    │
+└─────────────────────┴───────────────────┴─────────┴──────────────────────┘
+
- - token_ids_1 (SelectOption) (None, None) 0 ['token_ids[0][0]'] - - padding_mask_2 (SelectOpti (None, None) 0 ['padding_mask[0][0]'] +
 Total params: 70,830,337 (270.20 MB)
+
- on) - - token_ids_2 (SelectOption) (None, None) 0 ['token_ids[0][0]'] - +
 Trainable params: 70,830,337 (270.20 MB)
+
- padding_mask_3 (SelectOpti (None, None) 0 ['padding_mask[0][0]'] - on) - - token_ids_3 (SelectOption) (None, None) 0 ['token_ids[0][0]'] +
 Non-trainable params: 0 (0.00 B)
+
- - deberta_v3_classifier (Deb (None, 1) 7083033 ['padding_mask_0[0][0]', - ertaV3Classifier) 7 'token_ids_0[0][0]', - - 'padding_mask_1[0][0]', - - 'token_ids_1[0][0]', - - 'padding_mask_2[0][0]', - - 'token_ids_2[0][0]', - - 'padding_mask_3[0][0]', - - 'token_ids_3[0][0]'] - - - - concatenate (Concatenate) (None, 4) 0 ['deberta_v3_classifier[0][0]' - - , 'deberta_v3_classifier[1][0] - - ', - - 'deberta_v3_classifier[2][0]' - - , 'deberta_v3_classifier[3][0] - - '] - - - - softmax (Softmax) (None, 4) 0 ['concatenate[0][0]'] - - - -================================================================================================== - -Total params: 70830337 (270.20 MB) - -Trainable params: 70830337 (270.20 MB) - -Non-trainable params: 0 (0.00 Byte) - -__________________________________________________________________________________________________ - -``` -
Finally, let's check the model structure visually if everything is in place. @@ -961,7 +693,7 @@ keras.utils.plot_model(model, show_shapes=True) -![png](/img/examples/nlp/multiple_choice_task_with_transfer_learning/multiple_choice_task_with_transfer_learning_43_0.png) +![png](/img/examples/nlp/multiple_choice_task_with_transfer_learning/multiple_choice_task_with_transfer_learning_42_0.png) @@ -987,1302 +719,1293 @@ history = model.fit( Epoch 1/5 WARNING: All log messages before absl::InitializeLog() is called are written to STDERR -I0000 00:00:1704605251.846942 12962 device_compiler.h:186] Compiled cluster using XLA! This line is logged at most once for the lifetime of the process. +I0000 00:00:1704937783.212808 6043 device_compiler.h:186] Compiled cluster using XLA! This line is logged at most once for the lifetime of the process. ``` - 1/183 [..............................] - ETA: 16:51:51 - loss: 1.3865 - accuracy: 0.3750 + 1/183 ━━━━━━━━━━━━━━━━━━━━ 18:42:09 370s/step - accuracy: 0.5000 - loss: 1.3671
``` - + ```
- 2/183 [..............................] - ETA: 44:52 - loss: 1.3652 - accuracy: 0.3750 + 2/183 ━━━━━━━━━━━━━━━━━━━━ 46:46 16s/step - accuracy: 0.4688 - loss: 1.3707
``` - + ```
- 3/183 [..............................] - ETA: 44:29 - loss: 1.3851 - accuracy: 0.2500 + 3/183 ━━━━━━━━━━━━━━━━━━━━ 44:54 15s/step - accuracy: 0.4236 - loss: 1.3734
``` - + ```
- 4/183 [..............................] - ETA: 44:12 - loss: 1.3875 - accuracy: 0.2188 + 4/183 ━━━━━━━━━━━━━━━━━━━━ 43:36 15s/step - accuracy: 0.3958 - loss: 1.3745
``` - + ```
- 5/183 [..............................] - ETA: 43:54 - loss: 1.3896 - accuracy: 0.2000 + 5/183 ━━━━━━━━━━━━━━━━━━━━ 42:47 14s/step - accuracy: 0.3967 - loss: 1.3732
``` - + ```
- 6/183 [..............................] - ETA: 43:41 - loss: 1.3942 - accuracy: 0.1875 + 6/183 ━━━━━━━━━━━━━━━━━━━━ 42:16 14s/step - accuracy: 0.3861 - loss: 1.3736
``` - + ```
- 7/183 [>.............................] - ETA: 43:25 - loss: 1.3928 - accuracy: 0.2143 + 7/183 ━━━━━━━━━━━━━━━━━━━━ 41:50 14s/step - accuracy: 0.3794 - loss: 1.3736
``` - + ```
- 8/183 [>.............................] - ETA: 43:22 - loss: 1.3933 - accuracy: 0.2031 + 8/183 ━━━━━━━━━━━━━━━━━━━━ 41:26 14s/step - accuracy: 0.3711 - loss: 1.3739
``` - + ```
- 9/183 [>.............................] - ETA: 42:54 - loss: 1.3934 - accuracy: 0.2083 + 9/183 ━━━━━━━━━━━━━━━━━━━━ 41:05 14s/step - accuracy: 0.3622 - loss: 1.3743
``` - + ```
- 10/183 [>.............................] - ETA: 42:27 - loss: 1.3901 - accuracy: 0.2375 + 10/183 ━━━━━━━━━━━━━━━━━━━━ 40:46 14s/step - accuracy: 0.3560 - loss: 1.3746
``` - + ```
- 11/183 [>.............................] - ETA: 42:04 - loss: 1.3898 - accuracy: 0.2500 + 11/183 ━━━━━━━━━━━━━━━━━━━━ 40:29 14s/step - accuracy: 0.3505 - loss: 1.3749
``` - + ```
- 12/183 [>.............................] - ETA: 41:42 - loss: 1.3903 - accuracy: 0.2396 + 12/183 ━━━━━━━━━━━━━━━━━━━━ 40:11 14s/step - accuracy: 0.3473 - loss: 1.3750
``` - + ```
- 13/183 [=>............................] - ETA: 41:21 - loss: 1.3900 - accuracy: 0.2500 + 13/183 ━━━━━━━━━━━━━━━━━━━━ 39:53 14s/step - accuracy: 0.3450 - loss: 1.3752
``` - + ```
- 14/183 [=>............................] - ETA: 41:02 - loss: 1.3908 - accuracy: 0.2321 + 14/183 ━━━━━━━━━━━━━━━━━━━━ 39:38 14s/step - accuracy: 0.3414 - loss: 1.3754
``` - + ```
- 15/183 [=>............................] - ETA: 40:45 - loss: 1.3919 - accuracy: 0.2167 + 15/183 ━━━━━━━━━━━━━━━━━━━━ 39:23 14s/step - accuracy: 0.3387 - loss: 1.3758
``` - + ```
- 16/183 [=>............................] - ETA: 40:26 - loss: 1.3927 - accuracy: 0.2109 + 16/183 ━━━━━━━━━━━━━━━━━━━━ 39:09 14s/step - accuracy: 0.3370 - loss: 1.3761
``` - + ```
- 17/183 [=>............................] - ETA: 40:08 - loss: 1.3935 - accuracy: 0.2132 + 17/183 ━━━━━━━━━━━━━━━━━━━━ 38:55 14s/step - accuracy: 0.3354 - loss: 1.3764
``` - + ```
- 18/183 [=>............................] - ETA: 39:51 - loss: 1.3920 - accuracy: 0.2153 + 18/183 ━━━━━━━━━━━━━━━━━━━━ 38:39 14s/step - accuracy: 0.3333 - loss: 1.3767
``` - + ```
- 19/183 [==>...........................] - ETA: 39:34 - loss: 1.3905 - accuracy: 0.2171 + 19/183 ━━━━━━━━━━━━━━━━━━━━ 38:25 14s/step - accuracy: 0.3310 - loss: 1.3771
``` - + ```
- 20/183 [==>...........................] - ETA: 39:16 - loss: 1.3900 - accuracy: 0.2188 + 20/183 ━━━━━━━━━━━━━━━━━━━━ 38:11 14s/step - accuracy: 0.3295 - loss: 1.3774
``` - + ```
- 21/183 [==>...........................] - ETA: 39:01 - loss: 1.3908 - accuracy: 0.2202 + 21/183 ━━━━━━━━━━━━━━━━━━━━ 37:56 14s/step - accuracy: 0.3280 - loss: 1.3777
``` - + ```
- 22/183 [==>...........................] - ETA: 38:44 - loss: 1.3915 - accuracy: 0.2159 + 22/183 ━━━━━━━━━━━━━━━━━━━━ 37:44 14s/step - accuracy: 0.3267 - loss: 1.3780
``` - + ```
- 23/183 [==>...........................] - ETA: 38:28 - loss: 1.3892 - accuracy: 0.2391 + 23/183 ━━━━━━━━━━━━━━━━━━━━ 37:31 14s/step - accuracy: 0.3253 - loss: 1.3783
``` - + ```
- 24/183 [==>...........................] - ETA: 38:12 - loss: 1.3891 - accuracy: 0.2396 + 24/183 ━━━━━━━━━━━━━━━━━━━━ 37:17 14s/step - accuracy: 0.3243 - loss: 1.3784
``` - + ```
- 25/183 [===>..........................] - ETA: 37:56 - loss: 1.3893 - accuracy: 0.2350 + 25/183 ━━━━━━━━━━━━━━━━━━━━ 37:03 14s/step - accuracy: 0.3235 - loss: 1.3786
``` - + ```
- 26/183 [===>..........................] - ETA: 37:40 - loss: 1.3893 - accuracy: 0.2404 + 26/183 ━━━━━━━━━━━━━━━━━━━━ 36:50 14s/step - accuracy: 0.3228 - loss: 1.3788
``` - + ```
- 27/183 [===>..........................] - ETA: 37:25 - loss: 1.3886 - accuracy: 0.2454 + 27/183 ━━━━━━━━━━━━━━━━━━━━ 36:37 14s/step - accuracy: 0.3219 - loss: 1.3790
``` - + ```
- 28/183 [===>..........................] - ETA: 37:09 - loss: 1.3880 - accuracy: 0.2455 + 28/183 ━━━━━━━━━━━━━━━━━━━━ 36:23 14s/step - accuracy: 0.3211 - loss: 1.3791
``` - + ```
- 29/183 [===>..........................] - ETA: 36:55 - loss: 1.3874 - accuracy: 0.2457 + 29/183 ━━━━━━━━━━━━━━━━━━━━ 36:09 14s/step - accuracy: 0.3203 - loss: 1.3793
``` - + ```
- 30/183 [===>..........................] - ETA: 36:39 - loss: 1.3877 - accuracy: 0.2458 + 30/183 ━━━━━━━━━━━━━━━━━━━━ 35:54 14s/step - accuracy: 0.3196 - loss: 1.3794
``` - + ```
- 31/183 [====>.........................] - ETA: 36:23 - loss: 1.3870 - accuracy: 0.2540 + 31/183 ━━━━━━━━━━━━━━━━━━━━ 35:40 14s/step - accuracy: 0.3191 - loss: 1.3795
``` - + ```
- 32/183 [====>.........................] - ETA: 36:08 - loss: 1.3870 - accuracy: 0.2578 + 32/183 ━━━━━━━━━━━━━━━━━━━━ 35:27 14s/step - accuracy: 0.3185 - loss: 1.3796
``` - + ```
- 33/183 [====>.........................] - ETA: 35:53 - loss: 1.3870 - accuracy: 0.2538 + 33/183 ━━━━━━━━━━━━━━━━━━━━ 35:13 14s/step - accuracy: 0.3182 - loss: 1.3797
``` - + ```
- 34/183 [====>.........................] - ETA: 35:38 - loss: 1.3882 - accuracy: 0.2500 + 34/183 ━━━━━━━━━━━━━━━━━━━━ 34:58 14s/step - accuracy: 0.3180 - loss: 1.3797
``` - + ```
- 35/183 [====>.........................] - ETA: 35:23 - loss: 1.3876 - accuracy: 0.2536 + 35/183 ━━━━━━━━━━━━━━━━━━━━ 34:44 14s/step - accuracy: 0.3177 - loss: 1.3798
``` - + ```
- 36/183 [====>.........................] - ETA: 35:07 - loss: 1.3878 - accuracy: 0.2500 + 36/183 ━━━━━━━━━━━━━━━━━━━━ 34:30 14s/step - accuracy: 0.3171 - loss: 1.3799
``` - + ```
- 37/183 [=====>........................] - ETA: 34:53 - loss: 1.3871 - accuracy: 0.2568 + 37/183 ━━━━━━━━━━━━━━━━━━━━ 34:16 14s/step - accuracy: 0.3165 - loss: 1.3800
``` - + ```
- 38/183 [=====>........................] - ETA: 34:38 - loss: 1.3875 - accuracy: 0.2566 + 38/183 ━━━━━━━━━━━━━━━━━━━━ 34:02 14s/step - accuracy: 0.3159 - loss: 1.3801
``` - + ```
- 39/183 [=====>........................] - ETA: 34:22 - loss: 1.3875 - accuracy: 0.2564 + 39/183 ━━━━━━━━━━━━━━━━━━━━ 33:48 14s/step - accuracy: 0.3153 - loss: 1.3802
``` - + ```
- 40/183 [=====>........................] - ETA: 34:07 - loss: 1.3875 - accuracy: 0.2531 + 40/183 ━━━━━━━━━━━━━━━━━━━━ 33:33 14s/step - accuracy: 0.3147 - loss: 1.3803
``` - + ```
- 41/183 [=====>........................] - ETA: 33:52 - loss: 1.3874 - accuracy: 0.2530 + 41/183 ━━━━━━━━━━━━━━━━━━━━ 33:19 14s/step - accuracy: 0.3140 - loss: 1.3804
``` - + ```
- 42/183 [=====>........................] - ETA: 33:38 - loss: 1.3886 - accuracy: 0.2500 + 42/183 ━━━━━━━━━━━━━━━━━━━━ 33:05 14s/step - accuracy: 0.3132 - loss: 1.3805
``` - + ```
- 43/183 [======>.......................] - ETA: 33:23 - loss: 1.3876 - accuracy: 0.2529 + 43/183 ━━━━━━━━━━━━━━━━━━━━ 32:50 14s/step - accuracy: 0.3125 - loss: 1.3806
``` - + ```
- 44/183 [======>.......................] - ETA: 33:08 - loss: 1.3876 - accuracy: 0.2557 + 44/183 ━━━━━━━━━━━━━━━━━━━━ 32:35 14s/step - accuracy: 0.3117 - loss: 1.3807
``` - + ```
- 45/183 [======>.......................] - ETA: 32:54 - loss: 1.3875 - accuracy: 0.2583 + 45/183 ━━━━━━━━━━━━━━━━━━━━ 32:20 14s/step - accuracy: 0.3110 - loss: 1.3807
``` - + ```
- 46/183 [======>.......................] - ETA: 32:39 - loss: 1.3875 - accuracy: 0.2582 + 46/183 ━━━━━━━━━━━━━━━━━━━━ 32:05 14s/step - accuracy: 0.3102 - loss: 1.3808
``` - + ```
- 47/183 [======>.......................] - ETA: 32:24 - loss: 1.3873 - accuracy: 0.2553 + 47/183 ━━━━━━━━━━━━━━━━━━━━ 31:51 14s/step - accuracy: 0.3095 - loss: 1.3809
``` - + ```
- 48/183 [======>.......................] - ETA: 32:09 - loss: 1.3866 - accuracy: 0.2604 + 48/183 ━━━━━━━━━━━━━━━━━━━━ 31:37 14s/step - accuracy: 0.3087 - loss: 1.3809
``` - + ```
- 49/183 [=======>......................] - ETA: 31:54 - loss: 1.3870 - accuracy: 0.2602 + 49/183 ━━━━━━━━━━━━━━━━━━━━ 31:23 14s/step - accuracy: 0.3079 - loss: 1.3810
``` - + ```
- 50/183 [=======>......................] - ETA: 31:40 - loss: 1.3869 - accuracy: 0.2600 + 50/183 ━━━━━━━━━━━━━━━━━━━━ 31:08 14s/step - accuracy: 0.3071 - loss: 1.3811
``` - + ```
- 51/183 [=======>......................] - ETA: 31:25 - loss: 1.3862 - accuracy: 0.2647 + 51/183 ━━━━━━━━━━━━━━━━━━━━ 30:53 14s/step - accuracy: 0.3065 - loss: 1.3811
``` - + ```
- 52/183 [=======>......................] - ETA: 31:10 - loss: 1.3865 - accuracy: 0.2596 + 52/183 ━━━━━━━━━━━━━━━━━━━━ 30:38 14s/step - accuracy: 0.3058 - loss: 1.3812
``` - + ```
- 53/183 [=======>......................] - ETA: 30:56 - loss: 1.3869 - accuracy: 0.2571 + 53/183 ━━━━━━━━━━━━━━━━━━━━ 30:24 14s/step - accuracy: 0.3052 - loss: 1.3812
``` - + ```
- 54/183 [=======>......................] - ETA: 30:41 - loss: 1.3869 - accuracy: 0.2546 + 54/183 ━━━━━━━━━━━━━━━━━━━━ 30:09 14s/step - accuracy: 0.3045 - loss: 1.3813
``` - + ```
- 55/183 [========>.....................] - ETA: 30:27 - loss: 1.3866 - accuracy: 0.2591 + 55/183 ━━━━━━━━━━━━━━━━━━━━ 29:55 14s/step - accuracy: 0.3039 - loss: 1.3813
``` - + ```
- 56/183 [========>.....................] - ETA: 30:12 - loss: 1.3869 - accuracy: 0.2589 + 56/183 ━━━━━━━━━━━━━━━━━━━━ 29:40 14s/step - accuracy: 0.3033 - loss: 1.3814
``` - + ```
- 57/183 [========>.....................] - ETA: 29:58 - loss: 1.3861 - accuracy: 0.2632 + 57/183 ━━━━━━━━━━━━━━━━━━━━ 29:26 14s/step - accuracy: 0.3026 - loss: 1.3814
``` - + ```
- 58/183 [========>.....................] - ETA: 29:43 - loss: 1.3857 - accuracy: 0.2651 + 58/183 ━━━━━━━━━━━━━━━━━━━━ 29:12 14s/step - accuracy: 0.3019 - loss: 1.3815
``` - + ```
- 59/183 [========>.....................] - ETA: 29:29 - loss: 1.3854 - accuracy: 0.2669 + 59/183 ━━━━━━━━━━━━━━━━━━━━ 28:58 14s/step - accuracy: 0.3014 - loss: 1.3815
``` - + ```
- 60/183 [========>.....................] - ETA: 29:14 - loss: 1.3854 - accuracy: 0.2688 + 60/183 ━━━━━━━━━━━━━━━━━━━━ 28:44 14s/step - accuracy: 0.3008 - loss: 1.3816
``` - + ```
- 61/183 [=========>....................] - ETA: 29:00 - loss: 1.3852 - accuracy: 0.2705 + 61/183 ━━━━━━━━━━━━━━━━━━━━ 28:30 14s/step - accuracy: 0.3002 - loss: 1.3816
``` - + ```
- 62/183 [=========>....................] - ETA: 28:45 - loss: 1.3851 - accuracy: 0.2702 + 62/183 ━━━━━━━━━━━━━━━━━━━━ 28:16 14s/step - accuracy: 0.2997 - loss: 1.3817
``` - + ```
- 63/183 [=========>....................] - ETA: 28:31 - loss: 1.3855 - accuracy: 0.2679 + 63/183 ━━━━━━━━━━━━━━━━━━━━ 28:02 14s/step - accuracy: 0.2992 - loss: 1.3817
``` - + ```
- 64/183 [=========>....................] - ETA: 28:17 - loss: 1.3857 - accuracy: 0.2656 + 64/183 ━━━━━━━━━━━━━━━━━━━━ 27:47 14s/step - accuracy: 0.2987 - loss: 1.3817
``` - + ```
- 65/183 [=========>....................] - ETA: 28:02 - loss: 1.3867 - accuracy: 0.2615 + 65/183 ━━━━━━━━━━━━━━━━━━━━ 27:33 14s/step - accuracy: 0.2982 - loss: 1.3818
``` - + ```
- 66/183 [=========>....................] - ETA: 27:48 - loss: 1.3868 - accuracy: 0.2614 + 66/183 ━━━━━━━━━━━━━━━━━━━━ 27:19 14s/step - accuracy: 0.2977 - loss: 1.3818
``` - + ```
- 67/183 [=========>....................] - ETA: 27:34 - loss: 1.3868 - accuracy: 0.2631 + 67/183 ━━━━━━━━━━━━━━━━━━━━ 27:05 14s/step - accuracy: 0.2973 - loss: 1.3818
``` - + ```
- 68/183 [==========>...................] - ETA: 27:19 - loss: 1.3864 - accuracy: 0.2610 + 68/183 ━━━━━━━━━━━━━━━━━━━━ 26:50 14s/step - accuracy: 0.2968 - loss: 1.3818
``` - + ```
- 69/183 [==========>...................] - ETA: 27:05 - loss: 1.3864 - accuracy: 0.2591 + 69/183 ━━━━━━━━━━━━━━━━━━━━ 26:36 14s/step - accuracy: 0.2964 - loss: 1.3819
``` - + ```
- 70/183 [==========>...................] - ETA: 26:51 - loss: 1.3860 - accuracy: 0.2607 + 70/183 ━━━━━━━━━━━━━━━━━━━━ 26:22 14s/step - accuracy: 0.2961 - loss: 1.3819
``` - + ```
- 71/183 [==========>...................] - ETA: 26:36 - loss: 1.3866 - accuracy: 0.2570 + 71/183 ━━━━━━━━━━━━━━━━━━━━ 26:07 14s/step - accuracy: 0.2957 - loss: 1.3819
``` - + ```
- 72/183 [==========>...................] - ETA: 26:22 - loss: 1.3858 - accuracy: 0.2622 + 72/183 ━━━━━━━━━━━━━━━━━━━━ 25:53 14s/step - accuracy: 0.2953 - loss: 1.3819
``` - + ```
- 73/183 [==========>...................] - ETA: 26:07 - loss: 1.3854 - accuracy: 0.2637 + 73/183 ━━━━━━━━━━━━━━━━━━━━ 25:39 14s/step - accuracy: 0.2949 - loss: 1.3819
``` - + ```
- 74/183 [===========>..................] - ETA: 25:53 - loss: 1.3858 - accuracy: 0.2601 + 74/183 ━━━━━━━━━━━━━━━━━━━━ 25:25 14s/step - accuracy: 0.2946 - loss: 1.3819
``` - + ```
- 75/183 [===========>..................] - ETA: 25:39 - loss: 1.3859 - accuracy: 0.2583 + 75/183 ━━━━━━━━━━━━━━━━━━━━ 25:10 14s/step - accuracy: 0.2944 - loss: 1.3820
``` - + ```
- 76/183 [===========>..................] - ETA: 25:24 - loss: 1.3859 - accuracy: 0.2599 + 76/183 ━━━━━━━━━━━━━━━━━━━━ 24:56 14s/step - accuracy: 0.2940 - loss: 1.3820
``` - + ```
- 77/183 [===========>..................] - ETA: 25:10 - loss: 1.3860 - accuracy: 0.2597 + 77/183 ━━━━━━━━━━━━━━━━━━━━ 24:42 14s/step - accuracy: 0.2937 - loss: 1.3820
``` - + ```
- 78/183 [===========>..................] - ETA: 24:55 - loss: 1.3862 - accuracy: 0.2580 + 78/183 ━━━━━━━━━━━━━━━━━━━━ 24:28 14s/step - accuracy: 0.2934 - loss: 1.3820
``` - + ```
- 79/183 [===========>..................] - ETA: 24:41 - loss: 1.3855 - accuracy: 0.2611 + 79/183 ━━━━━━━━━━━━━━━━━━━━ 24:14 14s/step - accuracy: 0.2931 - loss: 1.3820
``` - + ```
- 80/183 [============>.................] - ETA: 24:27 - loss: 1.3857 - accuracy: 0.2625 + 80/183 ━━━━━━━━━━━━━━━━━━━━ 23:59 14s/step - accuracy: 0.2928 - loss: 1.3820
``` - + ```
- 81/183 [============>.................] - ETA: 24:12 - loss: 1.3853 - accuracy: 0.2639 + 81/183 ━━━━━━━━━━━━━━━━━━━━ 23:45 14s/step - accuracy: 0.2925 - loss: 1.3820
``` - + ```
- 82/183 [============>.................] - ETA: 23:58 - loss: 1.3854 - accuracy: 0.2622 + 82/183 ━━━━━━━━━━━━━━━━━━━━ 23:33 14s/step - accuracy: 0.2922 - loss: 1.3820
``` - + ```
- 83/183 [============>.................] - ETA: 23:43 - loss: 1.3854 - accuracy: 0.2636 + 83/183 ━━━━━━━━━━━━━━━━━━━━ 23:19 14s/step - accuracy: 0.2919 - loss: 1.3820
``` - + ```
- 84/183 [============>.................] - ETA: 23:29 - loss: 1.3857 - accuracy: 0.2634 + 84/183 ━━━━━━━━━━━━━━━━━━━━ 23:05 14s/step - accuracy: 0.2917 - loss: 1.3820
``` - + ```
- 85/183 [============>.................] - ETA: 23:15 - loss: 1.3853 - accuracy: 0.2647 + 85/183 ━━━━━━━━━━━━━━━━━━━━ 22:52 14s/step - accuracy: 0.2914 - loss: 1.3820
``` - + ```
- 86/183 [=============>................] - ETA: 23:00 - loss: 1.3852 - accuracy: 0.2689 + 86/183 ━━━━━━━━━━━━━━━━━━━━ 22:38 14s/step - accuracy: 0.2912 - loss: 1.3820
``` - + ```
- 87/183 [=============>................] - ETA: 22:46 - loss: 1.3852 - accuracy: 0.2687 + 87/183 ━━━━━━━━━━━━━━━━━━━━ 22:24 14s/step - accuracy: 0.2909 - loss: 1.3820
``` - + ```
- 88/183 [=============>................] - ETA: 22:32 - loss: 1.3852 - accuracy: 0.2685 + 88/183 ━━━━━━━━━━━━━━━━━━━━ 22:11 14s/step - accuracy: 0.2906 - loss: 1.3820
``` - + ```
- 89/183 [=============>................] - ETA: 22:17 - loss: 1.3852 - accuracy: 0.2711 + 89/183 ━━━━━━━━━━━━━━━━━━━━ 21:57 14s/step - accuracy: 0.2904 - loss: 1.3820
``` - + ```
- 90/183 [=============>................] - ETA: 22:03 - loss: 1.3852 - accuracy: 0.2694 + 90/183 ━━━━━━━━━━━━━━━━━━━━ 21:43 14s/step - accuracy: 0.2901 - loss: 1.3820
``` - + ```
- 91/183 [=============>................] - ETA: 21:49 - loss: 1.3851 - accuracy: 0.2720 + 91/183 ━━━━━━━━━━━━━━━━━━━━ 21:29 14s/step - accuracy: 0.2898 - loss: 1.3820
``` - + ```
- 92/183 [==============>...............] - ETA: 21:35 - loss: 1.3851 - accuracy: 0.2717 + 92/183 ━━━━━━━━━━━━━━━━━━━━ 21:14 14s/step - accuracy: 0.2896 - loss: 1.3820
``` - + ```
- 93/183 [==============>...............] - ETA: 21:20 - loss: 1.3853 - accuracy: 0.2702 + 93/183 ━━━━━━━━━━━━━━━━━━━━ 21:01 14s/step - accuracy: 0.2894 - loss: 1.3820
``` - + ```
- 94/183 [==============>...............] - ETA: 21:06 - loss: 1.3856 - accuracy: 0.2699 + 94/183 ━━━━━━━━━━━━━━━━━━━━ 20:46 14s/step - accuracy: 0.2892 - loss: 1.3820
``` - + ```
- 95/183 [==============>...............] - ETA: 20:52 - loss: 1.3855 - accuracy: 0.2711 + 95/183 ━━━━━━━━━━━━━━━━━━━━ 20:32 14s/step - accuracy: 0.2890 - loss: 1.3820
``` - + ```
- 96/183 [==============>...............] - ETA: 20:37 - loss: 1.3856 - accuracy: 0.2695 + 96/183 ━━━━━━━━━━━━━━━━━━━━ 20:19 14s/step - accuracy: 0.2888 - loss: 1.3820
``` - + ```
- 97/183 [==============>...............] - ETA: 20:23 - loss: 1.3855 - accuracy: 0.2706 + 97/183 ━━━━━━━━━━━━━━━━━━━━ 20:05 14s/step - accuracy: 0.2886 - loss: 1.3820
``` - + ```
- 98/183 [===============>..............] - ETA: 20:09 - loss: 1.3852 - accuracy: 0.2730 + 98/183 ━━━━━━━━━━━━━━━━━━━━ 19:51 14s/step - accuracy: 0.2885 - loss: 1.3820
``` - + ```
- 99/183 [===============>..............] - ETA: 19:54 - loss: 1.3853 - accuracy: 0.2715 + 99/183 ━━━━━━━━━━━━━━━━━━━━ 19:37 14s/step - accuracy: 0.2883 - loss: 1.3820
``` - + ```
-100/183 [===============>..............] - ETA: 19:40 - loss: 1.3854 - accuracy: 0.2713 + 100/183 ━━━━━━━━━━━━━━━━━━━━ 19:23 14s/step - accuracy: 0.2881 - loss: 1.3820
``` - + ```
-101/183 [===============>..............] - ETA: 19:26 - loss: 1.3856 - accuracy: 0.2698 + 101/183 ━━━━━━━━━━━━━━━━━━━━ 19:09 14s/step - accuracy: 0.2880 - loss: 1.3820
``` - + ```
-102/183 [===============>..............] - ETA: 19:12 - loss: 1.3856 - accuracy: 0.2684 + 102/183 ━━━━━━━━━━━━━━━━━━━━ 18:55 14s/step - accuracy: 0.2879 - loss: 1.3820
``` - + ```
-103/183 [===============>..............] - ETA: 18:57 - loss: 1.3854 - accuracy: 0.2694 + 103/183 ━━━━━━━━━━━━━━━━━━━━ 18:41 14s/step - accuracy: 0.2877 - loss: 1.3820
``` - + ```
-104/183 [================>.............] - ETA: 18:43 - loss: 1.3852 - accuracy: 0.2716 + 104/183 ━━━━━━━━━━━━━━━━━━━━ 18:27 14s/step - accuracy: 0.2876 - loss: 1.3820
``` - + ```
-105/183 [================>.............] - ETA: 18:29 - loss: 1.3854 - accuracy: 0.2714 + 105/183 ━━━━━━━━━━━━━━━━━━━━ 18:13 14s/step - accuracy: 0.2875 - loss: 1.3819
``` - + ```
-106/183 [================>.............] - ETA: 18:15 - loss: 1.3851 - accuracy: 0.2748 + 106/183 ━━━━━━━━━━━━━━━━━━━━ 17:59 14s/step - accuracy: 0.2875 - loss: 1.3819
``` - + ```
-107/183 [================>.............] - ETA: 18:00 - loss: 1.3852 - accuracy: 0.2745 + 107/183 ━━━━━━━━━━━━━━━━━━━━ 17:45 14s/step - accuracy: 0.2874 - loss: 1.3819
``` - + ```
-108/183 [================>.............] - ETA: 17:46 - loss: 1.3853 - accuracy: 0.2720 + 108/183 ━━━━━━━━━━━━━━━━━━━━ 17:31 14s/step - accuracy: 0.2873 - loss: 1.3819
``` - + ```
-109/183 [================>.............] - ETA: 17:32 - loss: 1.3854 - accuracy: 0.2718 + 109/183 ━━━━━━━━━━━━━━━━━━━━ 17:17 14s/step - accuracy: 0.2872 - loss: 1.3819
``` - + ```
-110/183 [=================>............] - ETA: 17:18 - loss: 1.3855 - accuracy: 0.2716 + 110/183 ━━━━━━━━━━━━━━━━━━━━ 17:03 14s/step - accuracy: 0.2871 - loss: 1.3819
``` - + ```
-111/183 [=================>............] - ETA: 17:03 - loss: 1.3856 - accuracy: 0.2703 + 111/183 ━━━━━━━━━━━━━━━━━━━━ 16:49 14s/step - accuracy: 0.2871 - loss: 1.3819
``` - + ```
-112/183 [=================>............] - ETA: 16:49 - loss: 1.3859 - accuracy: 0.2701 + 112/183 ━━━━━━━━━━━━━━━━━━━━ 16:35 14s/step - accuracy: 0.2870 - loss: 1.3818
``` - + ```
-113/183 [=================>............] - ETA: 16:35 - loss: 1.3859 - accuracy: 0.2699 + 113/183 ━━━━━━━━━━━━━━━━━━━━ 16:21 14s/step - accuracy: 0.2869 - loss: 1.3818
``` - + ```
-114/183 [=================>............] - ETA: 16:21 - loss: 1.3859 - accuracy: 0.2697 + 114/183 ━━━━━━━━━━━━━━━━━━━━ 16:07 14s/step - accuracy: 0.2869 - loss: 1.3818
``` - + ```
-115/183 [=================>............] - ETA: 16:06 - loss: 1.3862 - accuracy: 0.2707 + 115/183 ━━━━━━━━━━━━━━━━━━━━ 15:53 14s/step - accuracy: 0.2868 - loss: 1.3818
``` - + ```
-116/183 [==================>...........] - ETA: 15:52 - loss: 1.3858 - accuracy: 0.2737 + 116/183 ━━━━━━━━━━━━━━━━━━━━ 15:39 14s/step - accuracy: 0.2867 - loss: 1.3818
``` - + ```
-117/183 [==================>...........] - ETA: 15:38 - loss: 1.3857 - accuracy: 0.2746 + 117/183 ━━━━━━━━━━━━━━━━━━━━ 15:25 14s/step - accuracy: 0.2867 - loss: 1.3818
``` - + ```
-118/183 [==================>...........] - ETA: 15:24 - loss: 1.3856 - accuracy: 0.2744 + 118/183 ━━━━━━━━━━━━━━━━━━━━ 15:11 14s/step - accuracy: 0.2866 - loss: 1.3818
``` - + ```
-119/183 [==================>...........] - ETA: 15:09 - loss: 1.3858 - accuracy: 0.2731 + 119/183 ━━━━━━━━━━━━━━━━━━━━ 14:57 14s/step - accuracy: 0.2865 - loss: 1.3818
``` - + ```
-120/183 [==================>...........] - ETA: 14:55 - loss: 1.3861 - accuracy: 0.2719 + 120/183 ━━━━━━━━━━━━━━━━━━━━ 14:43 14s/step - accuracy: 0.2864 - loss: 1.3818
``` - + ```
-121/183 [==================>...........] - ETA: 14:41 - loss: 1.3862 - accuracy: 0.2707 + 121/183 ━━━━━━━━━━━━━━━━━━━━ 14:29 14s/step - accuracy: 0.2863 - loss: 1.3817
``` - + ```
-122/183 [===================>..........] - ETA: 14:27 - loss: 1.3862 - accuracy: 0.2705 + 122/183 ━━━━━━━━━━━━━━━━━━━━ 14:15 14s/step - accuracy: 0.2862 - loss: 1.3817
``` - + ```
-123/183 [===================>..........] - ETA: 14:12 - loss: 1.3861 - accuracy: 0.2703 + 123/183 ━━━━━━━━━━━━━━━━━━━━ 14:01 14s/step - accuracy: 0.2862 - loss: 1.3817
``` - + ```
-124/183 [===================>..........] - ETA: 13:58 - loss: 1.3860 - accuracy: 0.2692 + 124/183 ━━━━━━━━━━━━━━━━━━━━ 13:47 14s/step - accuracy: 0.2861 - loss: 1.3817
``` - + ```
-125/183 [===================>..........] - ETA: 13:44 - loss: 1.3861 - accuracy: 0.2670 + 125/183 ━━━━━━━━━━━━━━━━━━━━ 13:33 14s/step - accuracy: 0.2860 - loss: 1.3817
``` - + ```
-126/183 [===================>..........] - ETA: 13:30 - loss: 1.3860 - accuracy: 0.2679 + 126/183 ━━━━━━━━━━━━━━━━━━━━ 13:19 14s/step - accuracy: 0.2859 - loss: 1.3817
``` - + ```
-127/183 [===================>..........] - ETA: 13:15 - loss: 1.3858 - accuracy: 0.2677 + 127/183 ━━━━━━━━━━━━━━━━━━━━ 13:05 14s/step - accuracy: 0.2859 - loss: 1.3817
``` - + ```
-128/183 [===================>..........] - ETA: 13:01 - loss: 1.3856 - accuracy: 0.2715 + 128/183 ━━━━━━━━━━━━━━━━━━━━ 12:51 14s/step - accuracy: 0.2858 - loss: 1.3817
``` - + ```
-129/183 [====================>.........] - ETA: 12:47 - loss: 1.3855 - accuracy: 0.2723 + 129/183 ━━━━━━━━━━━━━━━━━━━━ 12:37 14s/step - accuracy: 0.2858 - loss: 1.3817
``` - + ```
-130/183 [====================>.........] - ETA: 12:33 - loss: 1.3854 - accuracy: 0.2731 + 130/183 ━━━━━━━━━━━━━━━━━━━━ 12:23 14s/step - accuracy: 0.2857 - loss: 1.3817
``` - + ```
-131/183 [====================>.........] - ETA: 12:19 - loss: 1.3854 - accuracy: 0.2719 + 131/183 ━━━━━━━━━━━━━━━━━━━━ 12:09 14s/step - accuracy: 0.2857 - loss: 1.3816
``` - + ```
-132/183 [====================>.........] - ETA: 12:04 - loss: 1.3854 - accuracy: 0.2718 + 132/183 ━━━━━━━━━━━━━━━━━━━━ 11:55 14s/step - accuracy: 0.2856 - loss: 1.3816
``` - + ```
-133/183 [====================>.........] - ETA: 11:50 - loss: 1.3854 - accuracy: 0.2707 + 133/183 ━━━━━━━━━━━━━━━━━━━━ 11:41 14s/step - accuracy: 0.2856 - loss: 1.3816
``` - + ```
-134/183 [====================>.........] - ETA: 11:36 - loss: 1.3854 - accuracy: 0.2705 + 134/183 ━━━━━━━━━━━━━━━━━━━━ 11:27 14s/step - accuracy: 0.2855 - loss: 1.3816
``` - + ```
-135/183 [=====================>........] - ETA: 11:22 - loss: 1.3853 - accuracy: 0.2694 + 135/183 ━━━━━━━━━━━━━━━━━━━━ 11:13 14s/step - accuracy: 0.2855 - loss: 1.3816
``` - + ```
-136/183 [=====================>........] - ETA: 11:07 - loss: 1.3854 - accuracy: 0.2693 + 136/183 ━━━━━━━━━━━━━━━━━━━━ 10:59 14s/step - accuracy: 0.2855 - loss: 1.3816
``` - + ```
-137/183 [=====================>........] - ETA: 10:53 - loss: 1.3854 - accuracy: 0.2710 + 137/183 ━━━━━━━━━━━━━━━━━━━━ 10:45 14s/step - accuracy: 0.2855 - loss: 1.3816
``` - + ```
-138/183 [=====================>........] - ETA: 10:39 - loss: 1.3856 - accuracy: 0.2717 + 138/183 ━━━━━━━━━━━━━━━━━━━━ 10:31 14s/step - accuracy: 0.2854 - loss: 1.3816
``` - + ```
-139/183 [=====================>........] - ETA: 10:25 - loss: 1.3855 - accuracy: 0.2743 + 139/183 ━━━━━━━━━━━━━━━━━━━━ 10:17 14s/step - accuracy: 0.2854 - loss: 1.3816
``` - + ```
-140/183 [=====================>........] - ETA: 10:10 - loss: 1.3853 - accuracy: 0.2741 + 140/183 ━━━━━━━━━━━━━━━━━━━━ 10:03 14s/step - accuracy: 0.2854 - loss: 1.3816
``` - + ```
-141/183 [======================>.......] - ETA: 9:56 - loss: 1.3854 - accuracy: 0.2730 + 141/183 ━━━━━━━━━━━━━━━━━━━━ 9:49 14s/step - accuracy: 0.2853 - loss: 1.3816
``` - + ```
-142/183 [======================>.......] - ETA: 9:42 - loss: 1.3854 - accuracy: 0.2720 + 142/183 ━━━━━━━━━━━━━━━━━━━━ 9:35 14s/step - accuracy: 0.2853 - loss: 1.3816
``` - + ```
-143/183 [======================>.......] - ETA: 9:28 - loss: 1.3852 - accuracy: 0.2719 + 143/183 ━━━━━━━━━━━━━━━━━━━━ 9:21 14s/step - accuracy: 0.2853 - loss: 1.3816
``` - + ```
-144/183 [======================>.......] - ETA: 9:14 - loss: 1.3852 - accuracy: 0.2717 + 144/183 ━━━━━━━━━━━━━━━━━━━━ 9:07 14s/step - accuracy: 0.2852 - loss: 1.3815
``` - + ```
-145/183 [======================>.......] - ETA: 8:59 - loss: 1.3852 - accuracy: 0.2724 + 145/183 ━━━━━━━━━━━━━━━━━━━━ 8:53 14s/step - accuracy: 0.2852 - loss: 1.3815
``` - + ```
-146/183 [======================>.......] - ETA: 8:45 - loss: 1.3853 - accuracy: 0.2723 + 146/183 ━━━━━━━━━━━━━━━━━━━━ 8:39 14s/step - accuracy: 0.2852 - loss: 1.3815
``` - + ```
-147/183 [=======================>......] - ETA: 8:31 - loss: 1.3852 - accuracy: 0.2730 + 147/183 ━━━━━━━━━━━━━━━━━━━━ 8:25 14s/step - accuracy: 0.2851 - loss: 1.3815
``` - + ```
-148/183 [=======================>......] - ETA: 8:17 - loss: 1.3852 - accuracy: 0.2736 + 148/183 ━━━━━━━━━━━━━━━━━━━━ 8:11 14s/step - accuracy: 0.2851 - loss: 1.3815
``` - + ```
-149/183 [=======================>......] - ETA: 8:03 - loss: 1.3851 - accuracy: 0.2743 + 149/183 ━━━━━━━━━━━━━━━━━━━━ 7:57 14s/step - accuracy: 0.2851 - loss: 1.3815
``` - + ```
-150/183 [=======================>......] - ETA: 7:48 - loss: 1.3848 - accuracy: 0.2758 + 150/183 ━━━━━━━━━━━━━━━━━━━━ 7:43 14s/step - accuracy: 0.2850 - loss: 1.3815
``` - + ```
-151/183 [=======================>......] - ETA: 7:34 - loss: 1.3847 - accuracy: 0.2757 + 151/183 ━━━━━━━━━━━━━━━━━━━━ 7:29 14s/step - accuracy: 0.2850 - loss: 1.3815
``` - + ```
-152/183 [=======================>......] - ETA: 7:20 - loss: 1.3847 - accuracy: 0.2755 + 152/183 ━━━━━━━━━━━━━━━━━━━━ 7:15 14s/step - accuracy: 0.2850 - loss: 1.3815
``` - + ```
-153/183 [========================>.....] - ETA: 7:06 - loss: 1.3847 - accuracy: 0.2753 + 153/183 ━━━━━━━━━━━━━━━━━━━━ 7:01 14s/step - accuracy: 0.2850 - loss: 1.3815
``` - + ```
-154/183 [========================>.....] - ETA: 6:52 - loss: 1.3848 - accuracy: 0.2744 + 154/183 ━━━━━━━━━━━━━━━━━━━━ 6:47 14s/step - accuracy: 0.2850 - loss: 1.3815
``` - + ```
-155/183 [========================>.....] - ETA: 6:37 - loss: 1.3847 - accuracy: 0.2742 + 155/183 ━━━━━━━━━━━━━━━━━━━━ 6:33 14s/step - accuracy: 0.2849 - loss: 1.3815
``` - + ```
-156/183 [========================>.....] - ETA: 6:23 - loss: 1.3848 - accuracy: 0.2740 + 156/183 ━━━━━━━━━━━━━━━━━━━━ 6:19 14s/step - accuracy: 0.2849 - loss: 1.3815
``` - + ```
-157/183 [========================>.....] - ETA: 6:09 - loss: 1.3848 - accuracy: 0.2731 + 157/183 ━━━━━━━━━━━━━━━━━━━━ 6:05 14s/step - accuracy: 0.2849 - loss: 1.3814
``` - + ```
-158/183 [========================>.....] - ETA: 5:55 - loss: 1.3848 - accuracy: 0.2737 + 158/183 ━━━━━━━━━━━━━━━━━━━━ 5:51 14s/step - accuracy: 0.2849 - loss: 1.3814
``` - + ```
-159/183 [=========================>....] - ETA: 5:40 - loss: 1.3848 - accuracy: 0.2752 + 159/183 ━━━━━━━━━━━━━━━━━━━━ 5:37 14s/step - accuracy: 0.2848 - loss: 1.3814
``` - + ```
-160/183 [=========================>....] - ETA: 5:26 - loss: 1.3849 - accuracy: 0.2742 + 160/183 ━━━━━━━━━━━━━━━━━━━━ 5:23 14s/step - accuracy: 0.2848 - loss: 1.3814
``` - + ```
-161/183 [=========================>....] - ETA: 5:12 - loss: 1.3845 - accuracy: 0.2772 + 161/183 ━━━━━━━━━━━━━━━━━━━━ 5:09 14s/step - accuracy: 0.2848 - loss: 1.3814
``` - + ```
-162/183 [=========================>....] - ETA: 4:58 - loss: 1.3847 - accuracy: 0.2770 + 162/183 ━━━━━━━━━━━━━━━━━━━━ 4:55 14s/step - accuracy: 0.2848 - loss: 1.3814
``` - + ```
-163/183 [=========================>....] - ETA: 4:44 - loss: 1.3849 - accuracy: 0.2768 + 163/183 ━━━━━━━━━━━━━━━━━━━━ 4:40 14s/step - accuracy: 0.2848 - loss: 1.3814
``` - + ```
-164/183 [=========================>....] - ETA: 4:29 - loss: 1.3848 - accuracy: 0.2774 + 164/183 ━━━━━━━━━━━━━━━━━━━━ 4:26 14s/step - accuracy: 0.2848 - loss: 1.3814
``` - + ```
-165/183 [==========================>...] - ETA: 4:15 - loss: 1.3848 - accuracy: 0.2780 + 165/183 ━━━━━━━━━━━━━━━━━━━━ 4:12 14s/step - accuracy: 0.2848 - loss: 1.3814
``` - + ```
-166/183 [==========================>...] - ETA: 4:01 - loss: 1.3848 - accuracy: 0.2764 + 166/183 ━━━━━━━━━━━━━━━━━━━━ 3:58 14s/step - accuracy: 0.2848 - loss: 1.3814
``` - + ```
-167/183 [==========================>...] - ETA: 3:47 - loss: 1.3847 - accuracy: 0.2762 + 167/183 ━━━━━━━━━━━━━━━━━━━━ 3:44 14s/step - accuracy: 0.2848 - loss: 1.3814
``` - + ```
-168/183 [==========================>...] - ETA: 3:33 - loss: 1.3848 - accuracy: 0.2753 + 168/183 ━━━━━━━━━━━━━━━━━━━━ 3:30 14s/step - accuracy: 0.2848 - loss: 1.3813
``` - + ```
-169/183 [==========================>...] - ETA: 3:18 - loss: 1.3848 - accuracy: 0.2759 + 169/183 ━━━━━━━━━━━━━━━━━━━━ 3:16 14s/step - accuracy: 0.2848 - loss: 1.3813
``` - + ```
-170/183 [==========================>...] - ETA: 3:04 - loss: 1.3846 - accuracy: 0.2779 + 170/183 ━━━━━━━━━━━━━━━━━━━━ 3:02 14s/step - accuracy: 0.2848 - loss: 1.3813
``` - + ```
-171/183 [===========================>..] - ETA: 2:50 - loss: 1.3849 - accuracy: 0.2770 + 171/183 ━━━━━━━━━━━━━━━━━━━━ 2:48 14s/step - accuracy: 0.2848 - loss: 1.3813
``` - + ```
-172/183 [===========================>..] - ETA: 2:36 - loss: 1.3850 - accuracy: 0.2754 + 172/183 ━━━━━━━━━━━━━━━━━━━━ 2:34 14s/step - accuracy: 0.2848 - loss: 1.3813
``` - + ```
-173/183 [===========================>..] - ETA: 2:22 - loss: 1.3849 - accuracy: 0.2760 + 173/183 ━━━━━━━━━━━━━━━━━━━━ 2:20 14s/step - accuracy: 0.2848 - loss: 1.3813
``` - + ```
-174/183 [===========================>..] - ETA: 2:07 - loss: 1.3849 - accuracy: 0.2766 + 174/183 ━━━━━━━━━━━━━━━━━━━━ 2:06 14s/step - accuracy: 0.2849 - loss: 1.3813
``` - + ```
-175/183 [===========================>..] - ETA: 1:53 - loss: 1.3849 - accuracy: 0.2779 + 175/183 ━━━━━━━━━━━━━━━━━━━━ 1:52 14s/step - accuracy: 0.2849 - loss: 1.3813
``` - + ```
-176/183 [===========================>..] - ETA: 1:39 - loss: 1.3846 - accuracy: 0.2784 + 176/183 ━━━━━━━━━━━━━━━━━━━━ 1:38 14s/step - accuracy: 0.2849 - loss: 1.3813
``` - + ```
-177/183 [============================>.] - ETA: 1:25 - loss: 1.3846 - accuracy: 0.2797 + 177/183 ━━━━━━━━━━━━━━━━━━━━ 1:24 14s/step - accuracy: 0.2850 - loss: 1.3813
``` - + ```
-178/183 [============================>.] - ETA: 1:11 - loss: 1.3844 - accuracy: 0.2809 + 178/183 ━━━━━━━━━━━━━━━━━━━━ 1:10 14s/step - accuracy: 0.2850 - loss: 1.3813
``` - + ```
-179/183 [============================>.] - ETA: 56s - loss: 1.3844 - accuracy: 0.2807 + 179/183 ━━━━━━━━━━━━━━━━━━━━ 56s 14s/step - accuracy: 0.2850 - loss: 1.3813
``` - + ```
-180/183 [============================>.] - ETA: 42s - loss: 1.3843 - accuracy: 0.2806 + 180/183 ━━━━━━━━━━━━━━━━━━━━ 42s 14s/step - accuracy: 0.2851 - loss: 1.3812
``` - + ```
-181/183 [============================>.] - ETA: 28s - loss: 1.3843 - accuracy: 0.2818 + 181/183 ━━━━━━━━━━━━━━━━━━━━ 28s 14s/step - accuracy: 0.2851 - loss: 1.3812
``` - + ```
-182/183 [============================>.] - ETA: 14s - loss: 1.3843 - accuracy: 0.2823 + 182/183 ━━━━━━━━━━━━━━━━━━━━ 14s 14s/step - accuracy: 0.2851 - loss: 1.3812
``` - + ```
-183/183 [==============================] - ETA: 0s - loss: 1.3842 - accuracy: 0.2828 + 183/183 ━━━━━━━━━━━━━━━━━━━━ 0s 14s/step - accuracy: 0.2852 - loss: 1.3812
``` -/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/task.py:47: UserWarning: `Model.state_updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. - return id(getattr(self, attr)) not in self._functional_layer_ids -/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/task.py:47: UserWarning: `layer.updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. - return id(getattr(self, attr)) not in self._functional_layer_ids -/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/backbone.py:37: UserWarning: `Model.state_updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. - return id(getattr(self, attr)) not in self._functional_layer_ids -/usr/local/python/3.10.13/lib/python3.10/site-packages/keras_nlp/src/models/backbone.py:37: UserWarning: `layer.updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically. - return id(getattr(self, attr)) not in self._functional_layer_ids - - + ```
-183/183 [==============================] - 3111s 15s/step - loss: 1.3842 - accuracy: 0.2828 - val_loss: 1.3755 - val_accuracy: 0.5225 - lr: 1.0000e-06 + 183/183 ━━━━━━━━━━━━━━━━━━━━ 3110s 15s/step - accuracy: 0.2852 - loss: 1.3812 - val_accuracy: 0.5575 - val_loss: 1.3673 - learning_rate: 1.0000e-06
@@ -2292,1288 +2015,1288 @@ Epoch 2/5 ```
- 1/183 [..............................] - ETA: 46:52 - loss: 1.3583 - accuracy: 0.5000 + 1/183 ━━━━━━━━━━━━━━━━━━━━ 45:28 15s/step - accuracy: 0.3750 - loss: 1.3267
``` - + ```
- 2/183 [..............................] - ETA: 43:21 - loss: 1.3603 - accuracy: 0.3750 + 2/183 ━━━━━━━━━━━━━━━━━━━━ 43:00 14s/step - accuracy: 0.3438 - loss: 1.3379
``` - + ```
- 3/183 [..............................] - ETA: 43:12 - loss: 1.3608 - accuracy: 0.3750 + 3/183 ━━━━━━━━━━━━━━━━━━━━ 42:53 14s/step - accuracy: 0.3403 - loss: 1.3452
``` - + ```
- 4/183 [..............................] - ETA: 42:59 - loss: 1.3601 - accuracy: 0.4062 + 4/183 ━━━━━━━━━━━━━━━━━━━━ 42:37 14s/step - accuracy: 0.3255 - loss: 1.3510
``` - + ```
- 5/183 [..............................] - ETA: 42:33 - loss: 1.3611 - accuracy: 0.3750 + 5/183 ━━━━━━━━━━━━━━━━━━━━ 42:19 14s/step - accuracy: 0.3204 - loss: 1.3548
``` - + ```
- 6/183 [..............................] - ETA: 42:14 - loss: 1.3652 - accuracy: 0.3333 + 6/183 ━━━━━━━━━━━━━━━━━━━━ 42:05 14s/step - accuracy: 0.3156 - loss: 1.3585
``` - + ```
- 7/183 [>.............................] - ETA: 41:54 - loss: 1.3719 - accuracy: 0.2857 + 7/183 ━━━━━━━━━━━━━━━━━━━━ 41:45 14s/step - accuracy: 0.3165 - loss: 1.3608
``` - + ```
- 8/183 [>.............................] - ETA: 41:38 - loss: 1.3726 - accuracy: 0.2969 + 8/183 ━━━━━━━━━━━━━━━━━━━━ 41:31 14s/step - accuracy: 0.3160 - loss: 1.3626
``` - + ```
- 9/183 [>.............................] - ETA: 41:22 - loss: 1.3738 - accuracy: 0.2917 + 9/183 ━━━━━━━━━━━━━━━━━━━━ 41:12 14s/step - accuracy: 0.3194 - loss: 1.3634
``` - + ```
- 10/183 [>.............................] - ETA: 41:05 - loss: 1.3772 - accuracy: 0.2875 + 10/183 ━━━━━━━━━━━━━━━━━━━━ 40:56 14s/step - accuracy: 0.3225 - loss: 1.3643
``` - + ```
- 11/183 [>.............................] - ETA: 40:54 - loss: 1.3764 - accuracy: 0.2955 + 11/183 ━━━━━━━━━━━━━━━━━━━━ 40:42 14s/step - accuracy: 0.3262 - loss: 1.3648
``` - + ```
- 12/183 [>.............................] - ETA: 40:37 - loss: 1.3753 - accuracy: 0.3021 + 12/183 ━━━━━━━━━━━━━━━━━━━━ 40:28 14s/step - accuracy: 0.3294 - loss: 1.3651
``` - + ```
- 13/183 [=>............................] - ETA: 40:22 - loss: 1.3747 - accuracy: 0.3173 + 13/183 ━━━━━━━━━━━━━━━━━━━━ 40:13 14s/step - accuracy: 0.3322 - loss: 1.3655
``` - + ```
- 14/183 [=>............................] - ETA: 40:06 - loss: 1.3742 - accuracy: 0.3214 + 14/183 ━━━━━━━━━━━━━━━━━━━━ 39:59 14s/step - accuracy: 0.3340 - loss: 1.3656
``` - + ```
- 15/183 [=>............................] - ETA: 39:50 - loss: 1.3715 - accuracy: 0.3333 + 15/183 ━━━━━━━━━━━━━━━━━━━━ 39:46 14s/step - accuracy: 0.3345 - loss: 1.3659
``` - + ```
- 16/183 [=>............................] - ETA: 39:34 - loss: 1.3716 - accuracy: 0.3359 + 16/183 ━━━━━━━━━━━━━━━━━━━━ 39:33 14s/step - accuracy: 0.3351 - loss: 1.3662
``` - + ```
- 17/183 [=>............................] - ETA: 39:19 - loss: 1.3721 - accuracy: 0.3382 + 17/183 ━━━━━━━━━━━━━━━━━━━━ 39:18 14s/step - accuracy: 0.3357 - loss: 1.3664
``` - + ```
- 18/183 [=>............................] - ETA: 39:03 - loss: 1.3735 - accuracy: 0.3194 + 18/183 ━━━━━━━━━━━━━━━━━━━━ 39:03 14s/step - accuracy: 0.3356 - loss: 1.3667
``` - + ```
- 19/183 [==>...........................] - ETA: 38:48 - loss: 1.3746 - accuracy: 0.3158 + 19/183 ━━━━━━━━━━━━━━━━━━━━ 38:49 14s/step - accuracy: 0.3352 - loss: 1.3670
``` - + ```
- 20/183 [==>...........................] - ETA: 38:33 - loss: 1.3740 - accuracy: 0.3250 + 20/183 ━━━━━━━━━━━━━━━━━━━━ 38:34 14s/step - accuracy: 0.3344 - loss: 1.3673
``` - + ```
- 21/183 [==>...........................] - ETA: 38:18 - loss: 1.3744 - accuracy: 0.3274 + 21/183 ━━━━━━━━━━━━━━━━━━━━ 38:19 14s/step - accuracy: 0.3343 - loss: 1.3674
``` - + ```
- 22/183 [==>...........................] - ETA: 38:04 - loss: 1.3718 - accuracy: 0.3352 + 22/183 ━━━━━━━━━━━━━━━━━━━━ 38:04 14s/step - accuracy: 0.3346 - loss: 1.3675
``` - + ```
- 23/183 [==>...........................] - ETA: 37:49 - loss: 1.3711 - accuracy: 0.3424 + 23/183 ━━━━━━━━━━━━━━━━━━━━ 37:48 14s/step - accuracy: 0.3352 - loss: 1.3675
``` - + ```
- 24/183 [==>...........................] - ETA: 37:34 - loss: 1.3712 - accuracy: 0.3333 + 24/183 ━━━━━━━━━━━━━━━━━━━━ 37:33 14s/step - accuracy: 0.3356 - loss: 1.3676
``` - + ```
- 25/183 [===>..........................] - ETA: 37:20 - loss: 1.3700 - accuracy: 0.3400 + 25/183 ━━━━━━━━━━━━━━━━━━━━ 37:19 14s/step - accuracy: 0.3357 - loss: 1.3676
``` - + ```
- 26/183 [===>..........................] - ETA: 37:05 - loss: 1.3709 - accuracy: 0.3365 + 26/183 ━━━━━━━━━━━━━━━━━━━━ 37:03 14s/step - accuracy: 0.3358 - loss: 1.3677
``` - + ```
- 27/183 [===>..........................] - ETA: 36:51 - loss: 1.3708 - accuracy: 0.3380 + 27/183 ━━━━━━━━━━━━━━━━━━━━ 36:47 14s/step - accuracy: 0.3360 - loss: 1.3676
``` - + ```
- 28/183 [===>..........................] - ETA: 36:36 - loss: 1.3709 - accuracy: 0.3348 + 28/183 ━━━━━━━━━━━━━━━━━━━━ 36:31 14s/step - accuracy: 0.3361 - loss: 1.3676
``` - + ```
- 29/183 [===>..........................] - ETA: 36:22 - loss: 1.3708 - accuracy: 0.3362 + 29/183 ━━━━━━━━━━━━━━━━━━━━ 36:15 14s/step - accuracy: 0.3363 - loss: 1.3675
``` - + ```
- 30/183 [===>..........................] - ETA: 36:07 - loss: 1.3706 - accuracy: 0.3375 + 30/183 ━━━━━━━━━━━━━━━━━━━━ 35:59 14s/step - accuracy: 0.3365 - loss: 1.3674
``` - + ```
- 31/183 [====>.........................] - ETA: 35:53 - loss: 1.3708 - accuracy: 0.3387 + 31/183 ━━━━━━━━━━━━━━━━━━━━ 35:44 14s/step - accuracy: 0.3365 - loss: 1.3674
``` - + ```
- 32/183 [====>.........................] - ETA: 35:38 - loss: 1.3699 - accuracy: 0.3359 + 32/183 ━━━━━━━━━━━━━━━━━━━━ 35:28 14s/step - accuracy: 0.3368 - loss: 1.3673
``` - + ```
- 33/183 [====>.........................] - ETA: 35:24 - loss: 1.3704 - accuracy: 0.3295 + 33/183 ━━━━━━━━━━━━━━━━━━━━ 35:13 14s/step - accuracy: 0.3368 - loss: 1.3672
``` - + ```
- 34/183 [====>.........................] - ETA: 35:10 - loss: 1.3712 - accuracy: 0.3199 + 34/183 ━━━━━━━━━━━━━━━━━━━━ 34:58 14s/step - accuracy: 0.3371 - loss: 1.3670
``` - + ```
- 35/183 [====>.........................] - ETA: 34:55 - loss: 1.3718 - accuracy: 0.3214 + 35/183 ━━━━━━━━━━━━━━━━━━━━ 34:42 14s/step - accuracy: 0.3373 - loss: 1.3669
``` - + ```
- 36/183 [====>.........................] - ETA: 34:41 - loss: 1.3712 - accuracy: 0.3264 + 36/183 ━━━━━━━━━━━━━━━━━━━━ 34:27 14s/step - accuracy: 0.3378 - loss: 1.3667
``` - + ```
- 37/183 [=====>........................] - ETA: 34:27 - loss: 1.3713 - accuracy: 0.3243 + 37/183 ━━━━━━━━━━━━━━━━━━━━ 34:12 14s/step - accuracy: 0.3383 - loss: 1.3665
``` - + ```
- 38/183 [=====>........................] - ETA: 34:13 - loss: 1.3701 - accuracy: 0.3289 + 38/183 ━━━━━━━━━━━━━━━━━━━━ 33:58 14s/step - accuracy: 0.3390 - loss: 1.3662
``` - + ```
- 39/183 [=====>........................] - ETA: 33:58 - loss: 1.3701 - accuracy: 0.3237 + 39/183 ━━━━━━━━━━━━━━━━━━━━ 33:44 14s/step - accuracy: 0.3398 - loss: 1.3660
``` - + ```
- 40/183 [=====>........................] - ETA: 33:44 - loss: 1.3697 - accuracy: 0.3250 + 40/183 ━━━━━━━━━━━━━━━━━━━━ 33:30 14s/step - accuracy: 0.3405 - loss: 1.3657
``` - + ```
- 41/183 [=====>........................] - ETA: 33:30 - loss: 1.3700 - accuracy: 0.3201 + 41/183 ━━━━━━━━━━━━━━━━━━━━ 33:16 14s/step - accuracy: 0.3411 - loss: 1.3654
``` - + ```
- 42/183 [=====>........................] - ETA: 33:16 - loss: 1.3699 - accuracy: 0.3214 + 42/183 ━━━━━━━━━━━━━━━━━━━━ 33:02 14s/step - accuracy: 0.3419 - loss: 1.3651
``` - + ```
- 43/183 [======>.......................] - ETA: 33:01 - loss: 1.3695 - accuracy: 0.3227 + 43/183 ━━━━━━━━━━━━━━━━━━━━ 32:49 14s/step - accuracy: 0.3428 - loss: 1.3647
``` - + ```
- 44/183 [======>.......................] - ETA: 32:48 - loss: 1.3689 - accuracy: 0.3210 + 44/183 ━━━━━━━━━━━━━━━━━━━━ 32:35 14s/step - accuracy: 0.3436 - loss: 1.3644
``` - + ```
- 45/183 [======>.......................] - ETA: 32:33 - loss: 1.3685 - accuracy: 0.3222 + 45/183 ━━━━━━━━━━━━━━━━━━━━ 32:21 14s/step - accuracy: 0.3446 - loss: 1.3640
``` - + ```
- 46/183 [======>.......................] - ETA: 32:19 - loss: 1.3692 - accuracy: 0.3207 + 46/183 ━━━━━━━━━━━━━━━━━━━━ 32:08 14s/step - accuracy: 0.3454 - loss: 1.3637
``` - + ```
- 47/183 [======>.......................] - ETA: 32:05 - loss: 1.3682 - accuracy: 0.3271 + 47/183 ━━━━━━━━━━━━━━━━━━━━ 31:54 14s/step - accuracy: 0.3463 - loss: 1.3633
``` - + ```
- 48/183 [======>.......................] - ETA: 31:50 - loss: 1.3682 - accuracy: 0.3281 + 48/183 ━━━━━━━━━━━━━━━━━━━━ 31:40 14s/step - accuracy: 0.3471 - loss: 1.3629
``` - + ```
- 49/183 [=======>......................] - ETA: 31:36 - loss: 1.3685 - accuracy: 0.3291 + 49/183 ━━━━━━━━━━━━━━━━━━━━ 31:26 14s/step - accuracy: 0.3479 - loss: 1.3625
``` - + ```
- 50/183 [=======>......................] - ETA: 31:22 - loss: 1.3682 - accuracy: 0.3250 + 50/183 ━━━━━━━━━━━━━━━━━━━━ 31:12 14s/step - accuracy: 0.3487 - loss: 1.3622
``` - + ```
- 51/183 [=======>......................] - ETA: 31:08 - loss: 1.3690 - accuracy: 0.3235 + 51/183 ━━━━━━━━━━━━━━━━━━━━ 30:59 14s/step - accuracy: 0.3495 - loss: 1.3618
``` - + ```
- 52/183 [=======>......................] - ETA: 30:53 - loss: 1.3690 - accuracy: 0.3221 + 52/183 ━━━━━━━━━━━━━━━━━━━━ 30:45 14s/step - accuracy: 0.3503 - loss: 1.3614
``` - + ```
- 53/183 [=======>......................] - ETA: 30:39 - loss: 1.3692 - accuracy: 0.3231 + 53/183 ━━━━━━━━━━━━━━━━━━━━ 30:31 14s/step - accuracy: 0.3511 - loss: 1.3610
``` - + ```
- 54/183 [=======>......................] - ETA: 30:25 - loss: 1.3690 - accuracy: 0.3241 + 54/183 ━━━━━━━━━━━━━━━━━━━━ 30:17 14s/step - accuracy: 0.3518 - loss: 1.3606
``` - + ```
- 55/183 [========>.....................] - ETA: 30:11 - loss: 1.3688 - accuracy: 0.3273 + 55/183 ━━━━━━━━━━━━━━━━━━━━ 30:03 14s/step - accuracy: 0.3524 - loss: 1.3603
``` - + ```
- 56/183 [========>.....................] - ETA: 29:56 - loss: 1.3685 - accuracy: 0.3281 + 56/183 ━━━━━━━━━━━━━━━━━━━━ 29:49 14s/step - accuracy: 0.3530 - loss: 1.3600
``` - + ```
- 57/183 [========>.....................] - ETA: 29:42 - loss: 1.3679 - accuracy: 0.3311 + 57/183 ━━━━━━━━━━━━━━━━━━━━ 29:35 14s/step - accuracy: 0.3536 - loss: 1.3597
``` - + ```
- 58/183 [========>.....................] - ETA: 29:28 - loss: 1.3671 - accuracy: 0.3319 + 58/183 ━━━━━━━━━━━━━━━━━━━━ 29:21 14s/step - accuracy: 0.3541 - loss: 1.3593
``` - + ```
- 59/183 [========>.....................] - ETA: 29:14 - loss: 1.3670 - accuracy: 0.3326 + 59/183 ━━━━━━━━━━━━━━━━━━━━ 29:07 14s/step - accuracy: 0.3547 - loss: 1.3590
``` - + ```
- 60/183 [========>.....................] - ETA: 29:00 - loss: 1.3672 - accuracy: 0.3313 + 60/183 ━━━━━━━━━━━━━━━━━━━━ 28:52 14s/step - accuracy: 0.3551 - loss: 1.3588
``` - + ```
- 61/183 [=========>....................] - ETA: 28:45 - loss: 1.3673 - accuracy: 0.3279 + 61/183 ━━━━━━━━━━━━━━━━━━━━ 28:38 14s/step - accuracy: 0.3555 - loss: 1.3585
``` - + ```
- 62/183 [=========>....................] - ETA: 28:31 - loss: 1.3669 - accuracy: 0.3286 + 62/183 ━━━━━━━━━━━━━━━━━━━━ 28:24 14s/step - accuracy: 0.3559 - loss: 1.3582
``` - + ```
- 63/183 [=========>....................] - ETA: 28:17 - loss: 1.3667 - accuracy: 0.3234 + 63/183 ━━━━━━━━━━━━━━━━━━━━ 28:10 14s/step - accuracy: 0.3563 - loss: 1.3579
``` - + ```
- 64/183 [=========>....................] - ETA: 28:03 - loss: 1.3669 - accuracy: 0.3223 + 64/183 ━━━━━━━━━━━━━━━━━━━━ 27:55 14s/step - accuracy: 0.3567 - loss: 1.3576
``` - + ```
- 65/183 [=========>....................] - ETA: 27:49 - loss: 1.3662 - accuracy: 0.3231 + 65/183 ━━━━━━━━━━━━━━━━━━━━ 27:41 14s/step - accuracy: 0.3571 - loss: 1.3573
``` - + ```
- 66/183 [=========>....................] - ETA: 27:35 - loss: 1.3663 - accuracy: 0.3239 + 66/183 ━━━━━━━━━━━━━━━━━━━━ 27:27 14s/step - accuracy: 0.3575 - loss: 1.3570
``` - + ```
- 67/183 [=========>....................] - ETA: 27:20 - loss: 1.3659 - accuracy: 0.3265 + 67/183 ━━━━━━━━━━━━━━━━━━━━ 27:13 14s/step - accuracy: 0.3579 - loss: 1.3567
``` - + ```
- 68/183 [==========>...................] - ETA: 27:06 - loss: 1.3657 - accuracy: 0.3272 + 68/183 ━━━━━━━━━━━━━━━━━━━━ 26:59 14s/step - accuracy: 0.3583 - loss: 1.3564
``` - + ```
- 69/183 [==========>...................] - ETA: 26:52 - loss: 1.3648 - accuracy: 0.3315 + 69/183 ━━━━━━━━━━━━━━━━━━━━ 26:44 14s/step - accuracy: 0.3587 - loss: 1.3560
``` - + ```
- 70/183 [==========>...................] - ETA: 26:38 - loss: 1.3654 - accuracy: 0.3286 + 70/183 ━━━━━━━━━━━━━━━━━━━━ 26:30 14s/step - accuracy: 0.3591 - loss: 1.3557
``` - + ```
- 71/183 [==========>...................] - ETA: 26:24 - loss: 1.3644 - accuracy: 0.3327 + 71/183 ━━━━━━━━━━━━━━━━━━━━ 26:16 14s/step - accuracy: 0.3595 - loss: 1.3554
``` - + ```
- 72/183 [==========>...................] - ETA: 26:10 - loss: 1.3645 - accuracy: 0.3316 + 72/183 ━━━━━━━━━━━━━━━━━━━━ 26:02 14s/step - accuracy: 0.3598 - loss: 1.3550
``` - + ```
- 73/183 [==========>...................] - ETA: 25:56 - loss: 1.3645 - accuracy: 0.3305 + 73/183 ━━━━━━━━━━━━━━━━━━━━ 25:48 14s/step - accuracy: 0.3603 - loss: 1.3547
``` - + ```
- 74/183 [===========>..................] - ETA: 25:41 - loss: 1.3641 - accuracy: 0.3311 + 74/183 ━━━━━━━━━━━━━━━━━━━━ 25:34 14s/step - accuracy: 0.3607 - loss: 1.3543
``` - + ```
- 75/183 [===========>..................] - ETA: 25:27 - loss: 1.3628 - accuracy: 0.3367 + 75/183 ━━━━━━━━━━━━━━━━━━━━ 25:20 14s/step - accuracy: 0.3611 - loss: 1.3540
``` - + ```
- 76/183 [===========>..................] - ETA: 25:13 - loss: 1.3616 - accuracy: 0.3421 + 76/183 ━━━━━━━━━━━━━━━━━━━━ 25:06 14s/step - accuracy: 0.3615 - loss: 1.3536
``` - + ```
- 77/183 [===========>..................] - ETA: 24:59 - loss: 1.3614 - accuracy: 0.3425 + 77/183 ━━━━━━━━━━━━━━━━━━━━ 24:52 14s/step - accuracy: 0.3619 - loss: 1.3533
``` - + ```
- 78/183 [===========>..................] - ETA: 24:45 - loss: 1.3616 - accuracy: 0.3397 + 78/183 ━━━━━━━━━━━━━━━━━━━━ 24:38 14s/step - accuracy: 0.3623 - loss: 1.3529
``` - + ```
- 79/183 [===========>..................] - ETA: 24:31 - loss: 1.3610 - accuracy: 0.3418 + 79/183 ━━━━━━━━━━━━━━━━━━━━ 24:24 14s/step - accuracy: 0.3627 - loss: 1.3525
``` - + ```
- 80/183 [============>.................] - ETA: 24:17 - loss: 1.3608 - accuracy: 0.3438 + 80/183 ━━━━━━━━━━━━━━━━━━━━ 24:09 14s/step - accuracy: 0.3631 - loss: 1.3521
``` - + ```
- 81/183 [============>.................] - ETA: 24:03 - loss: 1.3599 - accuracy: 0.3441 + 81/183 ━━━━━━━━━━━━━━━━━━━━ 23:55 14s/step - accuracy: 0.3634 - loss: 1.3517
``` - + ```
- 82/183 [============>.................] - ETA: 23:49 - loss: 1.3591 - accuracy: 0.3460 + 82/183 ━━━━━━━━━━━━━━━━━━━━ 23:41 14s/step - accuracy: 0.3639 - loss: 1.3513
``` - + ```
- 83/183 [============>.................] - ETA: 23:35 - loss: 1.3589 - accuracy: 0.3479 + 83/183 ━━━━━━━━━━━━━━━━━━━━ 23:26 14s/step - accuracy: 0.3643 - loss: 1.3509
``` - + ```
- 84/183 [============>.................] - ETA: 23:21 - loss: 1.3583 - accuracy: 0.3482 + 84/183 ━━━━━━━━━━━━━━━━━━━━ 23:12 14s/step - accuracy: 0.3648 - loss: 1.3504
``` - + ```
- 85/183 [============>.................] - ETA: 23:07 - loss: 1.3575 - accuracy: 0.3515 + 85/183 ━━━━━━━━━━━━━━━━━━━━ 22:58 14s/step - accuracy: 0.3652 - loss: 1.3500
``` - + ```
- 86/183 [=============>................] - ETA: 22:53 - loss: 1.3558 - accuracy: 0.3561 + 86/183 ━━━━━━━━━━━━━━━━━━━━ 22:44 14s/step - accuracy: 0.3657 - loss: 1.3495
``` - + ```
- 87/183 [=============>................] - ETA: 22:39 - loss: 1.3560 - accuracy: 0.3549 + 87/183 ━━━━━━━━━━━━━━━━━━━━ 22:29 14s/step - accuracy: 0.3662 - loss: 1.3491
``` - + ```
- 88/183 [=============>................] - ETA: 22:25 - loss: 1.3535 - accuracy: 0.3594 + 88/183 ━━━━━━━━━━━━━━━━━━━━ 22:15 14s/step - accuracy: 0.3667 - loss: 1.3486
``` - + ```
- 89/183 [=============>................] - ETA: 22:10 - loss: 1.3529 - accuracy: 0.3596 + 89/183 ━━━━━━━━━━━━━━━━━━━━ 22:01 14s/step - accuracy: 0.3672 - loss: 1.3481
``` - + ```
- 90/183 [=============>................] - ETA: 21:56 - loss: 1.3529 - accuracy: 0.3597 + 90/183 ━━━━━━━━━━━━━━━━━━━━ 21:46 14s/step - accuracy: 0.3677 - loss: 1.3477
``` - + ```
- 91/183 [=============>................] - ETA: 21:42 - loss: 1.3510 - accuracy: 0.3613 + 91/183 ━━━━━━━━━━━━━━━━━━━━ 21:32 14s/step - accuracy: 0.3682 - loss: 1.3472
``` - + ```
- 92/183 [==============>...............] - ETA: 21:28 - loss: 1.3498 - accuracy: 0.3614 + 92/183 ━━━━━━━━━━━━━━━━━━━━ 21:19 14s/step - accuracy: 0.3687 - loss: 1.3467
``` - + ```
- 93/183 [==============>...............] - ETA: 21:14 - loss: 1.3492 - accuracy: 0.3629 + 93/183 ━━━━━━━━━━━━━━━━━━━━ 21:05 14s/step - accuracy: 0.3692 - loss: 1.3463
``` - + ```
- 94/183 [==============>...............] - ETA: 21:00 - loss: 1.3485 - accuracy: 0.3644 + 94/183 ━━━━━━━━━━━━━━━━━━━━ 20:51 14s/step - accuracy: 0.3696 - loss: 1.3458
``` - + ```
- 95/183 [==============>...............] - ETA: 20:45 - loss: 1.3484 - accuracy: 0.3658 + 95/183 ━━━━━━━━━━━━━━━━━━━━ 20:37 14s/step - accuracy: 0.3700 - loss: 1.3454
``` - + ```
- 96/183 [==============>...............] - ETA: 20:31 - loss: 1.3486 - accuracy: 0.3672 + 96/183 ━━━━━━━━━━━━━━━━━━━━ 20:23 14s/step - accuracy: 0.3705 - loss: 1.3449
``` - + ```
- 97/183 [==============>...............] - ETA: 20:17 - loss: 1.3488 - accuracy: 0.3647 + 97/183 ━━━━━━━━━━━━━━━━━━━━ 20:09 14s/step - accuracy: 0.3709 - loss: 1.3444
``` - + ```
- 98/183 [===============>..............] - ETA: 20:03 - loss: 1.3484 - accuracy: 0.3648 + 98/183 ━━━━━━━━━━━━━━━━━━━━ 19:55 14s/step - accuracy: 0.3714 - loss: 1.3440
``` - + ```
- 99/183 [===============>..............] - ETA: 19:49 - loss: 1.3478 - accuracy: 0.3662 + 99/183 ━━━━━━━━━━━━━━━━━━━━ 19:41 14s/step - accuracy: 0.3718 - loss: 1.3435
``` - + ```
-100/183 [===============>..............] - ETA: 19:34 - loss: 1.3469 - accuracy: 0.3650 + 100/183 ━━━━━━━━━━━━━━━━━━━━ 19:27 14s/step - accuracy: 0.3723 - loss: 1.3430
``` - + ```
-101/183 [===============>..............] - ETA: 19:20 - loss: 1.3474 - accuracy: 0.3651 + 101/183 ━━━━━━━━━━━━━━━━━━━━ 19:13 14s/step - accuracy: 0.3728 - loss: 1.3425
``` - + ```
-102/183 [===============>..............] - ETA: 19:06 - loss: 1.3457 - accuracy: 0.3689 + 102/183 ━━━━━━━━━━━━━━━━━━━━ 18:59 14s/step - accuracy: 0.3732 - loss: 1.3420
``` - + ```
-103/183 [===============>..............] - ETA: 18:52 - loss: 1.3453 - accuracy: 0.3689 + 103/183 ━━━━━━━━━━━━━━━━━━━━ 18:45 14s/step - accuracy: 0.3738 - loss: 1.3415
``` - + ```
-104/183 [================>.............] - ETA: 18:38 - loss: 1.3444 - accuracy: 0.3714 + 104/183 ━━━━━━━━━━━━━━━━━━━━ 18:31 14s/step - accuracy: 0.3743 - loss: 1.3410
``` - + ```
-105/183 [================>.............] - ETA: 18:24 - loss: 1.3441 - accuracy: 0.3726 + 105/183 ━━━━━━━━━━━━━━━━━━━━ 18:17 14s/step - accuracy: 0.3748 - loss: 1.3405
``` - + ```
-106/183 [================>.............] - ETA: 18:10 - loss: 1.3431 - accuracy: 0.3750 + 106/183 ━━━━━━━━━━━━━━━━━━━━ 18:03 14s/step - accuracy: 0.3753 - loss: 1.3400
``` - + ```
-107/183 [================>.............] - ETA: 17:55 - loss: 1.3425 - accuracy: 0.3738 + 107/183 ━━━━━━━━━━━━━━━━━━━━ 17:49 14s/step - accuracy: 0.3758 - loss: 1.3394
``` - + ```
-108/183 [================>.............] - ETA: 17:41 - loss: 1.3421 - accuracy: 0.3738 + 108/183 ━━━━━━━━━━━━━━━━━━━━ 17:35 14s/step - accuracy: 0.3763 - loss: 1.3389
``` - + ```
-109/183 [================>.............] - ETA: 17:27 - loss: 1.3419 - accuracy: 0.3739 + 109/183 ━━━━━━━━━━━━━━━━━━━━ 17:21 14s/step - accuracy: 0.3769 - loss: 1.3384
``` - + ```
-110/183 [=================>............] - ETA: 17:13 - loss: 1.3412 - accuracy: 0.3750 + 110/183 ━━━━━━━━━━━━━━━━━━━━ 17:07 14s/step - accuracy: 0.3774 - loss: 1.3378
``` - + ```
-111/183 [=================>............] - ETA: 16:59 - loss: 1.3400 - accuracy: 0.3773 + 111/183 ━━━━━━━━━━━━━━━━━━━━ 16:53 14s/step - accuracy: 0.3779 - loss: 1.3373
``` - + ```
-112/183 [=================>............] - ETA: 16:45 - loss: 1.3393 - accuracy: 0.3795 + 112/183 ━━━━━━━━━━━━━━━━━━━━ 16:39 14s/step - accuracy: 0.3785 - loss: 1.3368
``` - + ```
-113/183 [=================>............] - ETA: 16:30 - loss: 1.3380 - accuracy: 0.3827 + 113/183 ━━━━━━━━━━━━━━━━━━━━ 16:25 14s/step - accuracy: 0.3790 - loss: 1.3362
``` - + ```
-114/183 [=================>............] - ETA: 16:16 - loss: 1.3366 - accuracy: 0.3860 + 114/183 ━━━━━━━━━━━━━━━━━━━━ 16:11 14s/step - accuracy: 0.3796 - loss: 1.3357
``` - + ```
-115/183 [=================>............] - ETA: 16:02 - loss: 1.3350 - accuracy: 0.3870 + 115/183 ━━━━━━━━━━━━━━━━━━━━ 15:56 14s/step - accuracy: 0.3801 - loss: 1.3351
``` - + ```
-116/183 [==================>...........] - ETA: 15:48 - loss: 1.3334 - accuracy: 0.3901 + 116/183 ━━━━━━━━━━━━━━━━━━━━ 15:42 14s/step - accuracy: 0.3807 - loss: 1.3346
``` - + ```
-117/183 [==================>...........] - ETA: 15:34 - loss: 1.3331 - accuracy: 0.3900 + 117/183 ━━━━━━━━━━━━━━━━━━━━ 15:28 14s/step - accuracy: 0.3813 - loss: 1.3340
``` - + ```
-118/183 [==================>...........] - ETA: 15:20 - loss: 1.3324 - accuracy: 0.3909 + 118/183 ━━━━━━━━━━━━━━━━━━━━ 15:14 14s/step - accuracy: 0.3818 - loss: 1.3335
``` - + ```
-119/183 [==================>...........] - ETA: 15:06 - loss: 1.3308 - accuracy: 0.3929 + 119/183 ━━━━━━━━━━━━━━━━━━━━ 15:00 14s/step - accuracy: 0.3824 - loss: 1.3329
``` - + ```
-120/183 [==================>...........] - ETA: 14:51 - loss: 1.3316 - accuracy: 0.3906 + 120/183 ━━━━━━━━━━━━━━━━━━━━ 14:46 14s/step - accuracy: 0.3830 - loss: 1.3323
``` - + ```
-121/183 [==================>...........] - ETA: 14:37 - loss: 1.3312 - accuracy: 0.3895 + 121/183 ━━━━━━━━━━━━━━━━━━━━ 14:32 14s/step - accuracy: 0.3835 - loss: 1.3318
``` - + ```
-122/183 [===================>..........] - ETA: 14:23 - loss: 1.3294 - accuracy: 0.3924 + 122/183 ━━━━━━━━━━━━━━━━━━━━ 14:18 14s/step - accuracy: 0.3841 - loss: 1.3312
``` - + ```
-123/183 [===================>..........] - ETA: 14:09 - loss: 1.3284 - accuracy: 0.3953 + 123/183 ━━━━━━━━━━━━━━━━━━━━ 14:04 14s/step - accuracy: 0.3847 - loss: 1.3306
``` - + ```
-124/183 [===================>..........] - ETA: 13:55 - loss: 1.3269 - accuracy: 0.3972 + 124/183 ━━━━━━━━━━━━━━━━━━━━ 13:50 14s/step - accuracy: 0.3853 - loss: 1.3301
``` - + ```
-125/183 [===================>..........] - ETA: 13:40 - loss: 1.3249 - accuracy: 0.4000 + 125/183 ━━━━━━━━━━━━━━━━━━━━ 13:36 14s/step - accuracy: 0.3859 - loss: 1.3295
``` - + ```
-126/183 [===================>..........] - ETA: 13:26 - loss: 1.3245 - accuracy: 0.3988 + 126/183 ━━━━━━━━━━━━━━━━━━━━ 13:22 14s/step - accuracy: 0.3865 - loss: 1.3289
``` - + ```
-127/183 [===================>..........] - ETA: 13:12 - loss: 1.3231 - accuracy: 0.4006 + 127/183 ━━━━━━━━━━━━━━━━━━━━ 13:08 14s/step - accuracy: 0.3871 - loss: 1.3283
``` - + ```
-128/183 [===================>..........] - ETA: 12:58 - loss: 1.3233 - accuracy: 0.3994 + 128/183 ━━━━━━━━━━━━━━━━━━━━ 12:54 14s/step - accuracy: 0.3877 - loss: 1.3277
``` - + ```
-129/183 [====================>.........] - ETA: 12:44 - loss: 1.3212 - accuracy: 0.4021 + 129/183 ━━━━━━━━━━━━━━━━━━━━ 12:40 14s/step - accuracy: 0.3883 - loss: 1.3271
``` - + ```
-130/183 [====================>.........] - ETA: 12:30 - loss: 1.3206 - accuracy: 0.4029 + 130/183 ━━━━━━━━━━━━━━━━━━━━ 12:26 14s/step - accuracy: 0.3889 - loss: 1.3265
``` - + ```
-131/183 [====================>.........] - ETA: 12:16 - loss: 1.3187 - accuracy: 0.4065 + 131/183 ━━━━━━━━━━━━━━━━━━━━ 12:12 14s/step - accuracy: 0.3895 - loss: 1.3259
``` - + ```
-132/183 [====================>.........] - ETA: 12:01 - loss: 1.3173 - accuracy: 0.4091 + 132/183 ━━━━━━━━━━━━━━━━━━━━ 11:58 14s/step - accuracy: 0.3901 - loss: 1.3253
``` - + ```
-133/183 [====================>.........] - ETA: 11:47 - loss: 1.3162 - accuracy: 0.4098 + 133/183 ━━━━━━━━━━━━━━━━━━━━ 11:44 14s/step - accuracy: 0.3907 - loss: 1.3247
``` - + ```
-134/183 [====================>.........] - ETA: 11:33 - loss: 1.3148 - accuracy: 0.4123 + 134/183 ━━━━━━━━━━━━━━━━━━━━ 11:30 14s/step - accuracy: 0.3913 - loss: 1.3241
``` - + ```
-135/183 [=====================>........] - ETA: 11:19 - loss: 1.3149 - accuracy: 0.4120 + 135/183 ━━━━━━━━━━━━━━━━━━━━ 11:16 14s/step - accuracy: 0.3918 - loss: 1.3235
``` - + ```
-136/183 [=====================>........] - ETA: 11:05 - loss: 1.3150 - accuracy: 0.4118 + 136/183 ━━━━━━━━━━━━━━━━━━━━ 11:02 14s/step - accuracy: 0.3924 - loss: 1.3229
``` - + ```
-137/183 [=====================>........] - ETA: 10:51 - loss: 1.3143 - accuracy: 0.4106 + 137/183 ━━━━━━━━━━━━━━━━━━━━ 10:48 14s/step - accuracy: 0.3930 - loss: 1.3223
``` - + ```
-138/183 [=====================>........] - ETA: 10:36 - loss: 1.3133 - accuracy: 0.4130 + 138/183 ━━━━━━━━━━━━━━━━━━━━ 10:33 14s/step - accuracy: 0.3935 - loss: 1.3217
``` - + ```
-139/183 [=====================>........] - ETA: 10:22 - loss: 1.3127 - accuracy: 0.4128 + 139/183 ━━━━━━━━━━━━━━━━━━━━ 10:19 14s/step - accuracy: 0.3941 - loss: 1.3211
``` - + ```
-140/183 [=====================>........] - ETA: 10:08 - loss: 1.3136 - accuracy: 0.4125 + 140/183 ━━━━━━━━━━━━━━━━━━━━ 10:05 14s/step - accuracy: 0.3946 - loss: 1.3205
``` - + ```
-141/183 [======================>.......] - ETA: 9:54 - loss: 1.3125 - accuracy: 0.4131 + 141/183 ━━━━━━━━━━━━━━━━━━━━ 9:51 14s/step - accuracy: 0.3951 - loss: 1.3200
``` - + ```
-142/183 [======================>.......] - ETA: 9:40 - loss: 1.3115 - accuracy: 0.4155 + 142/183 ━━━━━━━━━━━━━━━━━━━━ 9:37 14s/step - accuracy: 0.3956 - loss: 1.3194
``` - + ```
-143/183 [======================>.......] - ETA: 9:26 - loss: 1.3108 - accuracy: 0.4161 + 143/183 ━━━━━━━━━━━━━━━━━━━━ 9:23 14s/step - accuracy: 0.3962 - loss: 1.3188
``` - + ```
-144/183 [======================>.......] - ETA: 9:11 - loss: 1.3098 - accuracy: 0.4167 + 144/183 ━━━━━━━━━━━━━━━━━━━━ 9:09 14s/step - accuracy: 0.3967 - loss: 1.3183
``` - + ```
-145/183 [======================>.......] - ETA: 8:57 - loss: 1.3086 - accuracy: 0.4172 + 145/183 ━━━━━━━━━━━━━━━━━━━━ 8:55 14s/step - accuracy: 0.3972 - loss: 1.3177
``` - + ```
-146/183 [======================>.......] - ETA: 8:43 - loss: 1.3083 - accuracy: 0.4161 + 146/183 ━━━━━━━━━━━━━━━━━━━━ 8:41 14s/step - accuracy: 0.3977 - loss: 1.3172
``` - + ```
-147/183 [=======================>......] - ETA: 8:29 - loss: 1.3067 - accuracy: 0.4184 + 147/183 ━━━━━━━━━━━━━━━━━━━━ 8:27 14s/step - accuracy: 0.3982 - loss: 1.3166
``` - + ```
-148/183 [=======================>......] - ETA: 8:15 - loss: 1.3047 - accuracy: 0.4215 + 148/183 ━━━━━━━━━━━━━━━━━━━━ 8:13 14s/step - accuracy: 0.3987 - loss: 1.3160
``` - + ```
-149/183 [=======================>......] - ETA: 8:01 - loss: 1.3037 - accuracy: 0.4211 + 149/183 ━━━━━━━━━━━━━━━━━━━━ 7:58 14s/step - accuracy: 0.3992 - loss: 1.3154
``` - + ```
-150/183 [=======================>......] - ETA: 7:47 - loss: 1.3029 - accuracy: 0.4217 + 150/183 ━━━━━━━━━━━━━━━━━━━━ 7:44 14s/step - accuracy: 0.3998 - loss: 1.3149
``` - + ```
-151/183 [=======================>......] - ETA: 7:32 - loss: 1.3021 - accuracy: 0.4222 + 151/183 ━━━━━━━━━━━━━━━━━━━━ 7:30 14s/step - accuracy: 0.4003 - loss: 1.3143
``` - + ```
-152/183 [=======================>......] - ETA: 7:18 - loss: 1.3007 - accuracy: 0.4243 + 152/183 ━━━━━━━━━━━━━━━━━━━━ 7:16 14s/step - accuracy: 0.4008 - loss: 1.3137
``` - + ```
-153/183 [========================>.....] - ETA: 7:04 - loss: 1.3017 - accuracy: 0.4240 + 153/183 ━━━━━━━━━━━━━━━━━━━━ 7:02 14s/step - accuracy: 0.4012 - loss: 1.3132
``` - + ```
-154/183 [========================>.....] - ETA: 6:50 - loss: 1.3006 - accuracy: 0.4253 + 154/183 ━━━━━━━━━━━━━━━━━━━━ 6:48 14s/step - accuracy: 0.4017 - loss: 1.3126
``` - + ```
-155/183 [========================>.....] - ETA: 6:36 - loss: 1.2986 - accuracy: 0.4282 + 155/183 ━━━━━━━━━━━━━━━━━━━━ 6:34 14s/step - accuracy: 0.4022 - loss: 1.3121
``` - + ```
-156/183 [========================>.....] - ETA: 6:22 - loss: 1.2965 - accuracy: 0.4303 + 156/183 ━━━━━━━━━━━━━━━━━━━━ 6:20 14s/step - accuracy: 0.4027 - loss: 1.3115
``` - + ```
-157/183 [========================>.....] - ETA: 6:08 - loss: 1.2964 - accuracy: 0.4283 + 157/183 ━━━━━━━━━━━━━━━━━━━━ 6:06 14s/step - accuracy: 0.4032 - loss: 1.3110
``` - + ```
-158/183 [========================>.....] - ETA: 5:53 - loss: 1.2953 - accuracy: 0.4288 + 158/183 ━━━━━━━━━━━━━━━━━━━━ 5:52 14s/step - accuracy: 0.4036 - loss: 1.3104
``` - + ```
-159/183 [=========================>....] - ETA: 5:39 - loss: 1.2931 - accuracy: 0.4316 + 159/183 ━━━━━━━━━━━━━━━━━━━━ 5:37 14s/step - accuracy: 0.4041 - loss: 1.3099
``` - + ```
-160/183 [=========================>....] - ETA: 5:25 - loss: 1.2923 - accuracy: 0.4320 + 160/183 ━━━━━━━━━━━━━━━━━━━━ 5:23 14s/step - accuracy: 0.4046 - loss: 1.3093
``` - + ```
-161/183 [=========================>....] - ETA: 5:11 - loss: 1.2916 - accuracy: 0.4332 + 161/183 ━━━━━━━━━━━━━━━━━━━━ 5:09 14s/step - accuracy: 0.4050 - loss: 1.3088
``` - + ```
-162/183 [=========================>....] - ETA: 4:57 - loss: 1.2905 - accuracy: 0.4344 + 162/183 ━━━━━━━━━━━━━━━━━━━━ 4:55 14s/step - accuracy: 0.4055 - loss: 1.3083
``` - + ```
-163/183 [=========================>....] - ETA: 4:43 - loss: 1.2901 - accuracy: 0.4348 + 163/183 ━━━━━━━━━━━━━━━━━━━━ 4:41 14s/step - accuracy: 0.4059 - loss: 1.3077
``` - + ```
-164/183 [=========================>....] - ETA: 4:28 - loss: 1.2891 - accuracy: 0.4360 + 164/183 ━━━━━━━━━━━━━━━━━━━━ 4:27 14s/step - accuracy: 0.4064 - loss: 1.3072
``` - + ```
-165/183 [==========================>...] - ETA: 4:14 - loss: 1.2881 - accuracy: 0.4356 + 165/183 ━━━━━━━━━━━━━━━━━━━━ 4:13 14s/step - accuracy: 0.4068 - loss: 1.3066
``` - + ```
-166/183 [==========================>...] - ETA: 4:00 - loss: 1.2860 - accuracy: 0.4375 + 166/183 ━━━━━━━━━━━━━━━━━━━━ 3:59 14s/step - accuracy: 0.4073 - loss: 1.3061
``` - + ```
-167/183 [==========================>...] - ETA: 3:46 - loss: 1.2835 - accuracy: 0.4386 + 167/183 ━━━━━━━━━━━━━━━━━━━━ 3:45 14s/step - accuracy: 0.4077 - loss: 1.3055
``` - + ```
-168/183 [==========================>...] - ETA: 3:32 - loss: 1.2838 - accuracy: 0.4375 + 168/183 ━━━━━━━━━━━━━━━━━━━━ 3:31 14s/step - accuracy: 0.4082 - loss: 1.3050
``` - + ```
-169/183 [==========================>...] - ETA: 3:18 - loss: 1.2829 - accuracy: 0.4379 + 169/183 ━━━━━━━━━━━━━━━━━━━━ 3:16 14s/step - accuracy: 0.4086 - loss: 1.3045
``` - + ```
-170/183 [==========================>...] - ETA: 3:03 - loss: 1.2830 - accuracy: 0.4390 + 170/183 ━━━━━━━━━━━━━━━━━━━━ 3:02 14s/step - accuracy: 0.4091 - loss: 1.3039
``` - + ```
-171/183 [===========================>..] - ETA: 2:49 - loss: 1.2800 - accuracy: 0.4415 + 171/183 ━━━━━━━━━━━━━━━━━━━━ 2:48 14s/step - accuracy: 0.4095 - loss: 1.3034
``` - + ```
-172/183 [===========================>..] - ETA: 2:35 - loss: 1.2784 - accuracy: 0.4419 + 172/183 ━━━━━━━━━━━━━━━━━━━━ 2:34 14s/step - accuracy: 0.4100 - loss: 1.3028
``` - + ```
-173/183 [===========================>..] - ETA: 2:21 - loss: 1.2765 - accuracy: 0.4429 + 173/183 ━━━━━━━━━━━━━━━━━━━━ 2:20 14s/step - accuracy: 0.4104 - loss: 1.3023
``` - + ```
-174/183 [===========================>..] - ETA: 2:07 - loss: 1.2746 - accuracy: 0.4447 + 174/183 ━━━━━━━━━━━━━━━━━━━━ 2:06 14s/step - accuracy: 0.4109 - loss: 1.3018
``` - + ```
-175/183 [===========================>..] - ETA: 1:53 - loss: 1.2730 - accuracy: 0.4457 + 175/183 ━━━━━━━━━━━━━━━━━━━━ 1:52 14s/step - accuracy: 0.4113 - loss: 1.3012
``` - + ```
-176/183 [===========================>..] - ETA: 1:39 - loss: 1.2705 - accuracy: 0.4489 + 176/183 ━━━━━━━━━━━━━━━━━━━━ 1:38 14s/step - accuracy: 0.4118 - loss: 1.3007
``` - + ```
-177/183 [============================>.] - ETA: 1:24 - loss: 1.2696 - accuracy: 0.4492 + 177/183 ━━━━━━━━━━━━━━━━━━━━ 1:24 14s/step - accuracy: 0.4122 - loss: 1.3002
``` - + ```
-178/183 [============================>.] - ETA: 1:10 - loss: 1.2686 - accuracy: 0.4501 + 178/183 ━━━━━━━━━━━━━━━━━━━━ 1:10 14s/step - accuracy: 0.4126 - loss: 1.2996
``` - + ```
-179/183 [============================>.] - ETA: 56s - loss: 1.2679 - accuracy: 0.4511 + 179/183 ━━━━━━━━━━━━━━━━━━━━ 56s 14s/step - accuracy: 0.4131 - loss: 1.2991
``` - + ```
-180/183 [============================>.] - ETA: 42s - loss: 1.2671 - accuracy: 0.4521 + 180/183 ━━━━━━━━━━━━━━━━━━━━ 42s 14s/step - accuracy: 0.4135 - loss: 1.2986
``` - + ```
-181/183 [============================>.] - ETA: 28s - loss: 1.2666 - accuracy: 0.4523 + 181/183 ━━━━━━━━━━━━━━━━━━━━ 28s 14s/step - accuracy: 0.4139 - loss: 1.2981
``` - + ```
-182/183 [============================>.] - ETA: 14s - loss: 1.2642 - accuracy: 0.4547 + 182/183 ━━━━━━━━━━━━━━━━━━━━ 14s 14s/step - accuracy: 0.4143 - loss: 1.2975
``` - + ```
-183/183 [==============================] - ETA: 0s - loss: 1.2631 - accuracy: 0.4556 + 183/183 ━━━━━━━━━━━━━━━━━━━━ 0s 14s/step - accuracy: 0.4147 - loss: 1.2970
``` - + ```
-183/183 [==============================] - 2748s 15s/step - loss: 1.2631 - accuracy: 0.4556 - val_loss: 0.9210 - val_accuracy: 0.7075 - lr: 2.9000e-06 + 183/183 ━━━━━━━━━━━━━━━━━━━━ 2725s 15s/step - accuracy: 0.4151 - loss: 1.2965 - val_accuracy: 0.7225 - val_loss: 0.8847 - learning_rate: 2.9000e-06
@@ -3583,1288 +3306,1288 @@ Epoch 3/5 ```
- 1/183 [..............................] - ETA: 46:11 - loss: 1.1680 - accuracy: 0.3750 + 1/183 ━━━━━━━━━━━━━━━━━━━━ 44:47 15s/step - accuracy: 0.7500 - loss: 0.9652
``` - + ```
- 2/183 [..............................] - ETA: 43:28 - loss: 1.0826 - accuracy: 0.5625 + 2/183 ━━━━━━━━━━━━━━━━━━━━ 43:26 14s/step - accuracy: 0.7500 - loss: 0.9399
``` - + ```
- 3/183 [..............................] - ETA: 43:21 - loss: 1.1881 - accuracy: 0.5417 + 3/183 ━━━━━━━━━━━━━━━━━━━━ 43:07 14s/step - accuracy: 0.7500 - loss: 0.9463
``` - + ```
- 4/183 [..............................] - ETA: 43:06 - loss: 1.1313 - accuracy: 0.5625 + 4/183 ━━━━━━━━━━━━━━━━━━━━ 42:38 14s/step - accuracy: 0.7578 - loss: 0.9380
``` - + ```
- 5/183 [..............................] - ETA: 42:50 - loss: 1.1148 - accuracy: 0.6000 + 5/183 ━━━━━━━━━━━━━━━━━━━━ 42:16 14s/step - accuracy: 0.7613 - loss: 0.9331
``` - + ```
- 6/183 [..............................] - ETA: 42:32 - loss: 1.0660 - accuracy: 0.6458 + 6/183 ━━━━━━━━━━━━━━━━━━━━ 41:57 14s/step - accuracy: 0.7559 - loss: 0.9292
``` - + ```
- 7/183 [>.............................] - ETA: 42:14 - loss: 1.0620 - accuracy: 0.6429 + 7/183 ━━━━━━━━━━━━━━━━━━━━ 41:35 14s/step - accuracy: 0.7500 - loss: 0.9297
``` - + ```
- 8/183 [>.............................] - ETA: 41:56 - loss: 1.0516 - accuracy: 0.6562 + 8/183 ━━━━━━━━━━━━━━━━━━━━ 41:17 14s/step - accuracy: 0.7480 - loss: 0.9275
``` - + ```
- 9/183 [>.............................] - ETA: 41:40 - loss: 1.0623 - accuracy: 0.6250 + 9/183 ━━━━━━━━━━━━━━━━━━━━ 41:01 14s/step - accuracy: 0.7421 - loss: 0.9286
``` - + ```
- 10/183 [>.............................] - ETA: 41:28 - loss: 1.0573 - accuracy: 0.6250 + 10/183 ━━━━━━━━━━━━━━━━━━━━ 40:45 14s/step - accuracy: 0.7366 - loss: 0.9294
``` - + ```
- 11/183 [>.............................] - ETA: 41:12 - loss: 1.0500 - accuracy: 0.6364 + 11/183 ━━━━━━━━━━━━━━━━━━━━ 40:29 14s/step - accuracy: 0.7316 - loss: 0.9302
``` - + ```
- 12/183 [>.............................] - ETA: 40:55 - loss: 1.0126 - accuracy: 0.6667 + 12/183 ━━━━━━━━━━━━━━━━━━━━ 40:11 14s/step - accuracy: 0.7288 - loss: 0.9287
``` - + ```
- 13/183 [=>............................] - ETA: 40:39 - loss: 1.0203 - accuracy: 0.6538 + 13/183 ━━━━━━━━━━━━━━━━━━━━ 39:55 14s/step - accuracy: 0.7260 - loss: 0.9278
``` - + ```
- 14/183 [=>............................] - ETA: 40:22 - loss: 1.0258 - accuracy: 0.6518 + 14/183 ━━━━━━━━━━━━━━━━━━━━ 39:39 14s/step - accuracy: 0.7239 - loss: 0.9275
``` - + ```
- 15/183 [=>............................] - ETA: 40:06 - loss: 1.0312 - accuracy: 0.6583 + 15/183 ━━━━━━━━━━━━━━━━━━━━ 39:22 14s/step - accuracy: 0.7223 - loss: 0.9271
``` - + ```
- 16/183 [=>............................] - ETA: 39:50 - loss: 1.0269 - accuracy: 0.6562 + 16/183 ━━━━━━━━━━━━━━━━━━━━ 39:07 14s/step - accuracy: 0.7201 - loss: 0.9277
``` - + ```
- 17/183 [=>............................] - ETA: 39:33 - loss: 1.0329 - accuracy: 0.6618 + 17/183 ━━━━━━━━━━━━━━━━━━━━ 38:53 14s/step - accuracy: 0.7184 - loss: 0.9287
``` - + ```
- 18/183 [=>............................] - ETA: 39:18 - loss: 1.0382 - accuracy: 0.6667 + 18/183 ━━━━━━━━━━━━━━━━━━━━ 38:37 14s/step - accuracy: 0.7155 - loss: 0.9305
``` - + ```
- 19/183 [==>...........................] - ETA: 39:03 - loss: 1.0372 - accuracy: 0.6579 + 19/183 ━━━━━━━━━━━━━━━━━━━━ 38:24 14s/step - accuracy: 0.7125 - loss: 0.9324
``` - + ```
- 20/183 [==>...........................] - ETA: 38:48 - loss: 1.0363 - accuracy: 0.6500 + 20/183 ━━━━━━━━━━━━━━━━━━━━ 38:10 14s/step - accuracy: 0.7097 - loss: 0.9338
``` - + ```
- 21/183 [==>...........................] - ETA: 38:33 - loss: 1.0430 - accuracy: 0.6369 + 21/183 ━━━━━━━━━━━━━━━━━━━━ 37:56 14s/step - accuracy: 0.7062 - loss: 0.9355
``` - + ```
- 22/183 [==>...........................] - ETA: 38:18 - loss: 1.0392 - accuracy: 0.6420 + 22/183 ━━━━━━━━━━━━━━━━━━━━ 37:42 14s/step - accuracy: 0.7033 - loss: 0.9369
``` - + ```
- 23/183 [==>...........................] - ETA: 38:03 - loss: 1.0438 - accuracy: 0.6250 + 23/183 ━━━━━━━━━━━━━━━━━━━━ 37:28 14s/step - accuracy: 0.7009 - loss: 0.9383
``` - + ```
- 24/183 [==>...........................] - ETA: 37:49 - loss: 1.0405 - accuracy: 0.6302 + 24/183 ━━━━━━━━━━━━━━━━━━━━ 37:13 14s/step - accuracy: 0.6988 - loss: 0.9392
``` - + ```
- 25/183 [===>..........................] - ETA: 37:34 - loss: 1.0383 - accuracy: 0.6250 + 25/183 ━━━━━━━━━━━━━━━━━━━━ 36:58 14s/step - accuracy: 0.6970 - loss: 0.9399
``` - + ```
- 26/183 [===>..........................] - ETA: 37:20 - loss: 1.0392 - accuracy: 0.6250 + 26/183 ━━━━━━━━━━━━━━━━━━━━ 36:44 14s/step - accuracy: 0.6954 - loss: 0.9404
``` - + ```
- 27/183 [===>..........................] - ETA: 37:05 - loss: 1.0422 - accuracy: 0.6204 + 27/183 ━━━━━━━━━━━━━━━━━━━━ 36:29 14s/step - accuracy: 0.6938 - loss: 0.9411
``` - + ```
- 28/183 [===>..........................] - ETA: 36:50 - loss: 1.0441 - accuracy: 0.6205 + 28/183 ━━━━━━━━━━━━━━━━━━━━ 36:15 14s/step - accuracy: 0.6920 - loss: 0.9420
``` - + ```
- 29/183 [===>..........................] - ETA: 36:35 - loss: 1.0482 - accuracy: 0.6164 + 29/183 ━━━━━━━━━━━━━━━━━━━━ 36:00 14s/step - accuracy: 0.6901 - loss: 0.9428
``` - + ```
- 30/183 [===>..........................] - ETA: 36:21 - loss: 1.0541 - accuracy: 0.6042 + 30/183 ━━━━━━━━━━━━━━━━━━━━ 35:46 14s/step - accuracy: 0.6884 - loss: 0.9439
``` - + ```
- 31/183 [====>.........................] - ETA: 36:06 - loss: 1.0507 - accuracy: 0.6089 + 31/183 ━━━━━━━━━━━━━━━━━━━━ 35:31 14s/step - accuracy: 0.6867 - loss: 0.9449
``` - + ```
- 32/183 [====>.........................] - ETA: 35:52 - loss: 1.0431 - accuracy: 0.6211 + 32/183 ━━━━━━━━━━━━━━━━━━━━ 35:16 14s/step - accuracy: 0.6851 - loss: 0.9457
``` - + ```
- 33/183 [====>.........................] - ETA: 35:37 - loss: 1.0418 - accuracy: 0.6250 + 33/183 ━━━━━━━━━━━━━━━━━━━━ 35:02 14s/step - accuracy: 0.6837 - loss: 0.9463
``` - + ```
- 34/183 [====>.........................] - ETA: 35:22 - loss: 1.0382 - accuracy: 0.6250 + 34/183 ━━━━━━━━━━━━━━━━━━━━ 34:48 14s/step - accuracy: 0.6822 - loss: 0.9470
``` - + ```
- 35/183 [====>.........................] - ETA: 35:08 - loss: 1.0369 - accuracy: 0.6250 + 35/183 ━━━━━━━━━━━━━━━━━━━━ 34:33 14s/step - accuracy: 0.6806 - loss: 0.9476
``` - + ```
- 36/183 [====>.........................] - ETA: 34:53 - loss: 1.0396 - accuracy: 0.6250 + 36/183 ━━━━━━━━━━━━━━━━━━━━ 34:20 14s/step - accuracy: 0.6791 - loss: 0.9484
``` - + ```
- 37/183 [=====>........................] - ETA: 34:38 - loss: 1.0396 - accuracy: 0.6216 + 37/183 ━━━━━━━━━━━━━━━━━━━━ 34:05 14s/step - accuracy: 0.6777 - loss: 0.9491
``` - + ```
- 38/183 [=====>........................] - ETA: 34:24 - loss: 1.0478 - accuracy: 0.6118 + 38/183 ━━━━━━━━━━━━━━━━━━━━ 33:50 14s/step - accuracy: 0.6764 - loss: 0.9498
``` - + ```
- 39/183 [=====>........................] - ETA: 34:09 - loss: 1.0412 - accuracy: 0.6154 + 39/183 ━━━━━━━━━━━━━━━━━━━━ 33:37 14s/step - accuracy: 0.6752 - loss: 0.9504
``` - + ```
- 40/183 [=====>........................] - ETA: 33:55 - loss: 1.0397 - accuracy: 0.6156 + 40/183 ━━━━━━━━━━━━━━━━━━━━ 33:22 14s/step - accuracy: 0.6739 - loss: 0.9509
``` - + ```
- 41/183 [=====>........................] - ETA: 33:41 - loss: 1.0378 - accuracy: 0.6159 + 41/183 ━━━━━━━━━━━━━━━━━━━━ 33:08 14s/step - accuracy: 0.6726 - loss: 0.9514
``` - + ```
- 42/183 [=====>........................] - ETA: 33:26 - loss: 1.0331 - accuracy: 0.6190 + 42/183 ━━━━━━━━━━━━━━━━━━━━ 32:54 14s/step - accuracy: 0.6715 - loss: 0.9519
``` - + ```
- 43/183 [======>.......................] - ETA: 33:13 - loss: 1.0287 - accuracy: 0.6192 + 43/183 ━━━━━━━━━━━━━━━━━━━━ 32:40 14s/step - accuracy: 0.6703 - loss: 0.9525
``` - + ```
- 44/183 [======>.......................] - ETA: 32:58 - loss: 1.0366 - accuracy: 0.6136 + 44/183 ━━━━━━━━━━━━━━━━━━━━ 32:26 14s/step - accuracy: 0.6689 - loss: 0.9533
``` - + ```
- 45/183 [======>.......................] - ETA: 32:43 - loss: 1.0337 - accuracy: 0.6167 + 45/183 ━━━━━━━━━━━━━━━━━━━━ 32:12 14s/step - accuracy: 0.6678 - loss: 0.9540
``` - + ```
- 46/183 [======>.......................] - ETA: 32:29 - loss: 1.0309 - accuracy: 0.6196 + 46/183 ━━━━━━━━━━━━━━━━━━━━ 31:58 14s/step - accuracy: 0.6666 - loss: 0.9547
``` - + ```
- 47/183 [======>.......................] - ETA: 32:15 - loss: 1.0355 - accuracy: 0.6144 + 47/183 ━━━━━━━━━━━━━━━━━━━━ 31:45 14s/step - accuracy: 0.6654 - loss: 0.9553
``` - + ```
- 48/183 [======>.......................] - ETA: 32:00 - loss: 1.0365 - accuracy: 0.6146 + 48/183 ━━━━━━━━━━━━━━━━━━━━ 31:32 14s/step - accuracy: 0.6644 - loss: 0.9558
``` - + ```
- 49/183 [=======>......................] - ETA: 31:46 - loss: 1.0344 - accuracy: 0.6173 + 49/183 ━━━━━━━━━━━━━━━━━━━━ 31:18 14s/step - accuracy: 0.6635 - loss: 0.9563
``` - + ```
- 50/183 [=======>......................] - ETA: 31:32 - loss: 1.0364 - accuracy: 0.6175 + 50/183 ━━━━━━━━━━━━━━━━━━━━ 31:04 14s/step - accuracy: 0.6625 - loss: 0.9568
``` - + ```
- 51/183 [=======>......................] - ETA: 31:17 - loss: 1.0385 - accuracy: 0.6152 + 51/183 ━━━━━━━━━━━━━━━━━━━━ 30:50 14s/step - accuracy: 0.6616 - loss: 0.9573
``` - + ```
- 52/183 [=======>......................] - ETA: 31:03 - loss: 1.0415 - accuracy: 0.6106 + 52/183 ━━━━━━━━━━━━━━━━━━━━ 30:36 14s/step - accuracy: 0.6606 - loss: 0.9580
``` - + ```
- 53/183 [=======>......................] - ETA: 30:50 - loss: 1.0360 - accuracy: 0.6156 + 53/183 ━━━━━━━━━━━━━━━━━━━━ 30:21 14s/step - accuracy: 0.6596 - loss: 0.9585
``` - + ```
- 54/183 [=======>......................] - ETA: 30:36 - loss: 1.0329 - accuracy: 0.6181 + 54/183 ━━━━━━━━━━━━━━━━━━━━ 30:07 14s/step - accuracy: 0.6586 - loss: 0.9590
``` - + ```
- 55/183 [========>.....................] - ETA: 30:21 - loss: 1.0340 - accuracy: 0.6136 + 55/183 ━━━━━━━━━━━━━━━━━━━━ 29:53 14s/step - accuracy: 0.6577 - loss: 0.9596
``` - + ```
- 56/183 [========>.....................] - ETA: 30:07 - loss: 1.0357 - accuracy: 0.6094 + 56/183 ━━━━━━━━━━━━━━━━━━━━ 29:39 14s/step - accuracy: 0.6568 - loss: 0.9602
``` - + ```
- 57/183 [========>.....................] - ETA: 29:53 - loss: 1.0389 - accuracy: 0.6096 + 57/183 ━━━━━━━━━━━━━━━━━━━━ 29:25 14s/step - accuracy: 0.6559 - loss: 0.9608
``` - + ```
- 58/183 [========>.....................] - ETA: 29:38 - loss: 1.0403 - accuracy: 0.6099 + 58/183 ━━━━━━━━━━━━━━━━━━━━ 29:11 14s/step - accuracy: 0.6551 - loss: 0.9613
``` - + ```
- 59/183 [========>.....................] - ETA: 29:24 - loss: 1.0437 - accuracy: 0.6038 + 59/183 ━━━━━━━━━━━━━━━━━━━━ 28:57 14s/step - accuracy: 0.6541 - loss: 0.9619
``` - + ```
- 60/183 [========>.....................] - ETA: 29:09 - loss: 1.0459 - accuracy: 0.6042 + 60/183 ━━━━━━━━━━━━━━━━━━━━ 28:43 14s/step - accuracy: 0.6532 - loss: 0.9625
``` - + ```
- 61/183 [=========>....................] - ETA: 28:55 - loss: 1.0509 - accuracy: 0.6025 + 61/183 ━━━━━━━━━━━━━━━━━━━━ 28:29 14s/step - accuracy: 0.6524 - loss: 0.9632
``` - + ```
- 62/183 [=========>....................] - ETA: 28:41 - loss: 1.0511 - accuracy: 0.5988 + 62/183 ━━━━━━━━━━━━━━━━━━━━ 28:15 14s/step - accuracy: 0.6516 - loss: 0.9637
``` - + ```
- 63/183 [=========>....................] - ETA: 28:27 - loss: 1.0479 - accuracy: 0.5992 + 63/183 ━━━━━━━━━━━━━━━━━━━━ 28:01 14s/step - accuracy: 0.6508 - loss: 0.9642
``` - + ```
- 64/183 [=========>....................] - ETA: 28:12 - loss: 1.0548 - accuracy: 0.5977 + 64/183 ━━━━━━━━━━━━━━━━━━━━ 27:47 14s/step - accuracy: 0.6501 - loss: 0.9648
``` - + ```
- 65/183 [=========>....................] - ETA: 27:58 - loss: 1.0570 - accuracy: 0.5962 + 65/183 ━━━━━━━━━━━━━━━━━━━━ 27:33 14s/step - accuracy: 0.6493 - loss: 0.9653
``` - + ```
- 66/183 [=========>....................] - ETA: 27:44 - loss: 1.0555 - accuracy: 0.5966 + 66/183 ━━━━━━━━━━━━━━━━━━━━ 27:18 14s/step - accuracy: 0.6486 - loss: 0.9659
``` - + ```
- 67/183 [=========>....................] - ETA: 27:29 - loss: 1.0566 - accuracy: 0.5951 + 67/183 ━━━━━━━━━━━━━━━━━━━━ 27:04 14s/step - accuracy: 0.6479 - loss: 0.9664
``` - + ```
- 68/183 [==========>...................] - ETA: 27:15 - loss: 1.0571 - accuracy: 0.5938 + 68/183 ━━━━━━━━━━━━━━━━━━━━ 26:50 14s/step - accuracy: 0.6472 - loss: 0.9669
``` - + ```
- 69/183 [==========>...................] - ETA: 27:01 - loss: 1.0523 - accuracy: 0.5978 + 69/183 ━━━━━━━━━━━━━━━━━━━━ 26:37 14s/step - accuracy: 0.6465 - loss: 0.9673
``` - + ```
- 70/183 [==========>...................] - ETA: 26:47 - loss: 1.0483 - accuracy: 0.6000 + 70/183 ━━━━━━━━━━━━━━━━━━━━ 26:22 14s/step - accuracy: 0.6460 - loss: 0.9676
``` - + ```
- 71/183 [==========>...................] - ETA: 26:32 - loss: 1.0489 - accuracy: 0.5968 + 71/183 ━━━━━━━━━━━━━━━━━━━━ 26:08 14s/step - accuracy: 0.6454 - loss: 0.9679
``` - + ```
- 72/183 [==========>...................] - ETA: 26:18 - loss: 1.0491 - accuracy: 0.5955 + 72/183 ━━━━━━━━━━━━━━━━━━━━ 25:54 14s/step - accuracy: 0.6448 - loss: 0.9683
``` - + ```
- 73/183 [==========>...................] - ETA: 26:04 - loss: 1.0486 - accuracy: 0.5959 + 73/183 ━━━━━━━━━━━━━━━━━━━━ 25:40 14s/step - accuracy: 0.6442 - loss: 0.9686
``` - + ```
- 74/183 [===========>..................] - ETA: 25:49 - loss: 1.0532 - accuracy: 0.5912 + 74/183 ━━━━━━━━━━━━━━━━━━━━ 25:26 14s/step - accuracy: 0.6437 - loss: 0.9689
``` - + ```
- 75/183 [===========>..................] - ETA: 25:35 - loss: 1.0535 - accuracy: 0.5917 + 75/183 ━━━━━━━━━━━━━━━━━━━━ 25:12 14s/step - accuracy: 0.6432 - loss: 0.9692
``` - + ```
- 76/183 [===========>..................] - ETA: 25:21 - loss: 1.0568 - accuracy: 0.5888 + 76/183 ━━━━━━━━━━━━━━━━━━━━ 24:58 14s/step - accuracy: 0.6426 - loss: 0.9695
``` - + ```
- 77/183 [===========>..................] - ETA: 25:06 - loss: 1.0600 - accuracy: 0.5844 + 77/183 ━━━━━━━━━━━━━━━━━━━━ 24:44 14s/step - accuracy: 0.6420 - loss: 0.9699
``` - + ```
- 78/183 [===========>..................] - ETA: 24:52 - loss: 1.0557 - accuracy: 0.5865 + 78/183 ━━━━━━━━━━━━━━━━━━━━ 24:30 14s/step - accuracy: 0.6415 - loss: 0.9703
``` - + ```
- 79/183 [===========>..................] - ETA: 24:38 - loss: 1.0538 - accuracy: 0.5870 + 79/183 ━━━━━━━━━━━━━━━━━━━━ 24:16 14s/step - accuracy: 0.6409 - loss: 0.9706
``` - + ```
- 80/183 [============>.................] - ETA: 24:23 - loss: 1.0543 - accuracy: 0.5844 + 80/183 ━━━━━━━━━━━━━━━━━━━━ 24:02 14s/step - accuracy: 0.6403 - loss: 0.9710
``` - + ```
- 81/183 [============>.................] - ETA: 24:09 - loss: 1.0528 - accuracy: 0.5864 + 81/183 ━━━━━━━━━━━━━━━━━━━━ 23:48 14s/step - accuracy: 0.6398 - loss: 0.9714
``` - + ```
- 82/183 [============>.................] - ETA: 23:55 - loss: 1.0547 - accuracy: 0.5838 + 82/183 ━━━━━━━━━━━━━━━━━━━━ 23:34 14s/step - accuracy: 0.6392 - loss: 0.9718
``` - + ```
- 83/183 [============>.................] - ETA: 23:41 - loss: 1.0558 - accuracy: 0.5798 + 83/183 ━━━━━━━━━━━━━━━━━━━━ 23:20 14s/step - accuracy: 0.6386 - loss: 0.9722
``` - + ```
- 84/183 [============>.................] - ETA: 23:26 - loss: 1.0564 - accuracy: 0.5804 + 84/183 ━━━━━━━━━━━━━━━━━━━━ 23:06 14s/step - accuracy: 0.6380 - loss: 0.9726
``` - + ```
- 85/183 [============>.................] - ETA: 23:12 - loss: 1.0548 - accuracy: 0.5794 + 85/183 ━━━━━━━━━━━━━━━━━━━━ 22:52 14s/step - accuracy: 0.6374 - loss: 0.9729
``` - + ```
- 86/183 [=============>................] - ETA: 22:58 - loss: 1.0542 - accuracy: 0.5770 + 86/183 ━━━━━━━━━━━━━━━━━━━━ 22:38 14s/step - accuracy: 0.6368 - loss: 0.9734
``` - + ```
- 87/183 [=============>................] - ETA: 22:44 - loss: 1.0569 - accuracy: 0.5761 + 87/183 ━━━━━━━━━━━━━━━━━━━━ 22:25 14s/step - accuracy: 0.6362 - loss: 0.9738
``` - + ```
- 88/183 [=============>................] - ETA: 22:29 - loss: 1.0551 - accuracy: 0.5781 + 88/183 ━━━━━━━━━━━━━━━━━━━━ 22:11 14s/step - accuracy: 0.6357 - loss: 0.9741
``` - + ```
- 89/183 [=============>................] - ETA: 22:15 - loss: 1.0525 - accuracy: 0.5815 + 89/183 ━━━━━━━━━━━━━━━━━━━━ 21:57 14s/step - accuracy: 0.6352 - loss: 0.9745
``` - + ```
- 90/183 [=============>................] - ETA: 22:01 - loss: 1.0552 - accuracy: 0.5778 + 90/183 ━━━━━━━━━━━━━━━━━━━━ 21:43 14s/step - accuracy: 0.6347 - loss: 0.9748
``` - + ```
- 91/183 [=============>................] - ETA: 21:47 - loss: 1.0529 - accuracy: 0.5797 + 91/183 ━━━━━━━━━━━━━━━━━━━━ 21:29 14s/step - accuracy: 0.6341 - loss: 0.9752
``` - + ```
- 92/183 [==============>...............] - ETA: 21:32 - loss: 1.0501 - accuracy: 0.5802 + 92/183 ━━━━━━━━━━━━━━━━━━━━ 21:15 14s/step - accuracy: 0.6336 - loss: 0.9755
``` - + ```
- 93/183 [==============>...............] - ETA: 21:18 - loss: 1.0496 - accuracy: 0.5793 + 93/183 ━━━━━━━━━━━━━━━━━━━━ 21:02 14s/step - accuracy: 0.6330 - loss: 0.9759
``` - + ```
- 94/183 [==============>...............] - ETA: 21:04 - loss: 1.0512 - accuracy: 0.5798 + 94/183 ━━━━━━━━━━━━━━━━━━━━ 20:48 14s/step - accuracy: 0.6325 - loss: 0.9762
``` - + ```
- 95/183 [==============>...............] - ETA: 20:49 - loss: 1.0518 - accuracy: 0.5803 + 95/183 ━━━━━━━━━━━━━━━━━━━━ 20:34 14s/step - accuracy: 0.6319 - loss: 0.9766
``` - + ```
- 96/183 [==============>...............] - ETA: 20:35 - loss: 1.0520 - accuracy: 0.5807 + 96/183 ━━━━━━━━━━━━━━━━━━━━ 20:20 14s/step - accuracy: 0.6314 - loss: 0.9770
``` - + ```
- 97/183 [==============>...............] - ETA: 20:21 - loss: 1.0550 - accuracy: 0.5812 + 97/183 ━━━━━━━━━━━━━━━━━━━━ 20:06 14s/step - accuracy: 0.6309 - loss: 0.9773
``` - + ```
- 98/183 [===============>..............] - ETA: 20:07 - loss: 1.0576 - accuracy: 0.5791 + 98/183 ━━━━━━━━━━━━━━━━━━━━ 19:52 14s/step - accuracy: 0.6303 - loss: 0.9777
``` - + ```
- 99/183 [===============>..............] - ETA: 19:53 - loss: 1.0571 - accuracy: 0.5770 + 99/183 ━━━━━━━━━━━━━━━━━━━━ 19:38 14s/step - accuracy: 0.6298 - loss: 0.9780
``` - + ```
-100/183 [===============>..............] - ETA: 19:38 - loss: 1.0547 - accuracy: 0.5775 + 100/183 ━━━━━━━━━━━━━━━━━━━━ 19:24 14s/step - accuracy: 0.6293 - loss: 0.9784
``` - + ```
-101/183 [===============>..............] - ETA: 19:24 - loss: 1.0547 - accuracy: 0.5767 + 101/183 ━━━━━━━━━━━━━━━━━━━━ 19:10 14s/step - accuracy: 0.6288 - loss: 0.9787
``` - + ```
-102/183 [===============>..............] - ETA: 19:10 - loss: 1.0536 - accuracy: 0.5748 + 102/183 ━━━━━━━━━━━━━━━━━━━━ 18:56 14s/step - accuracy: 0.6284 - loss: 0.9790
``` - + ```
-103/183 [===============>..............] - ETA: 18:56 - loss: 1.0514 - accuracy: 0.5752 + 103/183 ━━━━━━━━━━━━━━━━━━━━ 18:43 14s/step - accuracy: 0.6279 - loss: 0.9793
``` - + ```
-104/183 [================>.............] - ETA: 18:41 - loss: 1.0495 - accuracy: 0.5769 + 104/183 ━━━━━━━━━━━━━━━━━━━━ 18:29 14s/step - accuracy: 0.6275 - loss: 0.9796
``` - + ```
-105/183 [================>.............] - ETA: 18:27 - loss: 1.0462 - accuracy: 0.5774 + 105/183 ━━━━━━━━━━━━━━━━━━━━ 18:15 14s/step - accuracy: 0.6271 - loss: 0.9798
``` - + ```
-106/183 [================>.............] - ETA: 18:13 - loss: 1.0451 - accuracy: 0.5790 + 106/183 ━━━━━━━━━━━━━━━━━━━━ 18:01 14s/step - accuracy: 0.6267 - loss: 0.9801
``` - + ```
-107/183 [================>.............] - ETA: 17:59 - loss: 1.0434 - accuracy: 0.5818 + 107/183 ━━━━━━━━━━━━━━━━━━━━ 17:47 14s/step - accuracy: 0.6263 - loss: 0.9803
``` - + ```
-108/183 [================>.............] - ETA: 17:44 - loss: 1.0424 - accuracy: 0.5833 + 108/183 ━━━━━━━━━━━━━━━━━━━━ 17:34 14s/step - accuracy: 0.6259 - loss: 0.9805
``` - + ```
-109/183 [================>.............] - ETA: 17:30 - loss: 1.0421 - accuracy: 0.5826 + 109/183 ━━━━━━━━━━━━━━━━━━━━ 17:20 14s/step - accuracy: 0.6255 - loss: 0.9807
``` - + ```
-110/183 [=================>............] - ETA: 17:16 - loss: 1.0409 - accuracy: 0.5830 + 110/183 ━━━━━━━━━━━━━━━━━━━━ 17:06 14s/step - accuracy: 0.6251 - loss: 0.9809
``` - + ```
-111/183 [=================>............] - ETA: 17:02 - loss: 1.0415 - accuracy: 0.5833 + 111/183 ━━━━━━━━━━━━━━━━━━━━ 16:52 14s/step - accuracy: 0.6247 - loss: 0.9811
``` - + ```
-112/183 [=================>............] - ETA: 16:47 - loss: 1.0403 - accuracy: 0.5837 + 112/183 ━━━━━━━━━━━━━━━━━━━━ 16:38 14s/step - accuracy: 0.6244 - loss: 0.9813
``` - + ```
-113/183 [=================>............] - ETA: 16:33 - loss: 1.0377 - accuracy: 0.5852 + 113/183 ━━━━━━━━━━━━━━━━━━━━ 16:24 14s/step - accuracy: 0.6240 - loss: 0.9815
``` - + ```
-114/183 [=================>............] - ETA: 16:19 - loss: 1.0367 - accuracy: 0.5866 + 114/183 ━━━━━━━━━━━━━━━━━━━━ 16:10 14s/step - accuracy: 0.6237 - loss: 0.9816
``` - + ```
-115/183 [=================>............] - ETA: 16:05 - loss: 1.0357 - accuracy: 0.5880 + 115/183 ━━━━━━━━━━━━━━━━━━━━ 15:56 14s/step - accuracy: 0.6233 - loss: 0.9818
``` - + ```
-116/183 [==================>...........] - ETA: 15:50 - loss: 1.0347 - accuracy: 0.5884 + 116/183 ━━━━━━━━━━━━━━━━━━━━ 15:42 14s/step - accuracy: 0.6230 - loss: 0.9819
``` - + ```
-117/183 [==================>...........] - ETA: 15:36 - loss: 1.0329 - accuracy: 0.5897 + 117/183 ━━━━━━━━━━━━━━━━━━━━ 15:28 14s/step - accuracy: 0.6227 - loss: 0.9820
``` - + ```
-118/183 [==================>...........] - ETA: 15:22 - loss: 1.0314 - accuracy: 0.5900 + 118/183 ━━━━━━━━━━━━━━━━━━━━ 15:14 14s/step - accuracy: 0.6224 - loss: 0.9821
``` - + ```
-119/183 [==================>...........] - ETA: 15:08 - loss: 1.0309 - accuracy: 0.5903 + 119/183 ━━━━━━━━━━━━━━━━━━━━ 15:00 14s/step - accuracy: 0.6221 - loss: 0.9822
``` - + ```
-120/183 [==================>...........] - ETA: 14:54 - loss: 1.0273 - accuracy: 0.5927 + 120/183 ━━━━━━━━━━━━━━━━━━━━ 14:46 14s/step - accuracy: 0.6219 - loss: 0.9823
``` - + ```
-121/183 [==================>...........] - ETA: 14:39 - loss: 1.0271 - accuracy: 0.5919 + 121/183 ━━━━━━━━━━━━━━━━━━━━ 14:32 14s/step - accuracy: 0.6216 - loss: 0.9824
``` - + ```
-122/183 [===================>..........] - ETA: 14:25 - loss: 1.0277 - accuracy: 0.5922 + 122/183 ━━━━━━━━━━━━━━━━━━━━ 14:18 14s/step - accuracy: 0.6213 - loss: 0.9824
``` - + ```
-123/183 [===================>..........] - ETA: 14:11 - loss: 1.0252 - accuracy: 0.5925 + 123/183 ━━━━━━━━━━━━━━━━━━━━ 14:03 14s/step - accuracy: 0.6210 - loss: 0.9825
``` - + ```
-124/183 [===================>..........] - ETA: 13:57 - loss: 1.0260 - accuracy: 0.5927 + 124/183 ━━━━━━━━━━━━━━━━━━━━ 13:49 14s/step - accuracy: 0.6208 - loss: 0.9825
``` - + ```
-125/183 [===================>..........] - ETA: 13:42 - loss: 1.0269 - accuracy: 0.5930 + 125/183 ━━━━━━━━━━━━━━━━━━━━ 13:35 14s/step - accuracy: 0.6206 - loss: 0.9825
``` - + ```
-126/183 [===================>..........] - ETA: 13:28 - loss: 1.0241 - accuracy: 0.5942 + 126/183 ━━━━━━━━━━━━━━━━━━━━ 13:21 14s/step - accuracy: 0.6204 - loss: 0.9825
``` - + ```
-127/183 [===================>..........] - ETA: 13:14 - loss: 1.0223 - accuracy: 0.5965 + 127/183 ━━━━━━━━━━━━━━━━━━━━ 13:07 14s/step - accuracy: 0.6201 - loss: 0.9825
``` - + ```
-128/183 [===================>..........] - ETA: 13:00 - loss: 1.0215 - accuracy: 0.5947 + 128/183 ━━━━━━━━━━━━━━━━━━━━ 12:53 14s/step - accuracy: 0.6199 - loss: 0.9824
``` - + ```
-129/183 [====================>.........] - ETA: 12:46 - loss: 1.0225 - accuracy: 0.5940 + 129/183 ━━━━━━━━━━━━━━━━━━━━ 12:39 14s/step - accuracy: 0.6197 - loss: 0.9824
``` - + ```
-130/183 [====================>.........] - ETA: 12:31 - loss: 1.0200 - accuracy: 0.5962 + 130/183 ━━━━━━━━━━━━━━━━━━━━ 12:25 14s/step - accuracy: 0.6195 - loss: 0.9824
``` - + ```
-131/183 [====================>.........] - ETA: 12:17 - loss: 1.0190 - accuracy: 0.5964 + 131/183 ━━━━━━━━━━━━━━━━━━━━ 12:11 14s/step - accuracy: 0.6193 - loss: 0.9824
``` - + ```
-132/183 [====================>.........] - ETA: 12:03 - loss: 1.0178 - accuracy: 0.5975 + 132/183 ━━━━━━━━━━━━━━━━━━━━ 11:57 14s/step - accuracy: 0.6191 - loss: 0.9823
``` - + ```
-133/183 [====================>.........] - ETA: 11:49 - loss: 1.0159 - accuracy: 0.5987 + 133/183 ━━━━━━━━━━━━━━━━━━━━ 11:43 14s/step - accuracy: 0.6189 - loss: 0.9823
``` - + ```
-134/183 [====================>.........] - ETA: 11:35 - loss: 1.0160 - accuracy: 0.5989 + 134/183 ━━━━━━━━━━━━━━━━━━━━ 11:29 14s/step - accuracy: 0.6188 - loss: 0.9822
``` - + ```
-135/183 [=====================>........] - ETA: 11:20 - loss: 1.0147 - accuracy: 0.5991 + 135/183 ━━━━━━━━━━━━━━━━━━━━ 11:14 14s/step - accuracy: 0.6186 - loss: 0.9821
``` - + ```
-136/183 [=====================>........] - ETA: 11:06 - loss: 1.0153 - accuracy: 0.5993 + 136/183 ━━━━━━━━━━━━━━━━━━━━ 11:00 14s/step - accuracy: 0.6184 - loss: 0.9821
``` - + ```
-137/183 [=====================>........] - ETA: 10:52 - loss: 1.0184 - accuracy: 0.5976 + 137/183 ━━━━━━━━━━━━━━━━━━━━ 10:46 14s/step - accuracy: 0.6182 - loss: 0.9821
``` - + ```
-138/183 [=====================>........] - ETA: 10:38 - loss: 1.0174 - accuracy: 0.5978 + 138/183 ━━━━━━━━━━━━━━━━━━━━ 10:32 14s/step - accuracy: 0.6180 - loss: 0.9820
``` - + ```
-139/183 [=====================>........] - ETA: 10:24 - loss: 1.0192 - accuracy: 0.5980 + 139/183 ━━━━━━━━━━━━━━━━━━━━ 10:18 14s/step - accuracy: 0.6178 - loss: 0.9820
``` - + ```
-140/183 [=====================>........] - ETA: 10:09 - loss: 1.0221 - accuracy: 0.5955 + 140/183 ━━━━━━━━━━━━━━━━━━━━ 10:04 14s/step - accuracy: 0.6176 - loss: 0.9820
``` - + ```
-141/183 [======================>.......] - ETA: 9:55 - loss: 1.0244 - accuracy: 0.5931 + 141/183 ━━━━━━━━━━━━━━━━━━━━ 9:50 14s/step - accuracy: 0.6174 - loss: 0.9821
``` - + ```
-142/183 [======================>.......] - ETA: 9:41 - loss: 1.0228 - accuracy: 0.5951 + 142/183 ━━━━━━━━━━━━━━━━━━━━ 9:36 14s/step - accuracy: 0.6172 - loss: 0.9821
``` - + ```
-143/183 [======================>.......] - ETA: 9:27 - loss: 1.0211 - accuracy: 0.5970 + 143/183 ━━━━━━━━━━━━━━━━━━━━ 9:22 14s/step - accuracy: 0.6170 - loss: 0.9821
``` - + ```
-144/183 [======================>.......] - ETA: 9:13 - loss: 1.0235 - accuracy: 0.5946 + 144/183 ━━━━━━━━━━━━━━━━━━━━ 9:08 14s/step - accuracy: 0.6168 - loss: 0.9822
``` - + ```
-145/183 [======================>.......] - ETA: 8:59 - loss: 1.0241 - accuracy: 0.5940 + 145/183 ━━━━━━━━━━━━━━━━━━━━ 8:54 14s/step - accuracy: 0.6166 - loss: 0.9822
``` - + ```
-146/183 [======================>.......] - ETA: 8:44 - loss: 1.0228 - accuracy: 0.5950 + 146/183 ━━━━━━━━━━━━━━━━━━━━ 8:40 14s/step - accuracy: 0.6164 - loss: 0.9822
``` - + ```
-147/183 [=======================>......] - ETA: 8:30 - loss: 1.0229 - accuracy: 0.5961 + 147/183 ━━━━━━━━━━━━━━━━━━━━ 8:26 14s/step - accuracy: 0.6162 - loss: 0.9822
``` - + ```
-148/183 [=======================>......] - ETA: 8:16 - loss: 1.0204 - accuracy: 0.5980 + 148/183 ━━━━━━━━━━━━━━━━━━━━ 8:11 14s/step - accuracy: 0.6161 - loss: 0.9822
``` - + ```
-149/183 [=======================>......] - ETA: 8:02 - loss: 1.0193 - accuracy: 0.5990 + 149/183 ━━━━━━━━━━━━━━━━━━━━ 7:57 14s/step - accuracy: 0.6159 - loss: 0.9822
``` - + ```
-150/183 [=======================>......] - ETA: 7:48 - loss: 1.0173 - accuracy: 0.6000 + 150/183 ━━━━━━━━━━━━━━━━━━━━ 7:43 14s/step - accuracy: 0.6158 - loss: 0.9822
``` - + ```
-151/183 [=======================>......] - ETA: 7:33 - loss: 1.0190 - accuracy: 0.5993 + 151/183 ━━━━━━━━━━━━━━━━━━━━ 7:29 14s/step - accuracy: 0.6156 - loss: 0.9822
``` - + ```
-152/183 [=======================>......] - ETA: 7:19 - loss: 1.0233 - accuracy: 0.5979 + 152/183 ━━━━━━━━━━━━━━━━━━━━ 7:15 14s/step - accuracy: 0.6155 - loss: 0.9822
``` - + ```
-153/183 [========================>.....] - ETA: 7:05 - loss: 1.0230 - accuracy: 0.5972 + 153/183 ━━━━━━━━━━━━━━━━━━━━ 7:01 14s/step - accuracy: 0.6153 - loss: 0.9822
``` - + ```
-154/183 [========================>.....] - ETA: 6:51 - loss: 1.0230 - accuracy: 0.5974 + 154/183 ━━━━━━━━━━━━━━━━━━━━ 6:47 14s/step - accuracy: 0.6152 - loss: 0.9822
``` - + ```
-155/183 [========================>.....] - ETA: 6:37 - loss: 1.0223 - accuracy: 0.5992 + 155/183 ━━━━━━━━━━━━━━━━━━━━ 6:33 14s/step - accuracy: 0.6151 - loss: 0.9823
``` - + ```
-156/183 [========================>.....] - ETA: 6:22 - loss: 1.0204 - accuracy: 0.5994 + 156/183 ━━━━━━━━━━━━━━━━━━━━ 6:19 14s/step - accuracy: 0.6149 - loss: 0.9823
``` - + ```
-157/183 [========================>.....] - ETA: 6:08 - loss: 1.0204 - accuracy: 0.5987 + 157/183 ━━━━━━━━━━━━━━━━━━━━ 6:05 14s/step - accuracy: 0.6148 - loss: 0.9823
``` - + ```
-158/183 [========================>.....] - ETA: 5:54 - loss: 1.0201 - accuracy: 0.5965 + 158/183 ━━━━━━━━━━━━━━━━━━━━ 5:51 14s/step - accuracy: 0.6147 - loss: 0.9822
``` - + ```
-159/183 [=========================>....] - ETA: 5:40 - loss: 1.0199 - accuracy: 0.5975 + 159/183 ━━━━━━━━━━━━━━━━━━━━ 5:37 14s/step - accuracy: 0.6146 - loss: 0.9822
``` - + ```
-160/183 [=========================>....] - ETA: 5:26 - loss: 1.0168 - accuracy: 0.5992 + 160/183 ━━━━━━━━━━━━━━━━━━━━ 5:23 14s/step - accuracy: 0.6145 - loss: 0.9822
``` - + ```
-161/183 [=========================>....] - ETA: 5:12 - loss: 1.0155 - accuracy: 0.6009 + 161/183 ━━━━━━━━━━━━━━━━━━━━ 5:09 14s/step - accuracy: 0.6144 - loss: 0.9822
``` - + ```
-162/183 [=========================>....] - ETA: 4:57 - loss: 1.0131 - accuracy: 0.6019 + 162/183 ━━━━━━━━━━━━━━━━━━━━ 4:55 14s/step - accuracy: 0.6143 - loss: 0.9822
``` - + ```
-163/183 [=========================>....] - ETA: 4:43 - loss: 1.0144 - accuracy: 0.6020 + 163/183 ━━━━━━━━━━━━━━━━━━━━ 4:41 14s/step - accuracy: 0.6142 - loss: 0.9822
``` - + ```
-164/183 [=========================>....] - ETA: 4:29 - loss: 1.0145 - accuracy: 0.6021 + 164/183 ━━━━━━━━━━━━━━━━━━━━ 4:27 14s/step - accuracy: 0.6141 - loss: 0.9821
``` - + ```
-165/183 [==========================>...] - ETA: 4:15 - loss: 1.0138 - accuracy: 0.6030 + 165/183 ━━━━━━━━━━━━━━━━━━━━ 4:12 14s/step - accuracy: 0.6140 - loss: 0.9821
``` - + ```
-166/183 [==========================>...] - ETA: 4:01 - loss: 1.0127 - accuracy: 0.6032 + 166/183 ━━━━━━━━━━━━━━━━━━━━ 3:58 14s/step - accuracy: 0.6140 - loss: 0.9821
``` - + ```
-167/183 [==========================>...] - ETA: 3:46 - loss: 1.0127 - accuracy: 0.6018 + 167/183 ━━━━━━━━━━━━━━━━━━━━ 3:44 14s/step - accuracy: 0.6139 - loss: 0.9820
``` - + ```
-168/183 [==========================>...] - ETA: 3:32 - loss: 1.0102 - accuracy: 0.6027 + 168/183 ━━━━━━━━━━━━━━━━━━━━ 3:30 14s/step - accuracy: 0.6138 - loss: 0.9820
``` - + ```
-169/183 [==========================>...] - ETA: 3:18 - loss: 1.0119 - accuracy: 0.6013 + 169/183 ━━━━━━━━━━━━━━━━━━━━ 3:16 14s/step - accuracy: 0.6137 - loss: 0.9820
``` - + ```
-170/183 [==========================>...] - ETA: 3:04 - loss: 1.0113 - accuracy: 0.6007 + 170/183 ━━━━━━━━━━━━━━━━━━━━ 3:02 14s/step - accuracy: 0.6136 - loss: 0.9819
``` - + ```
-171/183 [===========================>..] - ETA: 2:50 - loss: 1.0134 - accuracy: 0.6001 + 171/183 ━━━━━━━━━━━━━━━━━━━━ 2:48 14s/step - accuracy: 0.6135 - loss: 0.9819
``` - + ```
-172/183 [===========================>..] - ETA: 2:36 - loss: 1.0117 - accuracy: 0.6010 + 172/183 ━━━━━━━━━━━━━━━━━━━━ 2:34 14s/step - accuracy: 0.6134 - loss: 0.9819
``` - + ```
-173/183 [===========================>..] - ETA: 2:21 - loss: 1.0100 - accuracy: 0.6012 + 173/183 ━━━━━━━━━━━━━━━━━━━━ 2:20 14s/step - accuracy: 0.6134 - loss: 0.9819
``` - + ```
-174/183 [===========================>..] - ETA: 2:07 - loss: 1.0084 - accuracy: 0.6020 + 174/183 ━━━━━━━━━━━━━━━━━━━━ 2:06 14s/step - accuracy: 0.6133 - loss: 0.9819
``` - + ```
-175/183 [===========================>..] - ETA: 1:53 - loss: 1.0060 - accuracy: 0.6043 + 175/183 ━━━━━━━━━━━━━━━━━━━━ 1:52 14s/step - accuracy: 0.6132 - loss: 0.9818
``` - + ```
-176/183 [===========================>..] - ETA: 1:39 - loss: 1.0041 - accuracy: 0.6044 + 176/183 ━━━━━━━━━━━━━━━━━━━━ 1:38 14s/step - accuracy: 0.6132 - loss: 0.9818
``` - + ```
-177/183 [============================>.] - ETA: 1:25 - loss: 1.0025 - accuracy: 0.6059 + 177/183 ━━━━━━━━━━━━━━━━━━━━ 1:24 14s/step - accuracy: 0.6131 - loss: 0.9817
``` - + ```
-178/183 [============================>.] - ETA: 1:10 - loss: 1.0034 - accuracy: 0.6053 + 178/183 ━━━━━━━━━━━━━━━━━━━━ 1:10 14s/step - accuracy: 0.6131 - loss: 0.9817
``` - + ```
-179/183 [============================>.] - ETA: 56s - loss: 1.0040 - accuracy: 0.6054 + 179/183 ━━━━━━━━━━━━━━━━━━━━ 56s 14s/step - accuracy: 0.6130 - loss: 0.9816
``` - + ```
-180/183 [============================>.] - ETA: 42s - loss: 1.0036 - accuracy: 0.6049 + 180/183 ━━━━━━━━━━━━━━━━━━━━ 42s 14s/step - accuracy: 0.6129 - loss: 0.9816
``` - + ```
-181/183 [============================>.] - ETA: 28s - loss: 1.0028 - accuracy: 0.6050 + 181/183 ━━━━━━━━━━━━━━━━━━━━ 28s 14s/step - accuracy: 0.6129 - loss: 0.9815
``` - + ```
-182/183 [============================>.] - ETA: 14s - loss: 1.0028 - accuracy: 0.6051 + 182/183 ━━━━━━━━━━━━━━━━━━━━ 14s 14s/step - accuracy: 0.6128 - loss: 0.9815
``` - + ```
-183/183 [==============================] - ETA: 0s - loss: 1.0013 - accuracy: 0.6052 + 183/183 ━━━━━━━━━━━━━━━━━━━━ 0s 14s/step - accuracy: 0.6128 - loss: 0.9815
``` - + ```
-183/183 [==============================] - 2755s 15s/step - loss: 1.0013 - accuracy: 0.6052 - val_loss: 0.7730 - val_accuracy: 0.7475 - lr: 4.8000e-06 + 183/183 ━━━━━━━━━━━━━━━━━━━━ 2722s 15s/step - accuracy: 0.6127 - loss: 0.9814 - val_accuracy: 0.7575 - val_loss: 0.7755 - learning_rate: 4.8000e-06
@@ -4874,1288 +4597,1288 @@ Epoch 4/5 ```
- 1/183 [..............................] - ETA: 45:34 - loss: 0.7885 - accuracy: 0.7500 + 1/183 ━━━━━━━━━━━━━━━━━━━━ 44:30 15s/step - accuracy: 0.7500 - loss: 0.8347
``` - + ```
- 2/183 [..............................] - ETA: 43:17 - loss: 0.8742 - accuracy: 0.6875 + 2/183 ━━━━━━━━━━━━━━━━━━━━ 42:33 14s/step - accuracy: 0.7188 - loss: 0.8343
``` - + ```
- 3/183 [..............................] - ETA: 43:02 - loss: 0.7851 - accuracy: 0.7083 + 3/183 ━━━━━━━━━━━━━━━━━━━━ 42:29 14s/step - accuracy: 0.7292 - loss: 0.7993
``` - + ```
- 4/183 [..............................] - ETA: 42:51 - loss: 0.9176 - accuracy: 0.6562 + 4/183 ━━━━━━━━━━━━━━━━━━━━ 42:09 14s/step - accuracy: 0.7266 - loss: 0.8006
``` - + ```
- 5/183 [..............................] - ETA: 42:39 - loss: 0.8677 - accuracy: 0.7000 + 5/183 ━━━━━━━━━━━━━━━━━━━━ 41:48 14s/step - accuracy: 0.7312 - loss: 0.8018
``` - + ```
- 6/183 [..............................] - ETA: 42:25 - loss: 0.8238 - accuracy: 0.7292 + 6/183 ━━━━━━━━━━━━━━━━━━━━ 41:35 14s/step - accuracy: 0.7344 - loss: 0.7997
``` - + ```
- 7/183 [>.............................] - ETA: 42:09 - loss: 0.8209 - accuracy: 0.7143 + 7/183 ━━━━━━━━━━━━━━━━━━━━ 41:19 14s/step - accuracy: 0.7366 - loss: 0.7965
``` - + ```
- 8/183 [>.............................] - ETA: 41:54 - loss: 0.8494 - accuracy: 0.6875 + 8/183 ━━━━━━━━━━━━━━━━━━━━ 41:02 14s/step - accuracy: 0.7363 - loss: 0.7959
``` - + ```
- 9/183 [>.............................] - ETA: 41:40 - loss: 0.8458 - accuracy: 0.6944 + 9/183 ━━━━━━━━━━━━━━━━━━━━ 40:48 14s/step - accuracy: 0.7378 - loss: 0.7934
``` - + ```
- 10/183 [>.............................] - ETA: 41:25 - loss: 0.8841 - accuracy: 0.6625 + 10/183 ━━━━━━━━━━━━━━━━━━━━ 40:30 14s/step - accuracy: 0.7378 - loss: 0.7934
``` - + ```
- 11/183 [>.............................] - ETA: 41:10 - loss: 0.8833 - accuracy: 0.6705 + 11/183 ━━━━━━━━━━━━━━━━━━━━ 40:12 14s/step - accuracy: 0.7369 - loss: 0.7948
``` - + ```
- 12/183 [>.............................] - ETA: 40:54 - loss: 0.8520 - accuracy: 0.6979 + 12/183 ━━━━━━━━━━━━━━━━━━━━ 39:55 14s/step - accuracy: 0.7371 - loss: 0.7945
``` - + ```
- 13/183 [=>............................] - ETA: 40:38 - loss: 0.8262 - accuracy: 0.7115 + 13/183 ━━━━━━━━━━━━━━━━━━━━ 39:39 14s/step - accuracy: 0.7381 - loss: 0.7932
``` - + ```
- 14/183 [=>............................] - ETA: 40:23 - loss: 0.8389 - accuracy: 0.7054 + 14/183 ━━━━━━━━━━━━━━━━━━━━ 39:23 14s/step - accuracy: 0.7389 - loss: 0.7922
``` - + ```
- 15/183 [=>............................] - ETA: 40:08 - loss: 0.8262 - accuracy: 0.7250 + 15/183 ━━━━━━━━━━━━━━━━━━━━ 39:08 14s/step - accuracy: 0.7397 - loss: 0.7905
``` - + ```
- 16/183 [=>............................] - ETA: 39:53 - loss: 0.8368 - accuracy: 0.7188 + 16/183 ━━━━━━━━━━━━━━━━━━━━ 38:53 14s/step - accuracy: 0.7408 - loss: 0.7893
``` - + ```
- 17/183 [=>............................] - ETA: 39:39 - loss: 0.8293 - accuracy: 0.7279 + 17/183 ━━━━━━━━━━━━━━━━━━━━ 38:37 14s/step - accuracy: 0.7418 - loss: 0.7880
``` - + ```
- 18/183 [=>............................] - ETA: 39:25 - loss: 0.8353 - accuracy: 0.7222 + 18/183 ━━━━━━━━━━━━━━━━━━━━ 38:22 14s/step - accuracy: 0.7418 - loss: 0.7879
``` - + ```
- 19/183 [==>...........................] - ETA: 39:09 - loss: 0.8331 - accuracy: 0.7237 + 19/183 ━━━━━━━━━━━━━━━━━━━━ 38:07 14s/step - accuracy: 0.7419 - loss: 0.7881
``` - + ```
- 20/183 [==>...........................] - ETA: 38:54 - loss: 0.8452 - accuracy: 0.7063 + 20/183 ━━━━━━━━━━━━━━━━━━━━ 37:52 14s/step - accuracy: 0.7417 - loss: 0.7885
``` - + ```
- 21/183 [==>...........................] - ETA: 38:38 - loss: 0.8396 - accuracy: 0.7083 + 21/183 ━━━━━━━━━━━━━━━━━━━━ 37:37 14s/step - accuracy: 0.7413 - loss: 0.7890
``` - + ```
- 22/183 [==>...........................] - ETA: 38:23 - loss: 0.8370 - accuracy: 0.7102 + 22/183 ━━━━━━━━━━━━━━━━━━━━ 37:23 14s/step - accuracy: 0.7409 - loss: 0.7894
``` - + ```
- 23/183 [==>...........................] - ETA: 38:08 - loss: 0.8350 - accuracy: 0.7120 + 23/183 ━━━━━━━━━━━━━━━━━━━━ 37:08 14s/step - accuracy: 0.7408 - loss: 0.7896
``` - + ```
- 24/183 [==>...........................] - ETA: 37:53 - loss: 0.8551 - accuracy: 0.7031 + 24/183 ━━━━━━━━━━━━━━━━━━━━ 36:54 14s/step - accuracy: 0.7399 - loss: 0.7910
``` - + ```
- 25/183 [===>..........................] - ETA: 37:38 - loss: 0.8385 - accuracy: 0.7150 + 25/183 ━━━━━━━━━━━━━━━━━━━━ 36:39 14s/step - accuracy: 0.7391 - loss: 0.7918
``` - + ```
- 26/183 [===>..........................] - ETA: 37:23 - loss: 0.8379 - accuracy: 0.7163 + 26/183 ━━━━━━━━━━━━━━━━━━━━ 36:25 14s/step - accuracy: 0.7382 - loss: 0.7926
``` - + ```
- 27/183 [===>..........................] - ETA: 37:09 - loss: 0.8418 - accuracy: 0.7130 + 27/183 ━━━━━━━━━━━━━━━━━━━━ 36:10 14s/step - accuracy: 0.7374 - loss: 0.7935
``` - + ```
- 28/183 [===>..........................] - ETA: 36:54 - loss: 0.8280 - accuracy: 0.7232 + 28/183 ━━━━━━━━━━━━━━━━━━━━ 35:55 14s/step - accuracy: 0.7368 - loss: 0.7944
``` - + ```
- 29/183 [===>..........................] - ETA: 36:39 - loss: 0.8371 - accuracy: 0.7069 + 29/183 ━━━━━━━━━━━━━━━━━━━━ 35:41 14s/step - accuracy: 0.7360 - loss: 0.7957
``` - + ```
- 30/183 [===>..........................] - ETA: 36:24 - loss: 0.8461 - accuracy: 0.7042 + 30/183 ━━━━━━━━━━━━━━━━━━━━ 35:27 14s/step - accuracy: 0.7350 - loss: 0.7970
``` - + ```
- 31/183 [====>.........................] - ETA: 36:10 - loss: 0.8476 - accuracy: 0.7056 + 31/183 ━━━━━━━━━━━━━━━━━━━━ 35:13 14s/step - accuracy: 0.7340 - loss: 0.7981
``` - + ```
- 32/183 [====>.........................] - ETA: 35:55 - loss: 0.8437 - accuracy: 0.7031 + 32/183 ━━━━━━━━━━━━━━━━━━━━ 34:59 14s/step - accuracy: 0.7332 - loss: 0.7990
``` - + ```
- 33/183 [====>.........................] - ETA: 35:40 - loss: 0.8428 - accuracy: 0.7045 + 33/183 ━━━━━━━━━━━━━━━━━━━━ 34:44 14s/step - accuracy: 0.7324 - loss: 0.7997
``` - + ```
- 34/183 [====>.........................] - ETA: 35:25 - loss: 0.8396 - accuracy: 0.7096 + 34/183 ━━━━━━━━━━━━━━━━━━━━ 34:30 14s/step - accuracy: 0.7319 - loss: 0.8003
``` - + ```
- 35/183 [====>.........................] - ETA: 35:11 - loss: 0.8330 - accuracy: 0.7107 + 35/183 ━━━━━━━━━━━━━━━━━━━━ 34:16 14s/step - accuracy: 0.7316 - loss: 0.8006
``` - + ```
- 36/183 [====>.........................] - ETA: 34:56 - loss: 0.8283 - accuracy: 0.7118 + 36/183 ━━━━━━━━━━━━━━━━━━━━ 34:01 14s/step - accuracy: 0.7312 - loss: 0.8009
``` - + ```
- 37/183 [=====>........................] - ETA: 34:41 - loss: 0.8235 - accuracy: 0.7162 + 37/183 ━━━━━━━━━━━━━━━━━━━━ 33:47 14s/step - accuracy: 0.7309 - loss: 0.8011
``` - + ```
- 38/183 [=====>........................] - ETA: 34:27 - loss: 0.8247 - accuracy: 0.7171 + 38/183 ━━━━━━━━━━━━━━━━━━━━ 33:33 14s/step - accuracy: 0.7305 - loss: 0.8012
``` - + ```
- 39/183 [=====>........................] - ETA: 34:12 - loss: 0.8305 - accuracy: 0.7147 + 39/183 ━━━━━━━━━━━━━━━━━━━━ 33:19 14s/step - accuracy: 0.7300 - loss: 0.8014
``` - + ```
- 40/183 [=====>........................] - ETA: 33:58 - loss: 0.8233 - accuracy: 0.7219 + 40/183 ━━━━━━━━━━━━━━━━━━━━ 33:05 14s/step - accuracy: 0.7295 - loss: 0.8015
``` - + ```
- 41/183 [=====>........................] - ETA: 33:43 - loss: 0.8217 - accuracy: 0.7195 + 41/183 ━━━━━━━━━━━━━━━━━━━━ 32:50 14s/step - accuracy: 0.7290 - loss: 0.8015
``` - + ```
- 42/183 [=====>........................] - ETA: 33:28 - loss: 0.8180 - accuracy: 0.7202 + 42/183 ━━━━━━━━━━━━━━━━━━━━ 32:36 14s/step - accuracy: 0.7286 - loss: 0.8016
``` - + ```
- 43/183 [======>.......................] - ETA: 33:15 - loss: 0.8268 - accuracy: 0.7209 + 43/183 ━━━━━━━━━━━━━━━━━━━━ 32:22 14s/step - accuracy: 0.7281 - loss: 0.8017
``` - + ```
- 44/183 [======>.......................] - ETA: 33:00 - loss: 0.8309 - accuracy: 0.7131 + 44/183 ━━━━━━━━━━━━━━━━━━━━ 32:08 14s/step - accuracy: 0.7277 - loss: 0.8017
``` - + ```
- 45/183 [======>.......................] - ETA: 32:46 - loss: 0.8377 - accuracy: 0.7111 + 45/183 ━━━━━━━━━━━━━━━━━━━━ 31:54 14s/step - accuracy: 0.7270 - loss: 0.8020
``` - + ```
- 46/183 [======>.......................] - ETA: 32:31 - loss: 0.8367 - accuracy: 0.7120 + 46/183 ━━━━━━━━━━━━━━━━━━━━ 31:40 14s/step - accuracy: 0.7264 - loss: 0.8022
``` - + ```
- 47/183 [======>.......................] - ETA: 32:17 - loss: 0.8331 - accuracy: 0.7154 + 47/183 ━━━━━━━━━━━━━━━━━━━━ 31:26 14s/step - accuracy: 0.7258 - loss: 0.8023
``` - + ```
- 48/183 [======>.......................] - ETA: 32:02 - loss: 0.8366 - accuracy: 0.7109 + 48/183 ━━━━━━━━━━━━━━━━━━━━ 31:13 14s/step - accuracy: 0.7250 - loss: 0.8027
``` - + ```
- 49/183 [=======>......................] - ETA: 31:48 - loss: 0.8383 - accuracy: 0.7117 + 49/183 ━━━━━━━━━━━━━━━━━━━━ 30:59 14s/step - accuracy: 0.7243 - loss: 0.8031
``` - + ```
- 50/183 [=======>......................] - ETA: 31:34 - loss: 0.8408 - accuracy: 0.7075 + 50/183 ━━━━━━━━━━━━━━━━━━━━ 30:45 14s/step - accuracy: 0.7236 - loss: 0.8035
``` - + ```
- 51/183 [=======>......................] - ETA: 31:19 - loss: 0.8529 - accuracy: 0.7010 + 51/183 ━━━━━━━━━━━━━━━━━━━━ 30:31 14s/step - accuracy: 0.7229 - loss: 0.8040
``` - + ```
- 52/183 [=======>......................] - ETA: 31:05 - loss: 0.8545 - accuracy: 0.7019 + 52/183 ━━━━━━━━━━━━━━━━━━━━ 30:17 14s/step - accuracy: 0.7222 - loss: 0.8045
``` - + ```
- 53/183 [=======>......................] - ETA: 30:50 - loss: 0.8502 - accuracy: 0.7075 + 53/183 ━━━━━━━━━━━━━━━━━━━━ 30:03 14s/step - accuracy: 0.7217 - loss: 0.8050
``` - + ```
- 54/183 [=======>......................] - ETA: 30:36 - loss: 0.8479 - accuracy: 0.7083 + 54/183 ━━━━━━━━━━━━━━━━━━━━ 29:49 14s/step - accuracy: 0.7212 - loss: 0.8055
``` - + ```
- 55/183 [========>.....................] - ETA: 30:21 - loss: 0.8517 - accuracy: 0.7068 + 55/183 ━━━━━━━━━━━━━━━━━━━━ 29:35 14s/step - accuracy: 0.7206 - loss: 0.8060
``` - + ```
- 56/183 [========>.....................] - ETA: 30:07 - loss: 0.8541 - accuracy: 0.7009 + 56/183 ━━━━━━━━━━━━━━━━━━━━ 29:21 14s/step - accuracy: 0.7201 - loss: 0.8065
``` - + ```
- 57/183 [========>.....................] - ETA: 29:53 - loss: 0.8560 - accuracy: 0.6996 + 57/183 ━━━━━━━━━━━━━━━━━━━━ 29:07 14s/step - accuracy: 0.7196 - loss: 0.8070
``` - + ```
- 58/183 [========>.....................] - ETA: 29:38 - loss: 0.8572 - accuracy: 0.6983 + 58/183 ━━━━━━━━━━━━━━━━━━━━ 28:53 14s/step - accuracy: 0.7190 - loss: 0.8077
``` - + ```
- 59/183 [========>.....................] - ETA: 29:24 - loss: 0.8588 - accuracy: 0.6928 + 59/183 ━━━━━━━━━━━━━━━━━━━━ 28:39 14s/step - accuracy: 0.7185 - loss: 0.8083
``` - + ```
- 60/183 [========>.....................] - ETA: 29:10 - loss: 0.8648 - accuracy: 0.6896 + 60/183 ━━━━━━━━━━━━━━━━━━━━ 28:25 14s/step - accuracy: 0.7179 - loss: 0.8090
``` - + ```
- 61/183 [=========>....................] - ETA: 28:55 - loss: 0.8662 - accuracy: 0.6885 + 61/183 ━━━━━━━━━━━━━━━━━━━━ 28:12 14s/step - accuracy: 0.7173 - loss: 0.8097
``` - + ```
- 62/183 [=========>....................] - ETA: 28:41 - loss: 0.8701 - accuracy: 0.6855 + 62/183 ━━━━━━━━━━━━━━━━━━━━ 27:59 14s/step - accuracy: 0.7168 - loss: 0.8105
``` - + ```
- 63/183 [=========>....................] - ETA: 28:27 - loss: 0.8699 - accuracy: 0.6845 + 63/183 ━━━━━━━━━━━━━━━━━━━━ 27:45 14s/step - accuracy: 0.7162 - loss: 0.8114
``` - + ```
- 64/183 [=========>....................] - ETA: 28:13 - loss: 0.8668 - accuracy: 0.6875 + 64/183 ━━━━━━━━━━━━━━━━━━━━ 27:32 14s/step - accuracy: 0.7156 - loss: 0.8122
``` - + ```
- 65/183 [=========>....................] - ETA: 27:58 - loss: 0.8760 - accuracy: 0.6846 + 65/183 ━━━━━━━━━━━━━━━━━━━━ 27:18 14s/step - accuracy: 0.7149 - loss: 0.8132
``` - + ```
- 66/183 [=========>....................] - ETA: 27:44 - loss: 0.8789 - accuracy: 0.6799 + 66/183 ━━━━━━━━━━━━━━━━━━━━ 27:05 14s/step - accuracy: 0.7143 - loss: 0.8141
``` - + ```
- 67/183 [=========>....................] - ETA: 27:30 - loss: 0.8779 - accuracy: 0.6791 + 67/183 ━━━━━━━━━━━━━━━━━━━━ 26:51 14s/step - accuracy: 0.7136 - loss: 0.8150
``` - + ```
- 68/183 [==========>...................] - ETA: 27:15 - loss: 0.8763 - accuracy: 0.6783 + 68/183 ━━━━━━━━━━━━━━━━━━━━ 26:37 14s/step - accuracy: 0.7130 - loss: 0.8159
``` - + ```
- 69/183 [==========>...................] - ETA: 27:01 - loss: 0.8751 - accuracy: 0.6775 + 69/183 ━━━━━━━━━━━━━━━━━━━━ 26:23 14s/step - accuracy: 0.7125 - loss: 0.8168
``` - + ```
- 70/183 [==========>...................] - ETA: 26:47 - loss: 0.8755 - accuracy: 0.6750 + 70/183 ━━━━━━━━━━━━━━━━━━━━ 26:09 14s/step - accuracy: 0.7119 - loss: 0.8176
``` - + ```
- 71/183 [==========>...................] - ETA: 26:32 - loss: 0.8697 - accuracy: 0.6778 + 71/183 ━━━━━━━━━━━━━━━━━━━━ 25:55 14s/step - accuracy: 0.7115 - loss: 0.8183
``` - + ```
- 72/183 [==========>...................] - ETA: 26:18 - loss: 0.8729 - accuracy: 0.6736 + 72/183 ━━━━━━━━━━━━━━━━━━━━ 25:41 14s/step - accuracy: 0.7110 - loss: 0.8191
``` - + ```
- 73/183 [==========>...................] - ETA: 26:04 - loss: 0.8713 - accuracy: 0.6747 + 73/183 ━━━━━━━━━━━━━━━━━━━━ 25:28 14s/step - accuracy: 0.7105 - loss: 0.8198
``` - + ```
- 74/183 [===========>..................] - ETA: 25:50 - loss: 0.8721 - accuracy: 0.6740 + 74/183 ━━━━━━━━━━━━━━━━━━━━ 25:14 14s/step - accuracy: 0.7100 - loss: 0.8206
``` - + ```
- 75/183 [===========>..................] - ETA: 25:35 - loss: 0.8787 - accuracy: 0.6700 + 75/183 ━━━━━━━━━━━━━━━━━━━━ 25:01 14s/step - accuracy: 0.7095 - loss: 0.8213
``` - + ```
- 76/183 [===========>..................] - ETA: 25:21 - loss: 0.8769 - accuracy: 0.6694 + 76/183 ━━━━━━━━━━━━━━━━━━━━ 24:47 14s/step - accuracy: 0.7090 - loss: 0.8220
``` - + ```
- 77/183 [===========>..................] - ETA: 25:07 - loss: 0.8743 - accuracy: 0.6705 + 77/183 ━━━━━━━━━━━━━━━━━━━━ 24:33 14s/step - accuracy: 0.7085 - loss: 0.8227
``` - + ```
- 78/183 [===========>..................] - ETA: 24:53 - loss: 0.8794 - accuracy: 0.6683 + 78/183 ━━━━━━━━━━━━━━━━━━━━ 24:19 14s/step - accuracy: 0.7080 - loss: 0.8234
``` - + ```
- 79/183 [===========>..................] - ETA: 24:39 - loss: 0.8800 - accuracy: 0.6677 + 79/183 ━━━━━━━━━━━━━━━━━━━━ 24:05 14s/step - accuracy: 0.7076 - loss: 0.8241
``` - + ```
- 80/183 [============>.................] - ETA: 24:24 - loss: 0.8773 - accuracy: 0.6687 + 80/183 ━━━━━━━━━━━━━━━━━━━━ 23:52 14s/step - accuracy: 0.7071 - loss: 0.8248
``` - + ```
- 81/183 [============>.................] - ETA: 24:10 - loss: 0.8769 - accuracy: 0.6682 + 81/183 ━━━━━━━━━━━━━━━━━━━━ 23:38 14s/step - accuracy: 0.7066 - loss: 0.8254
``` - + ```
- 82/183 [============>.................] - ETA: 23:56 - loss: 0.8788 - accuracy: 0.6677 + 82/183 ━━━━━━━━━━━━━━━━━━━━ 23:24 14s/step - accuracy: 0.7062 - loss: 0.8261
``` - + ```
- 83/183 [============>.................] - ETA: 23:42 - loss: 0.8773 - accuracy: 0.6672 + 83/183 ━━━━━━━━━━━━━━━━━━━━ 23:10 14s/step - accuracy: 0.7058 - loss: 0.8267
``` - + ```
- 84/183 [============>.................] - ETA: 23:27 - loss: 0.8800 - accuracy: 0.6652 + 84/183 ━━━━━━━━━━━━━━━━━━━━ 22:56 14s/step - accuracy: 0.7054 - loss: 0.8273
``` - + ```
- 85/183 [============>.................] - ETA: 23:13 - loss: 0.8819 - accuracy: 0.6632 + 85/183 ━━━━━━━━━━━━━━━━━━━━ 22:42 14s/step - accuracy: 0.7050 - loss: 0.8279
``` - + ```
- 86/183 [=============>................] - ETA: 22:59 - loss: 0.8789 - accuracy: 0.6657 + 86/183 ━━━━━━━━━━━━━━━━━━━━ 22:28 14s/step - accuracy: 0.7047 - loss: 0.8285
``` - + ```
- 87/183 [=============>................] - ETA: 22:45 - loss: 0.8813 - accuracy: 0.6667 + 87/183 ━━━━━━━━━━━━━━━━━━━━ 22:15 14s/step - accuracy: 0.7043 - loss: 0.8292
``` - + ```
- 88/183 [=============>................] - ETA: 22:31 - loss: 0.8872 - accuracy: 0.6619 + 88/183 ━━━━━━━━━━━━━━━━━━━━ 22:01 14s/step - accuracy: 0.7039 - loss: 0.8298
``` - + ```
- 89/183 [=============>................] - ETA: 22:16 - loss: 0.8847 - accuracy: 0.6629 + 89/183 ━━━━━━━━━━━━━━━━━━━━ 21:47 14s/step - accuracy: 0.7035 - loss: 0.8304
``` - + ```
- 90/183 [=============>................] - ETA: 22:02 - loss: 0.8823 - accuracy: 0.6639 + 90/183 ━━━━━━━━━━━━━━━━━━━━ 21:33 14s/step - accuracy: 0.7031 - loss: 0.8310
``` - + ```
- 91/183 [=============>................] - ETA: 21:48 - loss: 0.8859 - accuracy: 0.6621 + 91/183 ━━━━━━━━━━━━━━━━━━━━ 21:19 14s/step - accuracy: 0.7027 - loss: 0.8316
``` - + ```
- 92/183 [==============>...............] - ETA: 21:34 - loss: 0.8902 - accuracy: 0.6617 + 92/183 ━━━━━━━━━━━━━━━━━━━━ 21:05 14s/step - accuracy: 0.7024 - loss: 0.8321
``` - + ```
- 93/183 [==============>...............] - ETA: 21:20 - loss: 0.8896 - accuracy: 0.6626 + 93/183 ━━━━━━━━━━━━━━━━━━━━ 20:51 14s/step - accuracy: 0.7020 - loss: 0.8326
``` - + ```
- 94/183 [==============>...............] - ETA: 21:05 - loss: 0.8932 - accuracy: 0.6622 + 94/183 ━━━━━━━━━━━━━━━━━━━━ 20:37 14s/step - accuracy: 0.7017 - loss: 0.8332
``` - + ```
- 95/183 [==============>...............] - ETA: 20:51 - loss: 0.8946 - accuracy: 0.6618 + 95/183 ━━━━━━━━━━━━━━━━━━━━ 20:23 14s/step - accuracy: 0.7013 - loss: 0.8338
``` - + ```
- 96/183 [==============>...............] - ETA: 20:37 - loss: 0.8960 - accuracy: 0.6628 + 96/183 ━━━━━━━━━━━━━━━━━━━━ 20:09 14s/step - accuracy: 0.7009 - loss: 0.8344
``` - + ```
- 97/183 [==============>...............] - ETA: 20:23 - loss: 0.8934 - accuracy: 0.6649 + 97/183 ━━━━━━━━━━━━━━━━━━━━ 19:55 14s/step - accuracy: 0.7005 - loss: 0.8350
``` - + ```
- 98/183 [===============>..............] - ETA: 20:08 - loss: 0.8942 - accuracy: 0.6658 + 98/183 ━━━━━━━━━━━━━━━━━━━━ 19:41 14s/step - accuracy: 0.7002 - loss: 0.8356
``` - + ```
- 99/183 [===============>..............] - ETA: 19:54 - loss: 0.9002 - accuracy: 0.6629 + 99/183 ━━━━━━━━━━━━━━━━━━━━ 19:27 14s/step - accuracy: 0.6998 - loss: 0.8362
``` - + ```
-100/183 [===============>..............] - ETA: 19:40 - loss: 0.8975 - accuracy: 0.6637 + 100/183 ━━━━━━━━━━━━━━━━━━━━ 19:13 14s/step - accuracy: 0.6994 - loss: 0.8368
``` - + ```
-101/183 [===============>..............] - ETA: 19:26 - loss: 0.8965 - accuracy: 0.6646 + 101/183 ━━━━━━━━━━━━━━━━━━━━ 18:59 14s/step - accuracy: 0.6990 - loss: 0.8375
``` - + ```
-102/183 [===============>..............] - ETA: 19:11 - loss: 0.8963 - accuracy: 0.6642 + 102/183 ━━━━━━━━━━━━━━━━━━━━ 18:45 14s/step - accuracy: 0.6986 - loss: 0.8381
``` - + ```
-103/183 [===============>..............] - ETA: 18:57 - loss: 0.8950 - accuracy: 0.6650 + 103/183 ━━━━━━━━━━━━━━━━━━━━ 18:31 14s/step - accuracy: 0.6983 - loss: 0.8386
``` - + ```
-104/183 [================>.............] - ETA: 18:43 - loss: 0.8935 - accuracy: 0.6659 + 104/183 ━━━━━━━━━━━━━━━━━━━━ 18:17 14s/step - accuracy: 0.6979 - loss: 0.8392
``` - + ```
-105/183 [================>.............] - ETA: 18:29 - loss: 0.8912 - accuracy: 0.6667 + 105/183 ━━━━━━━━━━━━━━━━━━━━ 18:03 14s/step - accuracy: 0.6976 - loss: 0.8397
``` - + ```
-106/183 [================>.............] - ETA: 18:14 - loss: 0.8940 - accuracy: 0.6663 + 106/183 ━━━━━━━━━━━━━━━━━━━━ 17:50 14s/step - accuracy: 0.6973 - loss: 0.8402
``` - + ```
-107/183 [================>.............] - ETA: 18:00 - loss: 0.8913 - accuracy: 0.6671 + 107/183 ━━━━━━━━━━━━━━━━━━━━ 17:36 14s/step - accuracy: 0.6969 - loss: 0.8406
``` - + ```
-108/183 [================>.............] - ETA: 17:46 - loss: 0.8920 - accuracy: 0.6667 + 108/183 ━━━━━━━━━━━━━━━━━━━━ 17:22 14s/step - accuracy: 0.6966 - loss: 0.8411
``` - + ```
-109/183 [================>.............] - ETA: 17:32 - loss: 0.8915 - accuracy: 0.6674 + 109/183 ━━━━━━━━━━━━━━━━━━━━ 17:08 14s/step - accuracy: 0.6963 - loss: 0.8416
``` - + ```
-110/183 [=================>............] - ETA: 17:18 - loss: 0.8893 - accuracy: 0.6682 + 110/183 ━━━━━━━━━━━━━━━━━━━━ 16:54 14s/step - accuracy: 0.6960 - loss: 0.8420
``` - + ```
-111/183 [=================>............] - ETA: 17:03 - loss: 0.8909 - accuracy: 0.6667 + 111/183 ━━━━━━━━━━━━━━━━━━━━ 16:40 14s/step - accuracy: 0.6957 - loss: 0.8424
``` - + ```
-112/183 [=================>............] - ETA: 16:49 - loss: 0.8894 - accuracy: 0.6674 + 112/183 ━━━━━━━━━━━━━━━━━━━━ 16:26 14s/step - accuracy: 0.6954 - loss: 0.8428
``` - + ```
-113/183 [=================>............] - ETA: 16:35 - loss: 0.8909 - accuracy: 0.6659 + 113/183 ━━━━━━━━━━━━━━━━━━━━ 16:12 14s/step - accuracy: 0.6951 - loss: 0.8432
``` - + ```
-114/183 [=================>............] - ETA: 16:21 - loss: 0.8908 - accuracy: 0.6667 + 114/183 ━━━━━━━━━━━━━━━━━━━━ 15:58 14s/step - accuracy: 0.6949 - loss: 0.8436
``` - + ```
-115/183 [=================>............] - ETA: 16:07 - loss: 0.8943 - accuracy: 0.6652 + 115/183 ━━━━━━━━━━━━━━━━━━━━ 15:44 14s/step - accuracy: 0.6946 - loss: 0.8440
``` - + ```
-116/183 [==================>...........] - ETA: 15:53 - loss: 0.8956 - accuracy: 0.6659 + 116/183 ━━━━━━━━━━━━━━━━━━━━ 15:30 14s/step - accuracy: 0.6943 - loss: 0.8444
``` - + ```
-117/183 [==================>...........] - ETA: 15:40 - loss: 0.8949 - accuracy: 0.6656 + 117/183 ━━━━━━━━━━━━━━━━━━━━ 15:16 14s/step - accuracy: 0.6941 - loss: 0.8448
``` - + ```
-118/183 [==================>...........] - ETA: 15:26 - loss: 0.8907 - accuracy: 0.6684 + 118/183 ━━━━━━━━━━━━━━━━━━━━ 15:02 14s/step - accuracy: 0.6938 - loss: 0.8451
``` - + ```
-119/183 [==================>...........] - ETA: 15:11 - loss: 0.8892 - accuracy: 0.6691 + 119/183 ━━━━━━━━━━━━━━━━━━━━ 14:48 14s/step - accuracy: 0.6936 - loss: 0.8455
``` - + ```
-120/183 [==================>...........] - ETA: 14:57 - loss: 0.8889 - accuracy: 0.6677 + 120/183 ━━━━━━━━━━━━━━━━━━━━ 14:34 14s/step - accuracy: 0.6934 - loss: 0.8458
``` - + ```
-121/183 [==================>...........] - ETA: 14:43 - loss: 0.8853 - accuracy: 0.6694 + 121/183 ━━━━━━━━━━━━━━━━━━━━ 14:20 14s/step - accuracy: 0.6932 - loss: 0.8461
``` - + ```
-122/183 [===================>..........] - ETA: 14:29 - loss: 0.8860 - accuracy: 0.6691 + 122/183 ━━━━━━━━━━━━━━━━━━━━ 14:06 14s/step - accuracy: 0.6930 - loss: 0.8464
``` - + ```
-123/183 [===================>..........] - ETA: 14:14 - loss: 0.8832 - accuracy: 0.6707 + 123/183 ━━━━━━━━━━━━━━━━━━━━ 13:52 14s/step - accuracy: 0.6928 - loss: 0.8467
``` - + ```
-124/183 [===================>..........] - ETA: 14:00 - loss: 0.8812 - accuracy: 0.6724 + 124/183 ━━━━━━━━━━━━━━━━━━━━ 13:38 14s/step - accuracy: 0.6926 - loss: 0.8470
``` - + ```
-125/183 [===================>..........] - ETA: 13:46 - loss: 0.8806 - accuracy: 0.6720 + 125/183 ━━━━━━━━━━━━━━━━━━━━ 13:24 14s/step - accuracy: 0.6924 - loss: 0.8473
``` - + ```
-126/183 [===================>..........] - ETA: 13:32 - loss: 0.8807 - accuracy: 0.6696 + 126/183 ━━━━━━━━━━━━━━━━━━━━ 13:10 14s/step - accuracy: 0.6922 - loss: 0.8476
``` - + ```
-127/183 [===================>..........] - ETA: 13:17 - loss: 0.8778 - accuracy: 0.6713 + 127/183 ━━━━━━━━━━━━━━━━━━━━ 12:57 14s/step - accuracy: 0.6920 - loss: 0.8478
``` - + ```
-128/183 [===================>..........] - ETA: 13:03 - loss: 0.8790 - accuracy: 0.6719 + 128/183 ━━━━━━━━━━━━━━━━━━━━ 12:43 14s/step - accuracy: 0.6918 - loss: 0.8481
``` - + ```
-129/183 [====================>.........] - ETA: 12:49 - loss: 0.8775 - accuracy: 0.6725 + 129/183 ━━━━━━━━━━━━━━━━━━━━ 12:29 14s/step - accuracy: 0.6917 - loss: 0.8483
``` - + ```
-130/183 [====================>.........] - ETA: 12:35 - loss: 0.8775 - accuracy: 0.6731 + 130/183 ━━━━━━━━━━━━━━━━━━━━ 12:15 14s/step - accuracy: 0.6915 - loss: 0.8485
``` - + ```
-131/183 [====================>.........] - ETA: 12:21 - loss: 0.8785 - accuracy: 0.6718 + 131/183 ━━━━━━━━━━━━━━━━━━━━ 12:01 14s/step - accuracy: 0.6913 - loss: 0.8487
``` - + ```
-132/183 [====================>.........] - ETA: 12:07 - loss: 0.8759 - accuracy: 0.6733 + 132/183 ━━━━━━━━━━━━━━━━━━━━ 11:47 14s/step - accuracy: 0.6912 - loss: 0.8489
``` - + ```
-133/183 [====================>.........] - ETA: 11:52 - loss: 0.8739 - accuracy: 0.6739 + 133/183 ━━━━━━━━━━━━━━━━━━━━ 11:33 14s/step - accuracy: 0.6910 - loss: 0.8491
``` - + ```
-134/183 [====================>.........] - ETA: 11:38 - loss: 0.8749 - accuracy: 0.6735 + 134/183 ━━━━━━━━━━━━━━━━━━━━ 11:19 14s/step - accuracy: 0.6909 - loss: 0.8493
``` - + ```
-135/183 [=====================>........] - ETA: 11:24 - loss: 0.8742 - accuracy: 0.6741 + 135/183 ━━━━━━━━━━━━━━━━━━━━ 11:05 14s/step - accuracy: 0.6908 - loss: 0.8494
``` - + ```
-136/183 [=====================>........] - ETA: 11:10 - loss: 0.8738 - accuracy: 0.6728 + 136/183 ━━━━━━━━━━━━━━━━━━━━ 10:51 14s/step - accuracy: 0.6906 - loss: 0.8495
``` - + ```
-137/183 [=====================>........] - ETA: 10:56 - loss: 0.8752 - accuracy: 0.6715 + 137/183 ━━━━━━━━━━━━━━━━━━━━ 10:37 14s/step - accuracy: 0.6905 - loss: 0.8497
``` - + ```
-138/183 [=====================>........] - ETA: 10:41 - loss: 0.8792 - accuracy: 0.6694 + 138/183 ━━━━━━━━━━━━━━━━━━━━ 10:23 14s/step - accuracy: 0.6904 - loss: 0.8499
``` - + ```
-139/183 [=====================>........] - ETA: 10:27 - loss: 0.8795 - accuracy: 0.6691 + 139/183 ━━━━━━━━━━━━━━━━━━━━ 10:10 14s/step - accuracy: 0.6902 - loss: 0.8500
``` - + ```
-140/183 [=====================>........] - ETA: 10:13 - loss: 0.8808 - accuracy: 0.6670 + 140/183 ━━━━━━━━━━━━━━━━━━━━ 9:56 14s/step - accuracy: 0.6901 - loss: 0.8502
``` - + ```
-141/183 [======================>.......] - ETA: 9:59 - loss: 0.8836 - accuracy: 0.6667 + 141/183 ━━━━━━━━━━━━━━━━━━━━ 9:42 14s/step - accuracy: 0.6900 - loss: 0.8503
``` - + ```
-142/183 [======================>.......] - ETA: 9:44 - loss: 0.8848 - accuracy: 0.6664 + 142/183 ━━━━━━━━━━━━━━━━━━━━ 9:28 14s/step - accuracy: 0.6898 - loss: 0.8505
``` - + ```
-143/183 [======================>.......] - ETA: 9:30 - loss: 0.8833 - accuracy: 0.6661 + 143/183 ━━━━━━━━━━━━━━━━━━━━ 9:14 14s/step - accuracy: 0.6897 - loss: 0.8507
``` - + ```
-144/183 [======================>.......] - ETA: 9:16 - loss: 0.8850 - accuracy: 0.6641 + 144/183 ━━━━━━━━━━━━━━━━━━━━ 9:00 14s/step - accuracy: 0.6895 - loss: 0.8509
``` - + ```
-145/183 [======================>.......] - ETA: 9:02 - loss: 0.8841 - accuracy: 0.6647 + 145/183 ━━━━━━━━━━━━━━━━━━━━ 8:46 14s/step - accuracy: 0.6894 - loss: 0.8511
``` - + ```
-146/183 [======================>.......] - ETA: 8:47 - loss: 0.8825 - accuracy: 0.6661 + 146/183 ━━━━━━━━━━━━━━━━━━━━ 8:32 14s/step - accuracy: 0.6892 - loss: 0.8514
``` - + ```
-147/183 [=======================>......] - ETA: 8:33 - loss: 0.8814 - accuracy: 0.6675 + 147/183 ━━━━━━━━━━━━━━━━━━━━ 8:18 14s/step - accuracy: 0.6891 - loss: 0.8516
``` - + ```
-148/183 [=======================>......] - ETA: 8:19 - loss: 0.8801 - accuracy: 0.6698 + 148/183 ━━━━━━━━━━━━━━━━━━━━ 8:05 14s/step - accuracy: 0.6890 - loss: 0.8517
``` - + ```
-149/183 [=======================>......] - ETA: 8:05 - loss: 0.8782 - accuracy: 0.6703 + 149/183 ━━━━━━━━━━━━━━━━━━━━ 7:51 14s/step - accuracy: 0.6888 - loss: 0.8519
``` - + ```
-150/183 [=======================>......] - ETA: 7:51 - loss: 0.8789 - accuracy: 0.6700 + 150/183 ━━━━━━━━━━━━━━━━━━━━ 7:37 14s/step - accuracy: 0.6887 - loss: 0.8521
``` - + ```
-151/183 [=======================>......] - ETA: 7:36 - loss: 0.8776 - accuracy: 0.6705 + 151/183 ━━━━━━━━━━━━━━━━━━━━ 7:23 14s/step - accuracy: 0.6886 - loss: 0.8522
``` - + ```
-152/183 [=======================>......] - ETA: 7:22 - loss: 0.8797 - accuracy: 0.6694 + 152/183 ━━━━━━━━━━━━━━━━━━━━ 7:09 14s/step - accuracy: 0.6884 - loss: 0.8524
``` - + ```
-153/183 [========================>.....] - ETA: 7:08 - loss: 0.8804 - accuracy: 0.6691 + 153/183 ━━━━━━━━━━━━━━━━━━━━ 6:55 14s/step - accuracy: 0.6883 - loss: 0.8525
``` - + ```
-154/183 [========================>.....] - ETA: 6:53 - loss: 0.8793 - accuracy: 0.6688 + 154/183 ━━━━━━━━━━━━━━━━━━━━ 6:41 14s/step - accuracy: 0.6882 - loss: 0.8527
``` - + ```
-155/183 [========================>.....] - ETA: 6:39 - loss: 0.8793 - accuracy: 0.6685 + 155/183 ━━━━━━━━━━━━━━━━━━━━ 6:27 14s/step - accuracy: 0.6881 - loss: 0.8528
``` - + ```
-156/183 [========================>.....] - ETA: 6:25 - loss: 0.8776 - accuracy: 0.6691 + 156/183 ━━━━━━━━━━━━━━━━━━━━ 6:14 14s/step - accuracy: 0.6880 - loss: 0.8530
``` - + ```
-157/183 [========================>.....] - ETA: 6:11 - loss: 0.8755 - accuracy: 0.6704 + 157/183 ━━━━━━━━━━━━━━━━━━━━ 6:00 14s/step - accuracy: 0.6879 - loss: 0.8531
``` - + ```
-158/183 [========================>.....] - ETA: 5:57 - loss: 0.8768 - accuracy: 0.6701 + 158/183 ━━━━━━━━━━━━━━━━━━━━ 5:46 14s/step - accuracy: 0.6878 - loss: 0.8532
``` - + ```
-159/183 [=========================>....] - ETA: 5:42 - loss: 0.8771 - accuracy: 0.6698 + 159/183 ━━━━━━━━━━━━━━━━━━━━ 5:32 14s/step - accuracy: 0.6877 - loss: 0.8533
``` - + ```
-160/183 [=========================>....] - ETA: 5:28 - loss: 0.8761 - accuracy: 0.6703 + 160/183 ━━━━━━━━━━━━━━━━━━━━ 5:18 14s/step - accuracy: 0.6877 - loss: 0.8535
``` - + ```
-161/183 [=========================>....] - ETA: 5:14 - loss: 0.8734 - accuracy: 0.6716 + 161/183 ━━━━━━━━━━━━━━━━━━━━ 5:04 14s/step - accuracy: 0.6876 - loss: 0.8536
``` - + ```
-162/183 [=========================>....] - ETA: 4:59 - loss: 0.8730 - accuracy: 0.6713 + 162/183 ━━━━━━━━━━━━━━━━━━━━ 4:50 14s/step - accuracy: 0.6875 - loss: 0.8537
``` - + ```
-163/183 [=========================>....] - ETA: 4:45 - loss: 0.8722 - accuracy: 0.6710 + 163/183 ━━━━━━━━━━━━━━━━━━━━ 4:36 14s/step - accuracy: 0.6875 - loss: 0.8538
``` - + ```
-164/183 [=========================>....] - ETA: 4:31 - loss: 0.8728 - accuracy: 0.6707 + 164/183 ━━━━━━━━━━━━━━━━━━━━ 4:23 14s/step - accuracy: 0.6874 - loss: 0.8539
``` - + ```
-165/183 [==========================>...] - ETA: 4:17 - loss: 0.8743 - accuracy: 0.6697 + 165/183 ━━━━━━━━━━━━━━━━━━━━ 4:09 14s/step - accuracy: 0.6873 - loss: 0.8540
``` - + ```
-166/183 [==========================>...] - ETA: 4:02 - loss: 0.8745 - accuracy: 0.6702 + 166/183 ━━━━━━━━━━━━━━━━━━━━ 3:55 14s/step - accuracy: 0.6873 - loss: 0.8540
``` - + ```
-167/183 [==========================>...] - ETA: 3:48 - loss: 0.8753 - accuracy: 0.6684 + 167/183 ━━━━━━━━━━━━━━━━━━━━ 3:41 14s/step - accuracy: 0.6872 - loss: 0.8541
``` - + ```
-168/183 [==========================>...] - ETA: 3:34 - loss: 0.8738 - accuracy: 0.6696 + 168/183 ━━━━━━━━━━━━━━━━━━━━ 3:27 14s/step - accuracy: 0.6872 - loss: 0.8542
``` - + ```
-169/183 [==========================>...] - ETA: 3:20 - loss: 0.8724 - accuracy: 0.6694 + 169/183 ━━━━━━━━━━━━━━━━━━━━ 3:13 14s/step - accuracy: 0.6871 - loss: 0.8543
``` - + ```
-170/183 [==========================>...] - ETA: 3:05 - loss: 0.8757 - accuracy: 0.6676 + 170/183 ━━━━━━━━━━━━━━━━━━━━ 2:59 14s/step - accuracy: 0.6871 - loss: 0.8544
``` - + ```
-171/183 [===========================>..] - ETA: 2:51 - loss: 0.8752 - accuracy: 0.6674 + 171/183 ━━━━━━━━━━━━━━━━━━━━ 2:46 14s/step - accuracy: 0.6870 - loss: 0.8544
``` - + ```
-172/183 [===========================>..] - ETA: 2:37 - loss: 0.8768 - accuracy: 0.6672 + 172/183 ━━━━━━━━━━━━━━━━━━━━ 2:32 14s/step - accuracy: 0.6870 - loss: 0.8545
``` - + ```
-173/183 [===========================>..] - ETA: 2:22 - loss: 0.8750 - accuracy: 0.6676 + 173/183 ━━━━━━━━━━━━━━━━━━━━ 2:18 14s/step - accuracy: 0.6870 - loss: 0.8546
``` - + ```
-174/183 [===========================>..] - ETA: 2:08 - loss: 0.8753 - accuracy: 0.6681 + 174/183 ━━━━━━━━━━━━━━━━━━━━ 2:04 14s/step - accuracy: 0.6869 - loss: 0.8547
``` - + ```
-175/183 [===========================>..] - ETA: 1:54 - loss: 0.8749 - accuracy: 0.6679 + 175/183 ━━━━━━━━━━━━━━━━━━━━ 1:50 14s/step - accuracy: 0.6869 - loss: 0.8548
``` - + ```
-176/183 [===========================>..] - ETA: 1:40 - loss: 0.8739 - accuracy: 0.6683 + 176/183 ━━━━━━━━━━━━━━━━━━━━ 1:36 14s/step - accuracy: 0.6868 - loss: 0.8548
``` - + ```
-177/183 [============================>.] - ETA: 1:25 - loss: 0.8720 - accuracy: 0.6688 + 177/183 ━━━━━━━━━━━━━━━━━━━━ 1:23 14s/step - accuracy: 0.6868 - loss: 0.8549
``` - + ```
-178/183 [============================>.] - ETA: 1:11 - loss: 0.8719 - accuracy: 0.6692 + 178/183 ━━━━━━━━━━━━━━━━━━━━ 1:09 14s/step - accuracy: 0.6867 - loss: 0.8550
``` - + ```
-179/183 [============================>.] - ETA: 57s - loss: 0.8739 - accuracy: 0.6669 + 179/183 ━━━━━━━━━━━━━━━━━━━━ 55s 14s/step - accuracy: 0.6867 - loss: 0.8550
``` - + ```
-180/183 [============================>.] - ETA: 42s - loss: 0.8729 - accuracy: 0.6674 + 180/183 ━━━━━━━━━━━━━━━━━━━━ 41s 14s/step - accuracy: 0.6867 - loss: 0.8551
``` - + ```
-181/183 [============================>.] - ETA: 28s - loss: 0.8722 - accuracy: 0.6678 + 181/183 ━━━━━━━━━━━━━━━━━━━━ 27s 14s/step - accuracy: 0.6866 - loss: 0.8552
``` - + ```
-182/183 [============================>.] - ETA: 14s - loss: 0.8715 - accuracy: 0.6683 + 182/183 ━━━━━━━━━━━━━━━━━━━━ 13s 14s/step - accuracy: 0.6866 - loss: 0.8552
``` - + ```
-183/183 [==============================] - ETA: 0s - loss: 0.8728 - accuracy: 0.6680 + 183/183 ━━━━━━━━━━━━━━━━━━━━ 0s 14s/step - accuracy: 0.6865 - loss: 0.8553
``` - + ```
-183/183 [==============================] - 2778s 15s/step - loss: 0.8728 - accuracy: 0.6680 - val_loss: 0.7296 - val_accuracy: 0.7525 - lr: 4.7230e-06 + 183/183 ━━━━━━━━━━━━━━━━━━━━ 2677s 15s/step - accuracy: 0.6865 - loss: 0.8554 - val_accuracy: 0.7400 - val_loss: 0.7678 - learning_rate: 4.7230e-06
@@ -6165,1288 +5888,1288 @@ Epoch 5/5 ```
- 1/183 [..............................] - ETA: 45:36 - loss: 0.7472 - accuracy: 0.6250 + 1/183 ━━━━━━━━━━━━━━━━━━━━ 41:51 14s/step - accuracy: 0.6250 - loss: 0.7948
``` - + ```
- 2/183 [..............................] - ETA: 44:02 - loss: 0.7747 - accuracy: 0.6875 + 2/183 ━━━━━━━━━━━━━━━━━━━━ 41:14 14s/step - accuracy: 0.6562 - loss: 0.7674
``` - + ```
- 3/183 [..............................] - ETA: 43:51 - loss: 0.7801 - accuracy: 0.6667 + 3/183 ━━━━━━━━━━━━━━━━━━━━ 41:10 14s/step - accuracy: 0.6597 - loss: 0.7733
``` - + ```
- 4/183 [..............................] - ETA: 43:41 - loss: 0.7945 - accuracy: 0.6250 + 4/183 ━━━━━━━━━━━━━━━━━━━━ 40:52 14s/step - accuracy: 0.6589 - loss: 0.7755
``` - + ```
- 5/183 [..............................] - ETA: 43:26 - loss: 0.8398 - accuracy: 0.6500 + 5/183 ━━━━━━━━━━━━━━━━━━━━ 40:38 14s/step - accuracy: 0.6621 - loss: 0.7814
``` - + ```
- 6/183 [..............................] - ETA: 43:07 - loss: 0.7811 - accuracy: 0.6875 + 6/183 ━━━━━━━━━━━━━━━━━━━━ 40:26 14s/step - accuracy: 0.6698 - loss: 0.7804
``` - + ```
- 7/183 [>.............................] - ETA: 42:47 - loss: 0.8120 - accuracy: 0.6964 + 7/183 ━━━━━━━━━━━━━━━━━━━━ 40:09 14s/step - accuracy: 0.6761 - loss: 0.7780
``` - + ```
- 8/183 [>.............................] - ETA: 42:30 - loss: 0.7819 - accuracy: 0.6875 + 8/183 ━━━━━━━━━━━━━━━━━━━━ 39:59 14s/step - accuracy: 0.6834 - loss: 0.7721
``` - + ```
- 9/183 [>.............................] - ETA: 42:09 - loss: 0.7870 - accuracy: 0.6944 + 9/183 ━━━━━━━━━━━━━━━━━━━━ 39:46 14s/step - accuracy: 0.6908 - loss: 0.7682
``` - + ```
- 10/183 [>.............................] - ETA: 41:50 - loss: 0.7538 - accuracy: 0.7125 + 10/183 ━━━━━━━━━━━━━━━━━━━━ 39:33 14s/step - accuracy: 0.6967 - loss: 0.7655
``` - + ```
- 11/183 [>.............................] - ETA: 41:33 - loss: 0.7518 - accuracy: 0.7159 + 11/183 ━━━━━━━━━━━━━━━━━━━━ 39:23 14s/step - accuracy: 0.7005 - loss: 0.7653
``` - + ```
- 12/183 [>.............................] - ETA: 41:17 - loss: 0.7440 - accuracy: 0.7188 + 12/183 ━━━━━━━━━━━━━━━━━━━━ 39:08 14s/step - accuracy: 0.7021 - loss: 0.7669
``` - + ```
- 13/183 [=>............................] - ETA: 41:00 - loss: 0.7263 - accuracy: 0.7404 + 13/183 ━━━━━━━━━━━━━━━━━━━━ 38:57 14s/step - accuracy: 0.7028 - loss: 0.7679
``` - + ```
- 14/183 [=>............................] - ETA: 40:44 - loss: 0.7001 - accuracy: 0.7589 + 14/183 ━━━━━━━━━━━━━━━━━━━━ 38:44 14s/step - accuracy: 0.7043 - loss: 0.7668
``` - + ```
- 15/183 [=>............................] - ETA: 40:28 - loss: 0.7132 - accuracy: 0.7583 + 15/183 ━━━━━━━━━━━━━━━━━━━━ 38:29 14s/step - accuracy: 0.7062 - loss: 0.7654
``` - + ```
- 16/183 [=>............................] - ETA: 40:11 - loss: 0.7123 - accuracy: 0.7500 + 16/183 ━━━━━━━━━━━━━━━━━━━━ 38:16 14s/step - accuracy: 0.7089 - loss: 0.7633
``` - + ```
- 17/183 [=>............................] - ETA: 39:55 - loss: 0.7370 - accuracy: 0.7426 + 17/183 ━━━━━━━━━━━━━━━━━━━━ 38:00 14s/step - accuracy: 0.7113 - loss: 0.7622
``` - + ```
- 18/183 [=>............................] - ETA: 39:38 - loss: 0.7365 - accuracy: 0.7431 + 18/183 ━━━━━━━━━━━━━━━━━━━━ 37:49 14s/step - accuracy: 0.7127 - loss: 0.7620
``` - + ```
- 19/183 [==>...........................] - ETA: 39:22 - loss: 0.7469 - accuracy: 0.7303 + 19/183 ━━━━━━━━━━━━━━━━━━━━ 37:34 14s/step - accuracy: 0.7133 - loss: 0.7624
``` - + ```
- 20/183 [==>...........................] - ETA: 39:07 - loss: 0.7500 - accuracy: 0.7375 + 20/183 ━━━━━━━━━━━━━━━━━━━━ 37:21 14s/step - accuracy: 0.7142 - loss: 0.7625
``` - + ```
- 21/183 [==>...........................] - ETA: 38:52 - loss: 0.7459 - accuracy: 0.7440 + 21/183 ━━━━━━━━━━━━━━━━━━━━ 37:08 14s/step - accuracy: 0.7148 - loss: 0.7631
``` - + ```
- 22/183 [==>...........................] - ETA: 38:37 - loss: 0.7396 - accuracy: 0.7557 + 22/183 ━━━━━━━━━━━━━━━━━━━━ 36:54 14s/step - accuracy: 0.7151 - loss: 0.7641
``` - + ```
- 23/183 [==>...........................] - ETA: 38:21 - loss: 0.7387 - accuracy: 0.7500 + 23/183 ━━━━━━━━━━━━━━━━━━━━ 36:40 14s/step - accuracy: 0.7152 - loss: 0.7652
``` - + ```
- 24/183 [==>...........................] - ETA: 38:06 - loss: 0.7266 - accuracy: 0.7552 + 24/183 ━━━━━━━━━━━━━━━━━━━━ 36:26 14s/step - accuracy: 0.7153 - loss: 0.7664
``` - + ```
- 25/183 [===>..........................] - ETA: 37:51 - loss: 0.7416 - accuracy: 0.7400 + 25/183 ━━━━━━━━━━━━━━━━━━━━ 36:11 14s/step - accuracy: 0.7151 - loss: 0.7678
``` - + ```
- 26/183 [===>..........................] - ETA: 37:37 - loss: 0.7411 - accuracy: 0.7404 + 26/183 ━━━━━━━━━━━━━━━━━━━━ 35:57 14s/step - accuracy: 0.7152 - loss: 0.7691
``` - + ```
- 27/183 [===>..........................] - ETA: 37:23 - loss: 0.7337 - accuracy: 0.7454 + 27/183 ━━━━━━━━━━━━━━━━━━━━ 35:43 14s/step - accuracy: 0.7154 - loss: 0.7699
``` - + ```
- 28/183 [===>..........................] - ETA: 37:09 - loss: 0.7336 - accuracy: 0.7411 + 28/183 ━━━━━━━━━━━━━━━━━━━━ 35:29 14s/step - accuracy: 0.7155 - loss: 0.7706
``` - + ```
- 29/183 [===>..........................] - ETA: 36:54 - loss: 0.7294 - accuracy: 0.7457 + 29/183 ━━━━━━━━━━━━━━━━━━━━ 35:15 14s/step - accuracy: 0.7160 - loss: 0.7709
``` - + ```
- 30/183 [===>..........................] - ETA: 36:40 - loss: 0.7293 - accuracy: 0.7417 + 30/183 ━━━━━━━━━━━━━━━━━━━━ 35:02 14s/step - accuracy: 0.7163 - loss: 0.7713
``` - + ```
- 31/183 [====>.........................] - ETA: 36:26 - loss: 0.7399 - accuracy: 0.7379 + 31/183 ━━━━━━━━━━━━━━━━━━━━ 34:48 14s/step - accuracy: 0.7165 - loss: 0.7717
``` - + ```
- 32/183 [====>.........................] - ETA: 36:11 - loss: 0.7355 - accuracy: 0.7422 + 32/183 ━━━━━━━━━━━━━━━━━━━━ 34:35 14s/step - accuracy: 0.7169 - loss: 0.7719
``` - + ```
- 33/183 [====>.........................] - ETA: 35:57 - loss: 0.7283 - accuracy: 0.7462 + 33/183 ━━━━━━━━━━━━━━━━━━━━ 34:21 14s/step - accuracy: 0.7174 - loss: 0.7720
``` - + ```
- 34/183 [====>.........................] - ETA: 35:43 - loss: 0.7330 - accuracy: 0.7426 + 34/183 ━━━━━━━━━━━━━━━━━━━━ 34:07 14s/step - accuracy: 0.7180 - loss: 0.7720
``` - + ```
- 35/183 [====>.........................] - ETA: 35:28 - loss: 0.7390 - accuracy: 0.7321 + 35/183 ━━━━━━━━━━━━━━━━━━━━ 33:54 14s/step - accuracy: 0.7184 - loss: 0.7721
``` - + ```
- 36/183 [====>.........................] - ETA: 35:14 - loss: 0.7381 - accuracy: 0.7292 + 36/183 ━━━━━━━━━━━━━━━━━━━━ 33:40 14s/step - accuracy: 0.7190 - loss: 0.7719
``` - + ```
- 37/183 [=====>........................] - ETA: 34:59 - loss: 0.7374 - accuracy: 0.7264 + 37/183 ━━━━━━━━━━━━━━━━━━━━ 33:27 14s/step - accuracy: 0.7195 - loss: 0.7718
``` - + ```
- 38/183 [=====>........................] - ETA: 34:45 - loss: 0.7359 - accuracy: 0.7303 + 38/183 ━━━━━━━━━━━━━━━━━━━━ 33:14 14s/step - accuracy: 0.7201 - loss: 0.7715
``` - + ```
- 39/183 [=====>........................] - ETA: 34:31 - loss: 0.7345 - accuracy: 0.7340 + 39/183 ━━━━━━━━━━━━━━━━━━━━ 33:00 14s/step - accuracy: 0.7206 - loss: 0.7712
``` - + ```
- 40/183 [=====>........................] - ETA: 34:16 - loss: 0.7355 - accuracy: 0.7344 + 40/183 ━━━━━━━━━━━━━━━━━━━━ 32:46 14s/step - accuracy: 0.7211 - loss: 0.7708
``` - + ```
- 41/183 [=====>........................] - ETA: 34:01 - loss: 0.7277 - accuracy: 0.7378 + 41/183 ━━━━━━━━━━━━━━━━━━━━ 32:32 14s/step - accuracy: 0.7217 - loss: 0.7702
``` - + ```
- 42/183 [=====>........................] - ETA: 33:48 - loss: 0.7305 - accuracy: 0.7381 + 42/183 ━━━━━━━━━━━━━━━━━━━━ 32:17 14s/step - accuracy: 0.7223 - loss: 0.7697
``` - + ```
- 43/183 [======>.......................] - ETA: 33:33 - loss: 0.7320 - accuracy: 0.7355 + 43/183 ━━━━━━━━━━━━━━━━━━━━ 32:03 14s/step - accuracy: 0.7229 - loss: 0.7691
``` - + ```
- 44/183 [======>.......................] - ETA: 33:18 - loss: 0.7283 - accuracy: 0.7386 + 44/183 ━━━━━━━━━━━━━━━━━━━━ 31:50 14s/step - accuracy: 0.7233 - loss: 0.7687
``` - + ```
- 45/183 [======>.......................] - ETA: 33:03 - loss: 0.7341 - accuracy: 0.7333 + 45/183 ━━━━━━━━━━━━━━━━━━━━ 31:35 14s/step - accuracy: 0.7237 - loss: 0.7684
``` - + ```
- 46/183 [======>.......................] - ETA: 32:48 - loss: 0.7445 - accuracy: 0.7255 + 46/183 ━━━━━━━━━━━━━━━━━━━━ 31:22 14s/step - accuracy: 0.7238 - loss: 0.7683
``` - + ```
- 47/183 [======>.......................] - ETA: 32:33 - loss: 0.7413 - accuracy: 0.7287 + 47/183 ━━━━━━━━━━━━━━━━━━━━ 31:08 14s/step - accuracy: 0.7240 - loss: 0.7681
``` - + ```
- 48/183 [======>.......................] - ETA: 32:18 - loss: 0.7428 - accuracy: 0.7292 + 48/183 ━━━━━━━━━━━━━━━━━━━━ 30:54 14s/step - accuracy: 0.7242 - loss: 0.7679
``` - + ```
- 49/183 [=======>......................] - ETA: 32:03 - loss: 0.7457 - accuracy: 0.7270 + 49/183 ━━━━━━━━━━━━━━━━━━━━ 30:40 14s/step - accuracy: 0.7243 - loss: 0.7679
``` - + ```
- 50/183 [=======>......................] - ETA: 31:49 - loss: 0.7504 - accuracy: 0.7250 + 50/183 ━━━━━━━━━━━━━━━━━━━━ 30:26 14s/step - accuracy: 0.7244 - loss: 0.7678
``` - + ```
- 51/183 [=======>......................] - ETA: 31:34 - loss: 0.7524 - accuracy: 0.7181 + 51/183 ━━━━━━━━━━━━━━━━━━━━ 30:12 14s/step - accuracy: 0.7244 - loss: 0.7678
``` - + ```
- 52/183 [=======>......................] - ETA: 31:19 - loss: 0.7636 - accuracy: 0.7163 + 52/183 ━━━━━━━━━━━━━━━━━━━━ 29:58 14s/step - accuracy: 0.7244 - loss: 0.7678
``` - + ```
- 53/183 [=======>......................] - ETA: 31:04 - loss: 0.7691 - accuracy: 0.7123 + 53/183 ━━━━━━━━━━━━━━━━━━━━ 29:44 14s/step - accuracy: 0.7244 - loss: 0.7678
``` - + ```
- 54/183 [=======>......................] - ETA: 30:50 - loss: 0.7681 - accuracy: 0.7130 + 54/183 ━━━━━━━━━━━━━━━━━━━━ 29:31 14s/step - accuracy: 0.7243 - loss: 0.7677
``` - + ```
- 55/183 [========>.....................] - ETA: 30:35 - loss: 0.7717 - accuracy: 0.7091 + 55/183 ━━━━━━━━━━━━━━━━━━━━ 29:17 14s/step - accuracy: 0.7243 - loss: 0.7677
``` - + ```
- 56/183 [========>.....................] - ETA: 30:20 - loss: 0.7725 - accuracy: 0.7098 + 56/183 ━━━━━━━━━━━━━━━━━━━━ 29:03 14s/step - accuracy: 0.7242 - loss: 0.7678
``` - + ```
- 57/183 [========>.....................] - ETA: 30:05 - loss: 0.7781 - accuracy: 0.7105 + 57/183 ━━━━━━━━━━━━━━━━━━━━ 28:49 14s/step - accuracy: 0.7242 - loss: 0.7678
``` - + ```
- 58/183 [========>.....................] - ETA: 29:51 - loss: 0.7811 - accuracy: 0.7091 + 58/183 ━━━━━━━━━━━━━━━━━━━━ 28:35 14s/step - accuracy: 0.7242 - loss: 0.7679
``` - + ```
- 59/183 [========>.....................] - ETA: 29:36 - loss: 0.7856 - accuracy: 0.7097 + 59/183 ━━━━━━━━━━━━━━━━━━━━ 28:21 14s/step - accuracy: 0.7241 - loss: 0.7680
``` - + ```
- 60/183 [========>.....................] - ETA: 29:22 - loss: 0.7853 - accuracy: 0.7083 + 60/183 ━━━━━━━━━━━━━━━━━━━━ 28:07 14s/step - accuracy: 0.7241 - loss: 0.7681
``` - + ```
- 61/183 [=========>....................] - ETA: 29:07 - loss: 0.7866 - accuracy: 0.7111 + 61/183 ━━━━━━━━━━━━━━━━━━━━ 27:54 14s/step - accuracy: 0.7241 - loss: 0.7682
``` - + ```
- 62/183 [=========>....................] - ETA: 28:53 - loss: 0.7861 - accuracy: 0.7117 + 62/183 ━━━━━━━━━━━━━━━━━━━━ 27:40 14s/step - accuracy: 0.7240 - loss: 0.7684
``` - + ```
- 63/183 [=========>....................] - ETA: 28:38 - loss: 0.7909 - accuracy: 0.7083 + 63/183 ━━━━━━━━━━━━━━━━━━━━ 27:26 14s/step - accuracy: 0.7238 - loss: 0.7687
``` - + ```
- 64/183 [=========>....................] - ETA: 28:24 - loss: 0.7890 - accuracy: 0.7070 + 64/183 ━━━━━━━━━━━━━━━━━━━━ 27:12 14s/step - accuracy: 0.7238 - loss: 0.7689
``` - + ```
- 65/183 [=========>....................] - ETA: 28:09 - loss: 0.7919 - accuracy: 0.7058 + 65/183 ━━━━━━━━━━━━━━━━━━━━ 26:58 14s/step - accuracy: 0.7238 - loss: 0.7691
``` - + ```
- 66/183 [=========>....................] - ETA: 27:54 - loss: 0.7981 - accuracy: 0.7027 + 66/183 ━━━━━━━━━━━━━━━━━━━━ 26:44 14s/step - accuracy: 0.7237 - loss: 0.7694
``` - + ```
- 67/183 [=========>....................] - ETA: 27:40 - loss: 0.7995 - accuracy: 0.7015 + 67/183 ━━━━━━━━━━━━━━━━━━━━ 26:31 14s/step - accuracy: 0.7237 - loss: 0.7697
``` - + ```
- 68/183 [==========>...................] - ETA: 27:25 - loss: 0.7972 - accuracy: 0.7022 + 68/183 ━━━━━━━━━━━━━━━━━━━━ 26:17 14s/step - accuracy: 0.7237 - loss: 0.7699
``` - + ```
- 69/183 [==========>...................] - ETA: 27:11 - loss: 0.7957 - accuracy: 0.7029 + 69/183 ━━━━━━━━━━━━━━━━━━━━ 26:03 14s/step - accuracy: 0.7236 - loss: 0.7701
``` - + ```
- 70/183 [==========>...................] - ETA: 26:57 - loss: 0.7951 - accuracy: 0.7036 + 70/183 ━━━━━━━━━━━━━━━━━━━━ 25:49 14s/step - accuracy: 0.7236 - loss: 0.7704
``` - + ```
- 71/183 [==========>...................] - ETA: 26:43 - loss: 0.7939 - accuracy: 0.7042 + 71/183 ━━━━━━━━━━━━━━━━━━━━ 25:35 14s/step - accuracy: 0.7235 - loss: 0.7705
``` - + ```
- 72/183 [==========>...................] - ETA: 26:28 - loss: 0.7897 - accuracy: 0.7049 + 72/183 ━━━━━━━━━━━━━━━━━━━━ 25:21 14s/step - accuracy: 0.7235 - loss: 0.7706
``` - + ```
- 73/183 [==========>...................] - ETA: 26:13 - loss: 0.7879 - accuracy: 0.7055 + 73/183 ━━━━━━━━━━━━━━━━━━━━ 25:07 14s/step - accuracy: 0.7235 - loss: 0.7708
``` - + ```
- 74/183 [===========>..................] - ETA: 25:59 - loss: 0.7864 - accuracy: 0.7044 + 74/183 ━━━━━━━━━━━━━━━━━━━━ 24:54 14s/step - accuracy: 0.7235 - loss: 0.7710
``` - + ```
- 75/183 [===========>..................] - ETA: 25:44 - loss: 0.7859 - accuracy: 0.7050 + 75/183 ━━━━━━━━━━━━━━━━━━━━ 24:40 14s/step - accuracy: 0.7235 - loss: 0.7711
``` - + ```
- 76/183 [===========>..................] - ETA: 25:30 - loss: 0.7883 - accuracy: 0.7056 + 76/183 ━━━━━━━━━━━━━━━━━━━━ 24:26 14s/step - accuracy: 0.7235 - loss: 0.7713
``` - + ```
- 77/183 [===========>..................] - ETA: 25:16 - loss: 0.7881 - accuracy: 0.7062 + 77/183 ━━━━━━━━━━━━━━━━━━━━ 24:12 14s/step - accuracy: 0.7234 - loss: 0.7714
``` - + ```
- 78/183 [===========>..................] - ETA: 25:01 - loss: 0.7931 - accuracy: 0.7035 + 78/183 ━━━━━━━━━━━━━━━━━━━━ 23:59 14s/step - accuracy: 0.7234 - loss: 0.7716
``` - + ```
- 79/183 [===========>..................] - ETA: 24:47 - loss: 0.7971 - accuracy: 0.7009 + 79/183 ━━━━━━━━━━━━━━━━━━━━ 23:45 14s/step - accuracy: 0.7233 - loss: 0.7717
``` - + ```
- 80/183 [============>.................] - ETA: 24:32 - loss: 0.7980 - accuracy: 0.7000 + 80/183 ━━━━━━━━━━━━━━━━━━━━ 23:31 14s/step - accuracy: 0.7233 - loss: 0.7718
``` - + ```
- 81/183 [============>.................] - ETA: 24:18 - loss: 0.7948 - accuracy: 0.7022 + 81/183 ━━━━━━━━━━━━━━━━━━━━ 23:17 14s/step - accuracy: 0.7232 - loss: 0.7719
``` - + ```
- 82/183 [============>.................] - ETA: 24:03 - loss: 0.7942 - accuracy: 0.7027 + 82/183 ━━━━━━━━━━━━━━━━━━━━ 23:04 14s/step - accuracy: 0.7232 - loss: 0.7721
``` - + ```
- 83/183 [============>.................] - ETA: 23:49 - loss: 0.7900 - accuracy: 0.7048 + 83/183 ━━━━━━━━━━━━━━━━━━━━ 22:50 14s/step - accuracy: 0.7231 - loss: 0.7722
``` - + ```
- 84/183 [============>.................] - ETA: 23:35 - loss: 0.7926 - accuracy: 0.7024 + 84/183 ━━━━━━━━━━━━━━━━━━━━ 22:36 14s/step - accuracy: 0.7231 - loss: 0.7723
``` - + ```
- 85/183 [============>.................] - ETA: 23:20 - loss: 0.7966 - accuracy: 0.7000 + 85/183 ━━━━━━━━━━━━━━━━━━━━ 22:22 14s/step - accuracy: 0.7231 - loss: 0.7724
``` - + ```
- 86/183 [=============>................] - ETA: 23:06 - loss: 0.7997 - accuracy: 0.6977 + 86/183 ━━━━━━━━━━━━━━━━━━━━ 22:08 14s/step - accuracy: 0.7230 - loss: 0.7725
``` - + ```
- 87/183 [=============>................] - ETA: 22:52 - loss: 0.7973 - accuracy: 0.6997 + 87/183 ━━━━━━━━━━━━━━━━━━━━ 21:55 14s/step - accuracy: 0.7230 - loss: 0.7726
``` - + ```
- 88/183 [=============>................] - ETA: 22:38 - loss: 0.8052 - accuracy: 0.6960 + 88/183 ━━━━━━━━━━━━━━━━━━━━ 21:41 14s/step - accuracy: 0.7230 - loss: 0.7727
``` - + ```
- 89/183 [=============>................] - ETA: 22:23 - loss: 0.8064 - accuracy: 0.6952 + 89/183 ━━━━━━━━━━━━━━━━━━━━ 21:27 14s/step - accuracy: 0.7229 - loss: 0.7728
``` - + ```
- 90/183 [=============>................] - ETA: 22:09 - loss: 0.8023 - accuracy: 0.6972 + 90/183 ━━━━━━━━━━━━━━━━━━━━ 21:13 14s/step - accuracy: 0.7229 - loss: 0.7729
``` - + ```
- 91/183 [=============>................] - ETA: 21:54 - loss: 0.8045 - accuracy: 0.6978 + 91/183 ━━━━━━━━━━━━━━━━━━━━ 21:00 14s/step - accuracy: 0.7229 - loss: 0.7731
``` - + ```
- 92/183 [==============>...............] - ETA: 21:40 - loss: 0.8056 - accuracy: 0.6984 + 92/183 ━━━━━━━━━━━━━━━━━━━━ 20:46 14s/step - accuracy: 0.7228 - loss: 0.7733
``` - + ```
- 93/183 [==============>...............] - ETA: 21:26 - loss: 0.8058 - accuracy: 0.6976 + 93/183 ━━━━━━━━━━━━━━━━━━━━ 20:32 14s/step - accuracy: 0.7228 - loss: 0.7734
``` - + ```
- 94/183 [==============>...............] - ETA: 21:11 - loss: 0.8039 - accuracy: 0.6981 + 94/183 ━━━━━━━━━━━━━━━━━━━━ 20:18 14s/step - accuracy: 0.7229 - loss: 0.7735
``` - + ```
- 95/183 [==============>...............] - ETA: 20:57 - loss: 0.8073 - accuracy: 0.6987 + 95/183 ━━━━━━━━━━━━━━━━━━━━ 20:05 14s/step - accuracy: 0.7229 - loss: 0.7736
``` - + ```
- 96/183 [==============>...............] - ETA: 20:42 - loss: 0.8063 - accuracy: 0.6992 + 96/183 ━━━━━━━━━━━━━━━━━━━━ 19:51 14s/step - accuracy: 0.7229 - loss: 0.7737
``` - + ```
- 97/183 [==============>...............] - ETA: 20:28 - loss: 0.8076 - accuracy: 0.6972 + 97/183 ━━━━━━━━━━━━━━━━━━━━ 19:37 14s/step - accuracy: 0.7229 - loss: 0.7739
``` - + ```
- 98/183 [===============>..............] - ETA: 20:14 - loss: 0.8061 - accuracy: 0.6977 + 98/183 ━━━━━━━━━━━━━━━━━━━━ 19:23 14s/step - accuracy: 0.7230 - loss: 0.7740
``` - + ```
- 99/183 [===============>..............] - ETA: 19:59 - loss: 0.8094 - accuracy: 0.6944 + 99/183 ━━━━━━━━━━━━━━━━━━━━ 19:10 14s/step - accuracy: 0.7230 - loss: 0.7742
``` - + ```
-100/183 [===============>..............] - ETA: 19:45 - loss: 0.8154 - accuracy: 0.6925 + 100/183 ━━━━━━━━━━━━━━━━━━━━ 18:56 14s/step - accuracy: 0.7230 - loss: 0.7744
``` - + ```
-101/183 [===============>..............] - ETA: 19:31 - loss: 0.8130 - accuracy: 0.6943 + 101/183 ━━━━━━━━━━━━━━━━━━━━ 18:42 14s/step - accuracy: 0.7230 - loss: 0.7745
``` - + ```
-102/183 [===============>..............] - ETA: 19:16 - loss: 0.8113 - accuracy: 0.6949 + 102/183 ━━━━━━━━━━━━━━━━━━━━ 18:28 14s/step - accuracy: 0.7231 - loss: 0.7747
``` - + ```
-103/183 [===============>..............] - ETA: 19:02 - loss: 0.8098 - accuracy: 0.6966 + 103/183 ━━━━━━━━━━━━━━━━━━━━ 18:15 14s/step - accuracy: 0.7231 - loss: 0.7748
``` - + ```
-104/183 [================>.............] - ETA: 18:48 - loss: 0.8088 - accuracy: 0.6971 + 104/183 ━━━━━━━━━━━━━━━━━━━━ 18:01 14s/step - accuracy: 0.7231 - loss: 0.7750
``` - + ```
-105/183 [================>.............] - ETA: 18:33 - loss: 0.8074 - accuracy: 0.6976 + 105/183 ━━━━━━━━━━━━━━━━━━━━ 17:47 14s/step - accuracy: 0.7231 - loss: 0.7752
``` - + ```
-106/183 [================>.............] - ETA: 18:19 - loss: 0.8061 - accuracy: 0.6981 + 106/183 ━━━━━━━━━━━━━━━━━━━━ 17:33 14s/step - accuracy: 0.7231 - loss: 0.7753
``` - + ```
-107/183 [================>.............] - ETA: 18:05 - loss: 0.8043 - accuracy: 0.6986 + 107/183 ━━━━━━━━━━━━━━━━━━━━ 17:20 14s/step - accuracy: 0.7231 - loss: 0.7754
``` - + ```
-108/183 [================>.............] - ETA: 17:50 - loss: 0.8021 - accuracy: 0.7002 + 108/183 ━━━━━━━━━━━━━━━━━━━━ 17:06 14s/step - accuracy: 0.7231 - loss: 0.7755
``` - + ```
-109/183 [================>.............] - ETA: 17:36 - loss: 0.8002 - accuracy: 0.7018 + 109/183 ━━━━━━━━━━━━━━━━━━━━ 16:52 14s/step - accuracy: 0.7231 - loss: 0.7757
``` - + ```
-110/183 [=================>............] - ETA: 17:22 - loss: 0.7979 - accuracy: 0.7045 + 110/183 ━━━━━━━━━━━━━━━━━━━━ 16:39 14s/step - accuracy: 0.7231 - loss: 0.7758
``` - + ```
-111/183 [=================>............] - ETA: 17:07 - loss: 0.7951 - accuracy: 0.7050 + 111/183 ━━━━━━━━━━━━━━━━━━━━ 16:25 14s/step - accuracy: 0.7231 - loss: 0.7759
``` - + ```
-112/183 [=================>............] - ETA: 16:53 - loss: 0.7978 - accuracy: 0.7009 + 112/183 ━━━━━━━━━━━━━━━━━━━━ 16:11 14s/step - accuracy: 0.7231 - loss: 0.7760
``` - + ```
-113/183 [=================>............] - ETA: 16:39 - loss: 0.7977 - accuracy: 0.7013 + 113/183 ━━━━━━━━━━━━━━━━━━━━ 15:58 14s/step - accuracy: 0.7231 - loss: 0.7761
``` - + ```
-114/183 [=================>............] - ETA: 16:24 - loss: 0.8027 - accuracy: 0.6974 + 114/183 ━━━━━━━━━━━━━━━━━━━━ 15:44 14s/step - accuracy: 0.7230 - loss: 0.7763
``` - + ```
-115/183 [=================>............] - ETA: 16:10 - loss: 0.7983 - accuracy: 0.7000 + 115/183 ━━━━━━━━━━━━━━━━━━━━ 15:30 14s/step - accuracy: 0.7230 - loss: 0.7764
``` - + ```
-116/183 [==================>...........] - ETA: 15:56 - loss: 0.8009 - accuracy: 0.6983 + 116/183 ━━━━━━━━━━━━━━━━━━━━ 15:16 14s/step - accuracy: 0.7230 - loss: 0.7765
``` - + ```
-117/183 [==================>...........] - ETA: 15:41 - loss: 0.8030 - accuracy: 0.6976 + 117/183 ━━━━━━━━━━━━━━━━━━━━ 15:03 14s/step - accuracy: 0.7230 - loss: 0.7767
``` - + ```
-118/183 [==================>...........] - ETA: 15:27 - loss: 0.8015 - accuracy: 0.6981 + 118/183 ━━━━━━━━━━━━━━━━━━━━ 14:49 14s/step - accuracy: 0.7230 - loss: 0.7768
``` - + ```
-119/183 [==================>...........] - ETA: 15:13 - loss: 0.7986 - accuracy: 0.6996 + 119/183 ━━━━━━━━━━━━━━━━━━━━ 14:35 14s/step - accuracy: 0.7230 - loss: 0.7769
``` - + ```
-120/183 [==================>...........] - ETA: 14:59 - loss: 0.7966 - accuracy: 0.7010 + 120/183 ━━━━━━━━━━━━━━━━━━━━ 14:22 14s/step - accuracy: 0.7230 - loss: 0.7770
``` - + ```
-121/183 [==================>...........] - ETA: 14:44 - loss: 0.7946 - accuracy: 0.7025 + 121/183 ━━━━━━━━━━━━━━━━━━━━ 14:08 14s/step - accuracy: 0.7230 - loss: 0.7771
``` - + ```
-122/183 [===================>..........] - ETA: 14:30 - loss: 0.7923 - accuracy: 0.7049 + 122/183 ━━━━━━━━━━━━━━━━━━━━ 13:54 14s/step - accuracy: 0.7231 - loss: 0.7771
``` - + ```
-123/183 [===================>..........] - ETA: 14:16 - loss: 0.7925 - accuracy: 0.7043 + 123/183 ━━━━━━━━━━━━━━━━━━━━ 13:40 14s/step - accuracy: 0.7230 - loss: 0.7772
``` - + ```
-124/183 [===================>..........] - ETA: 14:01 - loss: 0.7932 - accuracy: 0.7046 + 124/183 ━━━━━━━━━━━━━━━━━━━━ 13:27 14s/step - accuracy: 0.7230 - loss: 0.7773
``` - + ```
-125/183 [===================>..........] - ETA: 13:47 - loss: 0.7914 - accuracy: 0.7070 + 125/183 ━━━━━━━━━━━━━━━━━━━━ 13:13 14s/step - accuracy: 0.7230 - loss: 0.7773
``` - + ```
-126/183 [===================>..........] - ETA: 13:33 - loss: 0.7918 - accuracy: 0.7054 + 126/183 ━━━━━━━━━━━━━━━━━━━━ 12:59 14s/step - accuracy: 0.7230 - loss: 0.7774
``` - + ```
-127/183 [===================>..........] - ETA: 13:19 - loss: 0.7911 - accuracy: 0.7057 + 127/183 ━━━━━━━━━━━━━━━━━━━━ 12:46 14s/step - accuracy: 0.7230 - loss: 0.7775
``` - + ```
-128/183 [===================>..........] - ETA: 13:04 - loss: 0.7901 - accuracy: 0.7061 + 128/183 ━━━━━━━━━━━━━━━━━━━━ 12:32 14s/step - accuracy: 0.7230 - loss: 0.7775
``` - + ```
-129/183 [====================>.........] - ETA: 12:50 - loss: 0.7908 - accuracy: 0.7054 + 129/183 ━━━━━━━━━━━━━━━━━━━━ 12:18 14s/step - accuracy: 0.7231 - loss: 0.7775
``` - + ```
-130/183 [====================>.........] - ETA: 12:36 - loss: 0.7887 - accuracy: 0.7067 + 130/183 ━━━━━━━━━━━━━━━━━━━━ 12:05 14s/step - accuracy: 0.7231 - loss: 0.7776
``` - + ```
-131/183 [====================>.........] - ETA: 12:21 - loss: 0.7877 - accuracy: 0.7080 + 131/183 ━━━━━━━━━━━━━━━━━━━━ 11:51 14s/step - accuracy: 0.7231 - loss: 0.7776
``` - + ```
-132/183 [====================>.........] - ETA: 12:07 - loss: 0.7871 - accuracy: 0.7083 + 132/183 ━━━━━━━━━━━━━━━━━━━━ 11:37 14s/step - accuracy: 0.7231 - loss: 0.7776
``` - + ```
-133/183 [====================>.........] - ETA: 11:53 - loss: 0.7852 - accuracy: 0.7096 + 133/183 ━━━━━━━━━━━━━━━━━━━━ 11:24 14s/step - accuracy: 0.7232 - loss: 0.7776
``` - + ```
-134/183 [====================>.........] - ETA: 11:39 - loss: 0.7828 - accuracy: 0.7118 + 134/183 ━━━━━━━━━━━━━━━━━━━━ 11:10 14s/step - accuracy: 0.7232 - loss: 0.7776
``` - + ```
-135/183 [=====================>........] - ETA: 11:24 - loss: 0.7804 - accuracy: 0.7139 + 135/183 ━━━━━━━━━━━━━━━━━━━━ 10:56 14s/step - accuracy: 0.7232 - loss: 0.7775
``` - + ```
-136/183 [=====================>........] - ETA: 11:10 - loss: 0.7790 - accuracy: 0.7151 + 136/183 ━━━━━━━━━━━━━━━━━━━━ 10:42 14s/step - accuracy: 0.7233 - loss: 0.7775
``` - + ```
-137/183 [=====================>........] - ETA: 10:56 - loss: 0.7804 - accuracy: 0.7144 + 137/183 ━━━━━━━━━━━━━━━━━━━━ 10:29 14s/step - accuracy: 0.7233 - loss: 0.7775
``` - + ```
-138/183 [=====================>........] - ETA: 10:41 - loss: 0.7795 - accuracy: 0.7156 + 138/183 ━━━━━━━━━━━━━━━━━━━━ 10:15 14s/step - accuracy: 0.7233 - loss: 0.7775
``` - + ```
-139/183 [=====================>........] - ETA: 10:27 - loss: 0.7800 - accuracy: 0.7149 + 139/183 ━━━━━━━━━━━━━━━━━━━━ 10:01 14s/step - accuracy: 0.7233 - loss: 0.7775
``` - + ```
-140/183 [=====================>........] - ETA: 10:13 - loss: 0.7802 - accuracy: 0.7143 + 140/183 ━━━━━━━━━━━━━━━━━━━━ 9:48 14s/step - accuracy: 0.7233 - loss: 0.7776
``` - + ```
-141/183 [======================>.......] - ETA: 9:59 - loss: 0.7813 - accuracy: 0.7137 + 141/183 ━━━━━━━━━━━━━━━━━━━━ 9:34 14s/step - accuracy: 0.7233 - loss: 0.7776
``` - + ```
-142/183 [======================>.......] - ETA: 9:44 - loss: 0.7843 - accuracy: 0.7130 + 142/183 ━━━━━━━━━━━━━━━━━━━━ 9:20 14s/step - accuracy: 0.7233 - loss: 0.7776
``` - + ```
-143/183 [======================>.......] - ETA: 9:30 - loss: 0.7841 - accuracy: 0.7133 + 143/183 ━━━━━━━━━━━━━━━━━━━━ 9:07 14s/step - accuracy: 0.7233 - loss: 0.7776
``` - + ```
-144/183 [======================>.......] - ETA: 9:16 - loss: 0.7848 - accuracy: 0.7135 + 144/183 ━━━━━━━━━━━━━━━━━━━━ 8:53 14s/step - accuracy: 0.7233 - loss: 0.7776
``` - + ```
-145/183 [======================>.......] - ETA: 9:01 - loss: 0.7835 - accuracy: 0.7138 + 145/183 ━━━━━━━━━━━━━━━━━━━━ 8:39 14s/step - accuracy: 0.7232 - loss: 0.7777
``` - + ```
-146/183 [======================>.......] - ETA: 8:47 - loss: 0.7817 - accuracy: 0.7149 + 146/183 ━━━━━━━━━━━━━━━━━━━━ 8:26 14s/step - accuracy: 0.7232 - loss: 0.7777
``` - + ```
-147/183 [=======================>......] - ETA: 8:33 - loss: 0.7827 - accuracy: 0.7143 + 147/183 ━━━━━━━━━━━━━━━━━━━━ 8:12 14s/step - accuracy: 0.7232 - loss: 0.7778
``` - + ```
-148/183 [=======================>......] - ETA: 8:19 - loss: 0.7813 - accuracy: 0.7145 + 148/183 ━━━━━━━━━━━━━━━━━━━━ 7:58 14s/step - accuracy: 0.7231 - loss: 0.7778
``` - + ```
-149/183 [=======================>......] - ETA: 8:04 - loss: 0.7820 - accuracy: 0.7148 + 149/183 ━━━━━━━━━━━━━━━━━━━━ 7:44 14s/step - accuracy: 0.7231 - loss: 0.7778
``` - + ```
-150/183 [=======================>......] - ETA: 7:50 - loss: 0.7804 - accuracy: 0.7158 + 150/183 ━━━━━━━━━━━━━━━━━━━━ 7:31 14s/step - accuracy: 0.7230 - loss: 0.7779
``` - + ```
-151/183 [=======================>......] - ETA: 7:36 - loss: 0.7809 - accuracy: 0.7169 + 151/183 ━━━━━━━━━━━━━━━━━━━━ 7:17 14s/step - accuracy: 0.7230 - loss: 0.7779
``` - + ```
-152/183 [=======================>......] - ETA: 7:22 - loss: 0.7802 - accuracy: 0.7171 + 152/183 ━━━━━━━━━━━━━━━━━━━━ 7:03 14s/step - accuracy: 0.7230 - loss: 0.7779
``` - + ```
-153/183 [========================>.....] - ETA: 7:07 - loss: 0.7851 - accuracy: 0.7141 + 153/183 ━━━━━━━━━━━━━━━━━━━━ 6:50 14s/step - accuracy: 0.7229 - loss: 0.7779
``` - + ```
-154/183 [========================>.....] - ETA: 6:53 - loss: 0.7865 - accuracy: 0.7135 + 154/183 ━━━━━━━━━━━━━━━━━━━━ 6:36 14s/step - accuracy: 0.7229 - loss: 0.7779
``` - + ```
-155/183 [========================>.....] - ETA: 6:39 - loss: 0.7845 - accuracy: 0.7145 + 155/183 ━━━━━━━━━━━━━━━━━━━━ 6:22 14s/step - accuracy: 0.7228 - loss: 0.7779
``` - + ```
-156/183 [========================>.....] - ETA: 6:24 - loss: 0.7830 - accuracy: 0.7155 + 156/183 ━━━━━━━━━━━━━━━━━━━━ 6:09 14s/step - accuracy: 0.7228 - loss: 0.7779
``` - + ```
-157/183 [========================>.....] - ETA: 6:10 - loss: 0.7830 - accuracy: 0.7150 + 157/183 ━━━━━━━━━━━━━━━━━━━━ 5:55 14s/step - accuracy: 0.7228 - loss: 0.7779
``` - + ```
-158/183 [========================>.....] - ETA: 5:56 - loss: 0.7843 - accuracy: 0.7152 + 158/183 ━━━━━━━━━━━━━━━━━━━━ 5:41 14s/step - accuracy: 0.7228 - loss: 0.7779
``` - + ```
-159/183 [=========================>....] - ETA: 5:42 - loss: 0.7841 - accuracy: 0.7146 + 159/183 ━━━━━━━━━━━━━━━━━━━━ 5:28 14s/step - accuracy: 0.7227 - loss: 0.7779
``` - + ```
-160/183 [=========================>....] - ETA: 5:27 - loss: 0.7842 - accuracy: 0.7148 + 160/183 ━━━━━━━━━━━━━━━━━━━━ 5:14 14s/step - accuracy: 0.7227 - loss: 0.7779
``` - + ```
-161/183 [=========================>....] - ETA: 5:13 - loss: 0.7826 - accuracy: 0.7151 + 161/183 ━━━━━━━━━━━━━━━━━━━━ 5:00 14s/step - accuracy: 0.7226 - loss: 0.7779
``` - + ```
-162/183 [=========================>....] - ETA: 4:59 - loss: 0.7822 - accuracy: 0.7160 + 162/183 ━━━━━━━━━━━━━━━━━━━━ 4:47 14s/step - accuracy: 0.7226 - loss: 0.7780
``` - + ```
-163/183 [=========================>....] - ETA: 4:45 - loss: 0.7811 - accuracy: 0.7163 + 163/183 ━━━━━━━━━━━━━━━━━━━━ 4:33 14s/step - accuracy: 0.7226 - loss: 0.7780
``` - + ```
-164/183 [=========================>....] - ETA: 4:30 - loss: 0.7808 - accuracy: 0.7157 + 164/183 ━━━━━━━━━━━━━━━━━━━━ 4:19 14s/step - accuracy: 0.7225 - loss: 0.7780
``` - + ```
-165/183 [==========================>...] - ETA: 4:16 - loss: 0.7798 - accuracy: 0.7167 + 165/183 ━━━━━━━━━━━━━━━━━━━━ 4:06 14s/step - accuracy: 0.7225 - loss: 0.7780
``` - + ```
-166/183 [==========================>...] - ETA: 4:02 - loss: 0.7796 - accuracy: 0.7169 + 166/183 ━━━━━━━━━━━━━━━━━━━━ 3:52 14s/step - accuracy: 0.7225 - loss: 0.7780
``` - + ```
-167/183 [==========================>...] - ETA: 3:48 - loss: 0.7798 - accuracy: 0.7171 + 167/183 ━━━━━━━━━━━━━━━━━━━━ 3:38 14s/step - accuracy: 0.7224 - loss: 0.7780
``` - + ```
-168/183 [==========================>...] - ETA: 3:33 - loss: 0.7794 - accuracy: 0.7173 + 168/183 ━━━━━━━━━━━━━━━━━━━━ 3:25 14s/step - accuracy: 0.7224 - loss: 0.7780
``` - + ```
-169/183 [==========================>...] - ETA: 3:19 - loss: 0.7796 - accuracy: 0.7167 + 169/183 ━━━━━━━━━━━━━━━━━━━━ 3:11 14s/step - accuracy: 0.7224 - loss: 0.7779
``` - + ```
-170/183 [==========================>...] - ETA: 3:05 - loss: 0.7789 - accuracy: 0.7162 + 170/183 ━━━━━━━━━━━━━━━━━━━━ 2:57 14s/step - accuracy: 0.7223 - loss: 0.7779
``` - + ```
-171/183 [===========================>..] - ETA: 2:51 - loss: 0.7807 - accuracy: 0.7142 + 171/183 ━━━━━━━━━━━━━━━━━━━━ 2:44 14s/step - accuracy: 0.7223 - loss: 0.7780
``` - + ```
-172/183 [===========================>..] - ETA: 2:36 - loss: 0.7788 - accuracy: 0.7151 + 172/183 ━━━━━━━━━━━━━━━━━━━━ 2:30 14s/step - accuracy: 0.7223 - loss: 0.7780
``` - + ```
-173/183 [===========================>..] - ETA: 2:22 - loss: 0.7807 - accuracy: 0.7139 + 173/183 ━━━━━━━━━━━━━━━━━━━━ 2:16 14s/step - accuracy: 0.7222 - loss: 0.7780
``` - + ```
-174/183 [===========================>..] - ETA: 2:08 - loss: 0.7793 - accuracy: 0.7148 + 174/183 ━━━━━━━━━━━━━━━━━━━━ 2:03 14s/step - accuracy: 0.7222 - loss: 0.7780
``` - + ```
-175/183 [===========================>..] - ETA: 1:54 - loss: 0.7791 - accuracy: 0.7157 + 175/183 ━━━━━━━━━━━━━━━━━━━━ 1:49 14s/step - accuracy: 0.7222 - loss: 0.7780
``` - + ```
-176/183 [===========================>..] - ETA: 1:39 - loss: 0.7799 - accuracy: 0.7138 + 176/183 ━━━━━━━━━━━━━━━━━━━━ 1:35 14s/step - accuracy: 0.7221 - loss: 0.7779
``` - + ```
-177/183 [============================>.] - ETA: 1:25 - loss: 0.7768 - accuracy: 0.7154 + 177/183 ━━━━━━━━━━━━━━━━━━━━ 1:22 14s/step - accuracy: 0.7221 - loss: 0.7779
``` - + ```
-178/183 [============================>.] - ETA: 1:11 - loss: 0.7748 - accuracy: 0.7156 + 178/183 ━━━━━━━━━━━━━━━━━━━━ 1:08 14s/step - accuracy: 0.7221 - loss: 0.7779
``` - + ```
-179/183 [============================>.] - ETA: 57s - loss: 0.7741 - accuracy: 0.7158 + 179/183 ━━━━━━━━━━━━━━━━━━━━ 54s 14s/step - accuracy: 0.7221 - loss: 0.7779
``` - + ```
-180/183 [============================>.] - ETA: 42s - loss: 0.7740 - accuracy: 0.7153 + 180/183 ━━━━━━━━━━━━━━━━━━━━ 41s 14s/step - accuracy: 0.7221 - loss: 0.7778
``` - + ```
-181/183 [============================>.] - ETA: 28s - loss: 0.7727 - accuracy: 0.7162 + 181/183 ━━━━━━━━━━━━━━━━━━━━ 27s 14s/step - accuracy: 0.7220 - loss: 0.7778
``` - + ```
-182/183 [============================>.] - ETA: 14s - loss: 0.7719 - accuracy: 0.7163 + 182/183 ━━━━━━━━━━━━━━━━━━━━ 13s 14s/step - accuracy: 0.7220 - loss: 0.7778
``` - + ```
-183/183 [==============================] - ETA: 0s - loss: 0.7714 - accuracy: 0.7158 + 183/183 ━━━━━━━━━━━━━━━━━━━━ 0s 14s/step - accuracy: 0.7220 - loss: 0.7778
``` - + ```
-183/183 [==============================] - 2764s 15s/step - loss: 0.7714 - accuracy: 0.7158 - val_loss: 0.7098 - val_accuracy: 0.7500 - lr: 4.4984e-06 + 183/183 ━━━━━━━━━━━━━━━━━━━━ 2649s 14s/step - accuracy: 0.7220 - loss: 0.7777 - val_accuracy: 0.7650 - val_loss: 0.7110 - learning_rate: 4.4984e-06 --- @@ -7479,357 +7202,357 @@ for i in range(0, 50, 10): ``` - 1/50 [..............................] - ETA: 32:35 + 1/50 ━━━━━━━━━━━━━━━━━━━━ 27:32 34s/step
``` - + ```
- 2/50 [>.............................] - ETA: 2:26 + 2/50 ━━━━━━━━━━━━━━━━━━━━ 2:17 3s/step
``` - + ```
- 3/50 [>.............................] - ETA: 2:25 + 3/50 ━━━━━━━━━━━━━━━━━━━━ 2:14 3s/step
``` - + ```
- 4/50 [=>............................] - ETA: 2:22 + 4/50 ━━━━━━━━━━━━━━━━━━━━ 2:12 3s/step
``` - + ```
- 5/50 [==>...........................] - ETA: 2:19 + 5/50 ━━━━━━━━━━━━━━━━━━━━ 2:10 3s/step
``` - + ```
- 6/50 [==>...........................] - ETA: 2:16 + 6/50 ━━━━━━━━━━━━━━━━━━━━ 2:06 3s/step
``` - + ```
- 7/50 [===>..........................] - ETA: 2:13 + 7/50 ━━━━━━━━━━━━━━━━━━━━ 2:04 3s/step
``` - + ```
- 8/50 [===>..........................] - ETA: 2:10 + 8/50 ━━━━━━━━━━━━━━━━━━━━ 2:01 3s/step
``` - + ```
- 9/50 [====>.........................] - ETA: 2:07 + 9/50 ━━━━━━━━━━━━━━━━━━━━ 1:58 3s/step
``` - + ```
-10/50 [=====>........................] - ETA: 2:04 + 10/50 ━━━━━━━━━━━━━━━━━━━━ 1:55 3s/step
``` - + ```
-11/50 [=====>........................] - ETA: 2:01 + 11/50 ━━━━━━━━━━━━━━━━━━━━ 1:52 3s/step
``` - + ```
-12/50 [======>.......................] - ETA: 1:58 + 12/50 ━━━━━━━━━━━━━━━━━━━━ 1:49 3s/step
``` - + ```
-13/50 [======>.......................] - ETA: 1:55 + 13/50 ━━━━━━━━━━━━━━━━━━━━ 1:46 3s/step
``` - + ```
-14/50 [=======>......................] - ETA: 1:51 + 14/50 ━━━━━━━━━━━━━━━━━━━━ 1:43 3s/step
``` - + ```
-15/50 [========>.....................] - ETA: 1:48 + 15/50 ━━━━━━━━━━━━━━━━━━━━ 1:41 3s/step
``` - + ```
-16/50 [========>.....................] - ETA: 1:45 + 16/50 ━━━━━━━━━━━━━━━━━━━━ 1:38 3s/step
``` - + ```
-17/50 [=========>....................] - ETA: 1:42 + 17/50 ━━━━━━━━━━━━━━━━━━━━ 1:35 3s/step
``` - + ```
-18/50 [=========>....................] - ETA: 1:39 + 18/50 ━━━━━━━━━━━━━━━━━━━━ 1:32 3s/step
``` - + ```
-19/50 [==========>...................] - ETA: 1:36 + 19/50 ━━━━━━━━━━━━━━━━━━━━ 1:29 3s/step
``` - + ```
-20/50 [===========>..................] - ETA: 1:33 + 20/50 ━━━━━━━━━━━━━━━━━━━━ 1:26 3s/step
``` - + ```
-21/50 [===========>..................] - ETA: 1:30 + 21/50 ━━━━━━━━━━━━━━━━━━━━ 1:23 3s/step
``` - + ```
-22/50 [============>.................] - ETA: 1:26 + 22/50 ━━━━━━━━━━━━━━━━━━━━ 1:20 3s/step
``` - + ```
-23/50 [============>.................] - ETA: 1:23 + 23/50 ━━━━━━━━━━━━━━━━━━━━ 1:17 3s/step
``` - + ```
-24/50 [=============>................] - ETA: 1:20 + 24/50 ━━━━━━━━━━━━━━━━━━━━ 1:15 3s/step
``` - + ```
-25/50 [==============>...............] - ETA: 1:17 + 25/50 ━━━━━━━━━━━━━━━━━━━━ 1:12 3s/step
``` - + ```
-26/50 [==============>...............] - ETA: 1:14 + 26/50 ━━━━━━━━━━━━━━━━━━━━ 1:09 3s/step
``` - + ```
-27/50 [===============>..............] - ETA: 1:11 + 27/50 ━━━━━━━━━━━━━━━━━━━━ 1:06 3s/step
``` - + ```
-28/50 [===============>..............] - ETA: 1:08 + 28/50 ━━━━━━━━━━━━━━━━━━━━ 1:03 3s/step
``` - + ```
-29/50 [================>.............] - ETA: 1:05 + 29/50 ━━━━━━━━━━━━━━━━━━━━ 1:00 3s/step
``` - + ```
-30/50 [=================>............] - ETA: 1:02 + 30/50 ━━━━━━━━━━━━━━━━━━━━ 57s 3s/step
``` - + ```
-31/50 [=================>............] - ETA: 58s + 31/50 ━━━━━━━━━━━━━━━━━━━━ 54s 3s/step
``` - + ```
-32/50 [==================>...........] - ETA: 55s + 32/50 ━━━━━━━━━━━━━━━━━━━━ 51s 3s/step
``` - + ```
-33/50 [==================>...........] - ETA: 52s + 33/50 ━━━━━━━━━━━━━━━━━━━━ 49s 3s/step
``` - + ```
-34/50 [===================>..........] - ETA: 49s + 34/50 ━━━━━━━━━━━━━━━━━━━━ 46s 3s/step
``` - + ```
-35/50 [====================>.........] - ETA: 46s + 35/50 ━━━━━━━━━━━━━━━━━━━━ 43s 3s/step
``` - + ```
-36/50 [====================>.........] - ETA: 43s + 36/50 ━━━━━━━━━━━━━━━━━━━━ 40s 3s/step
``` - + ```
-37/50 [=====================>........] - ETA: 40s + 37/50 ━━━━━━━━━━━━━━━━━━━━ 37s 3s/step
``` - + ```
-38/50 [=====================>........] - ETA: 37s + 38/50 ━━━━━━━━━━━━━━━━━━━━ 34s 3s/step
``` - + ```
-39/50 [======================>.......] - ETA: 34s + 39/50 ━━━━━━━━━━━━━━━━━━━━ 31s 3s/step
``` - + ```
-40/50 [=======================>......] - ETA: 31s + 40/50 ━━━━━━━━━━━━━━━━━━━━ 28s 3s/step
``` - + ```
-41/50 [=======================>......] - ETA: 27s + 41/50 ━━━━━━━━━━━━━━━━━━━━ 25s 3s/step
``` - + ```
-42/50 [========================>.....] - ETA: 24s + 42/50 ━━━━━━━━━━━━━━━━━━━━ 23s 3s/step
``` - + ```
-43/50 [========================>.....] - ETA: 21s + 43/50 ━━━━━━━━━━━━━━━━━━━━ 20s 3s/step
``` - + ```
-44/50 [=========================>....] - ETA: 18s + 44/50 ━━━━━━━━━━━━━━━━━━━━ 17s 3s/step
``` - + ```
-45/50 [==========================>...] - ETA: 15s + 45/50 ━━━━━━━━━━━━━━━━━━━━ 14s 3s/step
``` - + ```
-46/50 [==========================>...] - ETA: 12s + 46/50 ━━━━━━━━━━━━━━━━━━━━ 11s 3s/step
``` - + ```
-47/50 [===========================>..] - ETA: 9s + 47/50 ━━━━━━━━━━━━━━━━━━━━ 8s 3s/step
``` - + ```
-48/50 [===========================>..] - ETA: 6s + 48/50 ━━━━━━━━━━━━━━━━━━━━ 5s 3s/step
``` - + ```
-49/50 [============================>.] - ETA: 3s + 49/50 ━━━━━━━━━━━━━━━━━━━━ 2s 3s/step
``` - + ```
-50/50 [==============================] - ETA: 0s + 50/50 ━━━━━━━━━━━━━━━━━━━━ 0s 3s/step
``` - + ```
-50/50 [==============================] - 192s 3s/step + 50/50 ━━━━━━━━━━━━━━━━━━━━ 175s 3s/step
diff --git a/examples/nlp/multiple_choice_task_with_transfer_learning.py b/examples/nlp/multiple_choice_task_with_transfer_learning.py index 5c90ecb666..c83fafc375 100644 --- a/examples/nlp/multiple_choice_task_with_transfer_learning.py +++ b/examples/nlp/multiple_choice_task_with_transfer_learning.py @@ -2,7 +2,7 @@ Title: MultipleChoice Task with Transfer Learning Author: Md Awsafur Rahman Date created: 2023/09/14 -Last modified: 2024/01/06 +Last modified: 2024/01/10 Description: Use pre-trained nlp models for multiplechoice task. Accelerator: GPU """ @@ -20,9 +20,6 @@ ## Setup """ -"""shell -pip install -q keras-nlp --upgrade -""" import keras import keras_nlp