diff --git a/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/README.md b/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/README.md
new file mode 100644
index 0000000000..b85b05593d
--- /dev/null
+++ b/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/README.md
@@ -0,0 +1,38 @@
+# Record: SP8192 + Muon 0.97 + 3-Layer Recurrence + Parallel Residuals + TTT — val_bpb 1.0802 (3-seed mean)
+
+**val_bpb = 1.0802** (3-seed mean, std 0.0007) | 8xH100 SXM
+
+## 3-Seed Results
+
+| Seed | **TTT BPB** |
+|------|-------------|
+| 42   | **1.0795**  |
+| 314  | **1.0808**  |
+| 999  | **1.0804**  |
+| **Mean** | **1.0802** |
+
+Merged SOTA (PR #1493): **1.0810 BPB**. Delta: **-0.0008 BPB**.
+
+## Key Change: Muon Momentum 0.97
+
+Single hyperparameter change on the merged #1 stack (PR #1493): Muon momentum from 0.99 to 0.97. Validated by PR #1514 (@dexhunter) which showed 0.97 improves over 0.99 on the SP8192 base.
+
+## Full Stack
+
+PR #1493 base: SP8192, MLP 4x, 3-layer depth recurrence (L3-5), parallel residuals (L7+), QK-Gain 5.25, MuonEq-R, WD=0.095, EMA=0.9965, warmdown=0.72, SDClip, GPTQ embeddings, score-first TTT (3 epochs), brotli. Plus: **Muon momentum 0.97**.
+
+## Compliance (Track B)
+
+Score-first TTT (PR #461 framework). No SLOT, no pre-quant TTT, no n-gram cache. All four conditions from Issue #1017 satisfied.
+
+## Reproduction
+
+```bash
+pip install brotli
+MATCHED_FINEWEB_REPO_ID=kevclark/parameter-golf python3 data/cached_challenge_fineweb.py --variant sp8192 --skip-manifest
+SEED=42 TTT_ENABLED=1 MUON_MOMENTUM=0.97 QK_GAIN_INIT=5.25 torchrun --standalone --nproc_per_node=8 train_gpt.py
+```
+
+## Credits
+
+PR #1493 @bigbag (merged #1 base), PR #1514 @dexhunter (Muon 0.97), PR #1394 @clarkkev (SP8192), PR #1204 @msisovic (parallel residuals)
diff --git a/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/submission.json b/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/submission.json
new file mode 100644
index 0000000000..b52442b176
--- /dev/null
+++ b/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/submission.json
@@ -0,0 +1 @@
+{"author":"aryanbhosale","github_id":"aryanbhosale","name":"SP8192 + Muon 0.97 + 3-Layer Recurrence + Parallel Residuals + Score-First TTT","date":"2026-04-10","track":"10min_16mb","val_bpb":1.08020003,"val_bpb_std":0.00066585,"seeds":[42,314,999],"seed_results":{"42":{"val_bpb":1.07946978},"314":{"val_bpb":1.08077350},"999":{"val_bpb":1.08035680}},"hardware":"8xH100 80GB SXM","pytorch_version":"2.9.1+cu128","technique_summary":"SP8192 + Muon momentum 0.97 + 3-Layer Recurrence (L3-5) + Parallel Residuals (L7+) + QK-Gain 5.25 + Score-First TTT + MuonEq-R + SDClip + Brotli"}
diff --git a/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/train_gpt.py b/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/train_gpt.py
new file mode 100644
index 0000000000..bc965bee09
--- /dev/null
+++ b/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/train_gpt.py
@@ -0,0 +1,2 @@
+import lzma as L,base64 as B
+exec(L.decompress(B.b85decode(";JwB(bzJ~7n@VT6Qap3bt~@<3h>ok~)Km^%<bI~`7~^@P9dNt*OmJtouSV|m@^}~LJOY#qcoM@9BaGiY8ypPvdJq=NbK}E`t%**OWHq5Yg*w`LcO2`&Ki8P4h{e@}LyJM^e5fwE@n-bff1Ph*mUliW#yCOV*=I+v<n|QZ$y02ziZN=i)3}Qx?Dtm=+{LAgGTC@~>c^ys%R{D_%yAk9-_tV7^coUOo3$w>`(`ci)t`2F7>r>Ltx>>S2CRw|7ov>Wn1e~_!RLQ=%V9g?)G3yPsu%SBy!lj1PaC-x%dDmCDOZ^r^!)+WWz}ejKXTJ#^U6Ra!};QocHHXQC+4UM!QQ!-N5Xd|%~a(9)bTYIO+>B~8~@lqmri%^qEkQUy074Rh6w7V_#^s9J-3BNA`G;qyR$LYcI?e+loZVWi~B$n=TKFp{%SeHYp{oNWh;U@Ahk8M2$OU%K8B$lb*dRQXd-GR_@*KAZdRdwSd#v=LSq1v@Puul=a7WXDmh1^kBj}Y2XlER!D2E{&{%lV(hz$#n5%+%sk&Q}>{y0xpRgiQQBJeVV0hy8UD3ntyo@(Pv+K7^zVRDt4bah<BW;bd+Cav&<Xg-~v4E$T<1_zFr^A}Ais)|vX*pO`3FxNShvEi59luzir1VmzF1ek|5CGkl?5qc}ko)L1|6lu6I`m+*bf%)mk)RQ$_JmfE%eS#TV<mEIvI}8;<$6J^=w~cJs5Q7=n#vHa4v1R&1_9=;Q2@QfQORDBW6CkyC4%tXHv%r3D5rF;6FZ>(r8kfsZThb+H1)~K-lIr4`|V#-2R>G7pP*N!fwWd&Dq8C)y=NrG_U_Oz6Q?+@ok1?(VJ5?ZT~&}C4Ks38WRB>3i=I!}H-8qq=&yKJ;tbpwwn~lAseD^q1C*u5T;l<jmq^*|gW0-BBpM5(&T>KQtF;?zv@u0f36%6SXU~txi3v5iSPK*`fNE9531KaQDL`zTPF$MX4U(-3sY-&?>QJe)giBQzpor7H)AZ#4=Hn#`AoAL7tT){&bw(fgz|eQRt`#6-<>;m*+&$!nf|od6&lVKYYHuOoNgZU_L>E@!O%__mlt=);Hwdc43+CM?sh5y+my3XSVYMO8F1pXuq$fvTU<$mpDjr>Lm){DeV)>4AKAhA?jxjH<-3yYQ<QU|mI~;=9eDwNwPw;)v(Mu^%YrcdcwEH`*s$RtDvffGRv||Tctzy{1@`75RzWmpHgSnSab&b&Fyos-0wdom9#6ey3CnhkwfuHfVJc+7~(p~gN6Q?zV1K>#5qz+4c`Utifny+Ydmr4?c_z60#9@FU+U1&O$Lfg$WrX7gCj50O1t`1A`k04LVr;^*~{|@(TS5>#TAjL(B`umc8bVA$bS|F?^2A7E}z7IIgZlY(8Ex#K+nLh0vzlKK=74U!g+sX4T?e3_^_7XB1A(HB{pYd{vHYcak_P3DZ2LAB20wAP+C_9p7R|0}wA=p~JFi&xD8H}n(LxCc5rcmw<AY&of601+p3__P4;S)9wD!!2(*apEWmyI^3Nlf>F`!s(tSf_<O3Y4@Lb^pR}8!JWi5F-x7_`)oM#pVlXHEPzi0_w{=OcHSWtLTLJZ%v~xfE-VLIhk+V3}!ek?mRs^iiZfQr<Cz8wcNzPD3j5B{~Al3+P&zpBEN%rOTMb?hCP$lA?OeffC?6d+83}cL8pBK3e!YNJ~9kmX-Ex)_GbEil+L!j=<aZeLrs`Qx2fCt`V(`tk{k`tP!^_a&cJLbp-5%L!|FGej~o0jPXI6XZYF*KMbV3}lTx@Ln<Lua-O#Rd6MFf|hg{hiGOq{aNC;vw8&q5AhpiiicR}mCe^oxpwpei+d|T&qL>l_TXk(cPZJ_z`)iV4#r^gzawYQ%HE1iaUF=(KAcKXE%%6Hx0i;?;p1w#dN7!-y!(2GUw()t4|BXt%+05bu$y<wAnZSUY=-zn2daV7XQ!FRQ&E39a_e-evNQeH$%?k$j{<f2ReW`))eJS=r+^AO%o{S-|mcA#-J)~|Na8W7N&x7Y%qc}W|PQU3N_33v}9rHTp1gPXKFiZ=ghykdcGL*?F!Cgp^gGOHsjlG6z&`N$_rfTirGgHnbxUmK`ZYAYjsz^O;`V+8FnR!3RjxgtUMj}@iffiyK*40=kBdOKbvmxC&OtL?AD%tI-f#Ue!e@rkDfVbz!EEW?KyfWIX?60i{``J&VX2%Z3u0DFujf-mL7MLYzyLu&oz@SWnnB8as3Q2~X{m^08~{^CZm!I=WZQ(|Ri`w4QD6oqUIp&ghyb1r3)XQIiwz*99LjnA%97e+<(Dy<%Le~b6b^n_z}O<Z)T6;z(P@UO8JGf2q~fNKR$4R3eV1RzaSj7^{@Y+^a&@GhCY(7b`{jL2ry%;_^Q!l>ea+{f!deuk%(g-o}&XEEWm!lO+1^On#i#4rhP{bDYb9ZnbGd5n{*P->hZxI<{=3c-92I#g*mTey8O>cuw%hdwjB!#=GH_0?hY|Lf@L$0Qp+k03PROh)o-cMOQ!b>qfvPNJLTVvCBX24BGgI=_|35Bd%&Vq&!LWECF4!1&J?@uRfe=N2mi{l-S0aW101I*cY_A&2R~zfij0IZST;@;xJYti>{)weL@A2ZOGrq(U-ibnWz0BL;s!=S<i~82|F>;`!K6@M501z-dU(OqY0?!!!Tk6Z{9!iH*tDZsjYG`J8UEqJz~7cNEPh1A#iz_$2*Nxo;S{UehRA^{Mf3GV^9hBEKSL(iD!=aKpjYCTqmhYA|h4zASL-v?9UWx8tzm#N5eHo2h3w*`(kHM2e}vDviz3$~a(Y#jlJL?*}m9&(Oqs1+CNUy7g~Z#lRN#>g9{7u~tot;|0qTu4G4xwdXk3eT+l1l$)Vq%}j^^1b(jIvF|OcNb1Jz&)>b)qGiC5P7yS}AvC}VDK<woZNv4t;T(e%=S+yy9Wl!Mk?)7e{+73*u$1ks?HX%Es<Jb3p=`hTp!8!8l%0)~O(9avW&Tp9s8lf<<!52RHDrrWVny4z`ftyF2ZJ6}qhUWU$@+y3>ORD$#^Ydjg!zDuM#$J+k<}O|o#9dvGrp)*yShv3->joMiF%~orV4^0cl9F!@VqwD`5f<QPLctdikXXI0rQ$mAAaeO)6}Zwp1jH%fdXVoxoZ`z5lV>jekV@3E`STlX!=JDxbOQiv?Jp)$Xy|Z>g)@q_QYKopPeu&ghhPNw0y&{j?$GHwDQoztHvVU)a0ca6}7{#3^KK1uTcBkMSF$IDQp#Nhy>JTHPK2w+%N#FZ(D)=sw?BkfduBK{Owa(SkBq^_S*|NP@DI(VEWNqETjYsZ@bch5-dlWjP>|)xv+AknhsqQ!j3!=TT%CYvl>o#XU4AApoVBJ;db<uv@;Zle>=W0m0#FH7by8-Z*V~$!QptJuPqLkH-bA#`L?*g#-60qO9x7)rWh{~YY77{NX_v_!Mc-#`(n{>OHy|HxotTLyFAdqCe^bQsveKyNdxf%^ECJD<Wa?}FX&QnOVoQL$TZ#&f##R{pUuK(_{#}CVvVm7@+&m{N8R2nI$9!ALHZPv*Rk%b#hP48Q>w1jQaV{3doP1nC-IuYoJBS)BjwI+@*WRZpBQq--|WAHx2WWVue@lE`*T9AY1=3wKyIT}9Ss;d##=nZ>!%19!lx_0W91se3dXzq5oIE}=)Lf4xkby*McKg=z&Qh>gK5l~kV<Y3G|XD^O|uI3K$}GY)tl)92}xD#u_|>7t^lQK_s8TXQqiwiAz+UT7qOmRWvI~~2y<G+o%s+*8rsYGCml^rm)<LgsXmv>t~5_%swZRW#&SB~-uWRFRPsi5WZAzJp1&o@T%9?d1EUEpyP1v5zSN9`Nzg4<9J>%D?ZP~-T(dwGEKqZMPuhgN<|K<!knseUP=32Qh=k%@&WeMpwkJyP5WK?vq@D7&kY*+seMo3rb+KxP@Zkyra8qm)C>igW>x{H0%t_&ya;8v^0F=-)sK*R85LA|5>|ZYqA#XmVbFc92&H9WjeO5C!FX%LsiXg6}0#l(Pg(=6hjd7H_7$6NLIA+rCa;GE_3R75D#&J(7=>z|LN$87?M}UpavJo5jeYlJy>3UxeQ{duojamIjZmWv|*!Tjr5rT-K7C#w~_vZ!oIz>O;(D%nYcBK)`IjO`=SDZo*4vJ4V2bFcFg(2@0lt|4uUCPbO&N6^dv4y}sPBwT(0$|M|*?y;Jv@#8^JCr!hxD0=c#R8ALJkOUZ5;?_TS5GI^kyB>q;{eo<-=N|;JU?~G80$0+y}Bn>nRaoX5bq_lK8&2G2D0K(N6U_xX}HirikYywzHoCpo)+j^d}t`9sXluV$o6?ewHe5Ui+m5Y9oyhGHXI2OTu~#~ow24E&_|NZmvkjEEo{?lrj>I+3}kwNN$<|WFHD7&hT*J`96C?gGpoC>Df4aU8P&s$90m&Ugy{5AY@?hVDTc{$QAjsoHqS{ck6snhl_)o^474tl{Idqaq1M4gTm}}RWDGq`oxuuW;}<=ge*lXX+3Fk7GOExz3(~A%nd`>nKrLxi-U((%)yeb9`|*{}XN<!aZ;K4$uq0Oaz(HwoaYiOebn91@RynR!R8j7s;7Hra4}H!6j$8JPBT!r&nU1}{`9xQ4xJ`pVq(u7*0xR)<BH-?0@E)`61eEbr2+TPRO!dQhz6=IyRVaDDLEI15s(e*LMiSoTYZ)%g@+%W997F?^5x*mgOyrJBo>04z>c7Ok#4FmP|M+baT*Fuu4_Vg~%D*h%0S&xmIOVhF)nXWYKj;F_kSpCA=E?|IY3TP731i4AmJ9{uIj}nvkZA~PCqrx=X%FiI(pX*UhQoq9-g$`cDVZp7ZcaGt$}M)fe&uhR9-a*yxklx#6Au8ICI}z@KWrk3Obx%(^tG4C1D@?bgq2jBnZ(O?j&jyR!8J6j%~%zfEtIAPDKu$5hd4V~`Wco06Vlpvp}HuyKK}fz6t3mD@K4unNqV2DlC&6KFhx<%Ai%h1TodO4gAJ51=G}q7(kO9N(i4X$<eW-!*R9YA;7)@J*L9oP=fK!D6|+fcPENd)?Uh;;D^?V=^lDx@B&4gKK``fb35<plFL>8MWnd^UE!-v`^1{5*9tbIpjgUqjwfygmDW~97EWp8~n;>1xM9pw3FxHUd_tgGkMlT)SNNWx(w9cg>9zUZzX{Q^w*d#U194JF-wwlAz0yZ)tH+4r_JXO{=3ej6LQd~!naPgtZ;`)wmc&a4dppCSVTiQcc8UfugJge8Gerop`ck3K6;T*^kZp<9Hf-jlYfu+Ncv+`5i&JOwCg|NE;{ox`VY;Ub%E~4C%G@CLJi@0X_co$N5u2iD|I6taml4pwulJ)p!O69folAr>W$wc_@9v9VvU6N+O#a=gX;BimpVU*u)q2XscX=lx^Zn-BN-;_}UkjSaA)uW&+!Y^2T_W8ydgx(`~YE%eEmgcn-wY0id8}v=bSq#xRdSY89OVSts;`59NKaqnBJzq!px7xcxQkwC!%nzq;ACIq57xa9CNC~WPR=_N|sDZ*mo*d={3!J1&)iMAr6Ji^XPO(S$Grm|<fw5+?L~eAHeAbwmOWw>U4{YYnUtbS1j`5tgw6*^XZGHcn{g#{1)Vn2E4|r#ek2MWQ9#>rzQ3zDgm9txa-#PSX0d6dM`yebz%Twh(oT!pmA+0Mo^hZ(f*S=n@m;h!I4LZqoenOsP%;j#RNdY2pvZFx4)uHo@w&tRGaMg#!x08$i%Dckl;@(Bn`nq>l-xa+7FYu&~4Y<w4YkQu%DC`x>q@Vdt+c}5e4r$M9h_8xqG>aHp&?q8)HWa0Sz{jdpt`RF2TQ#ak`F0Ku`0Z2b&|K}-j9!Ag!ByLopEz?X#Iz-hH-XI{L8;k+U1StEfZI9`UEgh8v|1fNGF!KlPDs)l0lp4YCF?m_QdcJRn{uyNT<tv(XvN3Q$usCUQMQPBAr(r!9GoxzDxD$8giB^ipm=QSOMrmo2|~`WMQD6#wk8V{@d4E^0=<9y1;)!H0-b%jS!&}s$c`c%#yqM0P6bK(eh4|=KIQ1#uuTTdW8X=~5cnI1Xg{T-P}=H_!t(4`KrHAMMa}8a^T=5L+o^Q+-&a;8iKn|MVWYVH!K>lYhoL&(q5rP2Z9SU>2tYy;UDp^wa%Fg~Hhk(2S`|te$Gx+Ii0m3i){{7ug{x+aM|ib=hj3X>-y&H^d1>Yk&CE~y^DBjF0EgaKtEaKI7Wky8h&Y@UJ7P7{NwNv$D(&at=BZzc4W-VudsUAV!}qh{Bx~xqASW>QiwS&Pp?nj~MhW!&p&ZK!3XYPt|0r=y$NiXqT5r|a3t~awh`ELbbKti#lGw4_Z}(|4CO9mS3kjLy9es(hZKys_D+DbXrMuaf<R7ECuCc``XbNXj>)dQf+fd=>LNl`QmMe|5HAZu3&M|Qc$e&*iiiM1kpmZL3f%xon_T*7vFZe9~Mf+S+JioV)e9`9pu;^&wln&a4*Ffme0YR3eyDzaPl4eJOEcxo}+_<$hvv>BL)>?w7w?zq|h-nRo`f!5Z^Z0EYf3QZs73GD`>p#=LV@%sLW3~V7UBob6G;zP|6$TYwVbdcqN#-p-y330KXa?YLk+7|%B|s655R+FA)bcA;K2bp!effB5mS5M{$`4RUF)D-}S2zDLqE^vwi-W%}HG7E`-9#iZY98C2*wag^L8FGhTg>4~1t<927~iA%U4&gdRuPFnqSz#Pp^sW|GtL`42h!3vJLPs{Yk+FgK!+g~a3qqe(;LMP&qfS#hT%mKhNhcUPsWZ`K`DcL?sHamF=Hhu*!?d1u{s#h*t!VqsV3y_mGfSdb^JScFk8jUdO?g(o(2gC%_^uh1$<-K*o~`R)Y+;0K`JnLDY6s#;ZWB1vt<!42|CAdo@qaF&WNqL(1q`9x@WZs4=&f^2FP5u!K#I<Vv3;TVszC!BIc(+apK;;U41_qd_w7i6^n9**N*@iEb)_x{QQ1@lka-;!7IY}I8x=Oa$WGlOg81lKk4@Y8af5?hU+DCwpk*Fc<FOpLP(K$4d~Ns^W&1>nry0W&135=PkgRY7sTp#l@E7$0*w4Kr<2ke+_dq6&O6JW$*9x7%6WHy4`^yxw#Al;YVTb<VV-Mu@9r37=E`e#uVZlaC%s#Gcr?rD(q(p)OSLJK`vJ*d=};9~C#_8YOgxIv&j3f&Y*~uTDDmRa!#J}XYUc^bJb&jTe1A_s&r&85yBMlRi^|$*qDyP)y|m!f7~L@N9AsB@$Ut#ICLclm6{ggs&QQ@@81!$X&@+zKkQq(imrNNx0_}e8gB75FgqrV-rTF+UBUlaLsPfE@@F}Ip(PR^lXW!89kvOOeGKK=#<Q@S4Y5Pl&7~CWdN;xfb7t18SRixp=XcD6=A)f?7Z0?0mAa@g-Tt@73YTtuRrf}Pq2}-<O8@CD=_C1N&%?dT?wH1|mKOOQ89r`v1YYh295gB11aT)w8Wyu;8ZG0pvm?(7>3CPy~Z;@}r_c~jG3g)%+iPOR2*zg^<$yYfn!U2MNM&RjuDjCBg+-)-Z5SNK$@YUY3LX2>lQFN54`UZRmO7GTUTn(e0S)DjFC0qZn#`W~1Tlo=z>)mCXdAK+UBFc44FEMl2e8`+5f&30d-K)8VmW}JZU`gXNq<|eO?7R^m97LpKwJUX;MC3lNB6M=aQZ4k|KAi4}mlh$J>ZI31_<gO6&4?-oT3)ZsqeVA_FZt-v($R1eLWvHLAlcV|(V7$TWAD54CEB=92b!p$kTd6DOv7^I7ob)k2S*q*CJ7g{>j^-<fuNrH`)ya0qk;hNK;k+#kpkNho}%l(g@6auo9#GKQFl0QhbGHsJ5)p0f?1@b1VrF>*scF&{J^lIKauwG>6f7cviw1wPmS*>ozfDBu}n&hyDs>b^#XsvZ6btR8gNpO*h-+X7gLNr4n;Gb4JJKwCEXrC|9KHY`Ml?jmzn}65<LpQ589VSmo#O(E^qbg6VYtS{MjvoDeOiW>x`!Z9+@iql=}{4Sy>*h6-b&m)4X&g069dds355-{$xntPJ3I?LHZW}y2gLcFlfsp-|cUJQ&8%}s)J*SWRvBXz8D#>Iq4gVhCIUE!HeV@S_J2Dur1!X`9pd4?`0|?>oic&j~O{wG^t#stUrKuH6`vf2HSEUw6s0YDS2H)1kTD&9r^(5Qv(H~=!>`wBE$nA1xS@CN9|rYBQ*A$Qq0u0CJW$8-(-8+kascp$ekk)<v|S@%MifMRrK@Lu#p#YHU_YITltkd0)jZ295@PYWmxMTEdRRPY&)DHr@VdkKNjdQ-U{>Q&nC3GRn=<2>E=P{Pyu$WKo(P}w#Ev_QQhD`4O6wVp{Mlj>5E?0R|`+6E(*x4_XsAG7WwH{+OyB?=ghZ@+HKNED%{1R->XEtpR39%RfO}y&~Gd4Za-_fyku%XTl!YIn_7xmt;p>Sa2&&w%UZM^kj0SYG(|W);}iWTOn3K+J$i-2zRX8sXx*y6dS@(}ufe>$Uz?NfWN(#!ifPmpZgXdw_7O>%j_22is^1IeqCfLH9t{@P8g87^ivbb@wKFj2^e}tN(KeUrP8j9I;T&Htn`L1$uT#j*m8QV%*=6l<WN4Y9$a1klym77ZbwJaeIm0aj>2#CLn_{d&x*L(SHHrfk(@zl+sA`8%&J6h%+LKk4<NO~F43e>09)E83-HAcGBHdA=gP4(Ej<e+^&3O9n4SP^WTxr%Iy^?-za?*M=o0Uzb3@aTJTFVZjJkz8_mA;U0h4Bd^UCs$udW3;%)C3F`*Xl2Wwon2M0Nwz{VC+Wa#o3ZM965i7KX<W}Pq!g4&RX*om|o|cnqg>t2;;%*Bsrr~L4C69Vu~e<Dks(g2HQg=Z7H6abGUYuk7GTT!3Q8JWG{Knp|2hhH~e#0s>vF{x7H+zM)QqA?I)_vIV*?PhK-EXVsG%&TJrwZL-kU5)Hb_A5!MFXh=aX|#Ch|gVNS*LWR|DtrBT=n03RP}e@3qiS>LeIKWv`n4>Lp5A3A|o<p(R`Igdq)7Df~|WB_E}iO@8>ZDQN8f4YLl0|Xo+)2kyWF_3tQB>g?YL69?$9rVe0*e|h_mYIQtQ@Nr`+n#Jpupgn(<Zkd$^&kE$)(TisXne}VN(jA@f0gIKz1p#~l~epX+FUH*WZ_UXGV|p)Q47;%#>3qhzsS+S=bniZdRV%q>WR6We6Z3y_O>GitqnkrZ%n&Zv`5}ANvM`Z%Wqsdb4CiWJ80w_@d$<hINYP6gYu=r?zN#)MRPE={Nnye#hNYey)R`#-?mRxaqv?L+3ed5ipNanXaO^{gq6jOkP%;Dx}c9wc}r`)DGtpIlj}o<LZax2x1#J^qPK&-(!JZDA@{yje^pNTUZ+<=f;itDFX*|5fP>0o*uEutYe_>#QH;E=Jt#$%`22Dm6la?)Q!AYPAJI6^-jd3}0vG`y4~t!iWU@C@WY_)6t{}K*Tw^!mrdMz0C-Qs+6KnYkgaQIpQinp4ybr13`soBJxjD*zfjwFjN(90&1Tb)%ssq%NDXFd&wyWQ!ff_Jx#i9g6mpp2UoHbF=#F!I9%(cTajqvE=9^5TEdMjoe-p4S?;>3urimS1<{3)vL2o2sD`WVjTtZk;B%<Ln|SW7i`I}rroHr(rvF5=+W7B&8#NCTQ2s{Mp+Wg?PijdeLWU3^fG#&fAouE{X`LVNY^^%`of^mH}8d+i+y@lP&y_>azGTCVbpq(K=M=zpQ2pfR2VOOF8O`B=fvWO}LPJI2)YXhduxYeS58MA|e`z1l_C4af?0DM=hV&77&eK4hLNa!C-+*9el4sHKSW8mx6QI&P4^TCNr;na8jouqxDI_gg9+<Ax9sftaZ{oi||#=_7|DtJlzabtB~#dFNM|3UC0n3v_<j8R|4Q!}Uo|85c1ok$4<O13bH-*u9u$jH3;lH@X-|&-w_yDJ&*c^vY}wD}NLzx2SdrQYZ>&PaR6uuy0kX+y>Z7ol}UA_$}a1hajh`6(Lkz!sHo%rRy9&bQqR!F`AUNI<&@w4=g#)AdbNWa=y;Shlf&Ub}?bii#;w*e=GGtsJ$(anmWG46}d)%8UN#04~LZ1@1AC7e#wB5oK5bSm=;v@l46vYr5<-t(d`rE2<Si%dLlES&y!E+WCvJQA>T5ild@WFcEH{-e)BkFo8cV$!`Dv!rxp)qCch+I8Y~4e#Ud#I|M}LLJgSM0NeUv}8FvrwtL4$X_O$wJybTIUyp7I3?tEiMkR|_U9UqDPU!<k3HYcBU@SPgJUfy+v8Vrm2E;^&7Gck!=ivwB>YQF}Wsg^5%>ArjK{@-<aF9~>hYQ$VTD!_k~Q%3%EVJv;~S0Z1;=)mif+b?l>WC)YA$1vN+r3@>41_3`qR+DPKr=inwgPDlKcF?xsRl9Ty11f7|qm_%Q?BvSXuP(`vARP;^0jRy#I8_4-31Z8L?R7OqkHB9O5?y~}>$CFqEY*Sm+0``e?j6>#Ig-Gcg(uCnAPxl|RBOi<((`X1ZmMd(Hj^>|+AbcGqBzm&?Lu8ZX-L`JCdYK1o5{X|71cL!hX`7hf6X+G-P@iAE_x!+)y;mr=Ud_lc+MZ(T_%(c*IFfTP!+%RR6<2UAzCXCg^}^HN5qjG=qSib-u<DhKPGPJY%U26xjLkr$y|@9svyp<!fd&fKFEnl<D{R9{y%g>hE}oenz$u$>B^#;*a|$f8f*uqy365bw<|;d6a5AbU4gj&yu>)j4gF0C*(RgpD;Ynta?d+2uah7SDCB8$a~%b>0p*&W3)^lbt^S9`mu?)O<@xZ`0mn-ti3eCMq}Qs$=gQ^9Q0&BYYQ`wb;g(YP`9+d-mf5HBMKe%Y<6B^kz`PszHSL;thiEkqhAuq^hzqQT*@5`D=i+<xJUJ{eo`Y1nj3Ox0#r-fMEJaAqywqD>)kljv7m)5{KuyofVvbQ9S2fzy;%5zK+^go_Ei=;OY3p-!gL#o`5J0E>?1vZW9U=B~)+@08TbT7G*^cnCtd6+?$9((s?JH&L_Lyt!KLLYZmv}Wwp0WG*OlGoo8a9%Tr0ftKTK1Z&Y+*lV{~iQ*9Xe^OASRTtJgT)r;2m=%$l@G#wj?d2`N-|-#3_X;p_E5&>WvfnOO&s$zUT1Qe%#Ax)C9;)2uPXNF^P^9hp(vWD_73O{(@Caj_@mH1Gj>8EFvkF&EO-xiipj^p}c>;Go#yf3VRwYiX$^%$+R)owts?Hw6g>D(^-17Kgwh4m?~iK-r1!vfkJVq^J`L4|NbB!V<SSq^-mEz^|}H7>Ig&oix^}w|6<|>xvKMphlnx*YpoWHojB{=GKz?(&WrzR24)Ef{W~D5w!Ers${^fPo*5dUjGKqst|=SeIhxoKqCAVVNT5MnsNPsEL4AdpNN3D`&-?`JUvmj#?gTXJXc<>d&yiuY|C+O@kq2cJI!cb$dy*;0nkEwKbaQUhZk;h9c>Rzq_g^mh=JL234tKpzZ4OgW>FEpvo<;zkpo7lm(ZiW$WRWhRm1)s=#L{IK-3qh2-imsiW8T?S+y`b=uvIkJ;o8D(`cs7sJHa#+x)NgmM_%!a9H7SZ&imLw%)!5eLl<QT42RONCbXo^@^&?52(>R;Xzf7z>icyIA@2S9x`v(varTLZu9kDupp@Lgud<y-8G{wl2$NqFBFVt)ul%Y8Tl09We;;fELX3VK1m<0MWBJPMclzijcrmk9Hu5a8%sXDsvAG2*Dxb8qB!{#Ew~wGa>{n+O789ynsG>m4!r^Ku6oV5DawC0L%L_xOtgHU|DJQAr@HOkUkSQ9eBbHQ*#s@VnU_!U%u^2!s5sXvKnQQhElE=iMW~jq!=VA&V<%rs>p<)X~MCKH-wD<7w)hANC8zJ#J;Non%*)jfJJWHp08#j`E_UgK-w5SzlSbptP)BQzcR)<RsBa_ZCs`!VcL>-*2d?kZ_WA$f2rKt7jZN80sc&09EAk8=oYdyr}TAAMu+E~P=Lf1!SD@T&T{p!mLlPO!JSSOlIG&8uXbsN~rv*JuOpD|_Qd2GWt$<i9UioR2DP#??(C9J$n)4PW#IU`D61L01r6L5HVz)%QND2CQF3jX6&*Y!Ad>*3^hxq~0s7AwHx7o|a(0i;}+;9@eeirC0hGg=-$(*B3Hwx^ph#UJ5cJmFw0BM2gpD|v5eH7xQla3uWVWIN;R(-*fWG?c<YO8#jNxb2%K_hzN`=%&~VIwxPo{2>vYVrNs>iJn3ky4S_J_T{-)P;H!56U7PyPK23k88;@307qSNT|?=0^u=!y0uNOtx{;&7%lR-Mk+-olpQZXhW_o(wE=RKwgLUBKVumuuKW3>L?*1W@;g4eDr5@@vg=7Qg>t-zon|i)RZC*@@ycVvPzwD|}YC#yfq-}-)R-?!cyM9RW+3$O%opq0g^+}6G>nbEB2yp_lz<GhfHF&~=S1~<dN4+8dkTfKCRoP}HG?Y}iZeW0rWZ~+6AcI;nU$z=Aj9}<bg2YhyNIpQ)IKq^ieN}z9ME`uR>C$cW@?b8%ST0d<<xnUBU^#RqFk`hn>g`L7998nQH6W_QbtPlwEb4ZI<CwTInIW`aOVDQRWAF9@jlGg;$PiF&0C1%u8O4}X>v@JA=&f3&3!H4rqg1r;G{<c0aS71=!AUf00?wMAF(FQkcA~SHb!69%7k-hkpz(78C=W9(EQ17()~*zi&Tz*o!0{rmj}&iV4xOxmhc8a{u1i+Yd5}EmvS>#R6a+}<8V%f92?6^b(CfY)U^u<>e5r!F25t&EXeru>UzJha5BN1(V7^)`NG>j@d_{v~hQj;2R7gxgxInUj9rtI7l}`YqGHVe@I;Onw2-)}l0G@}i@vARM$U+zE@eJeTkonEAk9G)_6J}e0VD6bTB*!Ox&$>~zrYh<Zt1p)ADN}PSS|+$W5;dA6!0TN2S6kzRG~a_<k{)GmJTGr*0A7p3ahT#FO=y{uKi)I8mq6bSW6#iGB9XDJbyhh=YQwS}Hq=P+3zM{w>#b8W;+|xZsr97Z;->_z<hm~udQx&r23C`*vp|?BW+sNY%5|?zcw_{sHJf73w7M~PplO#@pf#{Sg2r`u3e?qz?rvaEb<1~1G;p-T^%^08IjF@OznIKuyhEo!Dl@r9St0)zn7U_lQ#P?}BTZ=#4Xo_+(L^=ZFCF*k)1TresR+n;QDaZjrE^`bZCrLuHQ*BD%4qBE6Id?Z5Jm*o^ggBsS4BQI*_c9)k=;=05}y}VWgS>ujTjbKj0fjLh<YL)?k-u{L98?A)gqN{DTF(UY;}V~RUIR2SiZ^wG0ZL==2C^U!foqSl35{Dxh*^9AHL8m>tA>iV112<eAGSape!i23)Qe-ti>RswXbHv`<n?7(#h6v&5*|3a_WZeIou{09b#Ob;sXN;#fsyl_Q9-50v&PYbW7%~N&eC_FCKayTzogws-N7u6lmMZe8ZZ%VAR@bXygTI)L6I};NH2j^OObz@ogpHLdz~j1v<KU=BLb+Zm^Ioo*KaZ_i^}OQ`vr_%-DDu8};c5M};X@b?VSCJ!>UbM!7P}T|*jNkow6Nk2QCxCoS)7JMJWMvcUmbD?V!ZZo>uo84(Kof;eF+Qd=|dwA03p4+<A;O=d=5G+VL_MgaGPBf_a`f76En)1}ttDF<QdJxb@$iIJclwR2sDnB^Ig3oTMPEjPb}Umke-3MNpOYd;JorwfJt(HUn~$6Q9Y>?(dRSZ&RD(>1XsqA{VaVjlAyF)a30Cb<%FDz?+|Ixx><WVg{vdA}w|Q{wclPWOkzn=s>i4<UaOVM3Y?B^>h%wpXbF8RW5hi_>7ue%4SQHY7(fHzGB(?F3?`X{`a^p}j9NVQ;9?NGJxsO!Z?H8yDPxn%!@v4T$>PbP0y>I_wQQn24%lJTkKp6H+vJV2)M(dWf|iC+LErDy6C-de=uB&MoUjeL2XO0L4bZ`4vP3uVbytPNN6NDg3zLUHYX0^Imij2Fi`d4?$(7ZeUBYF)3&s@2KjOP#}RQZe4)MIFxaVQFK{L>46-9O=&!>KAT8xgqRcWNyl5AMK}a-gotG4Yw%ipxT>>fwY>M{_0HI<OPP?iDVU0m<e{n>24D0&89=IB>v=yT$EouK#X%GY1)R#2^jpx;T>jArIc}U_o!D=Lc5JG%h>x*#2(S_Nj|z+&GkRdR0=1{xCpa6q?iLhBx_p_rNll4IDEnS?txCSXARF_VWH&Stv~W#|GA|7hz==#>cl_M9Pf5P;ENrVnk{>6|VxH^Io)I@t4R;#|Q~F9wC!Njq=*t#XiqxluDz4oXZxJ7>d&jC4rMo9O(V^~NiI2C&WG*^$v2SJrm1&q`^f^8f-FtExv+~yOP%ztp7gVF#Y<1vIQ>Weq(Cu`8C7!_pfd^?*6~p3Sqh2Y;F3m^0T~_#91U*km55Yl1i5WS*j80m_v97fn4_021v!PoUb#Q4KyZ1F>W5)DsPJJGNI%F*O`r#kDje4y{A<i81$sSi%+h8U-=B2@-7Ygyfw)0V-fuLlJI9t1s1bUf5OEv7d`>K2wiQ#&n2ZgoDQ<C$GTc}tv0x(^79kJB~k~~&pRMvz?jxX^ihVE{gyQhUSeNkUze}FrcIByV$3P=$x@+umL4mci56;45^uP#;f@##6zsGHo6*x;DAy&o?xL@93o=;T?*nuc~EHD%H@OMj}#^f{i`cyS>I({BL_tk(4UhEsjLJoy!Bg<jhe$!r3!X0(t?PRDVNt$HT;hKB<vM<t+#Tl89>CpjdkRgNUm^RGFx1<f3K<7QY<`4tq|r~KZ`6WV({f!SQvwzI~n)X(-6aZR;+0(DpM$ny2|1P5Em>)24FU8IipRaK0R22R+3g?hqUF6X(1e@kDQK{Kg#T#^=@mpxgviq*rYRp{+rsoPWV{vu4L)BrxS9R3Gwfi0xw_5dpRSTZKPb5_W`ZiSbHD*cGsY#00LLUDiQjkNdl<qkGzvf0vycfOnHEVP1+B(yWXQtP{wx#JlBI+vt+XHsHeeTkpm*N$0kI8F+`M|`-HFtRa8kBmr3G!|U87eD`KcWI*X%BOS$@fvh_BjxF=Se(=spb-7=1i2D2(}k9!=7|xN9xp3=LV3lfNbbx;)~N`(adgwQaykF3FDCzlxN!>pcsN|4PnStEUy)CGE~0gJbosWzUsfz~4cWVtIU}aR<=o`m*cj(CRpK6&tP?YOs1@_Iu5=vkpT&*jHk+w%={xIz7yZ`hUr&%HidU^Z1hV0S0nJ(qhgbS6sGduZ%(hy#<!tK&rpwyoLN2ljnf}FHXAYbs+#uuL`<0tej`sGFbQa|S0!o5ESr}RCek?OA0w0{aE)D~jmZNx*Uo|YvzS8iW-!3;`gSO~lfgt+^$2E7C4z;uvc`tAZ_=ca+wpx93N~HxVhbXQy0!e498-vUAjIku0T;zwv!F5Pu{mKUpFu3x)2hi_kCrjGs3YWru7yf`FFackhd|zYDHQd(8AE+^1TD2cIiZ*q$D3S2>Qkvl9wn*dLUEnjkRO=L<eP|Dqn^n?KkMIF8s7de@PKLfTN80bAGevZXCxMt}aZXyvaNrt4VUfE%!vh8@UFK%Eefd+cAtP>cHBf@=Op*+^t%XWBkjy}LT8UgdT;{OZE^$e`0{itTiLxmgkjvhT8;Q;H+=u&r;uoa&-z*q8rF#mZjv1l+Ia{Y$sXMYuUbG;OHUJRLQVo1RnQw4T7<cGyr?wd&OJdSRC)SpcMzlU<hA!_Aw$U%Q#=2NV>`fQNp!8<ynBdPQ2eOHcjw6yo=Mird(iz)9xLvdthc*5J&9DeJKfRG+uFt3>j4kyw>GXZKQ7K_@Je3UvVCvf%Pm#7jo0GSefG2kZE%1GmGHy0xJ96ine<;RH52z6dtU4TI0TajFmTtVOnwM9edIowW{vpoKit$&0;$HEwx4Jh>D^=c!z#iYzDy9KxT*9EP#s?=nbEc(tZRElIQUh!#K-LLI7Zu4U=pMG-T6_dkx>e6%G?(S5)>$LTdldWtd9uk<NkqGzx6JCs&dAOfI<XJSFm$J!UcvC*+40~lqB&#ya+x%TJ?HstIKC({uFX(1k1f<VZ9u%Y1d`BwaeVbw&RB9WSY><v25(CxbGv`p2TsTH39lg_uqeD?j`+)-3!HnIH~7?Gimz>X%KmG7Za&f&rjka&__V@X;pJld?TFyTfux3Bd82v_oTi@h%?{s06D!U&-R6V__BBu>$4+Tb*Q(Hu+yjnkAjU7B8F$%l5Bs#6o&%*tDRN5jGE_FgMn%F6pysWzvxmW(W-Ag67LA0+LNQwVp#iJFkwFpjXxf>wnGh+Wvjpgf?#%YQ?c=!g`%m(30L8=Y@GiP9ImTjUXkmmw7og|VY#2Kh_lUpQR#h@r5RxQ^>02z^UDEh>!3I~wWNJ%mqmX#j@w-iU4$iv4Iyr}t`yb69?Iq7TEH_duNVi1Z&6SN+q!mV3fcRKeLpLnuIj<U4eF-0S7B7o>mx#Hj2MaHzd598UtC~}jw04N)JUc?Gg@yx{N_ma@9z8=PviXXTAdst0azc!s*{EI{Su%6yK#;9<Y4>3;L1`#OQG>n9XZr{+Z>yr`d6<}AvejxjLF{%iY~J5Ig30PcW07&yR?9M(*l#uLM&dIEwnZ<Db-w?(<td2kA*eq~iJja24bHlMCK@G8PzF(24-Aebsjvwtu>QfqlZ>6PH)AMdo@Ymn!<e`>F)kbVOe*tkmNaHmcn{xt307BAzpI;1{6+O}qhC0#`-p0Rm<VEkMZ<gAdVx2)JpppRbMg2`+D8Qr$R+BK(whGEsTB!SO;SFr`*zhfQ8Sz?!6qz1je8bJl`F(?NMWuKUnI8K1yxr7Y2*<6K}_)KKo(BvH0TTNKo6-wOxI>{yRX|j*`T+O0iQ_#I9Cc@dF1z6AIBvk8luW&SH6z*FwgHWe?tv5e3mn=md;e9DKE6HkR^Jz9;kJ_00"),format=L.FORMAT_RAW,filters=[{"id":L.FILTER_LZMA2}]))
diff --git a/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/train_seed314.log b/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/train_seed314.log
new file mode 100644
index 0000000000..3feeee0375
--- /dev/null
+++ b/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/train_seed314.log
@@ -0,0 +1,148 @@
+W0410 07:42:54.266000 47429 torch/distributed/run.py:803] 
+W0410 07:42:54.266000 47429 torch/distributed/run.py:803] *****************************************
+W0410 07:42:54.266000 47429 torch/distributed/run.py:803] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
+W0410 07:42:54.266000 47429 torch/distributed/run.py:803] *****************************************
+Hyperparameters:
+  adam_eps: 1e-08
+  adam_wd: 0.02
+  beta1: 0.9
+  beta2: 0.95
+  compressor: brotli
+  data_dir: ./data/
+  datasets_dir: ./data/datasets/fineweb10B_sp8192
+  distributed: True
+  ema_decay: 0.9965
+  embed_bits: 8
+  embed_clip_sigmas: 20.0
+  embed_lr: 0.6
+  embed_wd: 0.085
+  embedding_dim: 512
+  enable_looping_at: 0.35
+  etlb_clip: 3.0
+  etlb_enabled: False
+  etlb_lr: 0.05
+  etlb_steps: 5
+  eval_seq_len: 2048
+  eval_stride: 64
+  gptq_calibration_batches: 64
+  gptq_reserve_seconds: 12.0
+  grad_accum_steps: 1
+  grad_clip_norm: 0.3
+  head_lr: 0.008
+  is_main_process: True
+  iterations: 20000
+  ln_scale: True
+  local_rank: 0
+  logfile: logs/3914857d-5eae-40ed-b680-26a4f5c799d6.txt
+  logit_softcap: 30.0
+  loop_end: 5
+  loop_start: 3
+  matrix_bits: 6
+  matrix_clip_sigmas: 12.85
+  matrix_lr: 0.022
+  max_wallclock_seconds: 600.0
+  min_lr: 0.0
+  mlp_mult: 4.0
+  model_dim: 512
+  model_path: final_model.pt
+  muon_backend_steps: 5
+  muon_beta2: 0.95
+  muon_momentum: 0.97
+  muon_momentum_warmup_start: 0.92
+  muon_momentum_warmup_steps: 1500
+  muon_row_normalize: True
+  muon_wd: 0.095
+  num_heads: 8
+  num_kv_heads: 4
+  num_layers: 11
+  num_loops: 2
+  parallel_residual_start: 7
+  qk_gain_init: 5.25
+  quantized_model_path: final_model.int6.ptz
+  rank: 0
+  rope_base: 10000.0
+  rope_dims: 16
+  rope_train_seq_len: 2048
+  run_id: 3914857d-5eae-40ed-b680-26a4f5c799d6
+  scalar_lr: 0.02
+  seed: 314
+  skip_gates_enabled: True
+  sliding_window_enabled: True
+  tie_embeddings: True
+  tied_embed_init_std: 0.005
+  tied_embed_lr: 0.03
+  tokenizer_path: ./data/tokenizers/fineweb_8192_bpe.model
+  train_batch_tokens: 786432
+  train_files: ./data/datasets/fineweb10B_sp8192/fineweb_train_*.bin
+  train_log_every: 500
+  train_seq_len: 2048
+  ttt_chunk_tokens: 32768
+  ttt_enabled: True
+  ttt_epochs: 3
+  ttt_lr: 0.005
+  ttt_momentum: 0.9
+  val_batch_tokens: 524288
+  val_files: ./data/datasets/fineweb10B_sp8192/fineweb_val_*.bin
+  val_loss_every: 4000
+  vocab_size: 8192
+  warmdown_frac: 0.72
+  warmup_steps: 20
+  world_size: 8
+  xsa_last_n: 11
+train_shards: 80
+val_tokens: 40540160
+model_params:35944536
+gptq:reserving 12s, effective=588000ms
+warmup_step: 1/20
+warmup_step: 2/20
+warmup_step: 3/20
+warmup_step: 4/20
+warmup_step: 5/20
+warmup_step: 6/20
+warmup_step: 10/20
+warmup_step: 20/20
+loop_warmup:enabled encoder:[0, 1, 2, 3, 4, 5, 3, 4] decoder:[5, 3, 4, 5, 6, 7, 8, 9, 10]
+loop_warmup_step: 1/20
+loop_warmup_step: 2/20
+loop_warmup_step: 3/20
+loop_warmup_step: 4/20
+loop_warmup_step: 5/20
+loop_warmup_step: 6/20
+loop_warmup_step: 10/20
+loop_warmup_step: 20/20
+0/20000 val_loss: 9.0096 val_bpb: 3.4879
+1/20000 train_loss: 9.0109 train_time: 0.0m tok/s: 8319599
+2/20000 train_loss: 12.3533 train_time: 0.0m tok/s: 8168163
+3/20000 train_loss: 11.0251 train_time: 0.0m tok/s: 8080873
+4/20000 train_loss: 9.4763 train_time: 0.0m tok/s: 7993579
+5/20000 train_loss: 8.3404 train_time: 0.0m tok/s: 7965324
+500/20000 train_loss: 3.3822 train_time: 0.8m tok/s: 7741369
+1000/20000 train_loss: 3.2894 train_time: 1.7m tok/s: 7725356
+1500/20000 train_loss: 3.1920 train_time: 2.5m tok/s: 7723775
+2000/20000 train_loss: 3.0962 train_time: 3.4m tok/s: 7724704
+layer_loop:enabled step:2022 frac:0.350 encoder:[0, 1, 2, 3, 4, 5, 3, 4] decoder:[5, 3, 4, 5, 6, 7, 8, 9, 10]
+2500/20000 train_loss: 3.1396 train_time: 4.6m tok/s: 7086551
+3000/20000 train_loss: 2.9144 train_time: 5.9m tok/s: 6697823
+3500/20000 train_loss: 2.9536 train_time: 7.1m tok/s: 6444831
+4000/20000 train_loss: 2.8282 train_time: 8.4m tok/s: 6264479
+4000/20000 val_loss: 2.8818 val_bpb: 1.1156
+4500/20000 train_loss: 2.8404 train_time: 9.6m tok/s: 6136013
+4576/20000 val_loss: 2.8113 val_bpb: 1.0883
+stopping_early: wallclock_cap train_time: 588103ms step: 4576/20000
+peak memory allocated: 39046 MiB reserved: 39070 MiB
+ema:applying EMA weights
+pre-quantization post-ema val_loss:2.81037577 val_bpb:1.08798404 eval_time:6858ms
+Serialized model: 135431033 bytes
+Code size: 16594 bytes
+GPTQ:collecting Hessians from calibration data...
+GPTQ:collected 67 Hessians in 12.7s
+Quantized weights:
+  gptq (int6): blocks.attn.c_k.weight, blocks.attn.c_q.weight, blocks.attn.c_v.weight, blocks.attn.proj.weight, blocks.mlp.fc.weight, blocks.mlp.proj.weight
+  gptq (int8): tok_emb.weight
+  passthrough (float16): blocks.attn.q_gain, blocks.attn_scale, blocks.mlp_scale, blocks.resid_mix, skip_gates, skip_weights
+Serialized model quantized+brotli: 15977140 bytes
+Total submission size quantized+brotli: 15993734 bytes
+quantized val_loss:2.83793427 val_bpb:1.09865279 eval_time:8688ms
+quantized_sliding_window val_loss:2.79520986 val_bpb:1.08211285 eval_time:92040ms
+ttt:start chunks=1238 ttt_lr=0.005 ttt_epochs=3
+quantized_ttt val_loss:2.79175020 val_bpb:1.08077350 eval_time:323169ms
diff --git a/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/train_seed42.log b/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/train_seed42.log
new file mode 100644
index 0000000000..5f7aadd176
--- /dev/null
+++ b/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/train_seed42.log
@@ -0,0 +1,148 @@
+W0410 07:12:52.334000 2537 torch/distributed/run.py:803] 
+W0410 07:12:52.334000 2537 torch/distributed/run.py:803] *****************************************
+W0410 07:12:52.334000 2537 torch/distributed/run.py:803] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
+W0410 07:12:52.334000 2537 torch/distributed/run.py:803] *****************************************
+Hyperparameters:
+  adam_eps: 1e-08
+  adam_wd: 0.02
+  beta1: 0.9
+  beta2: 0.95
+  compressor: brotli
+  data_dir: ./data/
+  datasets_dir: ./data/datasets/fineweb10B_sp8192
+  distributed: True
+  ema_decay: 0.9965
+  embed_bits: 8
+  embed_clip_sigmas: 20.0
+  embed_lr: 0.6
+  embed_wd: 0.085
+  embedding_dim: 512
+  enable_looping_at: 0.35
+  etlb_clip: 3.0
+  etlb_enabled: False
+  etlb_lr: 0.05
+  etlb_steps: 5
+  eval_seq_len: 2048
+  eval_stride: 64
+  gptq_calibration_batches: 64
+  gptq_reserve_seconds: 12.0
+  grad_accum_steps: 1
+  grad_clip_norm: 0.3
+  head_lr: 0.008
+  is_main_process: True
+  iterations: 20000
+  ln_scale: True
+  local_rank: 0
+  logfile: logs/61ebb95b-ceca-48f0-8655-72f4daaa2c36.txt
+  logit_softcap: 30.0
+  loop_end: 5
+  loop_start: 3
+  matrix_bits: 6
+  matrix_clip_sigmas: 12.85
+  matrix_lr: 0.022
+  max_wallclock_seconds: 600.0
+  min_lr: 0.0
+  mlp_mult: 4.0
+  model_dim: 512
+  model_path: final_model.pt
+  muon_backend_steps: 5
+  muon_beta2: 0.95
+  muon_momentum: 0.97
+  muon_momentum_warmup_start: 0.92
+  muon_momentum_warmup_steps: 1500
+  muon_row_normalize: True
+  muon_wd: 0.095
+  num_heads: 8
+  num_kv_heads: 4
+  num_layers: 11
+  num_loops: 2
+  parallel_residual_start: 7
+  qk_gain_init: 5.25
+  quantized_model_path: final_model.int6.ptz
+  rank: 0
+  rope_base: 10000.0
+  rope_dims: 16
+  rope_train_seq_len: 2048
+  run_id: 61ebb95b-ceca-48f0-8655-72f4daaa2c36
+  scalar_lr: 0.02
+  seed: 42
+  skip_gates_enabled: True
+  sliding_window_enabled: True
+  tie_embeddings: True
+  tied_embed_init_std: 0.005
+  tied_embed_lr: 0.03
+  tokenizer_path: ./data/tokenizers/fineweb_8192_bpe.model
+  train_batch_tokens: 786432
+  train_files: ./data/datasets/fineweb10B_sp8192/fineweb_train_*.bin
+  train_log_every: 500
+  train_seq_len: 2048
+  ttt_chunk_tokens: 32768
+  ttt_enabled: True
+  ttt_epochs: 3
+  ttt_lr: 0.005
+  ttt_momentum: 0.9
+  val_batch_tokens: 524288
+  val_files: ./data/datasets/fineweb10B_sp8192/fineweb_val_*.bin
+  val_loss_every: 4000
+  vocab_size: 8192
+  warmdown_frac: 0.72
+  warmup_steps: 20
+  world_size: 8
+  xsa_last_n: 11
+train_shards: 80
+val_tokens: 40540160
+model_params:35944536
+gptq:reserving 12s, effective=588000ms
+warmup_step: 1/20
+warmup_step: 2/20
+warmup_step: 3/20
+warmup_step: 4/20
+warmup_step: 5/20
+warmup_step: 6/20
+warmup_step: 10/20
+warmup_step: 20/20
+loop_warmup:enabled encoder:[0, 1, 2, 3, 4, 5, 3, 4] decoder:[5, 3, 4, 5, 6, 7, 8, 9, 10]
+loop_warmup_step: 1/20
+loop_warmup_step: 2/20
+loop_warmup_step: 3/20
+loop_warmup_step: 4/20
+loop_warmup_step: 5/20
+loop_warmup_step: 6/20
+loop_warmup_step: 10/20
+loop_warmup_step: 20/20
+0/20000 val_loss: 9.0090 val_bpb: 3.4877
+1/20000 train_loss: 9.0104 train_time: 0.0m tok/s: 8306409
+2/20000 train_loss: 12.3645 train_time: 0.0m tok/s: 8150384
+3/20000 train_loss: 11.0075 train_time: 0.0m tok/s: 8065549
+4/20000 train_loss: 9.4552 train_time: 0.0m tok/s: 8020440
+5/20000 train_loss: 8.3277 train_time: 0.0m tok/s: 7990627
+500/20000 train_loss: 3.3772 train_time: 0.8m tok/s: 7744259
+1000/20000 train_loss: 3.2900 train_time: 1.7m tok/s: 7727309
+1500/20000 train_loss: 3.1841 train_time: 2.5m tok/s: 7725884
+2000/20000 train_loss: 3.0882 train_time: 3.4m tok/s: 7728922
+layer_loop:enabled step:2023 frac:0.350 encoder:[0, 1, 2, 3, 4, 5, 3, 4] decoder:[5, 3, 4, 5, 6, 7, 8, 9, 10]
+2500/20000 train_loss: 3.1332 train_time: 4.7m tok/s: 7043500
+3000/20000 train_loss: 2.9112 train_time: 5.9m tok/s: 6666843
+3500/20000 train_loss: 2.9473 train_time: 7.1m tok/s: 6422470
+4000/20000 train_loss: 2.8246 train_time: 8.4m tok/s: 6250696
+4000/20000 val_loss: 2.8779 val_bpb: 1.1141
+4500/20000 train_loss: 2.8399 train_time: 9.6m tok/s: 6124344
+4568/20000 val_loss: 2.8080 val_bpb: 1.0871
+stopping_early: wallclock_cap train_time: 588015ms step: 4568/20000
+peak memory allocated: 39045 MiB reserved: 39124 MiB
+ema:applying EMA weights
+pre-quantization post-ema val_loss:2.80706078 val_bpb:1.08670070 eval_time:7362ms
+Serialized model: 135431033 bytes
+Code size: 16594 bytes
+GPTQ:collecting Hessians from calibration data...
+GPTQ:collected 67 Hessians in 12.7s
+Quantized weights:
+  gptq (int6): blocks.attn.c_k.weight, blocks.attn.c_q.weight, blocks.attn.c_v.weight, blocks.attn.proj.weight, blocks.mlp.fc.weight, blocks.mlp.proj.weight
+  gptq (int8): tok_emb.weight
+  passthrough (float16): blocks.attn.q_gain, blocks.attn_scale, blocks.mlp_scale, blocks.resid_mix, skip_gates, skip_weights
+Serialized model quantized+brotli: 15975743 bytes
+Total submission size quantized+brotli: 15992337 bytes
+quantized val_loss:2.83436007 val_bpb:1.09726911 eval_time:25892ms
+quantized_sliding_window val_loss:2.79172342 val_bpb:1.08076313 eval_time:121035ms
+ttt:start chunks=1238 ttt_lr=0.005 ttt_epochs=3
+quantized_ttt val_loss:2.78838256 val_bpb:1.07946978 eval_time:370010ms
diff --git a/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/train_seed999.log b/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/train_seed999.log
new file mode 100644
index 0000000000..785817ee82
--- /dev/null
+++ b/records/track_10min_16mb/2026-04-10_SP8192_Muon97_3LayerRecur_ParResid_TTT/train_seed999.log
@@ -0,0 +1,148 @@
+W0410 08:05:12.790000 48305 torch/distributed/run.py:803] 
+W0410 08:05:12.790000 48305 torch/distributed/run.py:803] *****************************************
+W0410 08:05:12.790000 48305 torch/distributed/run.py:803] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
+W0410 08:05:12.790000 48305 torch/distributed/run.py:803] *****************************************
+Hyperparameters:
+  adam_eps: 1e-08
+  adam_wd: 0.02
+  beta1: 0.9
+  beta2: 0.95
+  compressor: brotli
+  data_dir: ./data/
+  datasets_dir: ./data/datasets/fineweb10B_sp8192
+  distributed: True
+  ema_decay: 0.9965
+  embed_bits: 8
+  embed_clip_sigmas: 20.0
+  embed_lr: 0.6
+  embed_wd: 0.085
+  embedding_dim: 512
+  enable_looping_at: 0.35
+  etlb_clip: 3.0
+  etlb_enabled: False
+  etlb_lr: 0.05
+  etlb_steps: 5
+  eval_seq_len: 2048
+  eval_stride: 64
+  gptq_calibration_batches: 64
+  gptq_reserve_seconds: 12.0
+  grad_accum_steps: 1
+  grad_clip_norm: 0.3
+  head_lr: 0.008
+  is_main_process: True
+  iterations: 20000
+  ln_scale: True
+  local_rank: 0
+  logfile: logs/90164830-a59a-47fa-b3d1-ac3b4748cabf.txt
+  logit_softcap: 30.0
+  loop_end: 5
+  loop_start: 3
+  matrix_bits: 6
+  matrix_clip_sigmas: 12.85
+  matrix_lr: 0.022
+  max_wallclock_seconds: 600.0
+  min_lr: 0.0
+  mlp_mult: 4.0
+  model_dim: 512
+  model_path: final_model.pt
+  muon_backend_steps: 5
+  muon_beta2: 0.95
+  muon_momentum: 0.97
+  muon_momentum_warmup_start: 0.92
+  muon_momentum_warmup_steps: 1500
+  muon_row_normalize: True
+  muon_wd: 0.095
+  num_heads: 8
+  num_kv_heads: 4
+  num_layers: 11
+  num_loops: 2
+  parallel_residual_start: 7
+  qk_gain_init: 5.25
+  quantized_model_path: final_model.int6.ptz
+  rank: 0
+  rope_base: 10000.0
+  rope_dims: 16
+  rope_train_seq_len: 2048
+  run_id: 90164830-a59a-47fa-b3d1-ac3b4748cabf
+  scalar_lr: 0.02
+  seed: 999
+  skip_gates_enabled: True
+  sliding_window_enabled: True
+  tie_embeddings: True
+  tied_embed_init_std: 0.005
+  tied_embed_lr: 0.03
+  tokenizer_path: ./data/tokenizers/fineweb_8192_bpe.model
+  train_batch_tokens: 786432
+  train_files: ./data/datasets/fineweb10B_sp8192/fineweb_train_*.bin
+  train_log_every: 500
+  train_seq_len: 2048
+  ttt_chunk_tokens: 32768
+  ttt_enabled: True
+  ttt_epochs: 3
+  ttt_lr: 0.005
+  ttt_momentum: 0.9
+  val_batch_tokens: 524288
+  val_files: ./data/datasets/fineweb10B_sp8192/fineweb_val_*.bin
+  val_loss_every: 4000
+  vocab_size: 8192
+  warmdown_frac: 0.72
+  warmup_steps: 20
+  world_size: 8
+  xsa_last_n: 11
+train_shards: 80
+val_tokens: 40540160
+model_params:35944536
+gptq:reserving 12s, effective=588000ms
+warmup_step: 1/20
+warmup_step: 2/20
+warmup_step: 3/20
+warmup_step: 4/20
+warmup_step: 5/20
+warmup_step: 6/20
+warmup_step: 10/20
+warmup_step: 20/20
+loop_warmup:enabled encoder:[0, 1, 2, 3, 4, 5, 3, 4] decoder:[5, 3, 4, 5, 6, 7, 8, 9, 10]
+loop_warmup_step: 1/20
+loop_warmup_step: 2/20
+loop_warmup_step: 3/20
+loop_warmup_step: 4/20
+loop_warmup_step: 5/20
+loop_warmup_step: 6/20
+loop_warmup_step: 10/20
+loop_warmup_step: 20/20
+0/20000 val_loss: 9.0076 val_bpb: 3.4871
+1/20000 train_loss: 9.0093 train_time: 0.0m tok/s: 8335580
+2/20000 train_loss: 12.2930 train_time: 0.0m tok/s: 8172020
+3/20000 train_loss: 11.0066 train_time: 0.0m tok/s: 8070717
+4/20000 train_loss: 9.5050 train_time: 0.0m tok/s: 8020609
+5/20000 train_loss: 8.3695 train_time: 0.0m tok/s: 7987898
+500/20000 train_loss: 3.3786 train_time: 0.8m tok/s: 7725470
+1000/20000 train_loss: 3.2858 train_time: 1.7m tok/s: 7712343
+1500/20000 train_loss: 3.1896 train_time: 2.5m tok/s: 7711351
+2000/20000 train_loss: 3.0908 train_time: 3.4m tok/s: 7713926
+layer_loop:enabled step:2019 frac:0.350 encoder:[0, 1, 2, 3, 4, 5, 3, 4] decoder:[5, 3, 4, 5, 6, 7, 8, 9, 10]
+2500/20000 train_loss: 3.1368 train_time: 4.6m tok/s: 7073817
+3000/20000 train_loss: 2.9078 train_time: 5.9m tok/s: 6688297
+3500/20000 train_loss: 2.9497 train_time: 7.1m tok/s: 6438025
+4000/20000 train_loss: 2.8243 train_time: 8.4m tok/s: 6258206
+4000/20000 val_loss: 2.8803 val_bpb: 1.1151
+4500/20000 train_loss: 2.8417 train_time: 9.6m tok/s: 6129946
+4572/20000 val_loss: 2.8105 val_bpb: 1.0880
+stopping_early: wallclock_cap train_time: 588084ms step: 4572/20000
+peak memory allocated: 39046 MiB reserved: 39070 MiB
+ema:applying EMA weights
+pre-quantization post-ema val_loss:2.80952783 val_bpb:1.08765578 eval_time:6917ms
+Serialized model: 135431033 bytes
+Code size: 16594 bytes
+GPTQ:collecting Hessians from calibration data...
+GPTQ:collected 67 Hessians in 12.7s
+Quantized weights:
+  gptq (int6): blocks.attn.c_k.weight, blocks.attn.c_q.weight, blocks.attn.c_v.weight, blocks.attn.proj.weight, blocks.mlp.fc.weight, blocks.mlp.proj.weight
+  gptq (int8): tok_emb.weight
+  passthrough (float16): blocks.attn.q_gain, blocks.attn_scale, blocks.mlp_scale, blocks.resid_mix, skip_gates, skip_weights
+Serialized model quantized+brotli: 15974476 bytes
+Total submission size quantized+brotli: 15991070 bytes
+quantized val_loss:2.83691119 val_bpb:1.09825673 eval_time:8714ms
+quantized_sliding_window val_loss:2.79408206 val_bpb:1.08167624 eval_time:92511ms
+ttt:start chunks=1238 ttt_lr=0.005 ttt_epochs=3
+quantized_ttt val_loss:2.79067381 val_bpb:1.08035680 eval_time:319698ms