diff --git "a/protection_none_torch_compile/log2.txt" "b/protection_none_torch_compile/log2.txt" new file mode 100644--- /dev/null +++ "b/protection_none_torch_compile/log2.txt" @@ -0,0 +1,2703 @@ +max_steps: 2500 +0 val loss 10.9813 +0 val perplexity 58767.4961 +0 train 10.985553 (lr=8.3916e-07) (hash(x)=43020073) +1 train 10.963447 (lr=1.6783e-06) (hash(x)=41136063) +2 train 10.905601 (lr=2.5175e-06) (hash(x)=37358684) +3 train 10.828959 (lr=3.3566e-06) (hash(x)=43047763) +4 train 10.736231 (lr=4.1958e-06) (hash(x)=37916098) +5 train 10.627320 (lr=5.0350e-06) (hash(x)=42474534) +6 train 10.521407 (lr=5.8741e-06) (hash(x)=37880213) +7 train 10.418458 (lr=6.7133e-06) (hash(x)=42318600) +8 train 10.313049 (lr=7.5524e-06) (hash(x)=43188642) +9 train 10.236709 (lr=8.3916e-06) (hash(x)=43746730) +10 train 10.148825 (lr=9.2308e-06) (hash(x)=37955337) +11 train 10.086859 (lr=1.0070e-05) (hash(x)=38816937) +12 train 10.022991 (lr=1.0909e-05) (hash(x)=35883110) +13 train 9.967196 (lr=1.1748e-05) (hash(x)=48920958) +14 train 9.894051 (lr=1.2587e-05) (hash(x)=31358192) +15 train 9.851849 (lr=1.3427e-05) (hash(x)=40218940) +16 train 9.815812 (lr=1.4266e-05) (hash(x)=52575278) +17 train 9.774747 (lr=1.5105e-05) (hash(x)=43243482) +18 train 9.787950 (lr=1.5944e-05) (hash(x)=50506468) +19 train 9.782670 (lr=1.6783e-05) (hash(x)=38528894) +20 train 9.684865 (lr=1.7622e-05) (hash(x)=40784440) +21 train 9.648464 (lr=1.8462e-05) (hash(x)=29051732) +22 train 9.641328 (lr=1.9301e-05) (hash(x)=33747955) +23 train 9.621400 (lr=2.0140e-05) (hash(x)=38778457) +24 train 9.577639 (lr=2.0979e-05) (hash(x)=46187570) +25 val loss 9.5505 +25 val perplexity 14051.7842 +25 train 9.571191 (lr=2.1818e-05) (hash(x)=36327763) +26 train 9.558804 (lr=2.2657e-05) (hash(x)=41789010) +27 train 9.526335 (lr=2.3497e-05) (hash(x)=39402310) +28 train 9.509684 (lr=2.4336e-05) (hash(x)=44812707) +29 train 9.479240 (lr=2.5175e-05) (hash(x)=30948583) +30 train 9.499624 (lr=2.6014e-05) (hash(x)=39086453) +31 train 9.449280 (lr=2.6853e-05) (hash(x)=35948962) +32 train 9.442062 (lr=2.7692e-05) (hash(x)=46517299) +33 train 9.404938 (lr=2.8531e-05) (hash(x)=39494364) +34 train 9.332734 (lr=2.9371e-05) (hash(x)=42761865) +35 train 9.346293 (lr=3.0210e-05) (hash(x)=38361829) +36 train 9.340252 (lr=3.1049e-05) (hash(x)=39790163) +37 train 9.288192 (lr=3.1888e-05) (hash(x)=39144566) +38 train 9.253712 (lr=3.2727e-05) (hash(x)=41567158) +39 train 9.250922 (lr=3.3566e-05) (hash(x)=32382685) +40 train 9.230119 (lr=3.4406e-05) (hash(x)=39787056) +41 train 9.158819 (lr=3.5245e-05) (hash(x)=38761963) +42 train 9.141492 (lr=3.6084e-05) (hash(x)=38964119) +43 train 9.114965 (lr=3.6923e-05) (hash(x)=18463250) +44 train 9.100314 (lr=3.7762e-05) (hash(x)=39984913) +45 train 9.088501 (lr=3.8601e-05) (hash(x)=38365557) +46 train 9.038950 (lr=3.9441e-05) (hash(x)=42060610) +47 train 9.003553 (lr=4.0280e-05) (hash(x)=40192169) +48 train 8.982241 (lr=4.1119e-05) (hash(x)=38254656) +49 train 8.919492 (lr=4.1958e-05) (hash(x)=45241611) +50 val loss 8.9050 +50 val perplexity 7368.6250 +50 train 8.927713 (lr=4.2797e-05) (hash(x)=41016171) +51 train 8.873058 (lr=4.3636e-05) (hash(x)=41960203) +52 train 8.843029 (lr=4.4476e-05) (hash(x)=40482785) +53 train 8.806887 (lr=4.5315e-05) (hash(x)=41606506) +54 train 8.792999 (lr=4.6154e-05) (hash(x)=40257214) +55 train 8.759542 (lr=4.6993e-05) (hash(x)=42688716) +56 train 8.723410 (lr=4.7832e-05) (hash(x)=38987481) +57 train 8.702439 (lr=4.8671e-05) (hash(x)=42955987) +58 train 8.652745 (lr=4.9510e-05) (hash(x)=39716716) +59 train 8.623804 (lr=5.0350e-05) (hash(x)=41218506) +60 train 8.597829 (lr=5.1189e-05) (hash(x)=36886920) +61 train 8.580531 (lr=5.2028e-05) (hash(x)=47576691) +62 train 8.511808 (lr=5.2867e-05) (hash(x)=32658947) +63 train 8.473813 (lr=5.3706e-05) (hash(x)=38045442) +64 train 8.433111 (lr=5.4545e-05) (hash(x)=38975268) +65 train 8.415375 (lr=5.5385e-05) (hash(x)=40155319) +66 train 8.358398 (lr=5.6224e-05) (hash(x)=35199608) +67 train 8.342191 (lr=5.7063e-05) (hash(x)=38497847) +68 train 8.317028 (lr=5.7902e-05) (hash(x)=40630753) +69 train 8.232798 (lr=5.8741e-05) (hash(x)=43371265) +70 train 8.196128 (lr=5.9580e-05) (hash(x)=36438475) +71 train 8.202380 (lr=6.0420e-05) (hash(x)=36456333) +72 train 8.134385 (lr=6.1259e-05) (hash(x)=33277916) +73 train 8.099741 (lr=6.2098e-05) (hash(x)=40112658) +74 train 8.052616 (lr=6.2937e-05) (hash(x)=45141892) +75 val loss 8.0556 +75 val perplexity 3151.5442 +75 train 8.053989 (lr=6.3776e-05) (hash(x)=43169179) +76 train 7.989518 (lr=6.4615e-05) (hash(x)=37581771) +77 train 7.984672 (lr=6.5455e-05) (hash(x)=41893067) +78 train 7.947348 (lr=6.6294e-05) (hash(x)=41487541) +79 train 7.896566 (lr=6.7133e-05) (hash(x)=41755047) +80 train 7.868067 (lr=6.7972e-05) (hash(x)=40394153) +81 train 7.857352 (lr=6.8811e-05) (hash(x)=42526791) +82 train 7.806783 (lr=6.9650e-05) (hash(x)=34589516) +83 train 7.750386 (lr=7.0490e-05) (hash(x)=43703051) +84 train 7.731674 (lr=7.1329e-05) (hash(x)=37453964) +85 train 7.694523 (lr=7.2168e-05) (hash(x)=36925186) +86 train 7.671155 (lr=7.3007e-05) (hash(x)=41133801) +87 train 7.667558 (lr=7.3846e-05) (hash(x)=34856535) +88 train 7.640006 (lr=7.4685e-05) (hash(x)=38732024) +89 train 7.658576 (lr=7.5524e-05) (hash(x)=36825524) +90 train 7.580466 (lr=7.6364e-05) (hash(x)=34429787) +91 train 7.564632 (lr=7.7203e-05) (hash(x)=41232493) +92 train 7.570571 (lr=7.8042e-05) (hash(x)=37327176) +93 train 7.619775 (lr=7.8881e-05) (hash(x)=40760687) +94 train 7.613039 (lr=7.9720e-05) (hash(x)=42639290) +95 train 7.600494 (lr=8.0559e-05) (hash(x)=41146811) +96 train 7.555938 (lr=8.1399e-05) (hash(x)=37554529) +97 train 7.511914 (lr=8.2238e-05) (hash(x)=43241938) +98 train 7.537383 (lr=8.3077e-05) (hash(x)=51529150) +99 train 7.476875 (lr=8.3916e-05) (hash(x)=39423600) +100 val loss 7.4854 +100 val perplexity 1781.8303 +100 train 7.530900 (lr=8.4755e-05) (hash(x)=47918943) +101 train 7.454634 (lr=8.5594e-05) (hash(x)=34894003) +102 train 7.442733 (lr=8.6434e-05) (hash(x)=38127129) +103 train 7.336935 (lr=8.7273e-05) (hash(x)=37112566) +104 train 7.415893 (lr=8.8112e-05) (hash(x)=37715262) +105 train 7.424767 (lr=8.8951e-05) (hash(x)=39365879) +106 train 7.378431 (lr=8.9790e-05) (hash(x)=35558298) +107 train 7.322757 (lr=9.0629e-05) (hash(x)=35262991) +108 train 7.378599 (lr=9.1469e-05) (hash(x)=43357884) +109 train 7.396462 (lr=9.2308e-05) (hash(x)=34806302) +110 train 7.323207 (lr=9.3147e-05) (hash(x)=41573429) +111 train 7.304882 (lr=9.3986e-05) (hash(x)=42288007) +112 train 7.274498 (lr=9.4825e-05) (hash(x)=40170470) +113 train 7.330688 (lr=9.5664e-05) (hash(x)=41920091) +114 train 7.318342 (lr=9.6503e-05) (hash(x)=29943898) +115 train 7.280644 (lr=9.7343e-05) (hash(x)=36755667) +116 train 7.216402 (lr=9.8182e-05) (hash(x)=38108900) +117 train 7.129823 (lr=9.9021e-05) (hash(x)=37228744) +118 train 7.158122 (lr=9.9860e-05) (hash(x)=38429229) +119 train 7.200907 (lr=1.0070e-04) (hash(x)=40711635) +120 train 7.164865 (lr=1.0154e-04) (hash(x)=35377432) +121 train 7.155194 (lr=1.0238e-04) (hash(x)=47288470) +122 train 7.131368 (lr=1.0322e-04) (hash(x)=39317458) +123 train 7.117447 (lr=1.0406e-04) (hash(x)=42681144) +124 train 7.132321 (lr=1.0490e-04) (hash(x)=45781455) +125 val loss 7.1822 +125 val perplexity 1315.8254 +125 train 7.117499 (lr=1.0573e-04) (hash(x)=41620383) +126 train 7.100780 (lr=1.0657e-04) (hash(x)=37334030) +127 train 7.050600 (lr=1.0741e-04) (hash(x)=32269820) +128 train 7.021026 (lr=1.0825e-04) (hash(x)=38179209) +129 train 7.002790 (lr=1.0909e-04) (hash(x)=35546238) +130 train 7.054133 (lr=1.0993e-04) (hash(x)=42303524) +131 train 7.009112 (lr=1.1077e-04) (hash(x)=34999085) +132 train 7.005219 (lr=1.1161e-04) (hash(x)=41662264) +133 train 6.911733 (lr=1.1245e-04) (hash(x)=47780641) +134 train 6.907842 (lr=1.1329e-04) (hash(x)=32326200) +135 train 6.969793 (lr=1.1413e-04) (hash(x)=43741101) +136 train 6.944195 (lr=1.1497e-04) (hash(x)=37798628) +137 train 6.960860 (lr=1.1580e-04) (hash(x)=31326160) +138 train 6.896384 (lr=1.1664e-04) (hash(x)=37387156) +139 train 6.976185 (lr=1.1748e-04) (hash(x)=41284249) +140 train 7.071362 (lr=1.1832e-04) (hash(x)=43855133) +141 train 6.964739 (lr=1.1916e-04) (hash(x)=40615162) +142 train 7.018699 (lr=1.2000e-04) (hash(x)=40451800) +143 train 6.948346 (lr=1.2084e-04) (hash(x)=38373595) +144 train 6.956019 (lr=1.2168e-04) (hash(x)=38975698) +145 train 6.938947 (lr=1.2252e-04) (hash(x)=46676459) +146 train 6.933524 (lr=1.2336e-04) (hash(x)=41500725) +147 train 6.927428 (lr=1.2420e-04) (hash(x)=41386157) +148 train 6.918747 (lr=1.2503e-04) (hash(x)=42326119) +149 train 6.913380 (lr=1.2587e-04) (hash(x)=49861734) +150 val loss 6.8825 +150 val perplexity 975.0834 +150 train 6.894009 (lr=1.2671e-04) (hash(x)=36811718) +151 train 6.796099 (lr=1.2755e-04) (hash(x)=39093616) +152 train 6.817348 (lr=1.2839e-04) (hash(x)=36736942) +153 train 6.877935 (lr=1.2923e-04) (hash(x)=33558756) +154 train 6.776189 (lr=1.3007e-04) (hash(x)=35305390) +155 train 6.739007 (lr=1.3091e-04) (hash(x)=37118590) +156 train 6.810215 (lr=1.3175e-04) (hash(x)=40310783) +157 train 6.838595 (lr=1.3259e-04) (hash(x)=44123265) +158 train 6.823333 (lr=1.3343e-04) (hash(x)=41128188) +159 train 6.744976 (lr=1.3427e-04) (hash(x)=43358374) +160 train 6.680955 (lr=1.3510e-04) (hash(x)=36135701) +161 train 6.758813 (lr=1.3594e-04) (hash(x)=46217420) +162 train 6.651766 (lr=1.3678e-04) (hash(x)=41443881) +163 train 6.605563 (lr=1.3762e-04) (hash(x)=39750069) +164 train 6.649848 (lr=1.3846e-04) (hash(x)=39939052) +165 train 6.664865 (lr=1.3930e-04) (hash(x)=40724129) +166 train 6.497137 (lr=1.4014e-04) (hash(x)=42566590) +167 train 6.610975 (lr=1.4098e-04) (hash(x)=38557745) +168 train 6.563178 (lr=1.4182e-04) (hash(x)=32312721) +169 train 6.601635 (lr=1.4266e-04) (hash(x)=40801335) +170 train 6.561678 (lr=1.4350e-04) (hash(x)=41319929) +171 train 6.585115 (lr=1.4434e-04) (hash(x)=41550210) +172 train 6.560173 (lr=1.4517e-04) (hash(x)=46437931) +173 train 6.505449 (lr=1.4601e-04) (hash(x)=43120007) +174 train 6.466508 (lr=1.4685e-04) (hash(x)=48115241) +175 val loss 6.6102 +175 val perplexity 742.6159 +175 train 6.537608 (lr=1.4769e-04) (hash(x)=40280145) +176 train 6.464597 (lr=1.4853e-04) (hash(x)=40957875) +177 train 6.502585 (lr=1.4937e-04) (hash(x)=39433252) +178 train 6.447281 (lr=1.5021e-04) (hash(x)=36470769) +179 train 6.406983 (lr=1.5105e-04) (hash(x)=39128512) +180 train 6.393987 (lr=1.5189e-04) (hash(x)=36097227) +181 train 6.434790 (lr=1.5273e-04) (hash(x)=40876260) +182 train 6.413187 (lr=1.5357e-04) (hash(x)=38209318) +183 train 6.406355 (lr=1.5441e-04) (hash(x)=45010301) +184 train 6.417411 (lr=1.5524e-04) (hash(x)=40133284) +185 train 6.468648 (lr=1.5608e-04) (hash(x)=32369810) +186 train 6.490906 (lr=1.5692e-04) (hash(x)=40341410) +187 train 6.546777 (lr=1.5776e-04) (hash(x)=35170712) +188 train 6.505735 (lr=1.5860e-04) (hash(x)=43697287) +189 train 6.458137 (lr=1.5944e-04) (hash(x)=35640506) +190 train 6.517556 (lr=1.6028e-04) (hash(x)=42475999) +191 train 6.450164 (lr=1.6112e-04) (hash(x)=44775827) +192 train 6.431538 (lr=1.6196e-04) (hash(x)=38468697) +193 train 6.484678 (lr=1.6280e-04) (hash(x)=40217253) +194 train 6.392290 (lr=1.6364e-04) (hash(x)=40286692) +195 train 6.390860 (lr=1.6448e-04) (hash(x)=37642227) +196 train 6.363925 (lr=1.6531e-04) (hash(x)=42102483) +197 train 6.397184 (lr=1.6615e-04) (hash(x)=44953778) +198 train 6.389937 (lr=1.6699e-04) (hash(x)=36582287) +199 train 6.360559 (lr=1.6783e-04) (hash(x)=42366451) +200 val loss 6.3935 +200 val perplexity 597.9534 +200 train 6.352712 (lr=1.6867e-04) (hash(x)=42122518) +201 train 6.330259 (lr=1.6951e-04) (hash(x)=41477880) +202 train 6.317741 (lr=1.7035e-04) (hash(x)=41426565) +203 train 6.333629 (lr=1.7119e-04) (hash(x)=38017205) +204 train 6.291780 (lr=1.7203e-04) (hash(x)=39447894) +205 train 6.366374 (lr=1.7287e-04) (hash(x)=32293545) +206 train 6.340835 (lr=1.7371e-04) (hash(x)=40469981) +207 train 6.310456 (lr=1.7455e-04) (hash(x)=31716709) +208 train 6.219660 (lr=1.7538e-04) (hash(x)=43670218) +209 train 6.198154 (lr=1.7622e-04) (hash(x)=40554699) +210 train 6.225001 (lr=1.7706e-04) (hash(x)=38725807) +211 train 6.244884 (lr=1.7790e-04) (hash(x)=40467125) +212 train 6.296505 (lr=1.7874e-04) (hash(x)=42652430) +213 train 6.252005 (lr=1.7958e-04) (hash(x)=45435315) +214 train 6.256563 (lr=1.8042e-04) (hash(x)=29128159) +215 train 6.252096 (lr=1.8126e-04) (hash(x)=45169469) +216 train 6.205091 (lr=1.8210e-04) (hash(x)=36858419) +217 train 6.179334 (lr=1.8294e-04) (hash(x)=42312967) +218 train 6.177987 (lr=1.8378e-04) (hash(x)=39375221) +219 train 6.180394 (lr=1.8462e-04) (hash(x)=33173919) +220 train 6.093734 (lr=1.8545e-04) (hash(x)=39942230) +221 train 6.119827 (lr=1.8629e-04) (hash(x)=37912723) +222 train 6.157148 (lr=1.8713e-04) (hash(x)=42278516) +223 train 6.060851 (lr=1.8797e-04) (hash(x)=41117506) +224 train 6.109847 (lr=1.8881e-04) (hash(x)=40555532) +225 val loss 6.2245 +225 val perplexity 504.9691 +225 train 6.054298 (lr=1.8965e-04) (hash(x)=42273440) +226 train 6.037741 (lr=1.9049e-04) (hash(x)=39835965) +227 train 6.151709 (lr=1.9133e-04) (hash(x)=39343263) +228 train 6.056112 (lr=1.9217e-04) (hash(x)=36825672) +229 train 6.047573 (lr=1.9301e-04) (hash(x)=41292707) +230 train 6.042040 (lr=1.9385e-04) (hash(x)=41475387) +231 train 6.037692 (lr=1.9469e-04) (hash(x)=37608856) +232 train 6.212384 (lr=1.9552e-04) (hash(x)=51079827) +233 train 6.180878 (lr=1.9636e-04) (hash(x)=43709484) +234 train 6.200502 (lr=1.9720e-04) (hash(x)=33582711) +235 train 6.182674 (lr=1.9804e-04) (hash(x)=37674273) +236 train 6.213438 (lr=1.9888e-04) (hash(x)=43302793) +237 train 6.190109 (lr=1.9972e-04) (hash(x)=43071861) +238 train 6.130840 (lr=2.0056e-04) (hash(x)=44890833) +239 train 6.145987 (lr=2.0140e-04) (hash(x)=36471539) +240 train 6.139289 (lr=2.0224e-04) (hash(x)=37196901) +241 train 6.167604 (lr=2.0308e-04) (hash(x)=45492886) +242 train 6.141562 (lr=2.0392e-04) (hash(x)=39284513) +243 train 6.119276 (lr=2.0476e-04) (hash(x)=39734801) +244 train 6.042462 (lr=2.0559e-04) (hash(x)=35925717) +245 train 6.025711 (lr=2.0643e-04) (hash(x)=38470685) +246 train 6.042192 (lr=2.0727e-04) (hash(x)=35741825) +247 train 6.092535 (lr=2.0811e-04) (hash(x)=36084795) +248 train 6.071427 (lr=2.0895e-04) (hash(x)=37612515) +249 train 6.027603 (lr=2.0979e-04) (hash(x)=39611870) +250 val loss 6.0669 +250 val perplexity 431.3311 +250 train 6.055567 (lr=2.1063e-04) (hash(x)=40779745) +251 train 6.007662 (lr=2.1147e-04) (hash(x)=43073755) +252 train 6.083202 (lr=2.1231e-04) (hash(x)=32372068) +253 train 6.029825 (lr=2.1315e-04) (hash(x)=41185988) +254 train 6.032554 (lr=2.1399e-04) (hash(x)=44627432) +255 train 5.946129 (lr=2.1483e-04) (hash(x)=41228491) +256 train 5.992264 (lr=2.1566e-04) (hash(x)=43108878) +257 train 5.946641 (lr=2.1650e-04) (hash(x)=37715420) +258 train 5.945706 (lr=2.1734e-04) (hash(x)=44915520) +259 train 5.955254 (lr=2.1818e-04) (hash(x)=44807907) +260 train 5.878822 (lr=2.1902e-04) (hash(x)=41681981) +261 train 5.918091 (lr=2.1986e-04) (hash(x)=37931144) +262 train 5.897851 (lr=2.2070e-04) (hash(x)=34209166) +263 train 5.882171 (lr=2.2154e-04) (hash(x)=44747777) +264 train 5.896231 (lr=2.2238e-04) (hash(x)=36956980) +265 train 5.894491 (lr=2.2322e-04) (hash(x)=36363962) +266 train 5.949480 (lr=2.2406e-04) (hash(x)=43014347) +267 train 5.816743 (lr=2.2490e-04) (hash(x)=37332944) +268 train 5.823335 (lr=2.2573e-04) (hash(x)=37330861) +269 train 5.898746 (lr=2.2657e-04) (hash(x)=34449073) +270 train 5.862459 (lr=2.2741e-04) (hash(x)=41314235) +271 train 5.838128 (lr=2.2825e-04) (hash(x)=41494096) +272 train 5.804650 (lr=2.2909e-04) (hash(x)=36860812) +273 train 5.810693 (lr=2.2993e-04) (hash(x)=31334487) +274 train 5.770909 (lr=2.3077e-04) (hash(x)=39802055) +275 val loss 5.9435 +275 val perplexity 381.2727 +275 train 5.889434 (lr=2.3161e-04) (hash(x)=40789558) +276 train 5.833976 (lr=2.3245e-04) (hash(x)=44213534) +277 train 5.800230 (lr=2.3329e-04) (hash(x)=40678982) +278 train 5.951701 (lr=2.3413e-04) (hash(x)=38528614) +279 train 5.903155 (lr=2.3497e-04) (hash(x)=35260292) +280 train 5.943098 (lr=2.3580e-04) (hash(x)=37236528) +281 train 5.923005 (lr=2.3664e-04) (hash(x)=41986135) +282 train 5.897914 (lr=2.3748e-04) (hash(x)=41626718) +283 train 5.905075 (lr=2.3832e-04) (hash(x)=33681827) +284 train 5.952044 (lr=2.3916e-04) (hash(x)=41824148) +285 train 5.867492 (lr=2.4000e-04) (hash(x)=42186750) +286 train 5.892290 (lr=2.4084e-04) (hash(x)=39219951) +287 train 5.866047 (lr=2.4168e-04) (hash(x)=41026022) +288 train 5.854340 (lr=2.4252e-04) (hash(x)=39568202) +289 train 5.849307 (lr=2.4336e-04) (hash(x)=36416381) +290 train 5.772422 (lr=2.4420e-04) (hash(x)=40503598) +291 train 5.801560 (lr=2.4503e-04) (hash(x)=36599026) +292 train 5.752246 (lr=2.4587e-04) (hash(x)=37025321) +293 train 5.778594 (lr=2.4671e-04) (hash(x)=40739931) +294 train 5.864072 (lr=2.4755e-04) (hash(x)=39566749) +295 train 5.793361 (lr=2.4839e-04) (hash(x)=47756587) +296 train 5.792753 (lr=2.4923e-04) (hash(x)=36379804) +297 train 5.797366 (lr=2.5007e-04) (hash(x)=38616680) +298 train 5.776823 (lr=2.5091e-04) (hash(x)=32371362) +299 train 5.813749 (lr=2.5175e-04) (hash(x)=40579988) +300 val loss 5.8019 +300 val perplexity 330.9376 +300 train 5.851769 (lr=2.5259e-04) (hash(x)=41324766) +301 train 5.722897 (lr=2.5343e-04) (hash(x)=49088072) +302 train 5.737124 (lr=2.5427e-04) (hash(x)=39100661) +303 train 5.709328 (lr=2.5510e-04) (hash(x)=37345517) +304 train 5.712895 (lr=2.5594e-04) (hash(x)=40042320) +305 train 5.691333 (lr=2.5678e-04) (hash(x)=41433374) +306 train 5.693319 (lr=2.5762e-04) (hash(x)=40307388) +307 train 5.672678 (lr=2.5846e-04) (hash(x)=40740097) +308 train 5.673214 (lr=2.5930e-04) (hash(x)=33879047) +309 train 5.637316 (lr=2.6014e-04) (hash(x)=37470830) +310 train 5.654129 (lr=2.6098e-04) (hash(x)=40476028) +311 train 5.634073 (lr=2.6182e-04) (hash(x)=41896548) +312 train 5.624842 (lr=2.6266e-04) (hash(x)=43513953) +313 train 5.594166 (lr=2.6350e-04) (hash(x)=39523516) +314 train 5.599308 (lr=2.6434e-04) (hash(x)=40238039) +315 train 5.580833 (lr=2.6517e-04) (hash(x)=38464309) +316 train 5.619075 (lr=2.6601e-04) (hash(x)=35573716) +317 train 5.592001 (lr=2.6685e-04) (hash(x)=41134953) +318 train 5.632378 (lr=2.6769e-04) (hash(x)=38718172) +319 train 5.585436 (lr=2.6853e-04) (hash(x)=37125360) +320 train 5.529086 (lr=2.6937e-04) (hash(x)=44265657) +321 train 5.570932 (lr=2.7021e-04) (hash(x)=37463745) +322 train 5.533358 (lr=2.7105e-04) (hash(x)=41654567) +323 train 5.538893 (lr=2.7189e-04) (hash(x)=40072230) +324 train 5.684635 (lr=2.7273e-04) (hash(x)=42878827) +325 val loss 5.7110 +325 val perplexity 302.1718 +325 train 5.753618 (lr=2.7357e-04) (hash(x)=44631899) +326 train 5.705792 (lr=2.7441e-04) (hash(x)=39467189) +327 train 5.717961 (lr=2.7524e-04) (hash(x)=38539326) +328 train 5.688919 (lr=2.7608e-04) (hash(x)=37772076) +329 train 5.696706 (lr=2.7692e-04) (hash(x)=35060302) +330 train 5.726329 (lr=2.7776e-04) (hash(x)=40813035) +331 train 5.666445 (lr=2.7860e-04) (hash(x)=41027928) +332 train 5.689467 (lr=2.7944e-04) (hash(x)=37896555) +333 train 5.670465 (lr=2.8028e-04) (hash(x)=45148659) +334 train 5.692657 (lr=2.8112e-04) (hash(x)=43367722) +335 train 5.708185 (lr=2.8196e-04) (hash(x)=47148722) +336 train 5.578197 (lr=2.8280e-04) (hash(x)=37156305) +337 train 5.665496 (lr=2.8364e-04) (hash(x)=38038769) +338 train 5.620018 (lr=2.8448e-04) (hash(x)=36596536) +339 train 5.605708 (lr=2.8531e-04) (hash(x)=37257619) +340 train 5.627136 (lr=2.8615e-04) (hash(x)=44600996) +341 train 5.606728 (lr=2.8699e-04) (hash(x)=42454153) +342 train 5.633347 (lr=2.8783e-04) (hash(x)=41819997) +343 train 5.535309 (lr=2.8867e-04) (hash(x)=39687954) +344 train 5.598709 (lr=2.8951e-04) (hash(x)=38267931) +345 train 5.533250 (lr=2.9035e-04) (hash(x)=47357452) +346 train 5.535751 (lr=2.9119e-04) (hash(x)=37736592) +347 train 5.554239 (lr=2.9203e-04) (hash(x)=33228496) +348 train 5.487216 (lr=2.9287e-04) (hash(x)=39774441) +349 train 5.514224 (lr=2.9371e-04) (hash(x)=41746861) +350 val loss 5.5762 +350 val perplexity 264.0579 +350 train 5.494576 (lr=2.9455e-04) (hash(x)=34583550) +351 train 5.527035 (lr=2.9538e-04) (hash(x)=32074045) +352 train 5.474802 (lr=2.9622e-04) (hash(x)=36317994) +353 train 5.480605 (lr=2.9706e-04) (hash(x)=37723713) +354 train 5.513868 (lr=2.9790e-04) (hash(x)=40844973) +355 train 5.478679 (lr=2.9874e-04) (hash(x)=37832675) +356 train 5.423704 (lr=2.9958e-04) (hash(x)=40283056) +357 train 5.441723 (lr=3.0042e-04) (hash(x)=44214196) +358 train 5.443653 (lr=3.0126e-04) (hash(x)=41961977) +359 train 5.383656 (lr=3.0210e-04) (hash(x)=36095254) +360 train 5.394408 (lr=3.0294e-04) (hash(x)=39198575) +361 train 5.424721 (lr=3.0378e-04) (hash(x)=37057217) +362 train 5.450514 (lr=3.0462e-04) (hash(x)=40359908) +363 train 5.351687 (lr=3.0545e-04) (hash(x)=37310806) +364 train 5.418433 (lr=3.0629e-04) (hash(x)=36281566) +365 train 5.349003 (lr=3.0713e-04) (hash(x)=39592602) +366 train 5.340968 (lr=3.0797e-04) (hash(x)=35841879) +367 train 5.360373 (lr=3.0881e-04) (hash(x)=37094678) +368 train 5.392906 (lr=3.0965e-04) (hash(x)=42425037) +369 train 5.329267 (lr=3.1049e-04) (hash(x)=36793961) +370 train 5.378301 (lr=3.1133e-04) (hash(x)=37177660) +371 train 5.489535 (lr=3.1217e-04) (hash(x)=40499581) +372 train 5.549965 (lr=3.1301e-04) (hash(x)=35410498) +373 train 5.483834 (lr=3.1385e-04) (hash(x)=32005917) +374 train 5.507425 (lr=3.1469e-04) (hash(x)=47363906) +375 val loss 5.4907 +375 val perplexity 242.4289 +375 train 5.508036 (lr=3.1552e-04) (hash(x)=37292125) +376 train 5.531108 (lr=3.1636e-04) (hash(x)=37305319) +377 train 5.517948 (lr=3.1720e-04) (hash(x)=41160641) +378 train 5.542285 (lr=3.1804e-04) (hash(x)=41350459) +379 train 5.431089 (lr=3.1888e-04) (hash(x)=39483178) +380 train 5.468255 (lr=3.1972e-04) (hash(x)=40036833) +381 train 5.485754 (lr=3.2056e-04) (hash(x)=49075853) +382 train 5.398359 (lr=3.2140e-04) (hash(x)=38972596) +383 train 5.418650 (lr=3.2224e-04) (hash(x)=34405678) +384 train 5.396177 (lr=3.2308e-04) (hash(x)=39234765) +385 train 5.458688 (lr=3.2392e-04) (hash(x)=30356468) +386 train 5.537965 (lr=3.2476e-04) (hash(x)=37451510) +387 train 5.386930 (lr=3.2559e-04) (hash(x)=42780739) +388 train 5.407529 (lr=3.2643e-04) (hash(x)=38709129) +389 train 5.394099 (lr=3.2727e-04) (hash(x)=38034571) +390 train 5.384891 (lr=3.2811e-04) (hash(x)=38283697) +391 train 5.402844 (lr=3.2895e-04) (hash(x)=39032990) +392 train 5.339353 (lr=3.2979e-04) (hash(x)=37371015) +393 train 5.394370 (lr=3.3063e-04) (hash(x)=36620469) +394 train 5.271710 (lr=3.3147e-04) (hash(x)=36639924) +395 train 5.262527 (lr=3.3231e-04) (hash(x)=36101288) +396 train 5.320173 (lr=3.3315e-04) (hash(x)=38319370) +397 train 5.268435 (lr=3.3399e-04) (hash(x)=41132992) +398 train 5.283630 (lr=3.3483e-04) (hash(x)=39099391) +399 train 5.291853 (lr=3.3566e-04) (hash(x)=38882974) +400 val loss 5.3646 +400 val perplexity 213.7081 +400 train 5.279068 (lr=3.3650e-04) (hash(x)=40514688) +401 train 5.282629 (lr=3.3734e-04) (hash(x)=37598186) +402 train 5.245466 (lr=3.3818e-04) (hash(x)=38055661) +403 train 5.288932 (lr=3.3902e-04) (hash(x)=39342156) +404 train 5.252066 (lr=3.3986e-04) (hash(x)=41341470) +405 train 5.244284 (lr=3.4070e-04) (hash(x)=36865352) +406 train 5.187352 (lr=3.4154e-04) (hash(x)=39172689) +407 train 5.176376 (lr=3.4238e-04) (hash(x)=48109188) +408 train 5.161231 (lr=3.4322e-04) (hash(x)=38213549) +409 train 5.198978 (lr=3.4406e-04) (hash(x)=30123439) +410 train 5.182931 (lr=3.4490e-04) (hash(x)=37493045) +411 train 5.217394 (lr=3.4573e-04) (hash(x)=39086532) +412 train 5.213756 (lr=3.4657e-04) (hash(x)=36016991) +413 train 5.165464 (lr=3.4741e-04) (hash(x)=36446817) +414 train 5.190506 (lr=3.4825e-04) (hash(x)=37795410) +415 train 5.195673 (lr=3.4909e-04) (hash(x)=34879698) +416 train 5.269331 (lr=3.4993e-04) (hash(x)=37764486) +417 train 5.396779 (lr=3.5077e-04) (hash(x)=35430449) +418 train 5.370178 (lr=3.5161e-04) (hash(x)=35472793) +419 train 5.348699 (lr=3.5245e-04) (hash(x)=33545738) +420 train 5.302677 (lr=3.5329e-04) (hash(x)=37484590) +421 train 5.361448 (lr=3.5413e-04) (hash(x)=40094447) +422 train 5.269117 (lr=3.5497e-04) (hash(x)=42680366) +423 train 5.389090 (lr=3.5580e-04) (hash(x)=40426112) +424 train 5.316704 (lr=3.5664e-04) (hash(x)=44446735) +425 val loss 5.2814 +425 val perplexity 196.6430 +425 train 5.278439 (lr=3.5748e-04) (hash(x)=42553173) +426 train 5.240267 (lr=3.5832e-04) (hash(x)=39475039) +427 train 5.286255 (lr=3.5916e-04) (hash(x)=44207434) +428 train 5.224623 (lr=3.6000e-04) (hash(x)=42767292) +429 train 5.331515 (lr=3.6084e-04) (hash(x)=42999128) +430 train 5.272475 (lr=3.6168e-04) (hash(x)=41693299) +431 train 5.238976 (lr=3.6252e-04) (hash(x)=39678552) +432 train 5.297646 (lr=3.6336e-04) (hash(x)=39737753) +433 train 5.314342 (lr=3.6420e-04) (hash(x)=39268413) +434 train 5.174263 (lr=3.6503e-04) (hash(x)=39968419) +435 train 5.210058 (lr=3.6587e-04) (hash(x)=37896294) +436 train 5.167824 (lr=3.6671e-04) (hash(x)=42771814) +437 train 5.351962 (lr=3.6755e-04) (hash(x)=37230025) +438 train 5.214765 (lr=3.6839e-04) (hash(x)=35260870) +439 train 5.237310 (lr=3.6923e-04) (hash(x)=38443858) +440 train 5.079319 (lr=3.7007e-04) (hash(x)=37307923) +441 train 5.139539 (lr=3.7091e-04) (hash(x)=41566115) +442 train 5.108434 (lr=3.7175e-04) (hash(x)=43057153) +443 train 5.098994 (lr=3.7259e-04) (hash(x)=37013041) +444 train 5.149358 (lr=3.7343e-04) (hash(x)=35125597) +445 train 5.109326 (lr=3.7427e-04) (hash(x)=39783189) +446 train 5.138242 (lr=3.7510e-04) (hash(x)=36799261) +447 train 5.157615 (lr=3.7594e-04) (hash(x)=34593766) +448 train 5.164219 (lr=3.7678e-04) (hash(x)=43797827) +449 train 5.110564 (lr=3.7762e-04) (hash(x)=40906589) +450 val loss 5.1863 +450 val perplexity 178.8026 +450 train 5.123974 (lr=3.7846e-04) (hash(x)=32741282) +451 train 5.125225 (lr=3.7930e-04) (hash(x)=50294742) +452 train 5.023196 (lr=3.8014e-04) (hash(x)=35466429) +453 train 5.046290 (lr=3.8098e-04) (hash(x)=37104366) +454 train 5.069521 (lr=3.8182e-04) (hash(x)=41071825) +455 train 4.974266 (lr=3.8266e-04) (hash(x)=40380448) +456 train 5.060163 (lr=3.8350e-04) (hash(x)=34109120) +457 train 5.004193 (lr=3.8434e-04) (hash(x)=36634294) +458 train 5.047546 (lr=3.8517e-04) (hash(x)=36875461) +459 train 5.025526 (lr=3.8601e-04) (hash(x)=39460651) +460 train 4.992205 (lr=3.8685e-04) (hash(x)=43091341) +461 train 4.959994 (lr=3.8769e-04) (hash(x)=34613309) +462 train 4.927378 (lr=3.8853e-04) (hash(x)=42975942) +463 train 5.041049 (lr=3.8937e-04) (hash(x)=40204529) +464 train 5.113060 (lr=3.9021e-04) (hash(x)=45680967) +465 train 5.100714 (lr=3.9105e-04) (hash(x)=43702281) +466 train 5.195771 (lr=3.9189e-04) (hash(x)=38214306) +467 train 5.129907 (lr=3.9273e-04) (hash(x)=42669521) +468 train 5.148453 (lr=3.9357e-04) (hash(x)=39405300) +469 train 5.120042 (lr=3.9441e-04) (hash(x)=36057754) +470 train 5.089521 (lr=3.9524e-04) (hash(x)=37714138) +471 train 5.102021 (lr=3.9608e-04) (hash(x)=38908149) +472 train 5.112418 (lr=3.9692e-04) (hash(x)=45521440) +473 train 5.141387 (lr=3.9776e-04) (hash(x)=34608995) +474 train 5.103997 (lr=3.9860e-04) (hash(x)=37672167) +475 val loss 5.0839 +475 val perplexity 161.4021 +475 train 5.097307 (lr=3.9944e-04) (hash(x)=36781273) +476 train 5.021956 (lr=4.0028e-04) (hash(x)=40368140) +477 train 5.120284 (lr=4.0112e-04) (hash(x)=43565324) +478 train 5.075578 (lr=4.0196e-04) (hash(x)=39525402) +479 train 5.073175 (lr=4.0280e-04) (hash(x)=42180600) +480 train 5.057418 (lr=4.0364e-04) (hash(x)=45877865) +481 train 5.066048 (lr=4.0448e-04) (hash(x)=37255189) +482 train 5.052877 (lr=4.0531e-04) (hash(x)=42528092) +483 train 5.070672 (lr=4.0615e-04) (hash(x)=38033423) +484 train 5.049742 (lr=4.0699e-04) (hash(x)=52701801) +485 train 5.016688 (lr=4.0783e-04) (hash(x)=41671993) +486 train 5.009629 (lr=4.0867e-04) (hash(x)=42741729) +487 train 5.016788 (lr=4.0951e-04) (hash(x)=62841393) +488 train 4.949587 (lr=4.1035e-04) (hash(x)=37405674) +489 train 4.951458 (lr=4.1119e-04) (hash(x)=42163753) +490 train 5.011644 (lr=4.1203e-04) (hash(x)=40250737) +491 train 4.973010 (lr=4.1287e-04) (hash(x)=37721154) +492 train 4.996588 (lr=4.1371e-04) (hash(x)=37239312) +493 train 4.957820 (lr=4.1455e-04) (hash(x)=41936062) +494 train 4.968933 (lr=4.1538e-04) (hash(x)=39965572) +495 train 4.936748 (lr=4.1622e-04) (hash(x)=38091850) +496 train 4.966709 (lr=4.1706e-04) (hash(x)=40284836) +497 train 4.936623 (lr=4.1790e-04) (hash(x)=38188647) +498 train 4.893054 (lr=4.1874e-04) (hash(x)=45262540) +499 train 4.822873 (lr=4.1958e-04) (hash(x)=40801880) +500 val loss 4.9923 +500 val perplexity 147.2761 +500 train 4.925814 (lr=4.2042e-04) (hash(x)=43131219) +501 train 4.820529 (lr=4.2126e-04) (hash(x)=39865477) +502 train 4.824061 (lr=4.2210e-04) (hash(x)=41378087) +503 train 4.801290 (lr=4.2294e-04) (hash(x)=38007933) +504 train 4.862643 (lr=4.2378e-04) (hash(x)=36830388) +505 train 4.810861 (lr=4.2462e-04) (hash(x)=39113165) +506 train 4.915660 (lr=4.2545e-04) (hash(x)=37859347) +507 train 4.769210 (lr=4.2629e-04) (hash(x)=38009876) +508 train 4.756257 (lr=4.2713e-04) (hash(x)=39711489) +509 train 4.829582 (lr=4.2797e-04) (hash(x)=36877328) +510 train 4.985202 (lr=4.2881e-04) (hash(x)=41703782) +511 train 4.956995 (lr=4.2965e-04) (hash(x)=42683906) +512 train 4.973127 (lr=4.3049e-04) (hash(x)=39014072) +513 train 4.960346 (lr=4.3133e-04) (hash(x)=38754306) +514 train 4.961463 (lr=4.3217e-04) (hash(x)=36857195) +515 train 4.969834 (lr=4.3301e-04) (hash(x)=38785473) +516 train 5.129850 (lr=4.3385e-04) (hash(x)=40358308) +517 train 5.062445 (lr=4.3469e-04) (hash(x)=44278997) +518 train 4.977136 (lr=4.3552e-04) (hash(x)=38206502) +519 train 5.044161 (lr=4.3636e-04) (hash(x)=38246391) +520 train 4.996213 (lr=4.3720e-04) (hash(x)=39807203) +521 train 4.936701 (lr=4.3804e-04) (hash(x)=35855541) +522 train 4.942749 (lr=4.3888e-04) (hash(x)=37971869) +523 train 4.906857 (lr=4.3972e-04) (hash(x)=42641567) +524 train 4.874279 (lr=4.4056e-04) (hash(x)=41170656) +525 val loss 4.8933 +525 val perplexity 133.3936 +525 train 4.865292 (lr=4.4140e-04) (hash(x)=40070395) +526 train 4.904939 (lr=4.4224e-04) (hash(x)=36662895) +527 train 4.842498 (lr=4.4308e-04) (hash(x)=34953639) +528 train 4.886062 (lr=4.4392e-04) (hash(x)=43354241) +529 train 4.858136 (lr=4.4476e-04) (hash(x)=42670048) +530 train 4.847679 (lr=4.4559e-04) (hash(x)=42787056) +531 train 4.832190 (lr=4.4643e-04) (hash(x)=38135462) +532 train 4.835494 (lr=4.4727e-04) (hash(x)=44202482) +533 train 4.809732 (lr=4.4811e-04) (hash(x)=37591210) +534 train 4.791667 (lr=4.4895e-04) (hash(x)=42693647) +535 train 4.771936 (lr=4.4979e-04) (hash(x)=41257155) +536 train 4.821037 (lr=4.5063e-04) (hash(x)=41097913) +537 train 4.779957 (lr=4.5147e-04) (hash(x)=41674689) +538 train 4.767700 (lr=4.5231e-04) (hash(x)=42866093) +539 train 4.806075 (lr=4.5315e-04) (hash(x)=51906844) +540 train 4.729607 (lr=4.5399e-04) (hash(x)=37116649) +541 train 4.745914 (lr=4.5483e-04) (hash(x)=39244142) +542 train 4.826232 (lr=4.5566e-04) (hash(x)=43373482) +543 train 4.753059 (lr=4.5650e-04) (hash(x)=37463724) +544 train 4.769698 (lr=4.5734e-04) (hash(x)=38231273) +545 train 4.669314 (lr=4.5818e-04) (hash(x)=44465367) +546 train 4.657365 (lr=4.5902e-04) (hash(x)=36621097) +547 train 4.649123 (lr=4.5986e-04) (hash(x)=35218318) +548 train 4.666662 (lr=4.6070e-04) (hash(x)=37197314) +549 train 4.644151 (lr=4.6154e-04) (hash(x)=40188127) +550 val loss 4.7802 +550 val perplexity 119.1231 +550 train 4.669133 (lr=4.6238e-04) (hash(x)=44513553) +551 train 4.629128 (lr=4.6322e-04) (hash(x)=42828431) +552 train 4.563756 (lr=4.6406e-04) (hash(x)=40519227) +553 train 4.731197 (lr=4.6490e-04) (hash(x)=42226323) +554 train 4.614608 (lr=4.6573e-04) (hash(x)=37260250) +555 train 4.598952 (lr=4.6657e-04) (hash(x)=47260674) +556 train 4.618718 (lr=4.6741e-04) (hash(x)=38537913) +557 train 4.796545 (lr=4.6825e-04) (hash(x)=40565197) +558 train 4.771357 (lr=4.6909e-04) (hash(x)=44454398) +559 train 4.764670 (lr=4.6993e-04) (hash(x)=39058948) +560 train 4.815691 (lr=4.7077e-04) (hash(x)=39132596) +561 train 4.753218 (lr=4.7161e-04) (hash(x)=49300187) +562 train 4.734506 (lr=4.7245e-04) (hash(x)=38233404) +563 train 4.745300 (lr=4.7329e-04) (hash(x)=44797172) +564 train 4.756500 (lr=4.7413e-04) (hash(x)=41771031) +565 train 4.743266 (lr=4.7497e-04) (hash(x)=39472099) +566 train 4.712947 (lr=4.7580e-04) (hash(x)=39401704) +567 train 4.753609 (lr=4.7664e-04) (hash(x)=35782719) +568 train 4.730371 (lr=4.7748e-04) (hash(x)=39842801) +569 train 4.721108 (lr=4.7832e-04) (hash(x)=37760632) +570 train 4.667242 (lr=4.7916e-04) (hash(x)=31858208) +571 train 4.718445 (lr=4.8000e-04) (hash(x)=38239030) +572 train 4.676560 (lr=4.8084e-04) (hash(x)=46172346) +573 train 4.682487 (lr=4.8168e-04) (hash(x)=44482742) +574 train 4.628520 (lr=4.8252e-04) (hash(x)=38254938) +575 val loss 4.6710 +575 val perplexity 106.8085 +575 train 4.685813 (lr=4.8336e-04) (hash(x)=37988620) +576 train 4.648889 (lr=4.8420e-04) (hash(x)=41296886) +577 train 4.692020 (lr=4.8503e-04) (hash(x)=52585118) +578 train 4.667552 (lr=4.8587e-04) (hash(x)=40678246) +579 train 4.612870 (lr=4.8671e-04) (hash(x)=39527458) +580 train 4.599270 (lr=4.8755e-04) (hash(x)=38856652) +581 train 4.566880 (lr=4.8839e-04) (hash(x)=35707074) +582 train 4.536991 (lr=4.8923e-04) (hash(x)=34320045) +583 train 4.565465 (lr=4.9007e-04) (hash(x)=46435416) +584 train 4.588707 (lr=4.9091e-04) (hash(x)=39956559) +585 train 4.585146 (lr=4.9175e-04) (hash(x)=44947632) +586 train 4.595325 (lr=4.9259e-04) (hash(x)=43905552) +587 train 4.646179 (lr=4.9343e-04) (hash(x)=40475274) +588 train 4.647529 (lr=4.9427e-04) (hash(x)=39321345) +589 train 4.643122 (lr=4.9510e-04) (hash(x)=35332000) +590 train 4.656626 (lr=4.9594e-04) (hash(x)=42345886) +591 train 4.544851 (lr=4.9678e-04) (hash(x)=39532509) +592 train 4.476758 (lr=4.9762e-04) (hash(x)=44596668) +593 train 4.512810 (lr=4.9846e-04) (hash(x)=43556802) +594 train 4.515790 (lr=4.9930e-04) (hash(x)=42101064) +595 train 4.495581 (lr=5.0014e-04) (hash(x)=48446808) +596 train 4.480376 (lr=5.0098e-04) (hash(x)=45569690) +597 train 4.539573 (lr=5.0182e-04) (hash(x)=41190293) +598 train 4.473361 (lr=5.0266e-04) (hash(x)=40089456) +599 train 4.459393 (lr=5.0350e-04) (hash(x)=41600024) +600 val loss 4.6118 +600 val perplexity 100.6661 +600 train 4.437472 (lr=5.0434e-04) (hash(x)=38669085) +601 train 4.434711 (lr=5.0517e-04) (hash(x)=44167517) +602 train 4.434674 (lr=5.0601e-04) (hash(x)=36746700) +603 train 4.537838 (lr=5.0685e-04) (hash(x)=30478797) +604 train 4.572436 (lr=5.0769e-04) (hash(x)=40463152) +605 train 4.640467 (lr=5.0853e-04) (hash(x)=36683463) +606 train 4.591427 (lr=5.0937e-04) (hash(x)=36547788) +607 train 4.570364 (lr=5.1021e-04) (hash(x)=40724442) +608 train 4.619559 (lr=5.1105e-04) (hash(x)=41514731) +609 train 4.551582 (lr=5.1189e-04) (hash(x)=31913874) +610 train 4.575820 (lr=5.1273e-04) (hash(x)=37770847) +611 train 4.638728 (lr=5.1357e-04) (hash(x)=37405410) +612 train 4.568518 (lr=5.1441e-04) (hash(x)=40475350) +613 train 4.559225 (lr=5.1524e-04) (hash(x)=43152570) +614 train 4.566629 (lr=5.1608e-04) (hash(x)=39406152) +615 train 4.579521 (lr=5.1692e-04) (hash(x)=40620371) +616 train 4.544508 (lr=5.1776e-04) (hash(x)=40889048) +617 train 4.558961 (lr=5.1860e-04) (hash(x)=35317866) +618 train 4.509014 (lr=5.1944e-04) (hash(x)=37082153) +619 train 4.532469 (lr=5.2028e-04) (hash(x)=42929149) +620 train 4.566469 (lr=5.2112e-04) (hash(x)=38457725) +621 train 4.531068 (lr=5.2196e-04) (hash(x)=37511763) +622 train 4.543059 (lr=5.2280e-04) (hash(x)=45660679) +623 train 4.496360 (lr=5.2364e-04) (hash(x)=38053682) +624 train 4.509298 (lr=5.2448e-04) (hash(x)=40891889) +625 val loss 4.5171 +625 val perplexity 91.5725 +625 train 4.522902 (lr=5.2531e-04) (hash(x)=44526095) +626 train 4.478418 (lr=5.2615e-04) (hash(x)=40812669) +627 train 4.452729 (lr=5.2699e-04) (hash(x)=38887608) +628 train 4.434969 (lr=5.2783e-04) (hash(x)=38463879) +629 train 4.443930 (lr=5.2867e-04) (hash(x)=41289017) +630 train 4.434757 (lr=5.2951e-04) (hash(x)=44000461) +631 train 4.471131 (lr=5.3035e-04) (hash(x)=38138893) +632 train 4.440707 (lr=5.3119e-04) (hash(x)=43469352) +633 train 4.454401 (lr=5.3203e-04) (hash(x)=40364233) +634 train 4.497955 (lr=5.3287e-04) (hash(x)=44013950) +635 train 4.478124 (lr=5.3371e-04) (hash(x)=42598990) +636 train 4.508774 (lr=5.3455e-04) (hash(x)=45866229) +637 train 4.689642 (lr=5.3538e-04) (hash(x)=38484658) +638 train 4.421919 (lr=5.3622e-04) (hash(x)=30634717) +639 train 4.412553 (lr=5.3706e-04) (hash(x)=44533851) +640 train 4.360892 (lr=5.3790e-04) (hash(x)=37495188) +641 train 4.427009 (lr=5.3874e-04) (hash(x)=36400232) +642 train 4.461541 (lr=5.3958e-04) (hash(x)=37861057) +643 train 4.430070 (lr=5.4042e-04) (hash(x)=39159549) +644 train 4.388494 (lr=5.4126e-04) (hash(x)=35644970) +645 train 4.360243 (lr=5.4210e-04) (hash(x)=40491290) +646 train 4.394261 (lr=5.4294e-04) (hash(x)=41378104) +647 train 4.394340 (lr=5.4378e-04) (hash(x)=41718169) +648 train 4.388676 (lr=5.4462e-04) (hash(x)=39902441) +649 train 4.321836 (lr=5.4545e-04) (hash(x)=43379394) +650 val loss 4.4976 +650 val perplexity 89.8008 +650 train 4.511988 (lr=5.4629e-04) (hash(x)=36674443) +651 train 4.510714 (lr=5.4713e-04) (hash(x)=38798747) +652 train 4.609245 (lr=5.4797e-04) (hash(x)=42008564) +653 train 4.500731 (lr=5.4881e-04) (hash(x)=38598496) +654 train 4.453125 (lr=5.4965e-04) (hash(x)=39357989) +655 train 4.530188 (lr=5.5049e-04) (hash(x)=42786805) +656 train 4.445328 (lr=5.5133e-04) (hash(x)=47355557) +657 train 4.470876 (lr=5.5217e-04) (hash(x)=39844717) +658 train 4.452274 (lr=5.5301e-04) (hash(x)=43636053) +659 train 4.497320 (lr=5.5385e-04) (hash(x)=38652073) +660 train 4.452655 (lr=5.5469e-04) (hash(x)=43932572) +661 train 4.444983 (lr=5.5552e-04) (hash(x)=40073309) +662 train 4.410947 (lr=5.5636e-04) (hash(x)=42985858) +663 train 4.428905 (lr=5.5720e-04) (hash(x)=37209997) +664 train 4.403090 (lr=5.5804e-04) (hash(x)=36867872) +665 train 4.386535 (lr=5.5888e-04) (hash(x)=39384860) +666 train 4.444014 (lr=5.5972e-04) (hash(x)=42414038) +667 train 4.369735 (lr=5.6056e-04) (hash(x)=37826377) +668 train 4.406319 (lr=5.6140e-04) (hash(x)=39548450) +669 train 4.405441 (lr=5.6224e-04) (hash(x)=35505639) +670 train 4.382154 (lr=5.6308e-04) (hash(x)=44724579) +671 train 4.413471 (lr=5.6392e-04) (hash(x)=44062284) +672 train 4.382106 (lr=5.6476e-04) (hash(x)=47248937) +673 train 4.389572 (lr=5.6559e-04) (hash(x)=38927467) +674 train 4.344962 (lr=5.6643e-04) (hash(x)=39622879) +675 val loss 4.4036 +675 val perplexity 81.7465 +675 train 4.398212 (lr=5.6727e-04) (hash(x)=40826621) +676 train 4.339713 (lr=5.6811e-04) (hash(x)=30373139) +677 train 4.411911 (lr=5.6895e-04) (hash(x)=44027308) +678 train 4.327590 (lr=5.6979e-04) (hash(x)=39015852) +679 train 4.347897 (lr=5.7063e-04) (hash(x)=43429793) +680 train 4.358779 (lr=5.7147e-04) (hash(x)=38197526) +681 train 4.339445 (lr=5.7231e-04) (hash(x)=42358288) +682 train 4.323690 (lr=5.7315e-04) (hash(x)=36645097) +683 train 4.377207 (lr=5.7399e-04) (hash(x)=45678234) +684 train 4.259017 (lr=5.7483e-04) (hash(x)=36248295) +685 train 4.244685 (lr=5.7566e-04) (hash(x)=37232885) +686 train 4.241268 (lr=5.7650e-04) (hash(x)=34516779) +687 train 4.260520 (lr=5.7734e-04) (hash(x)=37144766) +688 train 4.229081 (lr=5.7818e-04) (hash(x)=53954346) +689 train 4.250473 (lr=5.7902e-04) (hash(x)=43308151) +690 train 4.270399 (lr=5.7986e-04) (hash(x)=38621738) +691 train 4.264443 (lr=5.8070e-04) (hash(x)=35012330) +692 train 4.247956 (lr=5.8154e-04) (hash(x)=37010540) +693 train 4.268403 (lr=5.8238e-04) (hash(x)=43354294) +694 train 4.202319 (lr=5.8322e-04) (hash(x)=37038255) +695 train 4.209389 (lr=5.8406e-04) (hash(x)=40839125) +696 train 4.374321 (lr=5.8490e-04) (hash(x)=37959437) +697 train 4.549854 (lr=5.8573e-04) (hash(x)=36377276) +698 train 4.396733 (lr=5.8657e-04) (hash(x)=40344463) +699 train 4.424053 (lr=5.8741e-04) (hash(x)=47172950) +700 val loss 4.3836 +700 val perplexity 80.1248 +700 train 4.373107 (lr=5.8825e-04) (hash(x)=39532815) +701 train 4.372699 (lr=5.8909e-04) (hash(x)=49765965) +702 train 4.361523 (lr=5.8993e-04) (hash(x)=36567916) +703 train 4.385524 (lr=5.9077e-04) (hash(x)=47560394) +704 train 4.373585 (lr=5.9161e-04) (hash(x)=41603257) +705 train 4.335427 (lr=5.9245e-04) (hash(x)=44217858) +706 train 4.398786 (lr=5.9329e-04) (hash(x)=48585075) +707 train 4.396399 (lr=5.9413e-04) (hash(x)=42059145) +708 train 4.383014 (lr=5.9497e-04) (hash(x)=44091046) +709 train 4.418180 (lr=5.9580e-04) (hash(x)=43738599) +710 train 4.328532 (lr=5.9664e-04) (hash(x)=39600697) +711 train 4.352094 (lr=5.9748e-04) (hash(x)=38811998) +712 train 4.316091 (lr=5.9832e-04) (hash(x)=40845943) +713 train 4.317547 (lr=5.9916e-04) (hash(x)=35937572) +714 train 4.279293 (lr=6.0000e-04) (hash(x)=37546953) +715 train 4.367594 (lr=6.0000e-04) (hash(x)=37381881) +716 train 4.388096 (lr=6.0000e-04) (hash(x)=35751665) +717 train 4.376417 (lr=6.0000e-04) (hash(x)=43590026) +718 train 4.416241 (lr=6.0000e-04) (hash(x)=40623777) +719 train 4.355280 (lr=5.9999e-04) (hash(x)=28355226) +720 train 4.315039 (lr=5.9999e-04) (hash(x)=33067249) +721 train 4.265349 (lr=5.9998e-04) (hash(x)=40325093) +722 train 4.290266 (lr=5.9998e-04) (hash(x)=40848580) +723 train 4.295376 (lr=5.9997e-04) (hash(x)=42740181) +724 train 4.299123 (lr=5.9997e-04) (hash(x)=30711865) +725 val loss 4.3187 +725 val perplexity 75.0900 +725 train 4.321283 (lr=5.9996e-04) (hash(x)=33523723) +726 train 4.307452 (lr=5.9995e-04) (hash(x)=40668641) +727 train 4.283385 (lr=5.9994e-04) (hash(x)=47201748) +728 train 4.194109 (lr=5.9993e-04) (hash(x)=43543987) +729 train 4.264617 (lr=5.9992e-04) (hash(x)=38715956) +730 train 4.247189 (lr=5.9991e-04) (hash(x)=38236630) +731 train 4.247550 (lr=5.9989e-04) (hash(x)=40922107) +732 train 4.128951 (lr=5.9988e-04) (hash(x)=40258881) +733 train 4.170204 (lr=5.9986e-04) (hash(x)=41064272) +734 train 4.150249 (lr=5.9985e-04) (hash(x)=37011183) +735 train 4.158675 (lr=5.9983e-04) (hash(x)=41878943) +736 train 4.136734 (lr=5.9982e-04) (hash(x)=40702587) +737 train 4.160110 (lr=5.9980e-04) (hash(x)=29747514) +738 train 4.143781 (lr=5.9978e-04) (hash(x)=36255690) +739 train 4.168670 (lr=5.9976e-04) (hash(x)=40678193) +740 train 4.130680 (lr=5.9974e-04) (hash(x)=37290251) +741 train 4.125319 (lr=5.9972e-04) (hash(x)=34887978) +742 train 4.093748 (lr=5.9970e-04) (hash(x)=39915531) +743 train 4.201945 (lr=5.9967e-04) (hash(x)=38768828) +744 train 4.262208 (lr=5.9965e-04) (hash(x)=50771607) +745 train 4.293015 (lr=5.9962e-04) (hash(x)=45371867) +746 train 4.333402 (lr=5.9960e-04) (hash(x)=45549718) +747 train 4.326212 (lr=5.9957e-04) (hash(x)=39759525) +748 train 4.279240 (lr=5.9954e-04) (hash(x)=34398954) +749 train 4.288420 (lr=5.9952e-04) (hash(x)=42336146) +750 val loss 4.2740 +750 val perplexity 71.8078 +750 train 4.311561 (lr=5.9949e-04) (hash(x)=44494291) +751 train 4.378017 (lr=5.9946e-04) (hash(x)=41411573) +752 train 4.316670 (lr=5.9943e-04) (hash(x)=39995024) +753 train 4.294633 (lr=5.9940e-04) (hash(x)=43753701) +754 train 4.268312 (lr=5.9936e-04) (hash(x)=40600597) +755 train 4.292472 (lr=5.9933e-04) (hash(x)=39362560) +756 train 4.293246 (lr=5.9930e-04) (hash(x)=41041798) +757 train 4.233847 (lr=5.9926e-04) (hash(x)=33560879) +758 train 4.269686 (lr=5.9923e-04) (hash(x)=40965435) +759 train 4.329728 (lr=5.9919e-04) (hash(x)=40466202) +760 train 4.230306 (lr=5.9915e-04) (hash(x)=40700218) +761 train 4.299222 (lr=5.9912e-04) (hash(x)=34989047) +762 train 4.313166 (lr=5.9908e-04) (hash(x)=46255080) +763 train 4.237935 (lr=5.9904e-04) (hash(x)=38405682) +764 train 4.277899 (lr=5.9900e-04) (hash(x)=37231070) +765 train 4.182391 (lr=5.9896e-04) (hash(x)=38217555) +766 train 4.295722 (lr=5.9891e-04) (hash(x)=41550874) +767 train 4.197299 (lr=5.9887e-04) (hash(x)=38866456) +768 train 4.186273 (lr=5.9883e-04) (hash(x)=38089088) +769 train 4.216965 (lr=5.9878e-04) (hash(x)=51169241) +770 train 4.199101 (lr=5.9874e-04) (hash(x)=36794805) +771 train 4.198718 (lr=5.9869e-04) (hash(x)=38650618) +772 train 4.214489 (lr=5.9864e-04) (hash(x)=40958464) +773 train 4.219755 (lr=5.9859e-04) (hash(x)=46571035) +774 train 4.191722 (lr=5.9855e-04) (hash(x)=37706616) +775 val loss 4.2206 +775 val perplexity 68.0726 +775 train 4.183026 (lr=5.9850e-04) (hash(x)=39321699) +776 train 4.168395 (lr=5.9845e-04) (hash(x)=43754829) +777 train 4.161526 (lr=5.9839e-04) (hash(x)=35318450) +778 train 4.119040 (lr=5.9834e-04) (hash(x)=44393038) +779 train 4.155591 (lr=5.9829e-04) (hash(x)=28393233) +780 train 4.169344 (lr=5.9824e-04) (hash(x)=44897094) +781 train 4.069591 (lr=5.9818e-04) (hash(x)=36179787) +782 train 4.049945 (lr=5.9812e-04) (hash(x)=39663716) +783 train 4.045378 (lr=5.9807e-04) (hash(x)=39489154) +784 train 4.098168 (lr=5.9801e-04) (hash(x)=34346346) +785 train 4.139562 (lr=5.9795e-04) (hash(x)=41492091) +786 train 4.081279 (lr=5.9789e-04) (hash(x)=36936347) +787 train 4.102677 (lr=5.9784e-04) (hash(x)=37860690) +788 train 4.093746 (lr=5.9777e-04) (hash(x)=34078992) +789 train 4.135485 (lr=5.9771e-04) (hash(x)=54296928) +790 train 4.197360 (lr=5.9765e-04) (hash(x)=21470997) +791 train 4.226735 (lr=5.9759e-04) (hash(x)=54918220) +792 train 4.226764 (lr=5.9752e-04) (hash(x)=43511142) +793 train 4.236177 (lr=5.9746e-04) (hash(x)=34973263) +794 train 4.243711 (lr=5.9739e-04) (hash(x)=41314317) +795 train 4.260103 (lr=5.9733e-04) (hash(x)=41785286) +796 train 4.221408 (lr=5.9726e-04) (hash(x)=38822054) +797 train 4.208872 (lr=5.9719e-04) (hash(x)=30881828) +798 train 4.217287 (lr=5.9712e-04) (hash(x)=40436138) +799 train 4.185388 (lr=5.9705e-04) (hash(x)=40499406) +800 val loss 4.1830 +800 val perplexity 65.5612 +800 train 4.205553 (lr=5.9698e-04) (hash(x)=36982137) +801 train 4.195429 (lr=5.9691e-04) (hash(x)=36805072) +802 train 4.236105 (lr=5.9684e-04) (hash(x)=42878755) +803 train 4.195213 (lr=5.9677e-04) (hash(x)=35820618) +804 train 4.237148 (lr=5.9669e-04) (hash(x)=42118044) +805 train 4.192019 (lr=5.9662e-04) (hash(x)=38118592) +806 train 4.156423 (lr=5.9654e-04) (hash(x)=34376516) +807 train 4.189648 (lr=5.9647e-04) (hash(x)=36815750) +808 train 4.225250 (lr=5.9639e-04) (hash(x)=42514638) +809 train 4.190702 (lr=5.9631e-04) (hash(x)=35855942) +810 train 4.145771 (lr=5.9623e-04) (hash(x)=34947209) +811 train 4.160828 (lr=5.9616e-04) (hash(x)=38700746) +812 train 4.130572 (lr=5.9607e-04) (hash(x)=42429570) +813 train 4.131639 (lr=5.9599e-04) (hash(x)=38329771) +814 train 4.134538 (lr=5.9591e-04) (hash(x)=41924250) +815 train 4.124511 (lr=5.9583e-04) (hash(x)=38759699) +816 train 4.081165 (lr=5.9575e-04) (hash(x)=36002853) +817 train 4.106771 (lr=5.9566e-04) (hash(x)=36966867) +818 train 4.112845 (lr=5.9558e-04) (hash(x)=38357805) +819 train 4.118140 (lr=5.9549e-04) (hash(x)=39417962) +820 train 4.104887 (lr=5.9540e-04) (hash(x)=34913195) +821 train 4.129365 (lr=5.9532e-04) (hash(x)=40918872) +822 train 4.169496 (lr=5.9523e-04) (hash(x)=46827088) +823 train 4.029638 (lr=5.9514e-04) (hash(x)=34556452) +824 train 3.986514 (lr=5.9505e-04) (hash(x)=39012714) +825 val loss 4.1457 +825 val perplexity 63.1615 +825 train 4.026810 (lr=5.9496e-04) (hash(x)=43648489) +826 train 3.984773 (lr=5.9486e-04) (hash(x)=34605912) +827 train 4.031074 (lr=5.9477e-04) (hash(x)=39413012) +828 train 4.052982 (lr=5.9468e-04) (hash(x)=41280600) +829 train 4.029035 (lr=5.9458e-04) (hash(x)=35830407) +830 train 3.971043 (lr=5.9449e-04) (hash(x)=37292957) +831 train 3.998439 (lr=5.9439e-04) (hash(x)=35157991) +832 train 3.917349 (lr=5.9430e-04) (hash(x)=36584810) +833 train 3.978909 (lr=5.9420e-04) (hash(x)=36569520) +834 train 3.993109 (lr=5.9410e-04) (hash(x)=42363915) +835 train 4.158829 (lr=5.9400e-04) (hash(x)=38794389) +836 train 4.100919 (lr=5.9390e-04) (hash(x)=41322967) +837 train 4.135384 (lr=5.9380e-04) (hash(x)=39415054) +838 train 4.178088 (lr=5.9370e-04) (hash(x)=39546100) +839 train 4.171432 (lr=5.9360e-04) (hash(x)=39434782) +840 train 4.135862 (lr=5.9349e-04) (hash(x)=44666235) +841 train 4.209771 (lr=5.9339e-04) (hash(x)=37580189) +842 train 4.146210 (lr=5.9328e-04) (hash(x)=43320180) +843 train 4.183834 (lr=5.9318e-04) (hash(x)=49002945) +844 train 4.169401 (lr=5.9307e-04) (hash(x)=38243360) +845 train 4.157609 (lr=5.9296e-04) (hash(x)=38494232) +846 train 4.163245 (lr=5.9286e-04) (hash(x)=40964732) +847 train 4.203861 (lr=5.9275e-04) (hash(x)=39050106) +848 train 4.176471 (lr=5.9264e-04) (hash(x)=36912534) +849 train 4.166086 (lr=5.9253e-04) (hash(x)=41337679) +850 val loss 4.1202 +850 val perplexity 61.5728 +850 train 4.143362 (lr=5.9241e-04) (hash(x)=40709278) +851 train 4.109224 (lr=5.9230e-04) (hash(x)=37262006) +852 train 4.216650 (lr=5.9219e-04) (hash(x)=45530331) +853 train 4.121093 (lr=5.9208e-04) (hash(x)=38166620) +854 train 4.109550 (lr=5.9196e-04) (hash(x)=40323244) +855 train 4.138419 (lr=5.9185e-04) (hash(x)=39417999) +856 train 4.101808 (lr=5.9173e-04) (hash(x)=42070014) +857 train 4.144685 (lr=5.9161e-04) (hash(x)=29856567) +858 train 4.090040 (lr=5.9149e-04) (hash(x)=39759264) +859 train 4.065966 (lr=5.9138e-04) (hash(x)=40219564) +860 train 4.075730 (lr=5.9126e-04) (hash(x)=36642239) +861 train 4.079085 (lr=5.9114e-04) (hash(x)=43131736) +862 train 4.092059 (lr=5.9101e-04) (hash(x)=36614707) +863 train 4.070812 (lr=5.9089e-04) (hash(x)=40894805) +864 train 4.052975 (lr=5.9077e-04) (hash(x)=40765943) +865 train 4.025002 (lr=5.9065e-04) (hash(x)=41190470) +866 train 4.061742 (lr=5.9052e-04) (hash(x)=37826834) +867 train 4.076919 (lr=5.9040e-04) (hash(x)=40444968) +868 train 3.986053 (lr=5.9027e-04) (hash(x)=40037832) +869 train 3.968329 (lr=5.9014e-04) (hash(x)=42945560) +870 train 3.936845 (lr=5.9002e-04) (hash(x)=46058535) +871 train 3.928041 (lr=5.8989e-04) (hash(x)=43306480) +872 train 3.937093 (lr=5.8976e-04) (hash(x)=42726960) +873 train 3.956087 (lr=5.8963e-04) (hash(x)=34445591) +874 train 3.891890 (lr=5.8950e-04) (hash(x)=41018355) +875 val loss 4.0926 +875 val perplexity 59.8927 +875 train 3.907792 (lr=5.8937e-04) (hash(x)=35764688) +876 train 3.932513 (lr=5.8923e-04) (hash(x)=32756271) +877 train 3.971438 (lr=5.8910e-04) (hash(x)=38855770) +878 train 3.998705 (lr=5.8897e-04) (hash(x)=38054280) +879 train 3.905936 (lr=5.8883e-04) (hash(x)=41744630) +880 train 3.997240 (lr=5.8869e-04) (hash(x)=37483265) +881 train 4.095444 (lr=5.8856e-04) (hash(x)=40200985) +882 train 4.228524 (lr=5.8842e-04) (hash(x)=38498652) +883 train 4.143603 (lr=5.8828e-04) (hash(x)=39366803) +884 train 4.084905 (lr=5.8814e-04) (hash(x)=33952585) +885 train 4.130663 (lr=5.8800e-04) (hash(x)=37432000) +886 train 4.062424 (lr=5.8786e-04) (hash(x)=39089242) +887 train 4.151559 (lr=5.8772e-04) (hash(x)=37787367) +888 train 4.115151 (lr=5.8758e-04) (hash(x)=47081969) +889 train 4.071699 (lr=5.8744e-04) (hash(x)=34191548) +890 train 4.085431 (lr=5.8729e-04) (hash(x)=40614910) +891 train 4.091922 (lr=5.8715e-04) (hash(x)=44458277) +892 train 4.103353 (lr=5.8700e-04) (hash(x)=44906637) +893 train 4.041891 (lr=5.8686e-04) (hash(x)=38524045) +894 train 4.058805 (lr=5.8671e-04) (hash(x)=43759894) +895 train 4.094904 (lr=5.8656e-04) (hash(x)=44616332) +896 train 4.062178 (lr=5.8642e-04) (hash(x)=36516068) +897 train 4.029906 (lr=5.8627e-04) (hash(x)=46061746) +898 train 4.049340 (lr=5.8612e-04) (hash(x)=38624537) +899 train 4.020172 (lr=5.8597e-04) (hash(x)=42840748) +900 val loss 4.0477 +900 val perplexity 57.2677 +900 train 4.076698 (lr=5.8581e-04) (hash(x)=36495996) +901 train 4.068372 (lr=5.8566e-04) (hash(x)=42836330) +902 train 4.035782 (lr=5.8551e-04) (hash(x)=38573084) +903 train 4.017597 (lr=5.8535e-04) (hash(x)=38648626) +904 train 3.994053 (lr=5.8520e-04) (hash(x)=35394475) +905 train 4.017010 (lr=5.8504e-04) (hash(x)=35288700) +906 train 4.024552 (lr=5.8489e-04) (hash(x)=38980218) +907 train 3.984344 (lr=5.8473e-04) (hash(x)=40141088) +908 train 3.975082 (lr=5.8457e-04) (hash(x)=41560638) +909 train 4.011002 (lr=5.8441e-04) (hash(x)=46740483) +910 train 4.073177 (lr=5.8425e-04) (hash(x)=39158333) +911 train 4.019581 (lr=5.8409e-04) (hash(x)=42864726) +912 train 4.018666 (lr=5.8393e-04) (hash(x)=49405395) +913 train 4.069102 (lr=5.8377e-04) (hash(x)=41096819) +914 train 3.960147 (lr=5.8361e-04) (hash(x)=39031702) +915 train 3.877431 (lr=5.8345e-04) (hash(x)=39071072) +916 train 3.899873 (lr=5.8328e-04) (hash(x)=39441392) +917 train 3.890803 (lr=5.8312e-04) (hash(x)=35374128) +918 train 3.909783 (lr=5.8295e-04) (hash(x)=38330077) +919 train 3.848352 (lr=5.8278e-04) (hash(x)=40118792) +920 train 3.873950 (lr=5.8262e-04) (hash(x)=40927335) +921 train 3.897594 (lr=5.8245e-04) (hash(x)=38704341) +922 train 3.886919 (lr=5.8228e-04) (hash(x)=33380410) +923 train 3.903976 (lr=5.8211e-04) (hash(x)=38819907) +924 train 3.915311 (lr=5.8194e-04) (hash(x)=42675699) +925 val loss 4.0345 +925 val perplexity 56.5128 +925 train 3.897414 (lr=5.8177e-04) (hash(x)=36912034) +926 train 3.975716 (lr=5.8160e-04) (hash(x)=42472236) +927 train 4.104331 (lr=5.8142e-04) (hash(x)=41341292) +928 train 4.062667 (lr=5.8125e-04) (hash(x)=43897708) +929 train 4.022419 (lr=5.8107e-04) (hash(x)=40766515) +930 train 4.041725 (lr=5.8090e-04) (hash(x)=37386807) +931 train 4.053329 (lr=5.8072e-04) (hash(x)=45471825) +932 train 4.061965 (lr=5.8055e-04) (hash(x)=44215632) +933 train 4.101871 (lr=5.8037e-04) (hash(x)=40022034) +934 train 4.089040 (lr=5.8019e-04) (hash(x)=42777658) +935 train 4.092485 (lr=5.8001e-04) (hash(x)=35545367) +936 train 4.039953 (lr=5.7983e-04) (hash(x)=43493612) +937 train 4.045743 (lr=5.7965e-04) (hash(x)=41090883) +938 train 4.062847 (lr=5.7947e-04) (hash(x)=32095037) +939 train 4.070151 (lr=5.7929e-04) (hash(x)=45238191) +940 train 4.039684 (lr=5.7911e-04) (hash(x)=40986746) +941 train 4.040018 (lr=5.7892e-04) (hash(x)=38151115) +942 train 4.068494 (lr=5.7874e-04) (hash(x)=38802382) +943 train 4.049187 (lr=5.7855e-04) (hash(x)=38047114) +944 train 3.992061 (lr=5.7837e-04) (hash(x)=38854207) +945 train 4.034536 (lr=5.7818e-04) (hash(x)=41490196) +946 train 4.014715 (lr=5.7799e-04) (hash(x)=29121316) +947 train 4.067402 (lr=5.7780e-04) (hash(x)=37758888) +948 train 4.032947 (lr=5.7761e-04) (hash(x)=43172379) +949 train 3.980064 (lr=5.7742e-04) (hash(x)=39633975) +950 val loss 3.9992 +950 val perplexity 54.5566 +950 train 4.008409 (lr=5.7723e-04) (hash(x)=41868499) +951 train 3.980688 (lr=5.7704e-04) (hash(x)=36708927) +952 train 3.895369 (lr=5.7685e-04) (hash(x)=41581402) +953 train 3.991268 (lr=5.7666e-04) (hash(x)=39320725) +954 train 3.992403 (lr=5.7646e-04) (hash(x)=44279825) +955 train 3.932415 (lr=5.7627e-04) (hash(x)=34095005) +956 train 3.954352 (lr=5.7607e-04) (hash(x)=46771946) +957 train 3.893143 (lr=5.7588e-04) (hash(x)=34251048) +958 train 3.943259 (lr=5.7568e-04) (hash(x)=37208056) +959 train 3.967968 (lr=5.7548e-04) (hash(x)=42296553) +960 train 3.929402 (lr=5.7529e-04) (hash(x)=43142648) +961 train 3.872317 (lr=5.7509e-04) (hash(x)=40457174) +962 train 3.845215 (lr=5.7489e-04) (hash(x)=39560029) +963 train 3.791209 (lr=5.7469e-04) (hash(x)=43400375) +964 train 3.850741 (lr=5.7449e-04) (hash(x)=36893397) +965 train 3.882121 (lr=5.7428e-04) (hash(x)=36533138) +966 train 3.773533 (lr=5.7408e-04) (hash(x)=44341824) +967 train 3.836007 (lr=5.7388e-04) (hash(x)=41521370) +968 train 3.860348 (lr=5.7367e-04) (hash(x)=37749996) +969 train 3.874159 (lr=5.7347e-04) (hash(x)=39771680) +970 train 3.865778 (lr=5.7326e-04) (hash(x)=41346838) +971 train 3.893390 (lr=5.7306e-04) (hash(x)=36735686) +972 train 3.859044 (lr=5.7285e-04) (hash(x)=39006774) +973 train 4.003430 (lr=5.7264e-04) (hash(x)=43389462) +974 train 3.991252 (lr=5.7243e-04) (hash(x)=39625722) +975 val loss 3.9860 +975 val perplexity 53.8414 +975 train 3.991463 (lr=5.7222e-04) (hash(x)=38266780) +976 train 4.027308 (lr=5.7201e-04) (hash(x)=39522790) +977 train 4.018387 (lr=5.7180e-04) (hash(x)=46170838) +978 train 4.064434 (lr=5.7159e-04) (hash(x)=41657274) +979 train 4.016747 (lr=5.7138e-04) (hash(x)=37768530) +980 train 4.007830 (lr=5.7116e-04) (hash(x)=43182062) +981 train 3.965825 (lr=5.7095e-04) (hash(x)=40065882) +982 train 3.957985 (lr=5.7073e-04) (hash(x)=38922462) +983 train 3.999262 (lr=5.7052e-04) (hash(x)=46329995) +984 train 3.979599 (lr=5.7030e-04) (hash(x)=45311179) +985 train 3.964531 (lr=5.7008e-04) (hash(x)=38497622) +986 train 3.941161 (lr=5.6987e-04) (hash(x)=36785962) +987 train 4.011598 (lr=5.6965e-04) (hash(x)=37757548) +988 train 3.961086 (lr=5.6943e-04) (hash(x)=40772090) +989 train 3.966273 (lr=5.6921e-04) (hash(x)=50508834) +990 train 3.961480 (lr=5.6899e-04) (hash(x)=40139233) +991 train 4.003122 (lr=5.6877e-04) (hash(x)=37253630) +992 train 3.955588 (lr=5.6854e-04) (hash(x)=39778910) +993 train 3.915147 (lr=5.6832e-04) (hash(x)=39975252) +994 train 3.944800 (lr=5.6810e-04) (hash(x)=44992815) +995 train 3.968296 (lr=5.6787e-04) (hash(x)=40473424) +996 train 3.882458 (lr=5.6765e-04) (hash(x)=34647847) +997 train 3.928668 (lr=5.6742e-04) (hash(x)=42372228) +998 train 3.919462 (lr=5.6720e-04) (hash(x)=39814820) +999 train 3.886496 (lr=5.6697e-04) (hash(x)=36244741) +1000 val loss 3.9498 +1000 val perplexity 51.9249 +1000 train 3.928899 (lr=5.6674e-04) (hash(x)=47443206) +1001 train 3.932372 (lr=5.6651e-04) (hash(x)=35954652) +1002 train 3.928463 (lr=5.6628e-04) (hash(x)=42898024) +1003 train 3.968755 (lr=5.6605e-04) (hash(x)=44605344) +1004 train 3.934056 (lr=5.6582e-04) (hash(x)=45898362) +1005 train 3.924667 (lr=5.6559e-04) (hash(x)=41542720) +1006 train 3.883351 (lr=5.6536e-04) (hash(x)=37782592) +1007 train 3.798866 (lr=5.6512e-04) (hash(x)=40670583) +1008 train 3.787844 (lr=5.6489e-04) (hash(x)=37830247) +1009 train 3.766600 (lr=5.6465e-04) (hash(x)=34783662) +1010 train 3.827455 (lr=5.6442e-04) (hash(x)=37647060) +1011 train 3.845906 (lr=5.6418e-04) (hash(x)=42563141) +1012 train 3.760194 (lr=5.6395e-04) (hash(x)=40843060) +1013 train 3.855458 (lr=5.6371e-04) (hash(x)=43259044) +1014 train 3.823984 (lr=5.6347e-04) (hash(x)=39261244) +1015 train 3.786577 (lr=5.6323e-04) (hash(x)=39639142) +1016 train 3.781655 (lr=5.6299e-04) (hash(x)=37644301) +1017 train 3.789092 (lr=5.6275e-04) (hash(x)=41755673) +1018 train 3.879670 (lr=5.6251e-04) (hash(x)=36418146) +1019 train 3.997784 (lr=5.6227e-04) (hash(x)=40524291) +1020 train 3.982095 (lr=5.6202e-04) (hash(x)=38433324) +1021 train 3.939674 (lr=5.6178e-04) (hash(x)=41290825) +1022 train 4.033683 (lr=5.6154e-04) (hash(x)=51089051) +1023 train 3.956215 (lr=5.6129e-04) (hash(x)=39200303) +1024 train 3.981293 (lr=5.6105e-04) (hash(x)=44895002) +1025 val loss 3.9328 +1025 val perplexity 51.0495 +1025 train 3.990130 (lr=5.6080e-04) (hash(x)=50965717) +1026 train 3.981002 (lr=5.6055e-04) (hash(x)=43371340) +1027 train 3.929279 (lr=5.6031e-04) (hash(x)=41341813) +1028 train 3.961602 (lr=5.6006e-04) (hash(x)=38681786) +1029 train 3.980373 (lr=5.5981e-04) (hash(x)=42770506) +1030 train 3.964507 (lr=5.5956e-04) (hash(x)=39378721) +1031 train 3.920295 (lr=5.5931e-04) (hash(x)=36214427) +1032 train 3.948158 (lr=5.5906e-04) (hash(x)=39529094) +1033 train 3.995198 (lr=5.5880e-04) (hash(x)=39920415) +1034 train 4.020067 (lr=5.5855e-04) (hash(x)=37352222) +1035 train 3.942978 (lr=5.5830e-04) (hash(x)=43307334) +1036 train 3.995712 (lr=5.5804e-04) (hash(x)=42199380) +1037 train 3.898301 (lr=5.5779e-04) (hash(x)=44414184) +1038 train 3.948725 (lr=5.5753e-04) (hash(x)=40581727) +1039 train 3.931988 (lr=5.5728e-04) (hash(x)=38617083) +1040 train 3.926904 (lr=5.5702e-04) (hash(x)=37948211) +1041 train 3.897901 (lr=5.5676e-04) (hash(x)=40016611) +1042 train 3.871663 (lr=5.5651e-04) (hash(x)=40647438) +1043 train 3.846992 (lr=5.5625e-04) (hash(x)=45115943) +1044 train 3.878449 (lr=5.5599e-04) (hash(x)=38945171) +1045 train 3.893141 (lr=5.5573e-04) (hash(x)=37685702) +1046 train 3.880489 (lr=5.5547e-04) (hash(x)=34514902) +1047 train 3.813326 (lr=5.5520e-04) (hash(x)=41843628) +1048 train 3.848621 (lr=5.5494e-04) (hash(x)=36956335) +1049 train 3.917444 (lr=5.5468e-04) (hash(x)=37912077) +1050 val loss 3.9065 +1050 val perplexity 49.7260 +1050 train 3.822737 (lr=5.5441e-04) (hash(x)=39394723) +1051 train 3.894176 (lr=5.5415e-04) (hash(x)=40062771) +1052 train 3.799939 (lr=5.5388e-04) (hash(x)=42158970) +1053 train 3.778237 (lr=5.5362e-04) (hash(x)=47040709) +1054 train 3.773222 (lr=5.5335e-04) (hash(x)=39582388) +1055 train 3.789969 (lr=5.5308e-04) (hash(x)=32729203) +1056 train 3.856973 (lr=5.5282e-04) (hash(x)=43665567) +1057 train 3.777457 (lr=5.5255e-04) (hash(x)=41719191) +1058 train 3.807087 (lr=5.5228e-04) (hash(x)=40402638) +1059 train 3.788643 (lr=5.5201e-04) (hash(x)=43508197) +1060 train 3.761606 (lr=5.5174e-04) (hash(x)=37929090) +1061 train 3.897396 (lr=5.5147e-04) (hash(x)=43739276) +1062 train 3.732353 (lr=5.5119e-04) (hash(x)=44354523) +1063 train 3.726008 (lr=5.5092e-04) (hash(x)=41422262) +1064 train 3.915957 (lr=5.5065e-04) (hash(x)=42517195) +1065 train 4.006998 (lr=5.5037e-04) (hash(x)=42314309) +1066 train 3.991477 (lr=5.5010e-04) (hash(x)=38822532) +1067 train 4.010064 (lr=5.4982e-04) (hash(x)=42392016) +1068 train 3.929035 (lr=5.4955e-04) (hash(x)=40800791) +1069 train 3.907880 (lr=5.4927e-04) (hash(x)=44639883) +1070 train 3.991375 (lr=5.4899e-04) (hash(x)=42388981) +1071 train 3.938759 (lr=5.4871e-04) (hash(x)=38177964) +1072 train 3.949802 (lr=5.4843e-04) (hash(x)=47018823) +1073 train 3.937953 (lr=5.4815e-04) (hash(x)=38234492) +1074 train 3.907612 (lr=5.4787e-04) (hash(x)=41469299) +1075 val loss 3.9024 +1075 val perplexity 49.5213 +1075 train 3.925509 (lr=5.4759e-04) (hash(x)=44335596) +1076 train 3.871824 (lr=5.4731e-04) (hash(x)=38569605) +1077 train 3.928349 (lr=5.4703e-04) (hash(x)=40611204) +1078 train 3.925040 (lr=5.4675e-04) (hash(x)=38524524) +1079 train 3.930130 (lr=5.4646e-04) (hash(x)=38537319) +1080 train 3.943947 (lr=5.4618e-04) (hash(x)=39538382) +1081 train 3.915817 (lr=5.4589e-04) (hash(x)=38481435) +1082 train 3.890467 (lr=5.4561e-04) (hash(x)=37059276) +1083 train 3.892709 (lr=5.4532e-04) (hash(x)=41714018) +1084 train 3.894568 (lr=5.4503e-04) (hash(x)=41773952) +1085 train 3.909009 (lr=5.4475e-04) (hash(x)=44474756) +1086 train 3.956262 (lr=5.4446e-04) (hash(x)=40129849) +1087 train 3.904357 (lr=5.4417e-04) (hash(x)=45430815) +1088 train 3.883564 (lr=5.4388e-04) (hash(x)=40188825) +1089 train 3.949847 (lr=5.4359e-04) (hash(x)=42376672) +1090 train 3.885797 (lr=5.4330e-04) (hash(x)=36976163) +1091 train 3.841689 (lr=5.4301e-04) (hash(x)=42457716) +1092 train 3.826647 (lr=5.4271e-04) (hash(x)=38827197) +1093 train 3.895093 (lr=5.4242e-04) (hash(x)=43740542) +1094 train 3.848688 (lr=5.4213e-04) (hash(x)=40180979) +1095 train 3.857971 (lr=5.4183e-04) (hash(x)=41417674) +1096 train 3.879076 (lr=5.4154e-04) (hash(x)=44519251) +1097 train 3.836498 (lr=5.4124e-04) (hash(x)=42968098) +1098 train 3.773298 (lr=5.4095e-04) (hash(x)=34216485) +1099 train 3.683290 (lr=5.4065e-04) (hash(x)=40481440) +1100 val loss 3.8744 +1100 val perplexity 48.1537 +1100 train 3.748641 (lr=5.4035e-04) (hash(x)=43358649) +1101 train 3.742725 (lr=5.4005e-04) (hash(x)=40977595) +1102 train 3.721818 (lr=5.3975e-04) (hash(x)=38444098) +1103 train 3.675073 (lr=5.3946e-04) (hash(x)=39070111) +1104 train 3.703984 (lr=5.3915e-04) (hash(x)=42158109) +1105 train 3.740700 (lr=5.3885e-04) (hash(x)=38608749) +1106 train 3.813029 (lr=5.3855e-04) (hash(x)=38079923) +1107 train 3.798955 (lr=5.3825e-04) (hash(x)=47617217) +1108 train 3.707566 (lr=5.3795e-04) (hash(x)=33135249) +1109 train 3.777400 (lr=5.3764e-04) (hash(x)=43240893) +1110 train 3.760346 (lr=5.3734e-04) (hash(x)=36876414) +1111 train 3.869817 (lr=5.3704e-04) (hash(x)=38524907) +1112 train 3.896986 (lr=5.3673e-04) (hash(x)=37555742) +1113 train 3.865799 (lr=5.3642e-04) (hash(x)=42857954) +1114 train 3.848332 (lr=5.3612e-04) (hash(x)=44234020) +1115 train 3.870189 (lr=5.3581e-04) (hash(x)=43509002) +1116 train 3.834453 (lr=5.3550e-04) (hash(x)=46492366) +1117 train 3.849056 (lr=5.3519e-04) (hash(x)=35102321) +1118 train 3.817056 (lr=5.3488e-04) (hash(x)=37817860) +1119 train 3.807764 (lr=5.3457e-04) (hash(x)=40580331) +1120 train 3.888708 (lr=5.3426e-04) (hash(x)=43413678) +1121 train 3.895157 (lr=5.3395e-04) (hash(x)=35265655) +1122 train 3.873836 (lr=5.3364e-04) (hash(x)=34434256) +1123 train 3.919927 (lr=5.3333e-04) (hash(x)=37972369) +1124 train 3.867946 (lr=5.3302e-04) (hash(x)=40820470) +1125 val loss 3.8598 +1125 val perplexity 47.4575 +1125 train 3.847416 (lr=5.3270e-04) (hash(x)=34098646) +1126 train 3.891842 (lr=5.3239e-04) (hash(x)=40675554) +1127 train 3.830226 (lr=5.3207e-04) (hash(x)=38218585) +1128 train 3.843754 (lr=5.3176e-04) (hash(x)=40140720) +1129 train 3.904889 (lr=5.3144e-04) (hash(x)=38076426) +1130 train 3.895969 (lr=5.3113e-04) (hash(x)=45345889) +1131 train 3.860304 (lr=5.3081e-04) (hash(x)=39686209) +1132 train 3.879747 (lr=5.3049e-04) (hash(x)=42112915) +1133 train 3.895717 (lr=5.3017e-04) (hash(x)=39549870) +1134 train 3.835091 (lr=5.2985e-04) (hash(x)=44210354) +1135 train 3.791628 (lr=5.2953e-04) (hash(x)=37709740) +1136 train 3.825078 (lr=5.2921e-04) (hash(x)=35404906) +1137 train 3.838824 (lr=5.2889e-04) (hash(x)=38503386) +1138 train 3.846770 (lr=5.2857e-04) (hash(x)=39720215) +1139 train 3.884500 (lr=5.2825e-04) (hash(x)=40770720) +1140 train 3.864937 (lr=5.2792e-04) (hash(x)=41874426) +1141 train 3.821395 (lr=5.2760e-04) (hash(x)=42155969) +1142 train 3.847271 (lr=5.2728e-04) (hash(x)=37266886) +1143 train 3.815418 (lr=5.2695e-04) (hash(x)=35958355) +1144 train 3.803405 (lr=5.2663e-04) (hash(x)=41806588) +1145 train 3.802660 (lr=5.2630e-04) (hash(x)=37269982) +1146 train 3.670650 (lr=5.2597e-04) (hash(x)=34672411) +1147 train 3.731469 (lr=5.2565e-04) (hash(x)=42135791) +1148 train 3.710707 (lr=5.2532e-04) (hash(x)=43542075) +1149 train 3.688686 (lr=5.2499e-04) (hash(x)=37408762) +1150 val loss 3.8432 +1150 val perplexity 46.6760 +1150 train 3.695652 (lr=5.2466e-04) (hash(x)=41700611) +1151 train 3.733653 (lr=5.2433e-04) (hash(x)=43943719) +1152 train 3.665301 (lr=5.2400e-04) (hash(x)=39378218) +1153 train 3.692446 (lr=5.2367e-04) (hash(x)=34000495) +1154 train 3.711901 (lr=5.2334e-04) (hash(x)=41475227) +1155 train 3.668773 (lr=5.2301e-04) (hash(x)=36207385) +1156 train 3.706984 (lr=5.2267e-04) (hash(x)=30886624) +1157 train 3.796907 (lr=5.2234e-04) (hash(x)=43519134) +1158 train 3.768206 (lr=5.2201e-04) (hash(x)=44851326) +1159 train 3.840398 (lr=5.2167e-04) (hash(x)=42027659) +1160 train 3.870838 (lr=5.2134e-04) (hash(x)=43020126) +1161 train 3.862642 (lr=5.2100e-04) (hash(x)=45686639) +1162 train 3.837069 (lr=5.2067e-04) (hash(x)=43508374) +1163 train 3.811600 (lr=5.2033e-04) (hash(x)=40718553) +1164 train 3.826904 (lr=5.1999e-04) (hash(x)=41705404) +1165 train 3.789980 (lr=5.1965e-04) (hash(x)=35125306) +1166 train 3.838515 (lr=5.1932e-04) (hash(x)=41839564) +1167 train 3.822980 (lr=5.1898e-04) (hash(x)=46200397) +1168 train 3.840632 (lr=5.1864e-04) (hash(x)=38392260) +1169 train 3.925732 (lr=5.1830e-04) (hash(x)=40971186) +1170 train 3.830515 (lr=5.1796e-04) (hash(x)=39828859) +1171 train 3.763041 (lr=5.1761e-04) (hash(x)=39368067) +1172 train 3.844853 (lr=5.1727e-04) (hash(x)=44145062) +1173 train 3.812151 (lr=5.1693e-04) (hash(x)=40447923) +1174 train 3.790269 (lr=5.1659e-04) (hash(x)=44786543) +1175 val loss 3.8223 +1175 val perplexity 45.7086 +1175 train 3.858265 (lr=5.1624e-04) (hash(x)=42498613) +1176 train 3.849009 (lr=5.1590e-04) (hash(x)=33428913) +1177 train 3.816700 (lr=5.1555e-04) (hash(x)=40893817) +1178 train 3.822788 (lr=5.1521e-04) (hash(x)=42574484) +1179 train 3.769648 (lr=5.1486e-04) (hash(x)=37050033) +1180 train 3.806257 (lr=5.1452e-04) (hash(x)=37928450) +1181 train 3.823592 (lr=5.1417e-04) (hash(x)=41092188) +1182 train 3.772776 (lr=5.1382e-04) (hash(x)=38524600) +1183 train 3.770584 (lr=5.1347e-04) (hash(x)=36478419) +1184 train 3.817219 (lr=5.1312e-04) (hash(x)=39697656) +1185 train 3.825908 (lr=5.1277e-04) (hash(x)=39987791) +1186 train 3.785229 (lr=5.1242e-04) (hash(x)=35897772) +1187 train 3.735741 (lr=5.1207e-04) (hash(x)=38845456) +1188 train 3.736730 (lr=5.1172e-04) (hash(x)=35842601) +1189 train 3.772653 (lr=5.1137e-04) (hash(x)=38348145) +1190 train 3.791341 (lr=5.1102e-04) (hash(x)=34073471) +1191 train 3.718957 (lr=5.1067e-04) (hash(x)=39733332) +1192 train 3.708091 (lr=5.1031e-04) (hash(x)=51535588) +1193 train 3.608960 (lr=5.0996e-04) (hash(x)=35926078) +1194 train 3.675334 (lr=5.0960e-04) (hash(x)=39030964) +1195 train 3.694850 (lr=5.0925e-04) (hash(x)=42519210) +1196 train 3.703925 (lr=5.0889e-04) (hash(x)=39722136) +1197 train 3.666627 (lr=5.0854e-04) (hash(x)=40570757) +1198 train 3.682207 (lr=5.0818e-04) (hash(x)=42034979) +1199 train 3.639948 (lr=5.0782e-04) (hash(x)=37267884) +1200 val loss 3.8117 +1200 val perplexity 45.2255 +1200 train 3.685686 (lr=5.0746e-04) (hash(x)=40198729) +1201 train 3.689188 (lr=5.0711e-04) (hash(x)=42943160) +1202 train 3.695016 (lr=5.0675e-04) (hash(x)=38259527) +1203 train 3.636412 (lr=5.0639e-04) (hash(x)=37006218) +1204 train 3.717360 (lr=5.0603e-04) (hash(x)=39921679) +1205 train 3.790882 (lr=5.0567e-04) (hash(x)=47752635) +1206 train 3.860384 (lr=5.0531e-04) (hash(x)=35492950) +1207 train 3.796703 (lr=5.0494e-04) (hash(x)=41907101) +1208 train 3.817282 (lr=5.0458e-04) (hash(x)=45772605) +1209 train 3.825103 (lr=5.0422e-04) (hash(x)=43471444) +1210 train 3.797362 (lr=5.0386e-04) (hash(x)=36948436) +1211 train 3.905641 (lr=5.0349e-04) (hash(x)=43498894) +1212 train 3.742952 (lr=5.0313e-04) (hash(x)=44895569) +1213 train 3.828414 (lr=5.0276e-04) (hash(x)=45960811) +1214 train 3.802964 (lr=5.0240e-04) (hash(x)=39869378) +1215 train 3.810433 (lr=5.0203e-04) (hash(x)=39366727) +1216 train 3.784622 (lr=5.0166e-04) (hash(x)=40375448) +1217 train 3.790106 (lr=5.0130e-04) (hash(x)=37567402) +1218 train 3.813329 (lr=5.0093e-04) (hash(x)=39114117) +1219 train 3.826756 (lr=5.0056e-04) (hash(x)=32956916) +1220 train 3.806350 (lr=5.0019e-04) (hash(x)=39600099) +1221 train 3.773166 (lr=4.9982e-04) (hash(x)=41072743) +1222 train 3.820630 (lr=4.9945e-04) (hash(x)=45921528) +1223 train 3.816135 (lr=4.9908e-04) (hash(x)=35171683) +1224 train 3.765165 (lr=4.9871e-04) (hash(x)=38712466) +1225 val loss 3.7918 +1225 val perplexity 44.3358 +1225 train 3.718264 (lr=4.9834e-04) (hash(x)=40379591) +1226 train 3.798827 (lr=4.9797e-04) (hash(x)=48862778) +1227 train 3.790401 (lr=4.9760e-04) (hash(x)=38523808) +1228 train 3.729950 (lr=4.9723e-04) (hash(x)=39082509) +1229 train 3.709605 (lr=4.9685e-04) (hash(x)=37153779) +1230 train 3.739675 (lr=4.9648e-04) (hash(x)=37398872) +1231 train 3.727564 (lr=4.9610e-04) (hash(x)=36301340) +1232 train 3.743723 (lr=4.9573e-04) (hash(x)=39252211) +1233 train 3.743573 (lr=4.9535e-04) (hash(x)=42781436) +1234 train 3.750340 (lr=4.9498e-04) (hash(x)=38575654) +1235 train 3.714171 (lr=4.9460e-04) (hash(x)=39573168) +1236 train 3.718942 (lr=4.9422e-04) (hash(x)=39722729) +1237 train 3.656142 (lr=4.9385e-04) (hash(x)=39858303) +1238 train 3.746544 (lr=4.9347e-04) (hash(x)=42474876) +1239 train 3.724801 (lr=4.9309e-04) (hash(x)=38929021) +1240 train 3.681449 (lr=4.9271e-04) (hash(x)=38531289) +1241 train 3.639128 (lr=4.9233e-04) (hash(x)=44649913) +1242 train 3.635540 (lr=4.9195e-04) (hash(x)=39234843) +1243 train 3.681515 (lr=4.9157e-04) (hash(x)=38369734) +1244 train 3.642877 (lr=4.9119e-04) (hash(x)=34843376) +1245 train 3.643442 (lr=4.9081e-04) (hash(x)=36480967) +1246 train 3.675571 (lr=4.9043e-04) (hash(x)=39252446) +1247 train 3.656128 (lr=4.9004e-04) (hash(x)=43941888) +1248 train 3.630701 (lr=4.8966e-04) (hash(x)=42707881) +1249 train 3.623615 (lr=4.8928e-04) (hash(x)=46747123) +1250 val loss 3.7825 +1250 val perplexity 43.9247 +1250 train 3.666899 (lr=4.8889e-04) (hash(x)=40518793) +1251 train 3.670846 (lr=4.8851e-04) (hash(x)=37827845) +1252 train 3.712491 (lr=4.8812e-04) (hash(x)=41253272) +1253 train 3.757093 (lr=4.8774e-04) (hash(x)=37157626) +1254 train 3.794523 (lr=4.8735e-04) (hash(x)=38523213) +1255 train 3.802957 (lr=4.8697e-04) (hash(x)=43240220) +1256 train 3.750344 (lr=4.8658e-04) (hash(x)=44226817) +1257 train 3.738783 (lr=4.8619e-04) (hash(x)=40090757) +1258 train 3.843879 (lr=4.8580e-04) (hash(x)=43821877) +1259 train 3.826541 (lr=4.8542e-04) (hash(x)=46505531) +1260 train 3.741626 (lr=4.8503e-04) (hash(x)=46409205) +1261 train 3.752117 (lr=4.8464e-04) (hash(x)=41497493) +1262 train 3.822958 (lr=4.8425e-04) (hash(x)=40543437) +1263 train 3.767776 (lr=4.8386e-04) (hash(x)=39134914) +1264 train 3.757852 (lr=4.8347e-04) (hash(x)=40511055) +1265 train 3.774655 (lr=4.8308e-04) (hash(x)=40354674) +1266 train 3.755742 (lr=4.8268e-04) (hash(x)=40178636) +1267 train 3.794242 (lr=4.8229e-04) (hash(x)=40917256) +1268 train 3.729855 (lr=4.8190e-04) (hash(x)=40886744) +1269 train 3.740843 (lr=4.8151e-04) (hash(x)=40712749) +1270 train 3.771435 (lr=4.8111e-04) (hash(x)=42877403) +1271 train 3.753157 (lr=4.8072e-04) (hash(x)=35075886) +1272 train 3.786157 (lr=4.8032e-04) (hash(x)=42463701) +1273 train 3.753242 (lr=4.7993e-04) (hash(x)=38853305) +1274 train 3.709409 (lr=4.7953e-04) (hash(x)=39049504) +1275 val loss 3.7592 +1275 val perplexity 42.9145 +1275 train 3.774518 (lr=4.7914e-04) (hash(x)=38708489) +1276 train 3.698164 (lr=4.7874e-04) (hash(x)=43447300) +1277 train 3.676099 (lr=4.7835e-04) (hash(x)=48808041) +1278 train 3.680877 (lr=4.7795e-04) (hash(x)=35948901) +1279 train 3.681998 (lr=4.7755e-04) (hash(x)=42302860) +1280 train 3.728553 (lr=4.7715e-04) (hash(x)=36663677) +1281 train 3.724765 (lr=4.7675e-04) (hash(x)=36351382) +1282 train 3.672477 (lr=4.7635e-04) (hash(x)=37877215) +1283 train 3.712210 (lr=4.7595e-04) (hash(x)=40817543) +1284 train 3.740474 (lr=4.7555e-04) (hash(x)=37356324) +1285 train 3.714576 (lr=4.7515e-04) (hash(x)=42573201) +1286 train 3.673174 (lr=4.7475e-04) (hash(x)=37748457) +1287 train 3.713702 (lr=4.7435e-04) (hash(x)=37765495) +1288 train 3.697990 (lr=4.7395e-04) (hash(x)=35907663) +1289 train 3.641459 (lr=4.7355e-04) (hash(x)=32295350) +1290 train 3.595676 (lr=4.7315e-04) (hash(x)=39763091) +1291 train 3.618091 (lr=4.7274e-04) (hash(x)=38690685) +1292 train 3.630708 (lr=4.7234e-04) (hash(x)=39898340) +1293 train 3.620064 (lr=4.7193e-04) (hash(x)=38839938) +1294 train 3.574871 (lr=4.7153e-04) (hash(x)=36075994) +1295 train 3.601268 (lr=4.7113e-04) (hash(x)=41094465) +1296 train 3.551632 (lr=4.7072e-04) (hash(x)=35760055) +1297 train 3.649523 (lr=4.7031e-04) (hash(x)=40359240) +1298 train 3.616046 (lr=4.6991e-04) (hash(x)=39859446) +1299 train 3.596160 (lr=4.6950e-04) (hash(x)=40620292) +1300 val loss 3.7541 +1300 val perplexity 42.6968 +1300 train 3.757757 (lr=4.6909e-04) (hash(x)=42952062) +1301 train 3.767109 (lr=4.6869e-04) (hash(x)=44178351) +1302 train 3.779945 (lr=4.6828e-04) (hash(x)=45887009) +1303 train 3.767429 (lr=4.6787e-04) (hash(x)=36674456) +1304 train 3.772755 (lr=4.6746e-04) (hash(x)=43812591) +1305 train 3.768416 (lr=4.6705e-04) (hash(x)=46823567) +1306 train 3.702056 (lr=4.6664e-04) (hash(x)=38752976) +1307 train 3.799511 (lr=4.6623e-04) (hash(x)=45328641) +1308 train 3.785555 (lr=4.6582e-04) (hash(x)=44199555) +1309 train 3.804028 (lr=4.6541e-04) (hash(x)=40516046) +1310 train 3.746855 (lr=4.6500e-04) (hash(x)=43476840) +1311 train 3.729972 (lr=4.6459e-04) (hash(x)=42479086) +1312 train 3.735683 (lr=4.6418e-04) (hash(x)=45036186) +1313 train 3.704886 (lr=4.6376e-04) (hash(x)=38656480) +1314 train 3.732569 (lr=4.6335e-04) (hash(x)=39002847) +1315 train 3.777216 (lr=4.6294e-04) (hash(x)=47974568) +1316 train 3.758669 (lr=4.6252e-04) (hash(x)=42387566) +1317 train 3.789941 (lr=4.6211e-04) (hash(x)=36733775) +1318 train 3.708486 (lr=4.6169e-04) (hash(x)=35980682) +1319 train 3.769172 (lr=4.6128e-04) (hash(x)=40696375) +1320 train 3.698886 (lr=4.6086e-04) (hash(x)=42316099) +1321 train 3.674066 (lr=4.6045e-04) (hash(x)=38183441) +1322 train 3.718276 (lr=4.6003e-04) (hash(x)=43445469) +1323 train 3.713372 (lr=4.5962e-04) (hash(x)=40321237) +1324 train 3.657950 (lr=4.5920e-04) (hash(x)=58155019) +1325 val loss 3.7371 +1325 val perplexity 41.9751 +1325 train 3.708789 (lr=4.5878e-04) (hash(x)=37149282) +1326 train 3.688866 (lr=4.5836e-04) (hash(x)=38166310) +1327 train 3.694783 (lr=4.5794e-04) (hash(x)=39981774) +1328 train 3.674420 (lr=4.5753e-04) (hash(x)=44197786) +1329 train 3.709412 (lr=4.5711e-04) (hash(x)=39088826) +1330 train 3.665816 (lr=4.5669e-04) (hash(x)=40603937) +1331 train 3.642024 (lr=4.5627e-04) (hash(x)=39192522) +1332 train 3.681931 (lr=4.5585e-04) (hash(x)=36600302) +1333 train 3.668558 (lr=4.5543e-04) (hash(x)=33316654) +1334 train 3.700199 (lr=4.5501e-04) (hash(x)=35659441) +1335 train 3.590440 (lr=4.5458e-04) (hash(x)=36409476) +1336 train 3.674525 (lr=4.5416e-04) (hash(x)=43027125) +1337 train 3.567596 (lr=4.5374e-04) (hash(x)=33570575) +1338 train 3.605717 (lr=4.5332e-04) (hash(x)=35132955) +1339 train 3.659873 (lr=4.5289e-04) (hash(x)=41080915) +1340 train 3.611343 (lr=4.5247e-04) (hash(x)=46326495) +1341 train 3.565814 (lr=4.5205e-04) (hash(x)=37595424) +1342 train 3.628096 (lr=4.5162e-04) (hash(x)=41731532) +1343 train 3.591566 (lr=4.5120e-04) (hash(x)=42180008) +1344 train 3.542997 (lr=4.5077e-04) (hash(x)=39453374) +1345 train 3.604987 (lr=4.5035e-04) (hash(x)=34613512) +1346 train 3.719654 (lr=4.4992e-04) (hash(x)=39014373) +1347 train 3.670125 (lr=4.4950e-04) (hash(x)=47038490) +1348 train 3.795709 (lr=4.4907e-04) (hash(x)=38746472) +1349 train 3.758698 (lr=4.4864e-04) (hash(x)=40771524) +1350 val loss 3.7284 +1350 val perplexity 41.6117 +1350 train 3.734010 (lr=4.4822e-04) (hash(x)=37472441) +1351 train 3.733540 (lr=4.4779e-04) (hash(x)=40217172) +1352 train 3.696060 (lr=4.4736e-04) (hash(x)=43731584) +1353 train 3.718236 (lr=4.4693e-04) (hash(x)=37474604) +1354 train 3.733632 (lr=4.4651e-04) (hash(x)=38105033) +1355 train 3.757124 (lr=4.4608e-04) (hash(x)=36886890) +1356 train 3.703157 (lr=4.4565e-04) (hash(x)=34730434) +1357 train 3.736418 (lr=4.4522e-04) (hash(x)=38700992) +1358 train 3.695821 (lr=4.4479e-04) (hash(x)=40757858) +1359 train 3.758385 (lr=4.4436e-04) (hash(x)=37850765) +1360 train 3.766192 (lr=4.4393e-04) (hash(x)=36936255) +1361 train 3.732840 (lr=4.4350e-04) (hash(x)=35172219) +1362 train 3.728623 (lr=4.4307e-04) (hash(x)=39602238) +1363 train 3.756159 (lr=4.4263e-04) (hash(x)=48026803) +1364 train 3.767598 (lr=4.4220e-04) (hash(x)=39336900) +1365 train 3.735737 (lr=4.4177e-04) (hash(x)=39052467) +1366 train 3.719213 (lr=4.4134e-04) (hash(x)=37213931) +1367 train 3.741616 (lr=4.4090e-04) (hash(x)=36710786) +1368 train 3.697589 (lr=4.4047e-04) (hash(x)=39326109) +1369 train 3.682483 (lr=4.4004e-04) (hash(x)=39831411) +1370 train 3.687229 (lr=4.3960e-04) (hash(x)=44651833) +1371 train 3.663316 (lr=4.3917e-04) (hash(x)=38177731) +1372 train 3.699128 (lr=4.3873e-04) (hash(x)=37351518) +1373 train 3.652197 (lr=4.3830e-04) (hash(x)=38930942) +1374 train 3.667414 (lr=4.3786e-04) (hash(x)=36586011) +1375 val loss 3.7136 +1375 val perplexity 41.0031 +1375 train 3.658816 (lr=4.3743e-04) (hash(x)=41217634) +1376 train 3.684621 (lr=4.3699e-04) (hash(x)=37688581) +1377 train 3.667542 (lr=4.3655e-04) (hash(x)=44598804) +1378 train 3.688289 (lr=4.3612e-04) (hash(x)=40236448) +1379 train 3.665592 (lr=4.3568e-04) (hash(x)=40699888) +1380 train 3.676996 (lr=4.3524e-04) (hash(x)=39737197) +1381 train 3.661951 (lr=4.3480e-04) (hash(x)=45943407) +1382 train 3.602280 (lr=4.3437e-04) (hash(x)=44660809) +1383 train 3.646279 (lr=4.3393e-04) (hash(x)=36215827) +1384 train 3.576258 (lr=4.3349e-04) (hash(x)=44908103) +1385 train 3.610922 (lr=4.3305e-04) (hash(x)=39732970) +1386 train 3.605319 (lr=4.3261e-04) (hash(x)=40325887) +1387 train 3.590639 (lr=4.3217e-04) (hash(x)=39659037) +1388 train 3.552141 (lr=4.3173e-04) (hash(x)=38401852) +1389 train 3.558136 (lr=4.3129e-04) (hash(x)=41797620) +1390 train 3.594865 (lr=4.3085e-04) (hash(x)=43946413) +1391 train 3.584032 (lr=4.3041e-04) (hash(x)=39715583) +1392 train 3.598349 (lr=4.2997e-04) (hash(x)=36873852) +1393 train 3.546929 (lr=4.2953e-04) (hash(x)=37815827) +1394 train 3.764429 (lr=4.2908e-04) (hash(x)=35540053) +1395 train 3.720359 (lr=4.2864e-04) (hash(x)=47424486) +1396 train 3.688541 (lr=4.2820e-04) (hash(x)=38732874) +1397 train 3.720801 (lr=4.2776e-04) (hash(x)=37113884) +1398 train 3.770833 (lr=4.2731e-04) (hash(x)=40078190) +1399 train 3.793030 (lr=4.2687e-04) (hash(x)=39935976) +1400 val loss 3.7086 +1400 val perplexity 40.7966 +1400 train 3.769136 (lr=4.2643e-04) (hash(x)=36741911) +1401 train 3.763404 (lr=4.2598e-04) (hash(x)=41647823) +1402 train 3.659821 (lr=4.2554e-04) (hash(x)=46989863) +1403 train 3.636989 (lr=4.2509e-04) (hash(x)=41278566) +1404 train 3.669350 (lr=4.2465e-04) (hash(x)=43844907) +1405 train 3.692005 (lr=4.2420e-04) (hash(x)=42249486) +1406 train 3.762938 (lr=4.2376e-04) (hash(x)=40333267) +1407 train 3.663598 (lr=4.2331e-04) (hash(x)=36421561) +1408 train 3.726354 (lr=4.2287e-04) (hash(x)=39513999) +1409 train 3.690652 (lr=4.2242e-04) (hash(x)=34703897) +1410 train 3.692441 (lr=4.2197e-04) (hash(x)=40622661) +1411 train 3.675276 (lr=4.2153e-04) (hash(x)=32351535) +1412 train 3.677930 (lr=4.2108e-04) (hash(x)=52232216) +1413 train 3.695021 (lr=4.2063e-04) (hash(x)=37067389) +1414 train 3.716766 (lr=4.2018e-04) (hash(x)=38917595) +1415 train 3.704474 (lr=4.1974e-04) (hash(x)=35318720) +1416 train 3.682275 (lr=4.1929e-04) (hash(x)=42791677) +1417 train 3.666353 (lr=4.1884e-04) (hash(x)=37610305) +1418 train 3.644103 (lr=4.1839e-04) (hash(x)=40259645) +1419 train 3.614122 (lr=4.1794e-04) (hash(x)=39520749) +1420 train 3.617738 (lr=4.1749e-04) (hash(x)=33205984) +1421 train 3.615763 (lr=4.1704e-04) (hash(x)=35997228) +1422 train 3.615487 (lr=4.1659e-04) (hash(x)=46770904) +1423 train 3.627719 (lr=4.1614e-04) (hash(x)=43713735) +1424 train 3.662035 (lr=4.1569e-04) (hash(x)=39019292) +1425 val loss 3.6921 +1425 val perplexity 40.1300 +1425 train 3.646670 (lr=4.1524e-04) (hash(x)=44668475) +1426 train 3.589464 (lr=4.1479e-04) (hash(x)=39500452) +1427 train 3.670447 (lr=4.1434e-04) (hash(x)=43392899) +1428 train 3.641783 (lr=4.1389e-04) (hash(x)=29478582) +1429 train 3.527827 (lr=4.1343e-04) (hash(x)=43947723) +1430 train 3.673009 (lr=4.1298e-04) (hash(x)=34887584) +1431 train 3.560367 (lr=4.1253e-04) (hash(x)=37282936) +1432 train 3.555105 (lr=4.1208e-04) (hash(x)=47078362) +1433 train 3.584897 (lr=4.1162e-04) (hash(x)=39982394) +1434 train 3.533837 (lr=4.1117e-04) (hash(x)=38310329) +1435 train 3.558531 (lr=4.1072e-04) (hash(x)=36656148) +1436 train 3.531259 (lr=4.1026e-04) (hash(x)=41459267) +1437 train 3.587653 (lr=4.0981e-04) (hash(x)=36671558) +1438 train 3.581496 (lr=4.0936e-04) (hash(x)=39138401) +1439 train 3.480253 (lr=4.0890e-04) (hash(x)=42213236) +1440 train 3.622922 (lr=4.0845e-04) (hash(x)=39727623) +1441 train 3.767722 (lr=4.0799e-04) (hash(x)=42741273) +1442 train 3.690295 (lr=4.0754e-04) (hash(x)=42070647) +1443 train 3.677707 (lr=4.0708e-04) (hash(x)=44215914) +1444 train 3.720163 (lr=4.0663e-04) (hash(x)=40842658) +1445 train 3.673863 (lr=4.0617e-04) (hash(x)=38153122) +1446 train 3.683098 (lr=4.0572e-04) (hash(x)=43009417) +1447 train 3.709333 (lr=4.0526e-04) (hash(x)=44488849) +1448 train 3.704930 (lr=4.0480e-04) (hash(x)=36040459) +1449 train 3.685183 (lr=4.0435e-04) (hash(x)=35298476) +1450 val loss 3.6832 +1450 val perplexity 39.7736 +1450 train 3.717721 (lr=4.0389e-04) (hash(x)=45161304) +1451 train 3.686184 (lr=4.0343e-04) (hash(x)=42164276) +1452 train 3.701905 (lr=4.0297e-04) (hash(x)=38004229) +1453 train 3.699865 (lr=4.0252e-04) (hash(x)=38794706) +1454 train 3.668853 (lr=4.0206e-04) (hash(x)=42442046) +1455 train 3.694147 (lr=4.0160e-04) (hash(x)=32734238) +1456 train 3.685610 (lr=4.0114e-04) (hash(x)=43356890) +1457 train 3.719308 (lr=4.0068e-04) (hash(x)=35241925) +1458 train 3.647034 (lr=4.0023e-04) (hash(x)=63122534) +1459 train 3.705816 (lr=3.9977e-04) (hash(x)=42587491) +1460 train 3.644549 (lr=3.9931e-04) (hash(x)=43104763) +1461 train 3.662913 (lr=3.9885e-04) (hash(x)=36453286) +1462 train 3.707593 (lr=3.9839e-04) (hash(x)=38645707) +1463 train 3.744144 (lr=3.9793e-04) (hash(x)=37552069) +1464 train 3.620642 (lr=3.9747e-04) (hash(x)=38813870) +1465 train 3.654189 (lr=3.9701e-04) (hash(x)=39224982) +1466 train 3.643884 (lr=3.9655e-04) (hash(x)=39107443) +1467 train 3.587156 (lr=3.9609e-04) (hash(x)=43392034) +1468 train 3.677244 (lr=3.9563e-04) (hash(x)=40824183) +1469 train 3.636030 (lr=3.9517e-04) (hash(x)=43821409) +1470 train 3.667843 (lr=3.9470e-04) (hash(x)=36310876) +1471 train 3.653711 (lr=3.9424e-04) (hash(x)=39284577) +1472 train 3.632045 (lr=3.9378e-04) (hash(x)=34388944) +1473 train 3.650522 (lr=3.9332e-04) (hash(x)=36028208) +1474 train 3.565589 (lr=3.9286e-04) (hash(x)=41101560) +1475 val loss 3.6736 +1475 val perplexity 39.3921 +1475 train 3.583710 (lr=3.9239e-04) (hash(x)=37915979) +1476 train 3.610857 (lr=3.9193e-04) (hash(x)=36557235) +1477 train 3.590495 (lr=3.9147e-04) (hash(x)=42355159) +1478 train 3.518299 (lr=3.9101e-04) (hash(x)=34800815) +1479 train 3.543741 (lr=3.9054e-04) (hash(x)=38120157) +1480 train 3.603409 (lr=3.9008e-04) (hash(x)=33021376) +1481 train 3.569710 (lr=3.8962e-04) (hash(x)=39688182) +1482 train 3.571676 (lr=3.8915e-04) (hash(x)=37181918) +1483 train 3.501813 (lr=3.8869e-04) (hash(x)=35840983) +1484 train 3.480481 (lr=3.8823e-04) (hash(x)=35092084) +1485 train 3.525297 (lr=3.8776e-04) (hash(x)=38089068) +1486 train 3.527769 (lr=3.8730e-04) (hash(x)=38922693) +1487 train 3.692703 (lr=3.8683e-04) (hash(x)=42881357) +1488 train 3.704690 (lr=3.8637e-04) (hash(x)=44095525) +1489 train 3.652666 (lr=3.8590e-04) (hash(x)=35158051) +1490 train 3.739909 (lr=3.8544e-04) (hash(x)=40158535) +1491 train 3.639332 (lr=3.8497e-04) (hash(x)=35710531) +1492 train 3.636827 (lr=3.8451e-04) (hash(x)=37084675) +1493 train 3.752980 (lr=3.8404e-04) (hash(x)=39245930) +1494 train 3.687636 (lr=3.8358e-04) (hash(x)=42266376) +1495 train 3.657789 (lr=3.8311e-04) (hash(x)=42158107) +1496 train 3.653243 (lr=3.8265e-04) (hash(x)=41124889) +1497 train 3.652723 (lr=3.8218e-04) (hash(x)=37303006) +1498 train 3.699228 (lr=3.8171e-04) (hash(x)=42742438) +1499 train 3.746555 (lr=3.8125e-04) (hash(x)=38803415) +1500 val loss 3.6657 +1500 val perplexity 39.0825 +1500 train 3.677017 (lr=3.8078e-04) (hash(x)=41046750) +1501 train 3.716015 (lr=3.8031e-04) (hash(x)=35920172) +1502 train 3.665495 (lr=3.7985e-04) (hash(x)=36357515) +1503 train 3.661754 (lr=3.7938e-04) (hash(x)=40124884) +1504 train 3.634352 (lr=3.7891e-04) (hash(x)=39103679) +1505 train 3.652564 (lr=3.7844e-04) (hash(x)=43818564) +1506 train 3.634249 (lr=3.7798e-04) (hash(x)=48284012) +1507 train 3.713284 (lr=3.7751e-04) (hash(x)=41676746) +1508 train 3.621633 (lr=3.7704e-04) (hash(x)=38865691) +1509 train 3.674196 (lr=3.7657e-04) (hash(x)=37839001) +1510 train 3.602989 (lr=3.7610e-04) (hash(x)=38853343) +1511 train 3.648192 (lr=3.7564e-04) (hash(x)=42304479) +1512 train 3.610081 (lr=3.7517e-04) (hash(x)=40196549) +1513 train 3.650626 (lr=3.7470e-04) (hash(x)=45997017) +1514 train 3.588056 (lr=3.7423e-04) (hash(x)=39401635) +1515 train 3.622179 (lr=3.7376e-04) (hash(x)=40650169) +1516 train 3.615604 (lr=3.7329e-04) (hash(x)=42648932) +1517 train 3.602059 (lr=3.7282e-04) (hash(x)=41929608) +1518 train 3.587805 (lr=3.7235e-04) (hash(x)=39079646) +1519 train 3.616088 (lr=3.7189e-04) (hash(x)=34497383) +1520 train 3.563661 (lr=3.7142e-04) (hash(x)=37692920) +1521 train 3.640368 (lr=3.7095e-04) (hash(x)=40402946) +1522 train 3.561891 (lr=3.7048e-04) (hash(x)=36557180) +1523 train 3.535115 (lr=3.7001e-04) (hash(x)=37947743) +1524 train 3.597102 (lr=3.6954e-04) (hash(x)=45948960) +1525 val loss 3.6558 +1525 val perplexity 38.6985 +1525 train 3.515032 (lr=3.6907e-04) (hash(x)=39032521) +1526 train 3.547094 (lr=3.6860e-04) (hash(x)=33132504) +1527 train 3.516775 (lr=3.6813e-04) (hash(x)=37785052) +1528 train 3.510003 (lr=3.6766e-04) (hash(x)=39792340) +1529 train 3.490880 (lr=3.6718e-04) (hash(x)=33878669) +1530 train 3.543250 (lr=3.6671e-04) (hash(x)=34729496) +1531 train 3.512896 (lr=3.6624e-04) (hash(x)=43233303) +1532 train 3.486372 (lr=3.6577e-04) (hash(x)=43365786) +1533 train 3.574091 (lr=3.6530e-04) (hash(x)=43042061) +1534 train 3.710569 (lr=3.6483e-04) (hash(x)=37318331) +1535 train 3.667128 (lr=3.6436e-04) (hash(x)=43481269) +1536 train 3.684953 (lr=3.6389e-04) (hash(x)=42190160) +1537 train 3.679110 (lr=3.6342e-04) (hash(x)=40233023) +1538 train 3.628202 (lr=3.6294e-04) (hash(x)=40775634) +1539 train 3.592206 (lr=3.6247e-04) (hash(x)=46936837) +1540 train 3.720549 (lr=3.6200e-04) (hash(x)=39163231) +1541 train 3.645471 (lr=3.6153e-04) (hash(x)=44674248) +1542 train 3.639826 (lr=3.6106e-04) (hash(x)=41614380) +1543 train 3.624347 (lr=3.6058e-04) (hash(x)=40924688) +1544 train 3.712934 (lr=3.6011e-04) (hash(x)=38457016) +1545 train 3.719132 (lr=3.5964e-04) (hash(x)=41935720) +1546 train 3.694984 (lr=3.5917e-04) (hash(x)=42306994) +1547 train 3.704732 (lr=3.5870e-04) (hash(x)=44877167) +1548 train 3.644170 (lr=3.5822e-04) (hash(x)=42835035) +1549 train 3.647271 (lr=3.5775e-04) (hash(x)=35157094) +1550 val loss 3.6455 +1550 val perplexity 38.3027 +1550 train 3.659489 (lr=3.5728e-04) (hash(x)=39500564) +1551 train 3.638375 (lr=3.5680e-04) (hash(x)=40982811) +1552 train 3.635634 (lr=3.5633e-04) (hash(x)=39731764) +1553 train 3.600760 (lr=3.5586e-04) (hash(x)=42527230) +1554 train 3.684654 (lr=3.5539e-04) (hash(x)=45624945) +1555 train 3.642231 (lr=3.5491e-04) (hash(x)=39217082) +1556 train 3.603474 (lr=3.5444e-04) (hash(x)=39102718) +1557 train 3.621475 (lr=3.5397e-04) (hash(x)=43500028) +1558 train 3.634593 (lr=3.5349e-04) (hash(x)=38873205) +1559 train 3.619307 (lr=3.5302e-04) (hash(x)=38324648) +1560 train 3.615055 (lr=3.5255e-04) (hash(x)=44881617) +1561 train 3.572767 (lr=3.5207e-04) (hash(x)=35984841) +1562 train 3.643668 (lr=3.5160e-04) (hash(x)=42272147) +1563 train 3.609511 (lr=3.5112e-04) (hash(x)=36533221) +1564 train 3.614260 (lr=3.5065e-04) (hash(x)=42022000) +1565 train 3.528743 (lr=3.5018e-04) (hash(x)=35969740) +1566 train 3.558277 (lr=3.4970e-04) (hash(x)=35411731) +1567 train 3.574154 (lr=3.4923e-04) (hash(x)=40483401) +1568 train 3.544511 (lr=3.4876e-04) (hash(x)=40043379) +1569 train 3.460928 (lr=3.4828e-04) (hash(x)=38067491) +1570 train 3.485501 (lr=3.4781e-04) (hash(x)=43371207) +1571 train 3.539912 (lr=3.4733e-04) (hash(x)=42223686) +1572 train 3.534252 (lr=3.4686e-04) (hash(x)=44001896) +1573 train 3.509765 (lr=3.4638e-04) (hash(x)=43325306) +1574 train 3.470408 (lr=3.4591e-04) (hash(x)=44176115) +1575 val loss 3.6412 +1575 val perplexity 38.1372 +1575 train 3.514309 (lr=3.4544e-04) (hash(x)=34044677) +1576 train 3.542710 (lr=3.4496e-04) (hash(x)=38393715) +1577 train 3.497907 (lr=3.4449e-04) (hash(x)=38218560) +1578 train 3.495978 (lr=3.4401e-04) (hash(x)=33068375) +1579 train 3.477127 (lr=3.4354e-04) (hash(x)=35855130) +1580 train 3.534893 (lr=3.4306e-04) (hash(x)=46317609) +1581 train 3.665166 (lr=3.4259e-04) (hash(x)=33389531) +1582 train 3.649863 (lr=3.4211e-04) (hash(x)=38950090) +1583 train 3.594836 (lr=3.4164e-04) (hash(x)=36664089) +1584 train 3.710130 (lr=3.4116e-04) (hash(x)=41494643) +1585 train 3.677492 (lr=3.4069e-04) (hash(x)=45578656) +1586 train 3.672868 (lr=3.4021e-04) (hash(x)=41477962) +1587 train 3.629669 (lr=3.3974e-04) (hash(x)=37122452) +1588 train 3.645457 (lr=3.3926e-04) (hash(x)=39928930) +1589 train 3.631367 (lr=3.3879e-04) (hash(x)=35996615) +1590 train 3.658840 (lr=3.3831e-04) (hash(x)=40205071) +1591 train 3.573514 (lr=3.3784e-04) (hash(x)=39084642) +1592 train 3.691108 (lr=3.3736e-04) (hash(x)=41270053) +1593 train 3.611567 (lr=3.3689e-04) (hash(x)=42335209) +1594 train 3.626339 (lr=3.3641e-04) (hash(x)=45650333) +1595 train 3.656539 (lr=3.3594e-04) (hash(x)=46189271) +1596 train 3.630453 (lr=3.3546e-04) (hash(x)=36889645) +1597 train 3.618974 (lr=3.3499e-04) (hash(x)=40418718) +1598 train 3.621779 (lr=3.3451e-04) (hash(x)=35364582) +1599 train 3.703077 (lr=3.3404e-04) (hash(x)=42110317) +1600 val loss 3.6313 +1600 val perplexity 37.7601 +1600 train 3.680639 (lr=3.3356e-04) (hash(x)=40818405) +1601 train 3.615819 (lr=3.3309e-04) (hash(x)=37254658) +1602 train 3.630574 (lr=3.3261e-04) (hash(x)=37542047) +1603 train 3.610619 (lr=3.3214e-04) (hash(x)=33585817) +1604 train 3.614610 (lr=3.3166e-04) (hash(x)=40202890) +1605 train 3.628075 (lr=3.3119e-04) (hash(x)=38127115) +1606 train 3.542224 (lr=3.3071e-04) (hash(x)=33817428) +1607 train 3.618417 (lr=3.3024e-04) (hash(x)=39520007) +1608 train 3.563867 (lr=3.2976e-04) (hash(x)=40044802) +1609 train 3.592737 (lr=3.2929e-04) (hash(x)=35547986) +1610 train 3.667086 (lr=3.2881e-04) (hash(x)=41699207) +1611 train 3.570904 (lr=3.2834e-04) (hash(x)=38204713) +1612 train 3.581799 (lr=3.2786e-04) (hash(x)=38589351) +1613 train 3.539803 (lr=3.2739e-04) (hash(x)=35791497) +1614 train 3.597571 (lr=3.2691e-04) (hash(x)=40437689) +1615 train 3.478336 (lr=3.2644e-04) (hash(x)=34637277) +1616 train 3.500034 (lr=3.2596e-04) (hash(x)=33556593) +1617 train 3.484376 (lr=3.2549e-04) (hash(x)=39554751) +1618 train 3.480626 (lr=3.2501e-04) (hash(x)=33635410) +1619 train 3.522544 (lr=3.2454e-04) (hash(x)=41891088) +1620 train 3.485698 (lr=3.2406e-04) (hash(x)=38774292) +1621 train 3.467072 (lr=3.2359e-04) (hash(x)=42994750) +1622 train 3.476006 (lr=3.2311e-04) (hash(x)=48566901) +1623 train 3.469699 (lr=3.2264e-04) (hash(x)=37519583) +1624 train 3.519744 (lr=3.2216e-04) (hash(x)=45003410) +1625 val loss 3.6279 +1625 val perplexity 37.6319 +1625 train 3.415712 (lr=3.2169e-04) (hash(x)=41425060) +1626 train 3.548392 (lr=3.2121e-04) (hash(x)=40066789) +1627 train 3.700148 (lr=3.2074e-04) (hash(x)=42158910) +1628 train 3.628216 (lr=3.2026e-04) (hash(x)=44039592) +1629 train 3.648615 (lr=3.1979e-04) (hash(x)=37950690) +1630 train 3.746471 (lr=3.1931e-04) (hash(x)=39453927) +1631 train 3.635342 (lr=3.1884e-04) (hash(x)=40616106) +1632 train 3.664698 (lr=3.1836e-04) (hash(x)=42423825) +1633 train 3.638495 (lr=3.1789e-04) (hash(x)=43045391) +1634 train 3.668104 (lr=3.1741e-04) (hash(x)=48442285) +1635 train 3.613426 (lr=3.1694e-04) (hash(x)=49029080) +1636 train 3.619349 (lr=3.1646e-04) (hash(x)=40331302) +1637 train 3.711187 (lr=3.1599e-04) (hash(x)=41188796) +1638 train 3.600416 (lr=3.1551e-04) (hash(x)=40912763) +1639 train 3.570274 (lr=3.1504e-04) (hash(x)=39751308) +1640 train 3.576071 (lr=3.1456e-04) (hash(x)=41067220) +1641 train 3.599973 (lr=3.1409e-04) (hash(x)=52706051) +1642 train 3.603680 (lr=3.1362e-04) (hash(x)=36053888) +1643 train 3.624903 (lr=3.1314e-04) (hash(x)=36662181) +1644 train 3.610888 (lr=3.1267e-04) (hash(x)=49250143) +1645 train 3.573613 (lr=3.1219e-04) (hash(x)=42651906) +1646 train 3.605511 (lr=3.1172e-04) (hash(x)=38969529) +1647 train 3.545721 (lr=3.1124e-04) (hash(x)=48381857) +1648 train 3.608776 (lr=3.1077e-04) (hash(x)=37979004) +1649 train 3.611006 (lr=3.1030e-04) (hash(x)=45893925) +1650 val loss 3.6139 +1650 val perplexity 37.1109 +1650 train 3.596686 (lr=3.0982e-04) (hash(x)=41038775) +1651 train 3.533737 (lr=3.0935e-04) (hash(x)=42161197) +1652 train 3.602991 (lr=3.0888e-04) (hash(x)=42896369) +1653 train 3.562817 (lr=3.0840e-04) (hash(x)=35065459) +1654 train 3.559453 (lr=3.0793e-04) (hash(x)=39116796) +1655 train 3.580140 (lr=3.0745e-04) (hash(x)=42064654) +1656 train 3.523488 (lr=3.0698e-04) (hash(x)=39833202) +1657 train 3.541108 (lr=3.0651e-04) (hash(x)=36655794) +1658 train 3.540673 (lr=3.0603e-04) (hash(x)=38352234) +1659 train 3.594183 (lr=3.0556e-04) (hash(x)=42488475) +1660 train 3.527268 (lr=3.0509e-04) (hash(x)=35651962) +1661 train 3.456301 (lr=3.0461e-04) (hash(x)=41497788) +1662 train 3.536682 (lr=3.0414e-04) (hash(x)=37872188) +1663 train 3.529287 (lr=3.0367e-04) (hash(x)=41696421) +1664 train 3.469410 (lr=3.0320e-04) (hash(x)=40731390) +1665 train 3.476776 (lr=3.0272e-04) (hash(x)=35864841) +1666 train 3.518743 (lr=3.0225e-04) (hash(x)=39051703) +1667 train 3.500496 (lr=3.0178e-04) (hash(x)=37764658) +1668 train 3.562426 (lr=3.0130e-04) (hash(x)=40378982) +1669 train 3.500750 (lr=3.0083e-04) (hash(x)=40321671) +1670 train 3.463542 (lr=3.0036e-04) (hash(x)=41498484) +1671 train 3.532420 (lr=2.9989e-04) (hash(x)=37958395) +1672 train 3.467268 (lr=2.9942e-04) (hash(x)=39517788) +1673 train 3.442151 (lr=2.9894e-04) (hash(x)=42298898) +1674 train 3.578893 (lr=2.9847e-04) (hash(x)=39297955) +1675 val loss 3.6156 +1675 val perplexity 37.1755 +1675 train 3.643381 (lr=2.9800e-04) (hash(x)=47672158) +1676 train 3.624942 (lr=2.9753e-04) (hash(x)=43844038) +1677 train 3.632973 (lr=2.9706e-04) (hash(x)=40806398) +1678 train 3.645426 (lr=2.9658e-04) (hash(x)=39241913) +1679 train 3.635555 (lr=2.9611e-04) (hash(x)=48126308) +1680 train 3.640507 (lr=2.9564e-04) (hash(x)=44196271) +1681 train 3.640077 (lr=2.9517e-04) (hash(x)=37147043) +1682 train 3.617527 (lr=2.9470e-04) (hash(x)=40085367) +1683 train 3.589880 (lr=2.9423e-04) (hash(x)=35039807) +1684 train 3.569667 (lr=2.9376e-04) (hash(x)=35734707) +1685 train 3.598836 (lr=2.9329e-04) (hash(x)=39402228) +1686 train 3.637345 (lr=2.9282e-04) (hash(x)=45446786) +1687 train 3.659732 (lr=2.9234e-04) (hash(x)=34522916) +1688 train 3.600092 (lr=2.9187e-04) (hash(x)=41048394) +1689 train 3.612040 (lr=2.9140e-04) (hash(x)=40757677) +1690 train 3.651504 (lr=2.9093e-04) (hash(x)=36364890) +1691 train 3.621273 (lr=2.9046e-04) (hash(x)=38368557) +1692 train 3.642760 (lr=2.8999e-04) (hash(x)=57006251) +1693 train 3.631901 (lr=2.8952e-04) (hash(x)=39538209) +1694 train 3.607013 (lr=2.8905e-04) (hash(x)=41050033) +1695 train 3.593718 (lr=2.8858e-04) (hash(x)=41697043) +1696 train 3.589826 (lr=2.8811e-04) (hash(x)=45366396) +1697 train 3.599848 (lr=2.8765e-04) (hash(x)=36291227) +1698 train 3.584135 (lr=2.8718e-04) (hash(x)=42429952) +1699 train 3.516496 (lr=2.8671e-04) (hash(x)=46285574) +1700 val loss 3.6009 +1700 val perplexity 36.6328 +1700 train 3.547438 (lr=2.8624e-04) (hash(x)=38875537) +1701 train 3.579610 (lr=2.8577e-04) (hash(x)=38449982) +1702 train 3.531330 (lr=2.8530e-04) (hash(x)=37316982) +1703 train 3.592592 (lr=2.8483e-04) (hash(x)=34019326) +1704 train 3.531068 (lr=2.8436e-04) (hash(x)=40363415) +1705 train 3.559946 (lr=2.8390e-04) (hash(x)=36255761) +1706 train 3.507435 (lr=2.8343e-04) (hash(x)=41711225) +1707 train 3.536431 (lr=2.8296e-04) (hash(x)=35309487) +1708 train 3.582307 (lr=2.8249e-04) (hash(x)=46388158) +1709 train 3.527063 (lr=2.8202e-04) (hash(x)=38167594) +1710 train 3.486487 (lr=2.8156e-04) (hash(x)=41658451) +1711 train 3.433422 (lr=2.8109e-04) (hash(x)=44543585) +1712 train 3.436673 (lr=2.8062e-04) (hash(x)=39338767) +1713 train 3.451236 (lr=2.8015e-04) (hash(x)=35516777) +1714 train 3.428549 (lr=2.7969e-04) (hash(x)=40432338) +1715 train 3.492095 (lr=2.7922e-04) (hash(x)=38581764) +1716 train 3.439938 (lr=2.7875e-04) (hash(x)=40799884) +1717 train 3.436142 (lr=2.7829e-04) (hash(x)=35633012) +1718 train 3.436485 (lr=2.7782e-04) (hash(x)=40443248) +1719 train 3.475516 (lr=2.7735e-04) (hash(x)=39749636) +1720 train 3.500504 (lr=2.7689e-04) (hash(x)=39786513) +1721 train 3.587986 (lr=2.7642e-04) (hash(x)=46400974) +1722 train 3.673248 (lr=2.7596e-04) (hash(x)=41085726) +1723 train 3.661823 (lr=2.7549e-04) (hash(x)=44241023) +1724 train 3.602729 (lr=2.7503e-04) (hash(x)=41965614) +1725 val loss 3.5934 +1725 val perplexity 36.3583 +1725 train 3.615222 (lr=2.7456e-04) (hash(x)=44780666) +1726 train 3.595406 (lr=2.7410e-04) (hash(x)=40299304) +1727 train 3.603830 (lr=2.7363e-04) (hash(x)=40570817) +1728 train 3.590713 (lr=2.7317e-04) (hash(x)=41936227) +1729 train 3.588142 (lr=2.7270e-04) (hash(x)=41963425) +1730 train 3.646201 (lr=2.7224e-04) (hash(x)=45084295) +1731 train 3.593414 (lr=2.7177e-04) (hash(x)=42515904) +1732 train 3.579788 (lr=2.7131e-04) (hash(x)=40016311) +1733 train 3.589402 (lr=2.7085e-04) (hash(x)=42188350) +1734 train 3.591892 (lr=2.7038e-04) (hash(x)=40190771) +1735 train 3.617103 (lr=2.6992e-04) (hash(x)=38416619) +1736 train 3.517089 (lr=2.6946e-04) (hash(x)=40904519) +1737 train 3.600017 (lr=2.6899e-04) (hash(x)=44370310) +1738 train 3.602398 (lr=2.6853e-04) (hash(x)=34237373) +1739 train 3.548237 (lr=2.6807e-04) (hash(x)=37297841) +1740 train 3.595305 (lr=2.6761e-04) (hash(x)=33563296) +1741 train 3.588122 (lr=2.6714e-04) (hash(x)=42288423) +1742 train 3.518953 (lr=2.6668e-04) (hash(x)=39344043) +1743 train 3.599410 (lr=2.6622e-04) (hash(x)=34074032) +1744 train 3.547901 (lr=2.6576e-04) (hash(x)=45278072) +1745 train 3.540728 (lr=2.6530e-04) (hash(x)=41076280) +1746 train 3.543662 (lr=2.6483e-04) (hash(x)=42402184) +1747 train 3.518315 (lr=2.6437e-04) (hash(x)=38167435) +1748 train 3.525113 (lr=2.6391e-04) (hash(x)=37905974) +1749 train 3.536365 (lr=2.6345e-04) (hash(x)=41039804) +1750 val loss 3.5851 +1750 val perplexity 36.0587 +1750 train 3.542170 (lr=2.6299e-04) (hash(x)=39101653) +1751 train 3.540313 (lr=2.6253e-04) (hash(x)=36230314) +1752 train 3.573506 (lr=2.6207e-04) (hash(x)=43842115) +1753 train 3.547161 (lr=2.6161e-04) (hash(x)=37393321) +1754 train 3.553379 (lr=2.6115e-04) (hash(x)=37342408) +1755 train 3.477588 (lr=2.6069e-04) (hash(x)=41870553) +1756 train 3.419375 (lr=2.6023e-04) (hash(x)=44472276) +1757 train 3.454189 (lr=2.5977e-04) (hash(x)=38195292) +1758 train 3.449322 (lr=2.5932e-04) (hash(x)=40719368) +1759 train 3.423136 (lr=2.5886e-04) (hash(x)=41406178) +1760 train 3.426066 (lr=2.5840e-04) (hash(x)=35618472) +1761 train 3.432875 (lr=2.5794e-04) (hash(x)=41526583) +1762 train 3.419812 (lr=2.5748e-04) (hash(x)=39200984) +1763 train 3.435396 (lr=2.5703e-04) (hash(x)=41998640) +1764 train 3.470866 (lr=2.5657e-04) (hash(x)=41647657) +1765 train 3.436930 (lr=2.5611e-04) (hash(x)=40388243) +1766 train 3.530713 (lr=2.5565e-04) (hash(x)=43454640) +1767 train 3.603718 (lr=2.5520e-04) (hash(x)=38182036) +1768 train 3.590742 (lr=2.5474e-04) (hash(x)=40742311) +1769 train 3.540200 (lr=2.5428e-04) (hash(x)=39793175) +1770 train 3.560204 (lr=2.5383e-04) (hash(x)=43612844) +1771 train 3.560807 (lr=2.5337e-04) (hash(x)=42111825) +1772 train 3.601136 (lr=2.5292e-04) (hash(x)=43173200) +1773 train 3.540278 (lr=2.5246e-04) (hash(x)=33532309) +1774 train 3.553014 (lr=2.5201e-04) (hash(x)=42499394) +1775 val loss 3.5744 +1775 val perplexity 35.6729 +1775 train 3.643564 (lr=2.5155e-04) (hash(x)=42391984) +1776 train 3.578998 (lr=2.5110e-04) (hash(x)=42478437) +1777 train 3.536276 (lr=2.5064e-04) (hash(x)=33213645) +1778 train 3.646001 (lr=2.5019e-04) (hash(x)=31601471) +1779 train 3.538254 (lr=2.4974e-04) (hash(x)=38964252) +1780 train 3.604998 (lr=2.4928e-04) (hash(x)=37950722) +1781 train 3.570009 (lr=2.4883e-04) (hash(x)=46420281) +1782 train 3.571822 (lr=2.4838e-04) (hash(x)=38556152) +1783 train 3.600804 (lr=2.4792e-04) (hash(x)=34064208) +1784 train 3.574597 (lr=2.4747e-04) (hash(x)=39175844) +1785 train 3.554581 (lr=2.4702e-04) (hash(x)=39532032) +1786 train 3.562634 (lr=2.4657e-04) (hash(x)=34633501) +1787 train 3.542289 (lr=2.4611e-04) (hash(x)=37358767) +1788 train 3.564419 (lr=2.4566e-04) (hash(x)=41518289) +1789 train 3.544332 (lr=2.4521e-04) (hash(x)=34579189) +1790 train 3.521387 (lr=2.4476e-04) (hash(x)=36199550) +1791 train 3.489436 (lr=2.4431e-04) (hash(x)=38496560) +1792 train 3.499224 (lr=2.4386e-04) (hash(x)=41277936) +1793 train 3.502719 (lr=2.4341e-04) (hash(x)=35401150) +1794 train 3.531236 (lr=2.4296e-04) (hash(x)=38141416) +1795 train 3.555149 (lr=2.4251e-04) (hash(x)=37372873) +1796 train 3.514011 (lr=2.4206e-04) (hash(x)=41575038) +1797 train 3.508821 (lr=2.4161e-04) (hash(x)=42622053) +1798 train 3.471996 (lr=2.4116e-04) (hash(x)=41618799) +1799 train 3.503161 (lr=2.4071e-04) (hash(x)=34914183) +1800 val loss 3.5701 +1800 val perplexity 35.5200 +1800 train 3.452366 (lr=2.4026e-04) (hash(x)=38641475) +1801 train 3.466824 (lr=2.3982e-04) (hash(x)=40475002) +1802 train 3.453088 (lr=2.3937e-04) (hash(x)=38468133) +1803 train 3.388264 (lr=2.3892e-04) (hash(x)=38024239) +1804 train 3.462373 (lr=2.3847e-04) (hash(x)=41508426) +1805 train 3.454552 (lr=2.3803e-04) (hash(x)=37387681) +1806 train 3.412353 (lr=2.3758e-04) (hash(x)=41389938) +1807 train 3.458556 (lr=2.3713e-04) (hash(x)=49597379) +1808 train 3.448682 (lr=2.3669e-04) (hash(x)=38789970) +1809 train 3.428935 (lr=2.3624e-04) (hash(x)=42484627) +1810 train 3.462933 (lr=2.3580e-04) (hash(x)=59222996) +1811 train 3.380932 (lr=2.3535e-04) (hash(x)=45728308) +1812 train 3.453746 (lr=2.3491e-04) (hash(x)=42415571) +1813 train 3.546428 (lr=2.3446e-04) (hash(x)=38164154) +1814 train 3.571406 (lr=2.3402e-04) (hash(x)=40182335) +1815 train 3.583643 (lr=2.3357e-04) (hash(x)=43758600) +1816 train 3.550841 (lr=2.3313e-04) (hash(x)=34096861) +1817 train 3.609582 (lr=2.3269e-04) (hash(x)=40403687) +1818 train 3.580853 (lr=2.3224e-04) (hash(x)=36571174) +1819 train 3.610465 (lr=2.3180e-04) (hash(x)=35453725) +1820 train 3.537299 (lr=2.3136e-04) (hash(x)=37780119) +1821 train 3.605489 (lr=2.3092e-04) (hash(x)=42734109) +1822 train 3.551284 (lr=2.3047e-04) (hash(x)=39708657) +1823 train 3.529688 (lr=2.3003e-04) (hash(x)=39673177) +1824 train 3.571167 (lr=2.2959e-04) (hash(x)=39564797) +1825 val loss 3.5638 +1825 val perplexity 35.2979 +1825 train 3.594433 (lr=2.2915e-04) (hash(x)=32238513) +1826 train 3.566247 (lr=2.2871e-04) (hash(x)=42433529) +1827 train 3.556494 (lr=2.2827e-04) (hash(x)=35907670) +1828 train 3.623133 (lr=2.2783e-04) (hash(x)=48565587) +1829 train 3.529910 (lr=2.2739e-04) (hash(x)=49651889) +1830 train 3.582146 (lr=2.2695e-04) (hash(x)=41422245) +1831 train 3.566539 (lr=2.2651e-04) (hash(x)=39789916) +1832 train 3.580391 (lr=2.2607e-04) (hash(x)=35971707) +1833 train 3.611262 (lr=2.2563e-04) (hash(x)=34002916) +1834 train 3.635404 (lr=2.2520e-04) (hash(x)=35021995) +1835 train 3.590672 (lr=2.2476e-04) (hash(x)=40196759) +1836 train 3.499888 (lr=2.2432e-04) (hash(x)=39568983) +1837 train 3.504034 (lr=2.2388e-04) (hash(x)=44386153) +1838 train 3.524247 (lr=2.2345e-04) (hash(x)=41473006) +1839 train 3.485747 (lr=2.2301e-04) (hash(x)=40850493) +1840 train 3.513559 (lr=2.2257e-04) (hash(x)=37662108) +1841 train 3.521381 (lr=2.2214e-04) (hash(x)=40914906) +1842 train 3.522214 (lr=2.2170e-04) (hash(x)=38144492) +1843 train 3.565921 (lr=2.2127e-04) (hash(x)=37872276) +1844 train 3.548668 (lr=2.2083e-04) (hash(x)=43529116) +1845 train 3.495619 (lr=2.2040e-04) (hash(x)=38382311) +1846 train 3.544261 (lr=2.1996e-04) (hash(x)=31310390) +1847 train 3.421326 (lr=2.1953e-04) (hash(x)=45383752) +1848 train 3.384409 (lr=2.1910e-04) (hash(x)=42021603) +1849 train 3.437965 (lr=2.1866e-04) (hash(x)=34197954) +1850 val loss 3.5594 +1850 val perplexity 35.1405 +1850 train 3.393279 (lr=2.1823e-04) (hash(x)=43845250) +1851 train 3.393770 (lr=2.1780e-04) (hash(x)=47488420) +1852 train 3.373499 (lr=2.1737e-04) (hash(x)=42561232) +1853 train 3.457247 (lr=2.1693e-04) (hash(x)=33780957) +1854 train 3.474109 (lr=2.1650e-04) (hash(x)=46681924) +1855 train 3.371766 (lr=2.1607e-04) (hash(x)=38388558) +1856 train 3.384353 (lr=2.1564e-04) (hash(x)=44423722) +1857 train 3.418682 (lr=2.1521e-04) (hash(x)=41898067) +1858 train 3.498189 (lr=2.1478e-04) (hash(x)=37354949) +1859 train 3.510562 (lr=2.1435e-04) (hash(x)=43102956) +1860 train 3.543349 (lr=2.1392e-04) (hash(x)=42953508) +1861 train 3.550156 (lr=2.1349e-04) (hash(x)=42153847) +1862 train 3.543632 (lr=2.1307e-04) (hash(x)=32474556) +1863 train 3.566440 (lr=2.1264e-04) (hash(x)=50555301) +1864 train 3.565232 (lr=2.1221e-04) (hash(x)=38917415) +1865 train 3.597298 (lr=2.1178e-04) (hash(x)=36206809) +1866 train 3.513778 (lr=2.1136e-04) (hash(x)=46654317) +1867 train 3.627375 (lr=2.1093e-04) (hash(x)=45680639) +1868 train 3.579560 (lr=2.1050e-04) (hash(x)=36889237) +1869 train 3.580197 (lr=2.1008e-04) (hash(x)=40003432) +1870 train 3.581306 (lr=2.0965e-04) (hash(x)=40577231) +1871 train 3.559618 (lr=2.0923e-04) (hash(x)=40820280) +1872 train 3.605442 (lr=2.0880e-04) (hash(x)=37854800) +1873 train 3.527109 (lr=2.0838e-04) (hash(x)=37828552) +1874 train 3.568660 (lr=2.0795e-04) (hash(x)=49907060) +1875 val loss 3.5504 +1875 val perplexity 34.8275 +1875 train 3.614866 (lr=2.0753e-04) (hash(x)=41909618) +1876 train 3.553949 (lr=2.0711e-04) (hash(x)=38927669) +1877 train 3.597601 (lr=2.0668e-04) (hash(x)=37276265) +1878 train 3.537311 (lr=2.0626e-04) (hash(x)=39041497) +1879 train 3.551238 (lr=2.0584e-04) (hash(x)=44047816) +1880 train 3.557475 (lr=2.0542e-04) (hash(x)=38126511) +1881 train 3.550637 (lr=2.0499e-04) (hash(x)=43139483) +1882 train 3.562316 (lr=2.0457e-04) (hash(x)=56654076) +1883 train 3.499530 (lr=2.0415e-04) (hash(x)=39971691) +1884 train 3.565210 (lr=2.0373e-04) (hash(x)=38600700) +1885 train 3.526002 (lr=2.0331e-04) (hash(x)=35084629) +1886 train 3.521982 (lr=2.0289e-04) (hash(x)=38700745) +1887 train 3.466001 (lr=2.0247e-04) (hash(x)=37018981) +1888 train 3.479447 (lr=2.0206e-04) (hash(x)=43385293) +1889 train 3.482634 (lr=2.0164e-04) (hash(x)=37308222) +1890 train 3.463836 (lr=2.0122e-04) (hash(x)=37877268) +1891 train 3.632922 (lr=2.0080e-04) (hash(x)=35545576) +1892 train 3.495818 (lr=2.0038e-04) (hash(x)=44236364) +1893 train 3.473249 (lr=1.9997e-04) (hash(x)=35811712) +1894 train 3.513153 (lr=1.9955e-04) (hash(x)=35864920) +1895 train 3.424565 (lr=1.9914e-04) (hash(x)=34358610) +1896 train 3.571267 (lr=1.9872e-04) (hash(x)=40409678) +1897 train 3.423770 (lr=1.9831e-04) (hash(x)=38220334) +1898 train 3.393496 (lr=1.9789e-04) (hash(x)=43379366) +1899 train 3.385415 (lr=1.9748e-04) (hash(x)=38376357) +1900 val loss 3.5516 +1900 val perplexity 34.8680 +1900 train 3.411870 (lr=1.9706e-04) (hash(x)=38192803) +1901 train 3.417613 (lr=1.9665e-04) (hash(x)=39445477) +1902 train 3.402949 (lr=1.9624e-04) (hash(x)=42409423) +1903 train 3.405551 (lr=1.9582e-04) (hash(x)=41042720) +1904 train 3.373713 (lr=1.9541e-04) (hash(x)=36553087) +1905 train 3.451554 (lr=1.9500e-04) (hash(x)=38480848) +1906 train 3.562085 (lr=1.9459e-04) (hash(x)=45797681) +1907 train 3.580295 (lr=1.9418e-04) (hash(x)=40075142) +1908 train 3.502502 (lr=1.9377e-04) (hash(x)=40866503) +1909 train 3.590530 (lr=1.9336e-04) (hash(x)=45265703) +1910 train 3.571724 (lr=1.9295e-04) (hash(x)=42661661) +1911 train 3.604841 (lr=1.9254e-04) (hash(x)=42634169) +1912 train 3.575412 (lr=1.9213e-04) (hash(x)=46204767) +1913 train 3.548359 (lr=1.9172e-04) (hash(x)=40244345) +1914 train 3.525528 (lr=1.9131e-04) (hash(x)=44550552) +1915 train 3.530393 (lr=1.9091e-04) (hash(x)=37875659) +1916 train 3.540525 (lr=1.9050e-04) (hash(x)=42656375) +1917 train 3.520573 (lr=1.9009e-04) (hash(x)=38889629) +1918 train 3.484433 (lr=1.8969e-04) (hash(x)=40137500) +1919 train 3.564485 (lr=1.8928e-04) (hash(x)=36535561) +1920 train 3.565476 (lr=1.8887e-04) (hash(x)=42577305) +1921 train 3.544487 (lr=1.8847e-04) (hash(x)=36314394) +1922 train 3.549729 (lr=1.8807e-04) (hash(x)=42741344) +1923 train 3.575864 (lr=1.8766e-04) (hash(x)=43006305) +1924 train 3.542495 (lr=1.8726e-04) (hash(x)=37509722) +1925 val loss 3.5404 +1925 val perplexity 34.4795 +1925 train 3.486192 (lr=1.8685e-04) (hash(x)=41660812) +1926 train 3.569404 (lr=1.8645e-04) (hash(x)=43344506) +1927 train 3.528926 (lr=1.8605e-04) (hash(x)=37257580) +1928 train 3.512994 (lr=1.8565e-04) (hash(x)=38228734) +1929 train 3.470472 (lr=1.8525e-04) (hash(x)=39170109) +1930 train 3.513167 (lr=1.8485e-04) (hash(x)=40149866) +1931 train 3.492839 (lr=1.8445e-04) (hash(x)=40388039) +1932 train 3.524145 (lr=1.8405e-04) (hash(x)=39003620) +1933 train 3.512147 (lr=1.8365e-04) (hash(x)=38098326) +1934 train 3.492130 (lr=1.8325e-04) (hash(x)=38516363) +1935 train 3.519016 (lr=1.8285e-04) (hash(x)=37968408) +1936 train 3.517557 (lr=1.8245e-04) (hash(x)=39759902) +1937 train 3.522413 (lr=1.8205e-04) (hash(x)=39081590) +1938 train 3.505694 (lr=1.8165e-04) (hash(x)=45112436) +1939 train 3.492585 (lr=1.8126e-04) (hash(x)=33638557) +1940 train 3.454814 (lr=1.8086e-04) (hash(x)=40090964) +1941 train 3.425332 (lr=1.8047e-04) (hash(x)=40954609) +1942 train 3.401567 (lr=1.8007e-04) (hash(x)=41861276) +1943 train 3.392219 (lr=1.7968e-04) (hash(x)=47624167) +1944 train 3.418061 (lr=1.7928e-04) (hash(x)=41738216) +1945 train 3.385371 (lr=1.7889e-04) (hash(x)=41080176) +1946 train 3.433913 (lr=1.7849e-04) (hash(x)=39106828) +1947 train 3.387731 (lr=1.7810e-04) (hash(x)=39449275) +1948 train 3.410700 (lr=1.7771e-04) (hash(x)=43351750) +1949 train 3.382718 (lr=1.7732e-04) (hash(x)=36465525) +1950 val loss 3.5388 +1950 val perplexity 34.4249 +1950 train 3.375895 (lr=1.7692e-04) (hash(x)=42593746) +1951 train 3.344388 (lr=1.7653e-04) (hash(x)=33726731) +1952 train 3.382804 (lr=1.7614e-04) (hash(x)=43345134) +1953 train 3.549014 (lr=1.7575e-04) (hash(x)=40316201) +1954 train 3.589354 (lr=1.7536e-04) (hash(x)=36544677) +1955 train 3.532007 (lr=1.7497e-04) (hash(x)=34708528) +1956 train 3.506267 (lr=1.7458e-04) (hash(x)=39034813) +1957 train 3.577009 (lr=1.7420e-04) (hash(x)=40502864) +1958 train 3.571034 (lr=1.7381e-04) (hash(x)=42061078) +1959 train 3.504575 (lr=1.7342e-04) (hash(x)=41399595) +1960 train 3.521677 (lr=1.7303e-04) (hash(x)=40122540) +1961 train 3.552051 (lr=1.7265e-04) (hash(x)=39787961) +1962 train 3.609396 (lr=1.7226e-04) (hash(x)=35468999) +1963 train 3.586785 (lr=1.7188e-04) (hash(x)=35750560) +1964 train 3.561920 (lr=1.7149e-04) (hash(x)=36344671) +1965 train 3.527865 (lr=1.7111e-04) (hash(x)=41041500) +1966 train 3.502354 (lr=1.7072e-04) (hash(x)=40321631) +1967 train 3.557075 (lr=1.7034e-04) (hash(x)=36661363) +1968 train 3.575921 (lr=1.6996e-04) (hash(x)=42791541) +1969 train 3.603529 (lr=1.6957e-04) (hash(x)=40454987) +1970 train 3.527209 (lr=1.6919e-04) (hash(x)=37243603) +1971 train 3.563807 (lr=1.6881e-04) (hash(x)=36637426) +1972 train 3.520003 (lr=1.6843e-04) (hash(x)=43364069) +1973 train 3.538855 (lr=1.6805e-04) (hash(x)=42864084) +1974 train 3.496483 (lr=1.6767e-04) (hash(x)=40200322) +1975 val loss 3.5281 +1975 val perplexity 34.0600 +1975 train 3.575953 (lr=1.6729e-04) (hash(x)=37590081) +1976 train 3.489909 (lr=1.6691e-04) (hash(x)=39908765) +1977 train 3.471770 (lr=1.6653e-04) (hash(x)=42122520) +1978 train 3.591267 (lr=1.6615e-04) (hash(x)=39018691) +1979 train 3.499397 (lr=1.6578e-04) (hash(x)=38257536) +1980 train 3.458145 (lr=1.6540e-04) (hash(x)=40297906) +1981 train 3.429745 (lr=1.6502e-04) (hash(x)=40423410) +1982 train 3.490385 (lr=1.6465e-04) (hash(x)=31452482) +1983 train 3.454390 (lr=1.6427e-04) (hash(x)=40407821) +1984 train 3.517419 (lr=1.6390e-04) (hash(x)=38364432) +1985 train 3.491242 (lr=1.6352e-04) (hash(x)=42370259) +1986 train 3.487020 (lr=1.6315e-04) (hash(x)=42297153) +1987 train 3.368124 (lr=1.6277e-04) (hash(x)=48861031) +1988 train 3.382236 (lr=1.6240e-04) (hash(x)=45388212) +1989 train 3.499426 (lr=1.6203e-04) (hash(x)=36828153) +1990 train 3.416447 (lr=1.6166e-04) (hash(x)=39275838) +1991 train 3.362909 (lr=1.6129e-04) (hash(x)=37170924) +1992 train 3.403339 (lr=1.6092e-04) (hash(x)=40940768) +1993 train 3.397955 (lr=1.6055e-04) (hash(x)=41628177) +1994 train 3.395271 (lr=1.6018e-04) (hash(x)=44006988) +1995 train 3.398163 (lr=1.5981e-04) (hash(x)=38174196) +1996 train 3.410738 (lr=1.5944e-04) (hash(x)=47094023) +1997 train 3.394688 (lr=1.5907e-04) (hash(x)=41576236) +1998 train 3.457036 (lr=1.5870e-04) (hash(x)=41662938) +1999 train 3.538126 (lr=1.5834e-04) (hash(x)=37794111) +2000 val loss 3.5279 +2000 val perplexity 34.0513 +2000 train 3.549481 (lr=1.5797e-04) (hash(x)=34883450) +2001 train 3.567354 (lr=1.5760e-04) (hash(x)=36841108) +2002 train 3.570254 (lr=1.5724e-04) (hash(x)=45150079) +2003 train 3.558276 (lr=1.5687e-04) (hash(x)=40108212) +2004 train 3.558632 (lr=1.5651e-04) (hash(x)=42723097) +2005 train 3.577043 (lr=1.5614e-04) (hash(x)=39264243) +2006 train 3.521180 (lr=1.5578e-04) (hash(x)=39906882) +2007 train 3.545696 (lr=1.5542e-04) (hash(x)=40053948) +2008 train 3.478782 (lr=1.5506e-04) (hash(x)=45293474) +2009 train 3.475231 (lr=1.5469e-04) (hash(x)=37925401) +2010 train 3.527702 (lr=1.5433e-04) (hash(x)=43718300) +2011 train 3.482749 (lr=1.5397e-04) (hash(x)=41306325) +2012 train 3.560378 (lr=1.5361e-04) (hash(x)=29968555) +2013 train 3.519566 (lr=1.5325e-04) (hash(x)=38218707) +2014 train 3.490395 (lr=1.5289e-04) (hash(x)=39590550) +2015 train 3.518810 (lr=1.5254e-04) (hash(x)=39565440) +2016 train 3.556073 (lr=1.5218e-04) (hash(x)=38464805) +2017 train 3.564095 (lr=1.5182e-04) (hash(x)=38611489) +2018 train 3.502102 (lr=1.5146e-04) (hash(x)=40680641) +2019 train 3.491476 (lr=1.5111e-04) (hash(x)=47622103) +2020 train 3.553649 (lr=1.5075e-04) (hash(x)=42876689) +2021 train 3.514563 (lr=1.5040e-04) (hash(x)=38346728) +2022 train 3.491863 (lr=1.5004e-04) (hash(x)=35751959) +2023 train 3.517623 (lr=1.4969e-04) (hash(x)=33191594) +2024 train 3.508807 (lr=1.4933e-04) (hash(x)=39943864) +2025 val loss 3.5233 +2025 val perplexity 33.8956 +2025 train 3.435419 (lr=1.4898e-04) (hash(x)=35815196) +2026 train 3.510600 (lr=1.4863e-04) (hash(x)=44921971) +2027 train 3.482556 (lr=1.4828e-04) (hash(x)=35458027) +2028 train 3.487814 (lr=1.4793e-04) (hash(x)=38991858) +2029 train 3.491167 (lr=1.4758e-04) (hash(x)=44396066) +2030 train 3.485300 (lr=1.4723e-04) (hash(x)=37414985) +2031 train 3.498661 (lr=1.4688e-04) (hash(x)=53227776) +2032 train 3.474646 (lr=1.4653e-04) (hash(x)=40878171) +2033 train 3.454327 (lr=1.4618e-04) (hash(x)=39776275) +2034 train 3.397360 (lr=1.4583e-04) (hash(x)=35604973) +2035 train 3.389697 (lr=1.4548e-04) (hash(x)=39616059) +2036 train 3.408781 (lr=1.4514e-04) (hash(x)=32609275) +2037 train 3.419122 (lr=1.4479e-04) (hash(x)=47225662) +2038 train 3.361522 (lr=1.4445e-04) (hash(x)=40493848) +2039 train 3.370997 (lr=1.4410e-04) (hash(x)=41053453) +2040 train 3.340220 (lr=1.4376e-04) (hash(x)=38459836) +2041 train 3.401122 (lr=1.4341e-04) (hash(x)=41037364) +2042 train 3.369042 (lr=1.4307e-04) (hash(x)=33582170) +2043 train 3.355249 (lr=1.4273e-04) (hash(x)=39862726) +2044 train 3.387670 (lr=1.4239e-04) (hash(x)=35292896) +2045 train 3.505338 (lr=1.4204e-04) (hash(x)=49078223) +2046 train 3.526513 (lr=1.4170e-04) (hash(x)=43337563) +2047 train 3.578756 (lr=1.4136e-04) (hash(x)=40942159) +2048 train 3.520325 (lr=1.4102e-04) (hash(x)=34244522) +2049 train 3.490762 (lr=1.4068e-04) (hash(x)=38900669) +2050 val loss 3.5161 +2050 val perplexity 33.6526 +2050 train 3.531989 (lr=1.4035e-04) (hash(x)=36653974) +2051 train 3.518730 (lr=1.4001e-04) (hash(x)=43342536) +2052 train 3.507866 (lr=1.3967e-04) (hash(x)=45079057) +2053 train 3.519520 (lr=1.3933e-04) (hash(x)=39960280) +2054 train 3.600029 (lr=1.3900e-04) (hash(x)=39936072) +2055 train 3.549022 (lr=1.3866e-04) (hash(x)=45929312) +2056 train 3.545072 (lr=1.3833e-04) (hash(x)=45862473) +2057 train 3.504902 (lr=1.3799e-04) (hash(x)=38024735) +2058 train 3.502180 (lr=1.3766e-04) (hash(x)=39304274) +2059 train 3.532736 (lr=1.3733e-04) (hash(x)=40902722) +2060 train 3.526983 (lr=1.3699e-04) (hash(x)=39706512) +2061 train 3.523273 (lr=1.3666e-04) (hash(x)=34085345) +2062 train 3.574406 (lr=1.3633e-04) (hash(x)=41214955) +2063 train 3.493440 (lr=1.3600e-04) (hash(x)=38610114) +2064 train 3.596840 (lr=1.3567e-04) (hash(x)=48563087) +2065 train 3.510615 (lr=1.3534e-04) (hash(x)=39860869) +2066 train 3.547574 (lr=1.3501e-04) (hash(x)=38119393) +2067 train 3.526146 (lr=1.3468e-04) (hash(x)=40594169) +2068 train 3.465240 (lr=1.3435e-04) (hash(x)=37103639) +2069 train 3.459851 (lr=1.3403e-04) (hash(x)=35868511) +2070 train 3.576754 (lr=1.3370e-04) (hash(x)=42307220) +2071 train 3.481981 (lr=1.3337e-04) (hash(x)=45734742) +2072 train 3.500586 (lr=1.3305e-04) (hash(x)=47794279) +2073 train 3.447216 (lr=1.3272e-04) (hash(x)=38468205) +2074 train 3.525699 (lr=1.3240e-04) (hash(x)=37068716) +2075 val loss 3.5134 +2075 val perplexity 33.5637 +2075 train 3.458233 (lr=1.3208e-04) (hash(x)=45524200) +2076 train 3.435360 (lr=1.3175e-04) (hash(x)=42908799) +2077 train 3.468855 (lr=1.3143e-04) (hash(x)=37508309) +2078 train 3.501432 (lr=1.3111e-04) (hash(x)=34436360) +2079 train 3.491805 (lr=1.3079e-04) (hash(x)=35043969) +2080 train 3.544693 (lr=1.3047e-04) (hash(x)=38272471) +2081 train 3.402282 (lr=1.3015e-04) (hash(x)=38284345) +2082 train 3.329895 (lr=1.2983e-04) (hash(x)=42267510) +2083 train 3.437170 (lr=1.2951e-04) (hash(x)=40289810) +2084 train 3.362624 (lr=1.2919e-04) (hash(x)=40923524) +2085 train 3.399936 (lr=1.2887e-04) (hash(x)=34657559) +2086 train 3.318475 (lr=1.2856e-04) (hash(x)=32915857) +2087 train 3.379888 (lr=1.2824e-04) (hash(x)=36803836) +2088 train 3.357896 (lr=1.2793e-04) (hash(x)=37015225) +2089 train 3.379380 (lr=1.2761e-04) (hash(x)=33720635) +2090 train 3.393670 (lr=1.2730e-04) (hash(x)=33044573) +2091 train 3.491410 (lr=1.2698e-04) (hash(x)=37422096) +2092 train 3.567044 (lr=1.2667e-04) (hash(x)=41384332) +2093 train 3.619732 (lr=1.2636e-04) (hash(x)=40145666) +2094 train 3.544418 (lr=1.2605e-04) (hash(x)=42093153) +2095 train 3.558424 (lr=1.2574e-04) (hash(x)=34198027) +2096 train 3.536844 (lr=1.2543e-04) (hash(x)=40993150) +2097 train 3.511130 (lr=1.2512e-04) (hash(x)=37321125) +2098 train 3.506401 (lr=1.2481e-04) (hash(x)=42450951) +2099 train 3.625723 (lr=1.2450e-04) (hash(x)=41033932) +2100 val loss 3.5088 +2100 val perplexity 33.4089 +2100 train 3.544929 (lr=1.2419e-04) (hash(x)=41913976) +2101 train 3.508652 (lr=1.2388e-04) (hash(x)=43571466) +2102 train 3.521103 (lr=1.2358e-04) (hash(x)=41885893) +2103 train 3.544971 (lr=1.2327e-04) (hash(x)=42928127) +2104 train 3.545412 (lr=1.2296e-04) (hash(x)=42940733) +2105 train 3.484907 (lr=1.2266e-04) (hash(x)=41229222) +2106 train 3.481153 (lr=1.2236e-04) (hash(x)=37805986) +2107 train 3.487045 (lr=1.2205e-04) (hash(x)=35792010) +2108 train 3.450263 (lr=1.2175e-04) (hash(x)=40241774) +2109 train 3.547072 (lr=1.2145e-04) (hash(x)=44390648) +2110 train 3.468090 (lr=1.2115e-04) (hash(x)=41844836) +2111 train 3.550861 (lr=1.2085e-04) (hash(x)=40006105) +2112 train 3.515285 (lr=1.2054e-04) (hash(x)=39653445) +2113 train 3.484458 (lr=1.2025e-04) (hash(x)=32422477) +2114 train 3.475967 (lr=1.1995e-04) (hash(x)=40967012) +2115 train 3.492208 (lr=1.1965e-04) (hash(x)=44483171) +2116 train 3.401269 (lr=1.1935e-04) (hash(x)=35458895) +2117 train 3.488046 (lr=1.1905e-04) (hash(x)=42049798) +2118 train 3.451129 (lr=1.1876e-04) (hash(x)=39665524) +2119 train 3.486966 (lr=1.1846e-04) (hash(x)=39459022) +2120 train 3.461096 (lr=1.1817e-04) (hash(x)=37696611) +2121 train 3.458066 (lr=1.1787e-04) (hash(x)=42951018) +2122 train 3.456601 (lr=1.1758e-04) (hash(x)=37373972) +2123 train 3.538403 (lr=1.1729e-04) (hash(x)=45929728) +2124 train 3.487468 (lr=1.1699e-04) (hash(x)=40596339) +2125 val loss 3.5037 +2125 val perplexity 33.2376 +2125 train 3.486898 (lr=1.1670e-04) (hash(x)=33764811) +2126 train 3.389878 (lr=1.1641e-04) (hash(x)=32939637) +2127 train 3.342710 (lr=1.1612e-04) (hash(x)=33428871) +2128 train 3.387551 (lr=1.1583e-04) (hash(x)=40142304) +2129 train 3.331817 (lr=1.1554e-04) (hash(x)=40536168) +2130 train 3.336989 (lr=1.1525e-04) (hash(x)=33978312) +2131 train 3.361398 (lr=1.1497e-04) (hash(x)=40113830) +2132 train 3.346929 (lr=1.1468e-04) (hash(x)=43729754) +2133 train 3.296107 (lr=1.1439e-04) (hash(x)=39205500) +2134 train 3.303455 (lr=1.1411e-04) (hash(x)=40347434) +2135 train 3.264247 (lr=1.1382e-04) (hash(x)=35356604) +2136 train 3.310856 (lr=1.1354e-04) (hash(x)=41965306) +2137 train 3.430775 (lr=1.1325e-04) (hash(x)=30566661) +2138 train 3.441730 (lr=1.1297e-04) (hash(x)=44214428) +2139 train 3.576815 (lr=1.1269e-04) (hash(x)=43922279) +2140 train 3.546565 (lr=1.1241e-04) (hash(x)=39997616) +2141 train 3.549227 (lr=1.1213e-04) (hash(x)=40222800) +2142 train 3.656689 (lr=1.1185e-04) (hash(x)=43667666) +2143 train 3.527862 (lr=1.1157e-04) (hash(x)=39258893) +2144 train 3.516382 (lr=1.1129e-04) (hash(x)=42894771) +2145 train 3.544010 (lr=1.1101e-04) (hash(x)=40439427) +2146 train 3.455174 (lr=1.1073e-04) (hash(x)=42173463) +2147 train 3.521562 (lr=1.1045e-04) (hash(x)=41644559) +2148 train 3.496027 (lr=1.1018e-04) (hash(x)=39021697) +2149 train 3.527779 (lr=1.0990e-04) (hash(x)=39479061) +2150 val loss 3.5015 +2150 val perplexity 33.1654 +2150 train 3.519200 (lr=1.0963e-04) (hash(x)=39584185) +2151 train 3.451012 (lr=1.0935e-04) (hash(x)=41915053) +2152 train 3.480946 (lr=1.0908e-04) (hash(x)=44003346) +2153 train 3.544236 (lr=1.0881e-04) (hash(x)=37064130) +2154 train 3.483366 (lr=1.0853e-04) (hash(x)=37380805) +2155 train 3.552061 (lr=1.0826e-04) (hash(x)=48867463) +2156 train 3.519688 (lr=1.0799e-04) (hash(x)=34724353) +2157 train 3.481766 (lr=1.0772e-04) (hash(x)=40716628) +2158 train 3.605158 (lr=1.0745e-04) (hash(x)=35926807) +2159 train 3.479957 (lr=1.0718e-04) (hash(x)=42717696) +2160 train 3.524878 (lr=1.0692e-04) (hash(x)=38577657) +2161 train 3.497355 (lr=1.0665e-04) (hash(x)=41936510) +2162 train 3.459097 (lr=1.0638e-04) (hash(x)=50070948) +2163 train 3.403988 (lr=1.0612e-04) (hash(x)=36826916) +2164 train 3.430843 (lr=1.0585e-04) (hash(x)=44716388) +2165 train 3.469927 (lr=1.0559e-04) (hash(x)=41270458) +2166 train 3.494215 (lr=1.0532e-04) (hash(x)=40784298) +2167 train 3.454676 (lr=1.0506e-04) (hash(x)=44547091) +2168 train 3.427631 (lr=1.0480e-04) (hash(x)=41279405) +2169 train 3.412688 (lr=1.0453e-04) (hash(x)=47887328) +2170 train 3.483797 (lr=1.0427e-04) (hash(x)=42281020) +2171 train 3.445736 (lr=1.0401e-04) (hash(x)=44430277) +2172 train 3.423562 (lr=1.0375e-04) (hash(x)=42200686) +2173 train 3.395783 (lr=1.0349e-04) (hash(x)=34508511) +2174 train 3.279299 (lr=1.0324e-04) (hash(x)=38074335) +2175 val loss 3.4977 +2175 val perplexity 33.0394 +2175 train 3.275393 (lr=1.0298e-04) (hash(x)=36937680) +2176 train 3.281708 (lr=1.0272e-04) (hash(x)=47007236) +2177 train 3.323048 (lr=1.0247e-04) (hash(x)=38602874) +2178 train 3.210806 (lr=1.0221e-04) (hash(x)=38016747) +2179 train 3.300800 (lr=1.0196e-04) (hash(x)=39233380) +2180 train 3.303809 (lr=1.0170e-04) (hash(x)=38931531) +2181 train 3.382205 (lr=1.0145e-04) (hash(x)=42115066) +2182 train 3.319949 (lr=1.0120e-04) (hash(x)=39927759) +2183 train 3.265964 (lr=1.0094e-04) (hash(x)=40088644) +2184 train 3.290431 (lr=1.0069e-04) (hash(x)=41269148) +2185 train 3.548147 (lr=1.0044e-04) (hash(x)=35305759) +2186 train 3.473902 (lr=1.0019e-04) (hash(x)=36751545) +2187 train 3.541794 (lr=9.9942e-05) (hash(x)=44318317) +2188 train 3.740568 (lr=9.9694e-05) (hash(x)=43722690) +2189 train 3.537958 (lr=9.9446e-05) (hash(x)=43461650) +2190 train 3.534666 (lr=9.9199e-05) (hash(x)=38696294) +2191 train 3.463367 (lr=9.8953e-05) (hash(x)=41010500) +2192 train 3.531038 (lr=9.8708e-05) (hash(x)=39156667) +2193 train 3.518734 (lr=9.8463e-05) (hash(x)=47012054) +2194 train 3.496547 (lr=9.8219e-05) (hash(x)=44461427) +2195 train 3.496490 (lr=9.7975e-05) (hash(x)=41605561) +2196 train 3.510001 (lr=9.7733e-05) (hash(x)=35595450) +2197 train 3.490343 (lr=9.7491e-05) (hash(x)=45022110) +2198 train 3.532116 (lr=9.7250e-05) (hash(x)=41019906) +2199 train 3.504167 (lr=9.7009e-05) (hash(x)=38613442) +2200 val loss 3.4947 +2200 val perplexity 32.9397 +2200 train 3.441964 (lr=9.6769e-05) (hash(x)=33897828) +2201 train 3.510783 (lr=9.6530e-05) (hash(x)=38628522) +2202 train 3.496859 (lr=9.6292e-05) (hash(x)=41906805) +2203 train 3.505091 (lr=9.6054e-05) (hash(x)=37597850) +2204 train 3.477515 (lr=9.5818e-05) (hash(x)=41477671) +2205 train 3.495064 (lr=9.5581e-05) (hash(x)=32201521) +2206 train 3.497057 (lr=9.5346e-05) (hash(x)=42792108) +2207 train 3.498960 (lr=9.5111e-05) (hash(x)=46056555) +2208 train 3.471261 (lr=9.4877e-05) (hash(x)=42046871) +2209 train 3.463300 (lr=9.4644e-05) (hash(x)=48975617) +2210 train 3.496562 (lr=9.4412e-05) (hash(x)=42805376) +2211 train 3.411229 (lr=9.4180e-05) (hash(x)=40941983) +2212 train 3.485748 (lr=9.3949e-05) (hash(x)=40646587) +2213 train 3.458892 (lr=9.3718e-05) (hash(x)=43254553) +2214 train 3.450073 (lr=9.3489e-05) (hash(x)=40894034) +2215 train 3.409783 (lr=9.3260e-05) (hash(x)=45911091) +2216 train 3.439569 (lr=9.3032e-05) (hash(x)=48137012) +2217 train 3.469149 (lr=9.2804e-05) (hash(x)=39961527) +2218 train 3.443981 (lr=9.2578e-05) (hash(x)=37995862) +2219 train 3.315442 (lr=9.2352e-05) (hash(x)=45980951) +2220 train 3.360754 (lr=9.2127e-05) (hash(x)=40595116) +2221 train 3.324254 (lr=9.1902e-05) (hash(x)=40222527) +2222 train 3.297612 (lr=9.1679e-05) (hash(x)=35916629) +2223 train 3.260213 (lr=9.1456e-05) (hash(x)=40284536) +2224 train 3.262510 (lr=9.1233e-05) (hash(x)=36145449) +2225 val loss 3.4923 +2225 val perplexity 32.8629 +2225 train 3.294953 (lr=9.1012e-05) (hash(x)=35083031) +2226 train 3.347785 (lr=9.0791e-05) (hash(x)=39996125) +2227 train 3.297627 (lr=9.0571e-05) (hash(x)=43189727) +2228 train 3.288252 (lr=9.0352e-05) (hash(x)=41260835) +2229 train 3.338972 (lr=9.0133e-05) (hash(x)=40279889) +2230 train 3.303335 (lr=8.9916e-05) (hash(x)=34349836) +2231 train 3.404154 (lr=8.9698e-05) (hash(x)=43659836) +2232 train 3.557029 (lr=8.9482e-05) (hash(x)=41371224) +2233 train 3.544271 (lr=8.9267e-05) (hash(x)=40095109) +2234 train 3.495068 (lr=8.9052e-05) (hash(x)=44732386) +2235 train 3.499290 (lr=8.8838e-05) (hash(x)=39336232) +2236 train 3.543629 (lr=8.8624e-05) (hash(x)=42262216) +2237 train 3.473300 (lr=8.8412e-05) (hash(x)=35939310) +2238 train 3.528005 (lr=8.8200e-05) (hash(x)=38110056) +2239 train 3.554132 (lr=8.7989e-05) (hash(x)=35313812) +2240 train 3.522755 (lr=8.7779e-05) (hash(x)=44131718) +2241 train 3.475949 (lr=8.7569e-05) (hash(x)=39662033) +2242 train 3.504891 (lr=8.7360e-05) (hash(x)=42530009) +2243 train 3.524139 (lr=8.7152e-05) (hash(x)=37812745) +2244 train 3.479420 (lr=8.6945e-05) (hash(x)=34489661) +2245 train 3.505593 (lr=8.6738e-05) (hash(x)=37452897) +2246 train 3.539934 (lr=8.6533e-05) (hash(x)=39635595) +2247 train 3.482299 (lr=8.6328e-05) (hash(x)=39264191) +2248 train 3.509848 (lr=8.6123e-05) (hash(x)=39173207) +2249 train 3.502130 (lr=8.5920e-05) (hash(x)=37554995) +2250 val loss 3.4857 +2250 val perplexity 32.6448 +2250 train 3.485457 (lr=8.5717e-05) (hash(x)=33661894) +2251 train 3.434894 (lr=8.5515e-05) (hash(x)=39445522) +2252 train 3.517654 (lr=8.5314e-05) (hash(x)=39089984) +2253 train 3.449229 (lr=8.5113e-05) (hash(x)=43323693) +2254 train 3.420841 (lr=8.4913e-05) (hash(x)=44445962) +2255 train 3.425032 (lr=8.4714e-05) (hash(x)=46631822) +2256 train 3.513489 (lr=8.4516e-05) (hash(x)=44637421) +2257 train 3.431263 (lr=8.4319e-05) (hash(x)=41434842) +2258 train 3.416781 (lr=8.4122e-05) (hash(x)=29677575) +2259 train 3.455940 (lr=8.3926e-05) (hash(x)=44351984) +2260 train 3.490329 (lr=8.3731e-05) (hash(x)=35164100) +2261 train 3.353348 (lr=8.3536e-05) (hash(x)=42494065) +2262 train 3.519757 (lr=8.3343e-05) (hash(x)=37378391) +2263 train 3.425682 (lr=8.3150e-05) (hash(x)=42739424) +2264 train 3.443134 (lr=8.2958e-05) (hash(x)=38137188) +2265 train 3.450404 (lr=8.2766e-05) (hash(x)=37818425) +2266 train 3.376328 (lr=8.2576e-05) (hash(x)=40908988) +2267 train 3.273186 (lr=8.2386e-05) (hash(x)=39052586) +2268 train 3.269928 (lr=8.2197e-05) (hash(x)=37621852) +2269 train 3.293233 (lr=8.2009e-05) (hash(x)=40524569) +2270 train 3.335417 (lr=8.1821e-05) (hash(x)=38523217) +2271 train 3.537995 (lr=8.1634e-05) (hash(x)=44010980) +2272 train 3.318977 (lr=8.1448e-05) (hash(x)=37453332) +2273 train 3.281454 (lr=8.1263e-05) (hash(x)=36331695) +2274 train 3.363123 (lr=8.1079e-05) (hash(x)=40681300) +2275 val loss 3.4892 +2275 val perplexity 32.7613 +2275 train 3.336379 (lr=8.0895e-05) (hash(x)=45013743) +2276 train 3.366558 (lr=8.0712e-05) (hash(x)=42437143) +2277 train 3.310879 (lr=8.0530e-05) (hash(x)=49061161) +2278 train 3.376388 (lr=8.0348e-05) (hash(x)=38501713) +2279 train 3.486764 (lr=8.0168e-05) (hash(x)=40223096) +2280 train 3.541595 (lr=7.9988e-05) (hash(x)=40931321) +2281 train 3.566038 (lr=7.9809e-05) (hash(x)=42966797) +2282 train 3.481232 (lr=7.9631e-05) (hash(x)=40620210) +2283 train 3.500033 (lr=7.9453e-05) (hash(x)=42845804) +2284 train 3.510804 (lr=7.9276e-05) (hash(x)=44905297) +2285 train 3.486172 (lr=7.9101e-05) (hash(x)=36885724) +2286 train 3.534862 (lr=7.8925e-05) (hash(x)=56162744) +2287 train 3.548485 (lr=7.8751e-05) (hash(x)=42597545) +2288 train 3.503032 (lr=7.8577e-05) (hash(x)=39755733) +2289 train 3.587567 (lr=7.8405e-05) (hash(x)=41072552) +2290 train 3.488083 (lr=7.8232e-05) (hash(x)=39270301) +2291 train 3.516464 (lr=7.8061e-05) (hash(x)=46127200) +2292 train 3.473129 (lr=7.7891e-05) (hash(x)=40267970) +2293 train 3.518964 (lr=7.7721e-05) (hash(x)=39371567) +2294 train 3.553862 (lr=7.7552e-05) (hash(x)=44107558) +2295 train 3.525681 (lr=7.7384e-05) (hash(x)=40140266) +2296 train 3.469390 (lr=7.7217e-05) (hash(x)=41491085) +2297 train 3.504817 (lr=7.7050e-05) (hash(x)=38322750) +2298 train 3.458256 (lr=7.6884e-05) (hash(x)=41538929) +2299 train 3.500552 (lr=7.6719e-05) (hash(x)=39181354) +2300 val loss 3.4804 +2300 val perplexity 32.4726 +2300 train 3.446026 (lr=7.6555e-05) (hash(x)=44088577) +2301 train 3.470631 (lr=7.6392e-05) (hash(x)=39775421) +2302 train 3.484969 (lr=7.6229e-05) (hash(x)=44116783) +2303 train 3.392590 (lr=7.6067e-05) (hash(x)=45671814) +2304 train 3.447606 (lr=7.5906e-05) (hash(x)=39178293) +2305 train 3.398934 (lr=7.5746e-05) (hash(x)=35488910) +2306 train 3.493495 (lr=7.5586e-05) (hash(x)=42794906) +2307 train 3.412974 (lr=7.5427e-05) (hash(x)=42301952) +2308 train 3.439382 (lr=7.5269e-05) (hash(x)=35419368) +2309 train 3.572668 (lr=7.5112e-05) (hash(x)=35389472) +2310 train 3.434715 (lr=7.4956e-05) (hash(x)=38574215) +2311 train 3.483020 (lr=7.4800e-05) (hash(x)=41163449) +2312 train 3.351832 (lr=7.4646e-05) (hash(x)=34418480) +2313 train 3.301422 (lr=7.4492e-05) (hash(x)=40130410) +2314 train 3.263746 (lr=7.4338e-05) (hash(x)=42208482) +2315 train 3.350759 (lr=7.4186e-05) (hash(x)=42549172) +2316 train 3.304806 (lr=7.4034e-05) (hash(x)=35073879) +2317 train 3.327575 (lr=7.3884e-05) (hash(x)=35367836) +2318 train 3.269464 (lr=7.3734e-05) (hash(x)=41014136) +2319 train 3.264832 (lr=7.3584e-05) (hash(x)=37998581) +2320 train 3.333715 (lr=7.3436e-05) (hash(x)=35372925) +2321 train 3.340719 (lr=7.3288e-05) (hash(x)=38519887) +2322 train 3.272811 (lr=7.3141e-05) (hash(x)=41257966) +2323 train 3.284635 (lr=7.2995e-05) (hash(x)=42037371) +2324 train 3.451016 (lr=7.2850e-05) (hash(x)=39235758) +2325 val loss 3.4815 +2325 val perplexity 32.5075 +2325 train 3.484147 (lr=7.2706e-05) (hash(x)=45173507) +2326 train 3.539394 (lr=7.2562e-05) (hash(x)=38343017) +2327 train 3.536554 (lr=7.2419e-05) (hash(x)=43361196) +2328 train 3.476282 (lr=7.2277e-05) (hash(x)=47065062) +2329 train 3.511485 (lr=7.2136e-05) (hash(x)=39936772) +2330 train 3.511969 (lr=7.1995e-05) (hash(x)=39427821) +2331 train 3.518562 (lr=7.1856e-05) (hash(x)=44534008) +2332 train 3.721654 (lr=7.1717e-05) (hash(x)=40982711) +2333 train 3.503712 (lr=7.1579e-05) (hash(x)=41772599) +2334 train 3.522501 (lr=7.1441e-05) (hash(x)=42638680) +2335 train 3.502686 (lr=7.1305e-05) (hash(x)=41106142) +2336 train 3.473300 (lr=7.1169e-05) (hash(x)=36747042) +2337 train 3.440464 (lr=7.1034e-05) (hash(x)=43139061) +2338 train 3.540678 (lr=7.0900e-05) (hash(x)=41915888) +2339 train 3.565990 (lr=7.0767e-05) (hash(x)=36363186) +2340 train 3.489214 (lr=7.0635e-05) (hash(x)=40470037) +2341 train 3.457186 (lr=7.0503e-05) (hash(x)=39044959) +2342 train 3.478046 (lr=7.0372e-05) (hash(x)=46296982) +2343 train 3.470668 (lr=7.0242e-05) (hash(x)=41443712) +2344 train 3.503165 (lr=7.0113e-05) (hash(x)=43040339) +2345 train 3.496919 (lr=6.9984e-05) (hash(x)=40784534) +2346 train 3.417346 (lr=6.9857e-05) (hash(x)=40448838) +2347 train 3.432849 (lr=6.9730e-05) (hash(x)=38104322) +2348 train 3.465298 (lr=6.9604e-05) (hash(x)=49240801) +2349 train 3.451904 (lr=6.9479e-05) (hash(x)=39552376) +2350 val loss 3.4762 +2350 val perplexity 32.3356 +2350 train 3.482195 (lr=6.9354e-05) (hash(x)=40472646) +2351 train 3.452404 (lr=6.9231e-05) (hash(x)=43833919) +2352 train 3.429232 (lr=6.9108e-05) (hash(x)=39851167) +2353 train 3.396115 (lr=6.8986e-05) (hash(x)=38628746) +2354 train 3.410411 (lr=6.8865e-05) (hash(x)=43790122) +2355 train 3.444836 (lr=6.8744e-05) (hash(x)=37547414) +2356 train 3.507251 (lr=6.8625e-05) (hash(x)=39609842) +2357 train 3.385866 (lr=6.8506e-05) (hash(x)=49933969) +2358 train 3.327290 (lr=6.8388e-05) (hash(x)=39851917) +2359 train 3.236592 (lr=6.8271e-05) (hash(x)=38472874) +2360 train 3.277196 (lr=6.8155e-05) (hash(x)=41488512) +2361 train 3.236726 (lr=6.8039e-05) (hash(x)=41211956) +2362 train 3.261045 (lr=6.7925e-05) (hash(x)=39677464) +2363 train 3.310220 (lr=6.7811e-05) (hash(x)=40091818) +2364 train 3.299831 (lr=6.7698e-05) (hash(x)=26519827) +2365 train 3.278245 (lr=6.7585e-05) (hash(x)=35373392) +2366 train 3.295583 (lr=6.7474e-05) (hash(x)=39129827) +2367 train 3.265746 (lr=6.7363e-05) (hash(x)=35904907) +2368 train 3.314778 (lr=6.7254e-05) (hash(x)=34949359) +2369 train 3.415097 (lr=6.7145e-05) (hash(x)=39207995) +2370 train 3.528470 (lr=6.7036e-05) (hash(x)=37073702) +2371 train 3.520937 (lr=6.6929e-05) (hash(x)=48110053) +2372 train 3.539064 (lr=6.6822e-05) (hash(x)=41385138) +2373 train 3.554958 (lr=6.6717e-05) (hash(x)=42840572) +2374 train 3.468048 (lr=6.6612e-05) (hash(x)=41175659) +2375 val loss 3.4751 +2375 val perplexity 32.3017 +2375 train 3.503218 (lr=6.6508e-05) (hash(x)=41525643) +2376 train 3.515576 (lr=6.6404e-05) (hash(x)=38843110) +2377 train 3.469164 (lr=6.6302e-05) (hash(x)=40490088) +2378 train 3.615451 (lr=6.6200e-05) (hash(x)=38771577) +2379 train 3.502278 (lr=6.6099e-05) (hash(x)=41681603) +2380 train 3.486763 (lr=6.5999e-05) (hash(x)=38643935) +2381 train 3.438914 (lr=6.5900e-05) (hash(x)=37682160) +2382 train 3.459429 (lr=6.5802e-05) (hash(x)=43054289) +2383 train 3.491763 (lr=6.5704e-05) (hash(x)=41332596) +2384 train 3.516998 (lr=6.5607e-05) (hash(x)=37730100) +2385 train 3.496620 (lr=6.5511e-05) (hash(x)=42581052) +2386 train 3.521285 (lr=6.5416e-05) (hash(x)=40049621) +2387 train 3.501640 (lr=6.5322e-05) (hash(x)=33256413) +2388 train 3.455670 (lr=6.5229e-05) (hash(x)=39361052) +2389 train 3.498215 (lr=6.5136e-05) (hash(x)=35457753) +2390 train 3.461458 (lr=6.5044e-05) (hash(x)=39163930) +2391 train 3.473210 (lr=6.4953e-05) (hash(x)=43563621) +2392 train 3.439571 (lr=6.4863e-05) (hash(x)=41951801) +2393 train 3.518830 (lr=6.4774e-05) (hash(x)=36653386) +2394 train 3.468594 (lr=6.4685e-05) (hash(x)=38775505) +2395 train 3.419482 (lr=6.4597e-05) (hash(x)=39670992) +2396 train 3.426459 (lr=6.4510e-05) (hash(x)=41025923) +2397 train 3.426970 (lr=6.4424e-05) (hash(x)=36938766) +2398 train 3.415904 (lr=6.4339e-05) (hash(x)=36487864) +2399 train 3.360934 (lr=6.4255e-05) (hash(x)=39374702) +2400 val loss 3.4732 +2400 val perplexity 32.2389 +2400 train 3.428086 (lr=6.4171e-05) (hash(x)=40359855) +2401 train 3.454748 (lr=6.4088e-05) (hash(x)=41418553) +2402 train 3.438181 (lr=6.4006e-05) (hash(x)=43344745) +2403 train 3.300122 (lr=6.3925e-05) (hash(x)=44695896) +2404 train 3.254824 (lr=6.3845e-05) (hash(x)=47678932) +2405 train 3.278430 (lr=6.3765e-05) (hash(x)=40718584) +2406 train 3.286399 (lr=6.3687e-05) (hash(x)=43106249) +2407 train 3.223525 (lr=6.3609e-05) (hash(x)=47021181) +2408 train 3.199786 (lr=6.3532e-05) (hash(x)=41568914) +2409 train 3.311039 (lr=6.3456e-05) (hash(x)=44237601) +2410 train 3.222852 (lr=6.3380e-05) (hash(x)=38601938) +2411 train 3.282460 (lr=6.3306e-05) (hash(x)=36871866) +2412 train 3.286951 (lr=6.3232e-05) (hash(x)=37657167) +2413 train 3.333930 (lr=6.3159e-05) (hash(x)=38066246) +2414 train 3.314653 (lr=6.3087e-05) (hash(x)=39247954) +2415 train 3.400836 (lr=6.3016e-05) (hash(x)=43174705) +2416 train 3.504103 (lr=6.2945e-05) (hash(x)=38014839) +2417 train 3.503571 (lr=6.2876e-05) (hash(x)=44558384) +2418 train 3.408098 (lr=6.2807e-05) (hash(x)=45620143) +2419 train 3.497142 (lr=6.2739e-05) (hash(x)=40581412) +2420 train 3.449421 (lr=6.2672e-05) (hash(x)=38119590) +2421 train 3.416629 (lr=6.2606e-05) (hash(x)=44656490) +2422 train 3.476480 (lr=6.2540e-05) (hash(x)=41948580) +2423 train 3.453336 (lr=6.2476e-05) (hash(x)=42293774) +2424 train 3.489816 (lr=6.2412e-05) (hash(x)=42740194) +2425 val loss 3.4701 +2425 val perplexity 32.1407 +2425 train 3.452473 (lr=6.2349e-05) (hash(x)=35215415) +2426 train 3.485325 (lr=6.2287e-05) (hash(x)=42075407) +2427 train 3.521256 (lr=6.2225e-05) (hash(x)=36734855) +2428 train 3.481723 (lr=6.2165e-05) (hash(x)=39357673) +2429 train 3.477429 (lr=6.2105e-05) (hash(x)=45665315) +2430 train 3.484104 (lr=6.2046e-05) (hash(x)=45360162) +2431 train 3.464130 (lr=6.1988e-05) (hash(x)=36345631) +2432 train 3.537596 (lr=6.1931e-05) (hash(x)=38667711) +2433 train 3.478508 (lr=6.1875e-05) (hash(x)=41585046) +2434 train 3.515662 (lr=6.1820e-05) (hash(x)=34089922) +2435 train 3.475208 (lr=6.1765e-05) (hash(x)=36249096) +2436 train 3.598841 (lr=6.1711e-05) (hash(x)=36896709) +2437 train 3.462548 (lr=6.1658e-05) (hash(x)=42984234) +2438 train 3.448741 (lr=6.1606e-05) (hash(x)=36909211) +2439 train 3.489091 (lr=6.1555e-05) (hash(x)=39204104) +2440 train 3.450736 (lr=6.1504e-05) (hash(x)=43244742) +2441 train 3.441318 (lr=6.1454e-05) (hash(x)=45664030) +2442 train 3.437394 (lr=6.1406e-05) (hash(x)=36861518) +2443 train 3.386029 (lr=6.1358e-05) (hash(x)=36644509) +2444 train 3.427694 (lr=6.1310e-05) (hash(x)=38481467) +2445 train 3.455888 (lr=6.1264e-05) (hash(x)=38785748) +2446 train 3.455021 (lr=6.1218e-05) (hash(x)=38566154) +2447 train 3.469810 (lr=6.1174e-05) (hash(x)=34848234) +2448 train 3.428103 (lr=6.1130e-05) (hash(x)=42552984) +2449 train 3.459350 (lr=6.1087e-05) (hash(x)=41920697) +2450 val loss 3.4689 +2450 val perplexity 32.1007 +2450 train 3.378489 (lr=6.1045e-05) (hash(x)=42607207) +2451 train 3.331685 (lr=6.1003e-05) (hash(x)=45600382) +2452 train 3.262958 (lr=6.0963e-05) (hash(x)=42303814) +2453 train 3.268775 (lr=6.0923e-05) (hash(x)=37754809) +2454 train 3.301906 (lr=6.0884e-05) (hash(x)=50510514) +2455 train 3.324005 (lr=6.0846e-05) (hash(x)=39631632) +2456 train 3.258786 (lr=6.0809e-05) (hash(x)=39542965) +2457 train 3.287796 (lr=6.0773e-05) (hash(x)=47227773) +2458 train 3.283774 (lr=6.0737e-05) (hash(x)=41555136) +2459 train 3.243697 (lr=6.0703e-05) (hash(x)=37987511) +2460 train 3.298467 (lr=6.0669e-05) (hash(x)=47820500) +2461 train 3.286315 (lr=6.0636e-05) (hash(x)=36633320) +2462 train 3.247951 (lr=6.0604e-05) (hash(x)=39080956) +2463 train 3.437802 (lr=6.0572e-05) (hash(x)=39816880) +2464 train 3.487874 (lr=6.0542e-05) (hash(x)=41546985) +2465 train 3.452911 (lr=6.0512e-05) (hash(x)=40136660) +2466 train 3.441544 (lr=6.0483e-05) (hash(x)=38768466) +2467 train 3.543539 (lr=6.0455e-05) (hash(x)=41076857) +2468 train 3.424929 (lr=6.0428e-05) (hash(x)=38220910) +2469 train 3.498156 (lr=6.0402e-05) (hash(x)=41858115) +2470 train 3.492936 (lr=6.0376e-05) (hash(x)=42643830) +2471 train 3.424304 (lr=6.0352e-05) (hash(x)=40012740) +2472 train 3.475295 (lr=6.0328e-05) (hash(x)=47724676) +2473 train 3.468166 (lr=6.0305e-05) (hash(x)=37673376) +2474 train 3.449678 (lr=6.0283e-05) (hash(x)=41184244) +2475 val loss 3.4661 +2475 val perplexity 32.0119 +2475 train 3.489268 (lr=6.0261e-05) (hash(x)=41208712) +2476 train 3.494833 (lr=6.0241e-05) (hash(x)=37476115) +2477 train 3.515890 (lr=6.0221e-05) (hash(x)=45094862) +2478 train 3.467008 (lr=6.0202e-05) (hash(x)=42035877) +2479 train 3.464045 (lr=6.0184e-05) (hash(x)=32818452) +2480 train 3.486079 (lr=6.0167e-05) (hash(x)=38740496) +2481 train 3.455403 (lr=6.0151e-05) (hash(x)=40095438) +2482 train 3.491903 (lr=6.0135e-05) (hash(x)=36369368) +2483 train 3.440755 (lr=6.0121e-05) (hash(x)=39894690) +2484 train 3.533568 (lr=6.0107e-05) (hash(x)=41848021) +2485 train 3.458566 (lr=6.0094e-05) (hash(x)=42083852) +2486 train 3.401711 (lr=6.0082e-05) (hash(x)=38232447) +2487 train 3.439260 (lr=6.0071e-05) (hash(x)=42419644) +2488 train 3.437687 (lr=6.0060e-05) (hash(x)=39230466) +2489 train 3.430784 (lr=6.0051e-05) (hash(x)=40425139) +2490 train 3.434643 (lr=6.0042e-05) (hash(x)=37570869) +2491 train 3.413746 (lr=6.0034e-05) (hash(x)=46289361) +2492 train 3.416671 (lr=6.0027e-05) (hash(x)=34602623) +2493 train 3.414483 (lr=6.0020e-05) (hash(x)=31949816) +2494 train 3.508740 (lr=6.0015e-05) (hash(x)=38674716) +2495 train 3.432242 (lr=6.0010e-05) (hash(x)=37444182) +2496 train 3.451755 (lr=6.0007e-05) (hash(x)=41118074) +2497 train 3.383641 (lr=6.0004e-05) (hash(x)=39346392) +2498 train 3.310288 (lr=6.0002e-05) (hash(x)=43799216) +2499 val loss 3.4670 +2499 val perplexity 32.0397 +2499 train 3.213573 (lr=6.0000e-05) (hash(x)=35849200)