diff --git "a/lr4e-4_total_batch_size20480_seq_len128/log2.txt" "b/lr4e-4_total_batch_size20480_seq_len128/log2.txt" --- "a/lr4e-4_total_batch_size20480_seq_len128/log2.txt" +++ "b/lr4e-4_total_batch_size20480_seq_len128/log2.txt" @@ -4,1040 +4,1040 @@ max_steps: 1000 0 train 11.700421 (lr=1.3986e-06) (hash(x)=5113283) 1 train 11.672828 (lr=2.7972e-06) (hash(x)=5534142) 2 train 11.699075 (lr=4.1958e-06) (hash(x)=6763231) -3 train 11.663286 (lr=5.5944e-06) (hash(x)=6328012) -4 train 11.656357 (lr=6.9930e-06) (hash(x)=7052161) -5 train 11.640671 (lr=8.3916e-06) (hash(x)=5556098) -6 train 11.608338 (lr=9.7902e-06) (hash(x)=4696943) -7 train 11.559019 (lr=1.1189e-05) (hash(x)=6219138) -8 train 11.508968 (lr=1.2587e-05) (hash(x)=6049878) -9 train 11.499625 (lr=1.3986e-05) (hash(x)=5491972) -10 train 11.449233 (lr=1.5385e-05) (hash(x)=8075458) -11 train 11.378419 (lr=1.6783e-05) (hash(x)=5917741) -12 train 11.348023 (lr=1.8182e-05) (hash(x)=5750403) -13 train 11.303619 (lr=1.9580e-05) (hash(x)=6112458) -14 train 11.241801 (lr=2.0979e-05) (hash(x)=5806490) -15 train 11.150006 (lr=2.2378e-05) (hash(x)=6568379) -16 train 11.067209 (lr=2.3776e-05) (hash(x)=7212403) -17 train 10.995203 (lr=2.5175e-05) (hash(x)=7386082) -18 train 10.955493 (lr=2.6573e-05) (hash(x)=6359743) -19 train 10.880232 (lr=2.7972e-05) (hash(x)=6151674) -20 train 10.850606 (lr=2.9371e-05) (hash(x)=7168704) -21 train 10.788665 (lr=3.0769e-05) (hash(x)=7859060) -22 train 10.694252 (lr=3.2168e-05) (hash(x)=6976239) -23 train 10.683619 (lr=3.3566e-05) (hash(x)=6391506) -24 train 10.643327 (lr=3.4965e-05) (hash(x)=5245999) -25 train 10.593281 (lr=3.6364e-05) (hash(x)=5985675) -26 train 10.498267 (lr=3.7762e-05) (hash(x)=4355733) -27 train 10.631542 (lr=3.9161e-05) (hash(x)=6984772) -28 train 10.496611 (lr=4.0559e-05) (hash(x)=6244096) -29 train 10.495267 (lr=4.1958e-05) (hash(x)=6603717) -30 train 10.398873 (lr=4.3357e-05) (hash(x)=5669522) -31 train 10.381268 (lr=4.4755e-05) (hash(x)=6190579) -32 train 10.434013 (lr=4.6154e-05) (hash(x)=4912983) -33 train 10.316533 (lr=4.7552e-05) (hash(x)=7276303) -34 train 10.372952 (lr=4.8951e-05) (hash(x)=5479947) -35 train 10.459206 (lr=5.0350e-05) (hash(x)=6630378) -36 train 10.396424 (lr=5.1748e-05) (hash(x)=8097010) -37 train 10.448638 (lr=5.3147e-05) (hash(x)=9989744) -38 train 10.327752 (lr=5.4545e-05) (hash(x)=6694932) -39 train 10.256584 (lr=5.5944e-05) (hash(x)=6317894) -40 train 10.175003 (lr=5.7343e-05) (hash(x)=5046327) -41 train 10.250850 (lr=5.8741e-05) (hash(x)=7947703) -42 train 10.121830 (lr=6.0140e-05) (hash(x)=5916068) -43 train 10.215761 (lr=6.1538e-05) (hash(x)=5777498) -44 train 10.148030 (lr=6.2937e-05) (hash(x)=5753092) -45 train 10.130989 (lr=6.4336e-05) (hash(x)=7723226) -46 train 10.124299 (lr=6.5734e-05) (hash(x)=7007016) -47 train 10.047805 (lr=6.7133e-05) (hash(x)=6491229) -48 train 10.097555 (lr=6.8531e-05) (hash(x)=6390752) -49 train 10.204393 (lr=6.9930e-05) (hash(x)=6019389) -50 val loss 10.0811 -50 val perplexity 23886.7793 -50 train 10.069889 (lr=7.1329e-05) (hash(x)=7662067) -51 train 10.069789 (lr=7.2727e-05) (hash(x)=4648609) -52 train 10.007125 (lr=7.4126e-05) (hash(x)=4725966) -53 train 9.967831 (lr=7.5524e-05) (hash(x)=5558355) -54 train 10.001527 (lr=7.6923e-05) (hash(x)=6524933) -55 train 9.953378 (lr=7.8322e-05) (hash(x)=6369326) -56 train 9.915675 (lr=7.9720e-05) (hash(x)=6022625) -57 train 9.855737 (lr=8.1119e-05) (hash(x)=4906853) -58 train 9.688809 (lr=8.2517e-05) (hash(x)=5589269) -59 train 9.800064 (lr=8.3916e-05) (hash(x)=6437376) -60 train 9.826277 (lr=8.5315e-05) (hash(x)=7304892) -61 train 9.777195 (lr=8.6713e-05) (hash(x)=7084093) -62 train 9.788608 (lr=8.8112e-05) (hash(x)=5908178) -63 train 9.581896 (lr=8.9510e-05) (hash(x)=7048804) -64 train 9.655831 (lr=9.0909e-05) (hash(x)=6085549) -65 train 9.653721 (lr=9.2308e-05) (hash(x)=5752594) -66 train 9.456213 (lr=9.3706e-05) (hash(x)=7662769) -67 train 9.309429 (lr=9.5105e-05) (hash(x)=6393520) -68 train 9.551364 (lr=9.6503e-05) (hash(x)=5942867) -69 train 9.532688 (lr=9.7902e-05) (hash(x)=6793550) -70 train 9.377486 (lr=9.9301e-05) (hash(x)=7105976) -71 train 9.401495 (lr=1.0070e-04) (hash(x)=6581348) -72 train 9.338243 (lr=1.0210e-04) (hash(x)=5555598) -73 train 9.265688 (lr=1.0350e-04) (hash(x)=6235837) -74 train 9.200271 (lr=1.0490e-04) (hash(x)=5591770) -75 train 9.390544 (lr=1.0629e-04) (hash(x)=7083021) -76 train 9.214975 (lr=1.0769e-04) (hash(x)=7281348) -77 train 9.240290 (lr=1.0909e-04) (hash(x)=6155821) -78 train 9.080822 (lr=1.1049e-04) (hash(x)=5736241) -79 train 8.993293 (lr=1.1189e-04) (hash(x)=5657123) -80 train 8.892729 (lr=1.1329e-04) (hash(x)=6452095) -81 train 8.879316 (lr=1.1469e-04) (hash(x)=5312267) -82 train 8.814240 (lr=1.1608e-04) (hash(x)=5434493) -83 train 8.938129 (lr=1.1748e-04) (hash(x)=6830813) -84 train 8.809291 (lr=1.1888e-04) (hash(x)=4752771) -85 train 8.839609 (lr=1.2028e-04) (hash(x)=6424933) -86 train 8.738819 (lr=1.2168e-04) (hash(x)=5786517) -87 train 8.764196 (lr=1.2308e-04) (hash(x)=6680023) -88 train 8.645253 (lr=1.2448e-04) (hash(x)=6474729) -89 train 8.689062 (lr=1.2587e-04) (hash(x)=7523279) -90 train 8.485591 (lr=1.2727e-04) (hash(x)=5508768) -91 train 8.615630 (lr=1.2867e-04) (hash(x)=6635925) -92 train 8.540660 (lr=1.3007e-04) (hash(x)=6663801) -93 train 8.502014 (lr=1.3147e-04) (hash(x)=5869441) -94 train 8.503474 (lr=1.3287e-04) (hash(x)=6698878) -95 train 8.440034 (lr=1.3427e-04) (hash(x)=6349004) -96 train 8.428391 (lr=1.3566e-04) (hash(x)=4986137) -97 train 8.213653 (lr=1.3706e-04) (hash(x)=6008454) -98 train 8.250460 (lr=1.3846e-04) (hash(x)=6550770) -99 train 8.353949 (lr=1.3986e-04) (hash(x)=7682741) -100 val loss 8.3184 -100 val perplexity 4098.7666 -100 train 8.396103 (lr=1.4126e-04) (hash(x)=7892158) -101 train 8.275209 (lr=1.4266e-04) (hash(x)=7794028) -102 train 8.269009 (lr=1.4406e-04) (hash(x)=7093523) -103 train 8.260232 (lr=1.4545e-04) (hash(x)=6166062) -104 train 8.194337 (lr=1.4685e-04) (hash(x)=6645781) -105 train 8.170750 (lr=1.4825e-04) (hash(x)=4811192) -106 train 8.084870 (lr=1.4965e-04) (hash(x)=5970866) -107 train 8.108835 (lr=1.5105e-04) (hash(x)=7822680) -108 train 8.034785 (lr=1.5245e-04) (hash(x)=6317317) -109 train 8.106247 (lr=1.5385e-04) (hash(x)=6431409) -110 train 8.122334 (lr=1.5524e-04) (hash(x)=6653337) -111 train 8.042282 (lr=1.5664e-04) (hash(x)=5323032) -112 train 7.955510 (lr=1.5804e-04) (hash(x)=5125339) -113 train 7.916279 (lr=1.5944e-04) (hash(x)=7363286) -114 train 8.207185 (lr=1.6084e-04) (hash(x)=7670050) -115 train 7.988898 (lr=1.6224e-04) (hash(x)=5616075) -116 train 8.030732 (lr=1.6364e-04) (hash(x)=6593764) -117 train 8.082897 (lr=1.6503e-04) (hash(x)=5672608) -118 train 7.939550 (lr=1.6643e-04) (hash(x)=6828653) -119 train 7.930516 (lr=1.6783e-04) (hash(x)=6839867) -120 train 8.023301 (lr=1.6923e-04) (hash(x)=8426992) -121 train 7.712131 (lr=1.7063e-04) (hash(x)=4916928) -122 train 7.917670 (lr=1.7203e-04) (hash(x)=6484050) -123 train 7.983311 (lr=1.7343e-04) (hash(x)=8353379) -124 train 7.881751 (lr=1.7483e-04) (hash(x)=6552510) -125 train 7.879014 (lr=1.7622e-04) (hash(x)=4838871) -126 train 7.617235 (lr=1.7762e-04) (hash(x)=3021697) -127 train 7.751260 (lr=1.7902e-04) (hash(x)=6795665) -128 train 7.748051 (lr=1.8042e-04) (hash(x)=5486935) -129 train 7.928158 (lr=1.8182e-04) (hash(x)=6678038) -130 train 7.940475 (lr=1.8322e-04) (hash(x)=6657714) -131 train 7.849248 (lr=1.8462e-04) (hash(x)=6112215) -132 train 7.868167 (lr=1.8601e-04) (hash(x)=8353143) -133 train 7.882381 (lr=1.8741e-04) (hash(x)=5915361) -134 train 7.779057 (lr=1.8881e-04) (hash(x)=6254885) -135 train 7.807247 (lr=1.9021e-04) (hash(x)=5771588) -136 train 7.778200 (lr=1.9161e-04) (hash(x)=5561507) -137 train 7.730793 (lr=1.9301e-04) (hash(x)=5688829) -138 train 7.696267 (lr=1.9441e-04) (hash(x)=5371951) -139 train 7.855422 (lr=1.9580e-04) (hash(x)=5443305) -140 train 7.853623 (lr=1.9720e-04) (hash(x)=5016757) -141 train 7.847708 (lr=1.9860e-04) (hash(x)=6901933) -142 train 7.797873 (lr=2.0000e-04) (hash(x)=6019085) -143 train 7.649871 (lr=2.0140e-04) (hash(x)=4294425) -144 train 7.747959 (lr=2.0280e-04) (hash(x)=6095229) -145 train 7.588701 (lr=2.0420e-04) (hash(x)=4363941) -146 train 7.664509 (lr=2.0559e-04) (hash(x)=4693798) -147 train 8.173172 (lr=2.0699e-04) (hash(x)=5486335) -148 train 7.993349 (lr=2.0839e-04) (hash(x)=7907450) -149 train 7.828030 (lr=2.0979e-04) (hash(x)=7295165) -150 val loss 7.7270 -150 val perplexity 2268.7385 -150 train 7.757653 (lr=2.1119e-04) (hash(x)=6814026) -151 train 7.846723 (lr=2.1259e-04) (hash(x)=6267424) -152 train 7.828159 (lr=2.1399e-04) (hash(x)=8086437) -153 train 7.879587 (lr=2.1538e-04) (hash(x)=5270452) -154 train 7.730044 (lr=2.1678e-04) (hash(x)=6420820) -155 train 7.628667 (lr=2.1818e-04) (hash(x)=6305297) -156 train 7.788452 (lr=2.1958e-04) (hash(x)=7889849) -157 train 8.134259 (lr=2.2098e-04) (hash(x)=6040077) -158 train 8.125292 (lr=2.2238e-04) (hash(x)=5652497) -159 train 7.714570 (lr=2.2378e-04) (hash(x)=7130251) -160 train 7.591569 (lr=2.2517e-04) (hash(x)=6610177) -161 train 7.643689 (lr=2.2657e-04) (hash(x)=6508350) -162 train 7.794116 (lr=2.2797e-04) (hash(x)=6994983) -163 train 7.741472 (lr=2.2937e-04) (hash(x)=5859576) -164 train 7.313273 (lr=2.3077e-04) (hash(x)=5487065) -165 train 7.542570 (lr=2.3217e-04) (hash(x)=4892065) -166 train 7.436973 (lr=2.3357e-04) (hash(x)=4933674) -167 train 7.707512 (lr=2.3497e-04) (hash(x)=7317289) -168 train 7.806946 (lr=2.3636e-04) (hash(x)=6811522) -169 train 7.634039 (lr=2.3776e-04) (hash(x)=5510218) -170 train 7.789076 (lr=2.3916e-04) (hash(x)=7304235) -171 train 7.947345 (lr=2.4056e-04) (hash(x)=6752265) -172 train 7.644037 (lr=2.4196e-04) (hash(x)=5994476) -173 train 7.613106 (lr=2.4336e-04) (hash(x)=6530867) -174 train 7.719955 (lr=2.4476e-04) (hash(x)=5746260) -175 train 7.669672 (lr=2.4615e-04) (hash(x)=5790078) -176 train 7.685869 (lr=2.4755e-04) (hash(x)=6430135) -177 train 7.755925 (lr=2.4895e-04) (hash(x)=7614023) -178 train 7.745198 (lr=2.5035e-04) (hash(x)=5244861) -179 train 7.718951 (lr=2.5175e-04) (hash(x)=5245146) -180 train 7.623196 (lr=2.5315e-04) (hash(x)=6415565) -181 train 7.671936 (lr=2.5455e-04) (hash(x)=5786972) -182 train 7.711048 (lr=2.5594e-04) (hash(x)=6131703) -183 train 7.731692 (lr=2.5734e-04) (hash(x)=6346459) -184 train 7.763904 (lr=2.5874e-04) (hash(x)=6504131) -185 train 7.757150 (lr=2.6014e-04) (hash(x)=5209234) -186 train 7.662239 (lr=2.6154e-04) (hash(x)=6163272) -187 train 7.664566 (lr=2.6294e-04) (hash(x)=5676768) -188 train 7.727629 (lr=2.6434e-04) (hash(x)=6090561) -189 train 7.876177 (lr=2.6573e-04) (hash(x)=5863092) -190 train 7.793953 (lr=2.6713e-04) (hash(x)=7201312) -191 train 7.870019 (lr=2.6853e-04) (hash(x)=7019489) -192 train 7.640486 (lr=2.6993e-04) (hash(x)=6225608) -193 train 7.726340 (lr=2.7133e-04) (hash(x)=5483019) -194 train 7.662089 (lr=2.7273e-04) (hash(x)=5903258) -195 train 7.703291 (lr=2.7413e-04) (hash(x)=5968716) -196 train 7.695203 (lr=2.7552e-04) (hash(x)=5778017) -197 train 7.426719 (lr=2.7692e-04) (hash(x)=7780194) -198 train 7.632934 (lr=2.7832e-04) (hash(x)=6140998) -199 train 7.620529 (lr=2.7972e-04) (hash(x)=3784321) -200 val loss 7.6541 -200 val perplexity 2109.2607 -200 train 7.648793 (lr=2.8112e-04) (hash(x)=5860821) -201 train 7.695865 (lr=2.8252e-04) (hash(x)=7774109) -202 train 7.862022 (lr=2.8392e-04) (hash(x)=7997664) -203 train 7.839151 (lr=2.8531e-04) (hash(x)=6576749) -204 train 7.745502 (lr=2.8671e-04) (hash(x)=7266655) -205 train 7.705393 (lr=2.8811e-04) (hash(x)=7072404) -206 train 7.620603 (lr=2.8951e-04) (hash(x)=6626459) -207 train 7.640181 (lr=2.9091e-04) (hash(x)=6556025) -208 train 7.670080 (lr=2.9231e-04) (hash(x)=5942129) -209 train 7.773512 (lr=2.9371e-04) (hash(x)=7325027) -210 train 7.769457 (lr=2.9510e-04) (hash(x)=7322467) -211 train 7.707861 (lr=2.9650e-04) (hash(x)=6373412) -212 train 7.487411 (lr=2.9790e-04) (hash(x)=7332255) -213 train 7.769811 (lr=2.9930e-04) (hash(x)=5262868) -214 train 7.481462 (lr=3.0070e-04) (hash(x)=5688247) -215 train 7.656564 (lr=3.0210e-04) (hash(x)=8055563) -216 train 7.666641 (lr=3.0350e-04) (hash(x)=5352405) -217 train 7.719462 (lr=3.0490e-04) (hash(x)=5932790) -218 train 7.671588 (lr=3.0629e-04) (hash(x)=6249312) -219 train 7.631391 (lr=3.0769e-04) (hash(x)=5680154) -220 train 7.730334 (lr=3.0909e-04) (hash(x)=8156280) -221 train 7.675781 (lr=3.1049e-04) (hash(x)=5914217) -222 train 7.517913 (lr=3.1189e-04) (hash(x)=7120215) -223 train 7.699361 (lr=3.1329e-04) (hash(x)=6424128) -224 train 7.449519 (lr=3.1469e-04) (hash(x)=4390027) -225 train 7.652171 (lr=3.1608e-04) (hash(x)=7804089) -226 train 7.747726 (lr=3.1748e-04) (hash(x)=7130267) -227 train 7.547658 (lr=3.1888e-04) (hash(x)=6490149) -228 train 7.601025 (lr=3.2028e-04) (hash(x)=9276378) -229 train 7.637883 (lr=3.2168e-04) (hash(x)=6283540) -230 train 7.616992 (lr=3.2308e-04) (hash(x)=5781680) -231 train 7.560999 (lr=3.2448e-04) (hash(x)=5728337) -232 train 7.546410 (lr=3.2587e-04) (hash(x)=6278202) -233 train 7.648108 (lr=3.2727e-04) (hash(x)=7400272) -234 train 7.611826 (lr=3.2867e-04) (hash(x)=5795128) -235 train 7.589363 (lr=3.3007e-04) (hash(x)=6473432) -236 train 7.605611 (lr=3.3147e-04) (hash(x)=5201502) -237 train 7.831241 (lr=3.3287e-04) (hash(x)=6922646) -238 train 7.539192 (lr=3.3427e-04) (hash(x)=5484641) -239 train 7.610104 (lr=3.3566e-04) (hash(x)=7277141) -240 train 7.605514 (lr=3.3706e-04) (hash(x)=5604614) -241 train 7.660578 (lr=3.3846e-04) (hash(x)=7443124) -242 train 7.677866 (lr=3.3986e-04) (hash(x)=5601968) -243 train 7.572083 (lr=3.4126e-04) (hash(x)=5632735) -244 train 7.565017 (lr=3.4266e-04) (hash(x)=5594810) -245 train 7.418117 (lr=3.4406e-04) (hash(x)=5881015) -246 train 7.574681 (lr=3.4545e-04) (hash(x)=6865361) -247 train 7.673841 (lr=3.4685e-04) (hash(x)=5809411) -248 train 7.631116 (lr=3.4825e-04) (hash(x)=6293025) -249 train 7.576523 (lr=3.4965e-04) (hash(x)=7232964) -250 val loss 7.5903 -250 val perplexity 1978.9337 -250 train 7.521509 (lr=3.5105e-04) (hash(x)=5646619) -251 train 7.637913 (lr=3.5245e-04) (hash(x)=6171829) -252 train 7.682011 (lr=3.5385e-04) (hash(x)=7787552) -253 train 7.628629 (lr=3.5524e-04) (hash(x)=5884456) -254 train 7.660127 (lr=3.5664e-04) (hash(x)=6752162) -255 train 7.570142 (lr=3.5804e-04) (hash(x)=5077031) -256 train 7.745372 (lr=3.5944e-04) (hash(x)=6883481) -257 train 7.630184 (lr=3.6084e-04) (hash(x)=6248895) -258 train 7.495297 (lr=3.6224e-04) (hash(x)=6636615) -259 train 7.691655 (lr=3.6364e-04) (hash(x)=6918004) -260 train 7.614872 (lr=3.6503e-04) (hash(x)=7302874) -261 train 7.718871 (lr=3.6643e-04) (hash(x)=6482466) -262 train 7.554568 (lr=3.6783e-04) (hash(x)=7298317) -263 train 7.597640 (lr=3.6923e-04) (hash(x)=6588573) -264 train 7.590458 (lr=3.7063e-04) (hash(x)=6229630) -265 train 7.670510 (lr=3.7203e-04) (hash(x)=6136939) -266 train 7.430586 (lr=3.7343e-04) (hash(x)=6394645) -267 train 7.649239 (lr=3.7483e-04) (hash(x)=7040157) -268 train 7.694551 (lr=3.7622e-04) (hash(x)=7041858) -269 train 7.601514 (lr=3.7762e-04) (hash(x)=6455595) -270 train 7.527848 (lr=3.7902e-04) (hash(x)=6480443) -271 train 7.705554 (lr=3.8042e-04) (hash(x)=4122983) -272 train 7.526193 (lr=3.8182e-04) (hash(x)=7672190) -273 train 7.558549 (lr=3.8322e-04) (hash(x)=4724052) -274 train 7.516334 (lr=3.8462e-04) (hash(x)=6654267) -275 train 7.504004 (lr=3.8601e-04) (hash(x)=6820797) -276 train 7.572878 (lr=3.8741e-04) (hash(x)=6458662) -277 train 7.959230 (lr=3.8881e-04) (hash(x)=7477594) -278 train 7.626729 (lr=3.9021e-04) (hash(x)=5876574) -279 train 7.350047 (lr=3.9161e-04) (hash(x)=6146305) -280 train 7.519811 (lr=3.9301e-04) (hash(x)=6162080) -281 train 7.486890 (lr=3.9441e-04) (hash(x)=6814831) -282 train 7.618848 (lr=3.9580e-04) (hash(x)=7138295) -283 train 7.408764 (lr=3.9720e-04) (hash(x)=5548298) -284 train 7.497830 (lr=3.9860e-04) (hash(x)=6265078) -285 train 7.869653 (lr=4.0000e-04) (hash(x)=7609416) -286 train 7.565840 (lr=4.0000e-04) (hash(x)=6909367) -287 train 7.667139 (lr=4.0000e-04) (hash(x)=7574342) -288 train 7.482962 (lr=3.9999e-04) (hash(x)=8859748) -289 train 7.437656 (lr=3.9998e-04) (hash(x)=5906937) -290 train 7.448060 (lr=3.9997e-04) (hash(x)=7243024) -291 train 7.568493 (lr=3.9996e-04) (hash(x)=8013471) -292 train 7.480510 (lr=3.9994e-04) (hash(x)=5659461) -293 train 7.522944 (lr=3.9991e-04) (hash(x)=6146213) -294 train 7.575163 (lr=3.9989e-04) (hash(x)=6602917) -295 train 7.490837 (lr=3.9986e-04) (hash(x)=6709902) -296 train 7.593400 (lr=3.9983e-04) (hash(x)=8154341) -297 train 7.746493 (lr=3.9979e-04) (hash(x)=6402571) -298 train 7.485673 (lr=3.9975e-04) (hash(x)=5605466) -299 train 7.451880 (lr=3.9971e-04) (hash(x)=7683614) -300 val loss 7.5142 -300 val perplexity 1833.8905 -300 train 7.542973 (lr=3.9966e-04) (hash(x)=5421572) -301 train 7.396899 (lr=3.9961e-04) (hash(x)=5453026) -302 train 7.457862 (lr=3.9955e-04) (hash(x)=6437746) -303 train 7.374797 (lr=3.9950e-04) (hash(x)=6260017) -304 train 7.478588 (lr=3.9944e-04) (hash(x)=6119053) -305 train 7.627518 (lr=3.9937e-04) (hash(x)=6591466) -306 train 7.541867 (lr=3.9930e-04) (hash(x)=5652701) -307 train 7.522711 (lr=3.9923e-04) (hash(x)=5501472) -308 train 7.696172 (lr=3.9916e-04) (hash(x)=6160695) -309 train 7.446716 (lr=3.9908e-04) (hash(x)=5871698) -310 train 7.423694 (lr=3.9900e-04) (hash(x)=7301184) -311 train 7.355983 (lr=3.9891e-04) (hash(x)=4282052) -312 train 7.567953 (lr=3.9882e-04) (hash(x)=5679330) -313 train 7.401403 (lr=3.9873e-04) (hash(x)=7824660) -314 train 7.453237 (lr=3.9864e-04) (hash(x)=4857318) -315 train 7.389629 (lr=3.9854e-04) (hash(x)=5954950) -316 train 7.464486 (lr=3.9843e-04) (hash(x)=5758178) -317 train 7.470260 (lr=3.9833e-04) (hash(x)=5484656) -318 train 7.483916 (lr=3.9822e-04) (hash(x)=6818913) -319 train 7.682001 (lr=3.9811e-04) (hash(x)=7031328) -320 train 7.523411 (lr=3.9799e-04) (hash(x)=6837621) -321 train 7.539083 (lr=3.9787e-04) (hash(x)=9157069) -322 train 7.783797 (lr=3.9775e-04) (hash(x)=6509536) -323 train 7.488003 (lr=3.9762e-04) (hash(x)=5996883) -324 train 7.736810 (lr=3.9749e-04) (hash(x)=6850868) -325 train 7.658040 (lr=3.9736e-04) (hash(x)=7645447) -326 train 7.682364 (lr=3.9722e-04) (hash(x)=6717515) -327 train 7.785436 (lr=3.9708e-04) (hash(x)=6336164) -328 train 7.491637 (lr=3.9694e-04) (hash(x)=6897445) -329 train 7.396650 (lr=3.9679e-04) (hash(x)=5224240) -330 train 7.555936 (lr=3.9664e-04) (hash(x)=6612945) -331 train 8.023050 (lr=3.9648e-04) (hash(x)=5447801) -332 train 7.544331 (lr=3.9633e-04) (hash(x)=7308579) -333 train 7.421063 (lr=3.9616e-04) (hash(x)=4155598) -334 train 7.434925 (lr=3.9600e-04) (hash(x)=6106773) -335 train 7.486042 (lr=3.9583e-04) (hash(x)=7482744) -336 train 7.555331 (lr=3.9566e-04) (hash(x)=6310687) -337 train 7.439886 (lr=3.9549e-04) (hash(x)=4733414) -338 train 7.542549 (lr=3.9531e-04) (hash(x)=6979734) -339 train 7.344533 (lr=3.9513e-04) (hash(x)=7806284) -340 train 7.354739 (lr=3.9494e-04) (hash(x)=5080536) -341 train 7.557064 (lr=3.9475e-04) (hash(x)=7236478) -342 train 7.489819 (lr=3.9456e-04) (hash(x)=6619318) -343 train 7.415064 (lr=3.9437e-04) (hash(x)=4656255) -344 train 7.342458 (lr=3.9417e-04) (hash(x)=5546888) -345 train 7.797825 (lr=3.9397e-04) (hash(x)=9298325) -346 train 7.483396 (lr=3.9376e-04) (hash(x)=5994232) -347 train 7.464743 (lr=3.9356e-04) (hash(x)=6287524) -348 train 7.583871 (lr=3.9334e-04) (hash(x)=6200049) -349 train 7.502278 (lr=3.9313e-04) (hash(x)=7895970) -350 val loss 7.4495 -350 val perplexity 1718.9470 -350 train 7.427850 (lr=3.9291e-04) (hash(x)=6051847) -351 train 7.552623 (lr=3.9269e-04) (hash(x)=8847992) -352 train 7.923444 (lr=3.9246e-04) (hash(x)=5123883) -353 train 7.526021 (lr=3.9223e-04) (hash(x)=6338998) -354 train 7.524910 (lr=3.9200e-04) (hash(x)=5765866) -355 train 7.864393 (lr=3.9177e-04) (hash(x)=7104011) -356 train 7.587577 (lr=3.9153e-04) (hash(x)=7438267) -357 train 7.320564 (lr=3.9129e-04) (hash(x)=5573214) -358 train 7.632944 (lr=3.9104e-04) (hash(x)=6897283) -359 train 7.391943 (lr=3.9079e-04) (hash(x)=6882897) -360 train 7.533899 (lr=3.9054e-04) (hash(x)=5343615) -361 train 7.436355 (lr=3.9029e-04) (hash(x)=5854242) -362 train 7.344234 (lr=3.9003e-04) (hash(x)=6317324) -363 train 7.275468 (lr=3.8977e-04) (hash(x)=6972494) -364 train 7.358955 (lr=3.8950e-04) (hash(x)=5661167) -365 train 7.379583 (lr=3.8923e-04) (hash(x)=6796805) -366 train 7.215770 (lr=3.8896e-04) (hash(x)=5817209) -367 train 7.265789 (lr=3.8869e-04) (hash(x)=6139120) -368 train 7.442384 (lr=3.8841e-04) (hash(x)=6121296) -369 train 7.423337 (lr=3.8813e-04) (hash(x)=6486796) -370 train 7.342756 (lr=3.8785e-04) (hash(x)=5514645) -371 train 7.254919 (lr=3.8756e-04) (hash(x)=5578797) -372 train 7.281869 (lr=3.8727e-04) (hash(x)=7651738) -373 train 7.471611 (lr=3.8697e-04) (hash(x)=6895326) -374 train 7.485798 (lr=3.8667e-04) (hash(x)=5490256) -375 train 7.370027 (lr=3.8637e-04) (hash(x)=7783160) -376 train 7.544970 (lr=3.8607e-04) (hash(x)=5608424) -377 train 7.333013 (lr=3.8576e-04) (hash(x)=4867625) -378 train 7.243606 (lr=3.8545e-04) (hash(x)=4655472) -379 train 7.309593 (lr=3.8514e-04) (hash(x)=6631123) -380 train 6.973507 (lr=3.8482e-04) (hash(x)=5751990) -381 train 7.271508 (lr=3.8450e-04) (hash(x)=6710965) -382 train 7.243104 (lr=3.8418e-04) (hash(x)=5293800) -383 train 7.276038 (lr=3.8385e-04) (hash(x)=6294657) -384 train 7.443870 (lr=3.8352e-04) (hash(x)=6999538) -385 train 7.417187 (lr=3.8319e-04) (hash(x)=5443606) -386 train 7.384171 (lr=3.8286e-04) (hash(x)=5650401) -387 train 7.408008 (lr=3.8252e-04) (hash(x)=7035770) -388 train 7.338608 (lr=3.8217e-04) (hash(x)=6678271) -389 train 7.547683 (lr=3.8183e-04) (hash(x)=4899541) -390 train 7.292682 (lr=3.8148e-04) (hash(x)=5359260) -391 train 7.294185 (lr=3.8113e-04) (hash(x)=6227120) -392 train 7.355081 (lr=3.8077e-04) (hash(x)=6643916) -393 train 7.424819 (lr=3.8042e-04) (hash(x)=5981648) -394 train 7.377169 (lr=3.8006e-04) (hash(x)=6467540) -395 train 7.313494 (lr=3.7969e-04) (hash(x)=5558993) -396 train 7.467900 (lr=3.7933e-04) (hash(x)=6698959) -397 train 7.292468 (lr=3.7896e-04) (hash(x)=7015671) -398 train 7.287083 (lr=3.7858e-04) (hash(x)=6800890) -399 train 7.448864 (lr=3.7821e-04) (hash(x)=5931234) -400 val loss 7.3784 -400 val perplexity 1600.9830 -400 train 7.432587 (lr=3.7783e-04) (hash(x)=3995070) -401 train 7.363217 (lr=3.7744e-04) (hash(x)=4582159) -402 train 7.439198 (lr=3.7706e-04) (hash(x)=7081906) -403 train 7.332005 (lr=3.7667e-04) (hash(x)=5029472) -404 train 7.327302 (lr=3.7628e-04) (hash(x)=3946232) -405 train 7.241664 (lr=3.7588e-04) (hash(x)=5434102) -406 train 8.010228 (lr=3.7549e-04) (hash(x)=5340646) -407 train 7.132459 (lr=3.7509e-04) (hash(x)=6810638) -408 train 7.397131 (lr=3.7468e-04) (hash(x)=6768026) -409 train 7.401068 (lr=3.7428e-04) (hash(x)=6521562) -410 train 7.363834 (lr=3.7387e-04) (hash(x)=4429434) -411 train 7.427893 (lr=3.7345e-04) (hash(x)=7226932) -412 train 7.236605 (lr=3.7304e-04) (hash(x)=5065932) -413 train 7.369333 (lr=3.7262e-04) (hash(x)=6957849) -414 train 7.363637 (lr=3.7220e-04) (hash(x)=6431457) -415 train 7.426032 (lr=3.7177e-04) (hash(x)=5334281) -416 train 7.437128 (lr=3.7135e-04) (hash(x)=5471747) -417 train 7.526937 (lr=3.7092e-04) (hash(x)=5887983) -418 train 7.425808 (lr=3.7048e-04) (hash(x)=5075909) -419 train 7.241815 (lr=3.7005e-04) (hash(x)=6393576) -420 train 7.371863 (lr=3.6961e-04) (hash(x)=6608979) -421 train 7.781045 (lr=3.6917e-04) (hash(x)=5057959) -422 train 7.693833 (lr=3.6872e-04) (hash(x)=6414858) -423 train 7.466870 (lr=3.6828e-04) (hash(x)=8595271) -424 train 7.336835 (lr=3.6782e-04) (hash(x)=6500949) -425 train 7.500569 (lr=3.6737e-04) (hash(x)=8395167) -426 train 7.617700 (lr=3.6692e-04) (hash(x)=6288420) -427 train 7.422984 (lr=3.6646e-04) (hash(x)=7634417) -428 train 7.320395 (lr=3.6599e-04) (hash(x)=6795561) -429 train 7.226711 (lr=3.6553e-04) (hash(x)=5257771) -430 train 7.380797 (lr=3.6506e-04) (hash(x)=7506860) -431 train 7.427154 (lr=3.6459e-04) (hash(x)=7674238) -432 train 7.529054 (lr=3.6412e-04) (hash(x)=5353794) -433 train 7.442874 (lr=3.6364e-04) (hash(x)=5300555) -434 train 7.158638 (lr=3.6316e-04) (hash(x)=5564419) -435 train 7.421156 (lr=3.6268e-04) (hash(x)=6066139) -436 train 7.384982 (lr=3.6220e-04) (hash(x)=6863709) -437 train 7.384432 (lr=3.6171e-04) (hash(x)=6688212) -438 train 7.548279 (lr=3.6122e-04) (hash(x)=7095090) -439 train 7.637533 (lr=3.6073e-04) (hash(x)=6642404) -440 train 7.350913 (lr=3.6023e-04) (hash(x)=6539227) -441 train 7.343325 (lr=3.5974e-04) (hash(x)=4961570) -442 train 7.282474 (lr=3.5924e-04) (hash(x)=6606391) -443 train 7.081844 (lr=3.5873e-04) (hash(x)=5105190) -444 train 7.669587 (lr=3.5823e-04) (hash(x)=5695997) -445 train 7.361680 (lr=3.5772e-04) (hash(x)=7155991) -446 train 7.332823 (lr=3.5721e-04) (hash(x)=7249727) -447 train 7.320885 (lr=3.5669e-04) (hash(x)=5132972) -448 train 7.311207 (lr=3.5618e-04) (hash(x)=5381802) -449 train 7.330151 (lr=3.5566e-04) (hash(x)=6269946) -450 val loss 7.3349 -450 val perplexity 1532.9175 -450 train 7.304922 (lr=3.5514e-04) (hash(x)=4976762) -451 train 7.394916 (lr=3.5461e-04) (hash(x)=5396133) -452 train 7.351671 (lr=3.5408e-04) (hash(x)=6173473) -453 train 7.329982 (lr=3.5355e-04) (hash(x)=6394083) -454 train 7.386403 (lr=3.5302e-04) (hash(x)=6436030) -455 train 7.248203 (lr=3.5249e-04) (hash(x)=5237804) -456 train 7.217991 (lr=3.5195e-04) (hash(x)=6540397) -457 train 7.480265 (lr=3.5141e-04) (hash(x)=5216638) -458 train 7.296997 (lr=3.5087e-04) (hash(x)=5750537) -459 train 7.295883 (lr=3.5032e-04) (hash(x)=6735565) -460 train 7.305536 (lr=3.4977e-04) (hash(x)=7297488) -461 train 7.497890 (lr=3.4922e-04) (hash(x)=5983575) -462 train 7.319165 (lr=3.4867e-04) (hash(x)=4808543) -463 train 7.431988 (lr=3.4812e-04) (hash(x)=5831619) -464 train 7.193366 (lr=3.4756e-04) (hash(x)=6280052) -465 train 7.224925 (lr=3.4700e-04) (hash(x)=9109083) -466 train 7.464886 (lr=3.4644e-04) (hash(x)=5848604) -467 train 7.403017 (lr=3.4587e-04) (hash(x)=6912967) -468 train 7.598088 (lr=3.4530e-04) (hash(x)=6615365) -469 train 7.643711 (lr=3.4473e-04) (hash(x)=5965674) -470 train 7.469454 (lr=3.4416e-04) (hash(x)=6879965) -471 train 7.434535 (lr=3.4359e-04) (hash(x)=5822533) -472 train 7.317868 (lr=3.4301e-04) (hash(x)=5794462) -473 train 7.386673 (lr=3.4243e-04) (hash(x)=5268216) -474 train 7.210080 (lr=3.4185e-04) (hash(x)=7058396) -475 train 7.314373 (lr=3.4127e-04) (hash(x)=6531900) -476 train 7.340644 (lr=3.4068e-04) (hash(x)=5878912) -477 train 7.157888 (lr=3.4009e-04) (hash(x)=5426499) -478 train 7.357786 (lr=3.3950e-04) (hash(x)=8107004) -479 train 8.084682 (lr=3.3891e-04) (hash(x)=7455372) -480 train 8.043467 (lr=3.3831e-04) (hash(x)=7727959) -481 train 8.002517 (lr=3.3771e-04) (hash(x)=8319119) -482 train 7.923566 (lr=3.3711e-04) (hash(x)=7581656) -483 train 7.973314 (lr=3.3651e-04) (hash(x)=7592128) -484 train 7.972460 (lr=3.3590e-04) (hash(x)=10506633) -485 train 7.926563 (lr=3.3530e-04) (hash(x)=8704170) -486 train 7.699511 (lr=3.3469e-04) (hash(x)=7461138) -487 train 7.539885 (lr=3.3408e-04) (hash(x)=7165037) -488 train 7.610208 (lr=3.3346e-04) (hash(x)=4976998) -489 train 7.311361 (lr=3.3285e-04) (hash(x)=7678000) -490 train 7.371429 (lr=3.3223e-04) (hash(x)=6299409) -491 train 7.297880 (lr=3.3161e-04) (hash(x)=7414788) -492 train 7.416718 (lr=3.3099e-04) (hash(x)=5063061) -493 train 7.351502 (lr=3.3036e-04) (hash(x)=7326216) -494 train 7.483407 (lr=3.2973e-04) (hash(x)=7492012) -495 train 7.431917 (lr=3.2911e-04) (hash(x)=5857162) -496 train 7.224462 (lr=3.2847e-04) (hash(x)=6169001) -497 train 9.223996 (lr=3.2784e-04) (hash(x)=14715669) -498 train 12.014521 (lr=3.2721e-04) (hash(x)=18256706) -499 train 11.784342 (lr=3.2657e-04) (hash(x)=16950560) -500 val loss 7.3506 -500 val perplexity 1557.1532 -500 train 8.058232 (lr=3.2593e-04) (hash(x)=6113563) -501 train 6.992707 (lr=3.2529e-04) (hash(x)=6159125) -502 train 7.386683 (lr=3.2464e-04) (hash(x)=5482303) -503 train 7.446765 (lr=3.2400e-04) (hash(x)=5908442) -504 train 7.311045 (lr=3.2335e-04) (hash(x)=4985045) -505 train 7.238109 (lr=3.2270e-04) (hash(x)=6668887) -506 train 7.326504 (lr=3.2205e-04) (hash(x)=6123910) -507 train 7.395772 (lr=3.2140e-04) (hash(x)=7662975) -508 train 7.346252 (lr=3.2074e-04) (hash(x)=7191898) -509 train 7.294250 (lr=3.2008e-04) (hash(x)=6669539) -510 train 7.358017 (lr=3.1943e-04) (hash(x)=6557481) -511 train 7.255944 (lr=3.1876e-04) (hash(x)=5015998) -512 train 7.317005 (lr=3.1810e-04) (hash(x)=4964540) -513 train 7.142015 (lr=3.1744e-04) (hash(x)=5458386) -514 train 7.541059 (lr=3.1677e-04) (hash(x)=6077616) -515 train 7.268070 (lr=3.1610e-04) (hash(x)=4849847) -516 train 7.318647 (lr=3.1543e-04) (hash(x)=5431422) -517 train 7.528705 (lr=3.1476e-04) (hash(x)=5125562) -518 train 7.420020 (lr=3.1408e-04) (hash(x)=5587715) -519 train 7.478749 (lr=3.1341e-04) (hash(x)=6012047) -520 train 7.329851 (lr=3.1273e-04) (hash(x)=5668436) -521 train 7.361660 (lr=3.1205e-04) (hash(x)=6079364) -522 train 7.473340 (lr=3.1137e-04) (hash(x)=5200504) -523 train 7.210963 (lr=3.1069e-04) (hash(x)=6030395) -524 train 7.451573 (lr=3.1000e-04) (hash(x)=6855319) -525 train 7.225374 (lr=3.0931e-04) (hash(x)=6781762) -526 train 7.378330 (lr=3.0862e-04) (hash(x)=6717939) -527 train 7.363630 (lr=3.0793e-04) (hash(x)=5238325) -528 train 7.265601 (lr=3.0724e-04) (hash(x)=5808069) -529 train 7.628414 (lr=3.0655e-04) (hash(x)=8611144) -530 train 7.271699 (lr=3.0585e-04) (hash(x)=6028738) -531 train 7.303637 (lr=3.0516e-04) (hash(x)=6901605) -532 train 7.242479 (lr=3.0446e-04) (hash(x)=6723307) -533 train 7.365186 (lr=3.0376e-04) (hash(x)=5499337) -534 train 7.286484 (lr=3.0306e-04) (hash(x)=6586372) -535 train 7.408593 (lr=3.0235e-04) (hash(x)=7134874) -536 train 7.297486 (lr=3.0165e-04) (hash(x)=8415623) -537 train 7.330126 (lr=3.0094e-04) (hash(x)=6149038) -538 train 7.363118 (lr=3.0023e-04) (hash(x)=6078325) -539 train 7.337748 (lr=2.9952e-04) (hash(x)=6609760) -540 train 7.231339 (lr=2.9881e-04) (hash(x)=6185253) -541 train 7.614024 (lr=2.9810e-04) (hash(x)=6652627) -542 train 7.417749 (lr=2.9738e-04) (hash(x)=7758536) -543 train 7.380561 (lr=2.9667e-04) (hash(x)=8618579) -544 train 7.360254 (lr=2.9595e-04) (hash(x)=6710226) -545 train 7.206186 (lr=2.9523e-04) (hash(x)=5896892) -546 train 7.224288 (lr=2.9451e-04) (hash(x)=6332995) -547 train 7.649704 (lr=2.9379e-04) (hash(x)=8945854) -548 train 7.222267 (lr=2.9307e-04) (hash(x)=4329129) -549 train 7.260049 (lr=2.9234e-04) (hash(x)=6775103) -550 val loss 7.2928 -550 val perplexity 1469.7389 -550 train 7.375446 (lr=2.9162e-04) (hash(x)=4465735) -551 train 7.241213 (lr=2.9089e-04) (hash(x)=6200024) -552 train 7.211312 (lr=2.9016e-04) (hash(x)=5520748) -553 train 7.214302 (lr=2.8943e-04) (hash(x)=5238139) -554 train 7.477874 (lr=2.8870e-04) (hash(x)=7639817) -555 train 7.244286 (lr=2.8797e-04) (hash(x)=5780948) -556 train 7.365036 (lr=2.8723e-04) (hash(x)=6733444) -557 train 7.318333 (lr=2.8650e-04) (hash(x)=6168407) -558 train 7.351531 (lr=2.8576e-04) (hash(x)=6680197) -559 train 7.230827 (lr=2.8502e-04) (hash(x)=3775881) -560 train 7.085499 (lr=2.8428e-04) (hash(x)=5784096) -561 train 7.513249 (lr=2.8354e-04) (hash(x)=6848709) -562 train 7.548810 (lr=2.8280e-04) (hash(x)=7449019) -563 train 7.647755 (lr=2.8206e-04) (hash(x)=6478113) -564 train 7.310112 (lr=2.8132e-04) (hash(x)=5925744) -565 train 7.360231 (lr=2.8057e-04) (hash(x)=6483914) -566 train 7.233283 (lr=2.7982e-04) (hash(x)=6010847) -567 train 7.331893 (lr=2.7908e-04) (hash(x)=5927795) -568 train 7.343916 (lr=2.7833e-04) (hash(x)=5896332) -569 train 7.303408 (lr=2.7758e-04) (hash(x)=8438033) -570 train 7.404140 (lr=2.7683e-04) (hash(x)=6081660) -571 train 7.299306 (lr=2.7607e-04) (hash(x)=5684788) -572 train 7.192412 (lr=2.7532e-04) (hash(x)=6272055) -573 train 7.161539 (lr=2.7457e-04) (hash(x)=5710182) -574 train 7.272127 (lr=2.7381e-04) (hash(x)=6219616) -575 train 7.246496 (lr=2.7306e-04) (hash(x)=6160063) -576 train 7.265047 (lr=2.7230e-04) (hash(x)=5710809) -577 train 7.024844 (lr=2.7154e-04) (hash(x)=5955100) -578 train 7.040871 (lr=2.7078e-04) (hash(x)=5356088) -579 train 7.083298 (lr=2.7002e-04) (hash(x)=6672309) -580 train 7.283853 (lr=2.6926e-04) (hash(x)=5841684) -581 train 7.632938 (lr=2.6850e-04) (hash(x)=9001564) -582 train 8.183352 (lr=2.6773e-04) (hash(x)=6897178) -583 train 7.391829 (lr=2.6697e-04) (hash(x)=5454654) -584 train 7.146838 (lr=2.6620e-04) (hash(x)=6391454) -585 train 7.241993 (lr=2.6544e-04) (hash(x)=5174062) -586 train 7.355693 (lr=2.6467e-04) (hash(x)=5197924) -587 train 7.313063 (lr=2.6390e-04) (hash(x)=6199203) -588 train 7.137313 (lr=2.6314e-04) (hash(x)=5786498) -589 train 7.287375 (lr=2.6237e-04) (hash(x)=8352747) -590 train 7.572512 (lr=2.6160e-04) (hash(x)=4829700) -591 train 7.071661 (lr=2.6083e-04) (hash(x)=4547106) -592 train 7.374060 (lr=2.6005e-04) (hash(x)=7686831) -593 train 7.254583 (lr=2.5928e-04) (hash(x)=6433099) -594 train 7.109669 (lr=2.5851e-04) (hash(x)=4826460) -595 train 7.211390 (lr=2.5773e-04) (hash(x)=6424428) -596 train 7.095765 (lr=2.5696e-04) (hash(x)=6073605) -597 train 7.441885 (lr=2.5618e-04) (hash(x)=5975712) -598 train 7.042920 (lr=2.5541e-04) (hash(x)=7030029) -599 train 7.353360 (lr=2.5463e-04) (hash(x)=5458532) -600 val loss 7.2687 -600 val perplexity 1434.7274 -600 train 7.190872 (lr=2.5385e-04) (hash(x)=7823919) -601 train 7.637245 (lr=2.5307e-04) (hash(x)=7002774) -602 train 7.428175 (lr=2.5230e-04) (hash(x)=7056399) -603 train 7.637279 (lr=2.5152e-04) (hash(x)=8206173) -604 train 7.469888 (lr=2.5074e-04) (hash(x)=8034846) -605 train 7.767740 (lr=2.4996e-04) (hash(x)=7784971) -606 train 7.912747 (lr=2.4917e-04) (hash(x)=7118076) -607 train 7.200405 (lr=2.4839e-04) (hash(x)=6001843) -608 train 7.297425 (lr=2.4761e-04) (hash(x)=5582437) -609 train 7.408721 (lr=2.4683e-04) (hash(x)=5698642) -610 train 7.256955 (lr=2.4604e-04) (hash(x)=6615301) -611 train 7.261686 (lr=2.4526e-04) (hash(x)=6600751) -612 train 7.176589 (lr=2.4448e-04) (hash(x)=6880955) -613 train 7.233938 (lr=2.4369e-04) (hash(x)=5804610) -614 train 7.166404 (lr=2.4291e-04) (hash(x)=6263347) -615 train 7.125833 (lr=2.4212e-04) (hash(x)=5162652) -616 train 7.184370 (lr=2.4133e-04) (hash(x)=6055710) -617 train 7.140441 (lr=2.4055e-04) (hash(x)=5297006) -618 train 7.168477 (lr=2.3976e-04) (hash(x)=5923648) -619 train 7.176470 (lr=2.3897e-04) (hash(x)=6728323) -620 train 7.185227 (lr=2.3818e-04) (hash(x)=6660239) -621 train 7.154287 (lr=2.3740e-04) (hash(x)=3964882) -622 train 7.203990 (lr=2.3661e-04) (hash(x)=5868942) -623 train 7.118853 (lr=2.3582e-04) (hash(x)=6735993) -624 train 7.468281 (lr=2.3503e-04) (hash(x)=5926190) -625 train 7.150704 (lr=2.3424e-04) (hash(x)=5150316) -626 train 7.166037 (lr=2.3345e-04) (hash(x)=7571467) -627 train 7.072007 (lr=2.3266e-04) (hash(x)=5220448) -628 train 7.086149 (lr=2.3187e-04) (hash(x)=6790397) -629 train 7.560840 (lr=2.3108e-04) (hash(x)=6971289) -630 train 7.514282 (lr=2.3029e-04) (hash(x)=7123359) -631 train 7.295150 (lr=2.2950e-04) (hash(x)=5012069) -632 train 7.258813 (lr=2.2871e-04) (hash(x)=6183574) -633 train 7.152743 (lr=2.2792e-04) (hash(x)=6576136) -634 train 7.178514 (lr=2.2713e-04) (hash(x)=6157346) -635 train 7.171775 (lr=2.2633e-04) (hash(x)=6077647) -636 train 7.413737 (lr=2.2554e-04) (hash(x)=8369488) -637 train 7.205590 (lr=2.2475e-04) (hash(x)=6032381) -638 train 7.130117 (lr=2.2396e-04) (hash(x)=5924756) -639 train 7.171339 (lr=2.2317e-04) (hash(x)=8410716) -640 train 7.155844 (lr=2.2238e-04) (hash(x)=5803440) -641 train 7.248858 (lr=2.2158e-04) (hash(x)=6212516) -642 train 7.325352 (lr=2.2079e-04) (hash(x)=7165945) -643 train 7.037984 (lr=2.2000e-04) (hash(x)=5298545) -644 train 7.292557 (lr=2.1921e-04) (hash(x)=6281739) -645 train 7.257489 (lr=2.1842e-04) (hash(x)=5779073) -646 train 7.117522 (lr=2.1762e-04) (hash(x)=5090107) -647 train 7.184642 (lr=2.1683e-04) (hash(x)=6340947) -648 train 6.941740 (lr=2.1604e-04) (hash(x)=4741418) -649 train 6.861466 (lr=2.1525e-04) (hash(x)=6530441) -650 val loss 7.2342 -650 val perplexity 1386.0918 -650 train 7.399755 (lr=2.1446e-04) (hash(x)=6396041) -651 train 7.084840 (lr=2.1367e-04) (hash(x)=7818007) -652 train 7.090919 (lr=2.1287e-04) (hash(x)=6478457) -653 train 7.159522 (lr=2.1208e-04) (hash(x)=6277435) -654 train 7.123230 (lr=2.1129e-04) (hash(x)=6042369) -655 train 7.139806 (lr=2.1050e-04) (hash(x)=6226320) -656 train 7.160164 (lr=2.0971e-04) (hash(x)=5826883) -657 train 7.271748 (lr=2.0892e-04) (hash(x)=5463751) -658 train 7.191085 (lr=2.0813e-04) (hash(x)=6433080) -659 train 7.041486 (lr=2.0734e-04) (hash(x)=6579329) -660 train 7.062831 (lr=2.0655e-04) (hash(x)=4724703) -661 train 7.415412 (lr=2.0576e-04) (hash(x)=6660540) -662 train 7.218508 (lr=2.0497e-04) (hash(x)=5918756) -663 train 7.151925 (lr=2.0418e-04) (hash(x)=6491272) -664 train 7.080535 (lr=2.0339e-04) (hash(x)=5452863) -665 train 7.272725 (lr=2.0260e-04) (hash(x)=6766947) -666 train 7.634573 (lr=2.0182e-04) (hash(x)=7459504) -667 train 7.294215 (lr=2.0103e-04) (hash(x)=3721218) -668 train 7.465971 (lr=2.0024e-04) (hash(x)=7929571) -669 train 7.136056 (lr=1.9945e-04) (hash(x)=5229898) -670 train 7.182530 (lr=1.9867e-04) (hash(x)=6083090) -671 train 7.041215 (lr=1.9788e-04) (hash(x)=6054428) -672 train 7.194268 (lr=1.9709e-04) (hash(x)=6072563) -673 train 7.283079 (lr=1.9631e-04) (hash(x)=6290464) -674 train 7.396589 (lr=1.9552e-04) (hash(x)=6314742) -675 train 7.069119 (lr=1.9474e-04) (hash(x)=6904498) -676 train 7.215933 (lr=1.9396e-04) (hash(x)=5378107) -677 train 7.333801 (lr=1.9317e-04) (hash(x)=7765805) -678 train 7.147527 (lr=1.9239e-04) (hash(x)=5871280) -679 train 7.303738 (lr=1.9161e-04) (hash(x)=6543764) -680 train 7.144301 (lr=1.9083e-04) (hash(x)=7369665) -681 train 7.253389 (lr=1.9004e-04) (hash(x)=7204955) -682 train 7.201522 (lr=1.8926e-04) (hash(x)=5856543) -683 train 7.077721 (lr=1.8848e-04) (hash(x)=4423711) -684 train 7.056482 (lr=1.8770e-04) (hash(x)=5818153) -685 train 7.152046 (lr=1.8693e-04) (hash(x)=5343477) -686 train 7.346313 (lr=1.8615e-04) (hash(x)=6581702) -687 train 7.176725 (lr=1.8537e-04) (hash(x)=6595856) -688 train 7.104743 (lr=1.8459e-04) (hash(x)=5325378) -689 train 7.037066 (lr=1.8382e-04) (hash(x)=7229015) -690 train 7.196552 (lr=1.8304e-04) (hash(x)=5918186) -691 train 7.068548 (lr=1.8227e-04) (hash(x)=5916034) -692 train 7.093777 (lr=1.8149e-04) (hash(x)=5280722) -693 train 7.472866 (lr=1.8072e-04) (hash(x)=6939521) -694 train 7.223158 (lr=1.7995e-04) (hash(x)=5172566) -695 train 7.084385 (lr=1.7917e-04) (hash(x)=5492185) -696 train 6.955538 (lr=1.7840e-04) (hash(x)=5779011) -697 train 7.224815 (lr=1.7763e-04) (hash(x)=6898006) -698 train 7.055333 (lr=1.7686e-04) (hash(x)=5779217) -699 train 6.919622 (lr=1.7610e-04) (hash(x)=5462008) -700 val loss 7.2164 -700 val perplexity 1361.5625 -700 train 7.072332 (lr=1.7533e-04) (hash(x)=6243843) -701 train 7.131474 (lr=1.7456e-04) (hash(x)=7821902) -702 train 7.196996 (lr=1.7380e-04) (hash(x)=5222501) -703 train 7.155895 (lr=1.7303e-04) (hash(x)=6608108) -704 train 7.264574 (lr=1.7227e-04) (hash(x)=7602879) -705 train 7.193008 (lr=1.7150e-04) (hash(x)=6295394) -706 train 7.152050 (lr=1.7074e-04) (hash(x)=6579907) -707 train 7.041983 (lr=1.6998e-04) (hash(x)=6803449) -708 train 7.111906 (lr=1.6922e-04) (hash(x)=5413733) -709 train 7.073820 (lr=1.6846e-04) (hash(x)=7444134) -710 train 7.233346 (lr=1.6770e-04) (hash(x)=7028652) -711 train 7.037975 (lr=1.6694e-04) (hash(x)=5361923) -712 train 7.141428 (lr=1.6619e-04) (hash(x)=5478293) -713 train 7.123958 (lr=1.6543e-04) (hash(x)=7803039) -714 train 7.308537 (lr=1.6468e-04) (hash(x)=6469017) -715 train 7.208521 (lr=1.6393e-04) (hash(x)=7042578) -716 train 7.267323 (lr=1.6317e-04) (hash(x)=6927957) -717 train 7.069807 (lr=1.6242e-04) (hash(x)=6647007) -718 train 7.038350 (lr=1.6167e-04) (hash(x)=6230888) -719 train 7.319347 (lr=1.6092e-04) (hash(x)=6303658) -720 train 7.342918 (lr=1.6018e-04) (hash(x)=6769880) -721 train 7.181073 (lr=1.5943e-04) (hash(x)=6158927) -722 train 7.158894 (lr=1.5868e-04) (hash(x)=5991631) -723 train 7.033717 (lr=1.5794e-04) (hash(x)=6419656) -724 train 7.028175 (lr=1.5720e-04) (hash(x)=7739209) -725 train 6.981717 (lr=1.5646e-04) (hash(x)=7891271) -726 train 7.347407 (lr=1.5572e-04) (hash(x)=7171433) -727 train 7.125878 (lr=1.5498e-04) (hash(x)=7099888) -728 train 7.128310 (lr=1.5424e-04) (hash(x)=6103730) -729 train 7.235734 (lr=1.5350e-04) (hash(x)=6352424) -730 train 7.133034 (lr=1.5277e-04) (hash(x)=4893671) -731 train 7.091638 (lr=1.5203e-04) (hash(x)=5863145) -732 train 7.193548 (lr=1.5130e-04) (hash(x)=5502233) -733 train 7.107647 (lr=1.5057e-04) (hash(x)=6844597) -734 train 7.123130 (lr=1.4984e-04) (hash(x)=6744526) -735 train 7.267018 (lr=1.4911e-04) (hash(x)=6009861) -736 train 7.126598 (lr=1.4838e-04) (hash(x)=6152358) -737 train 7.054047 (lr=1.4766e-04) (hash(x)=5374957) -738 train 7.081131 (lr=1.4693e-04) (hash(x)=6495309) -739 train 7.229886 (lr=1.4621e-04) (hash(x)=3923225) -740 train 7.007717 (lr=1.4549e-04) (hash(x)=6255243) -741 train 7.162672 (lr=1.4477e-04) (hash(x)=5848862) -742 train 7.171687 (lr=1.4405e-04) (hash(x)=4535000) -743 train 7.044148 (lr=1.4333e-04) (hash(x)=4440634) -744 train 7.043993 (lr=1.4262e-04) (hash(x)=5222077) -745 train 7.089469 (lr=1.4190e-04) (hash(x)=4788998) -746 train 7.086133 (lr=1.4119e-04) (hash(x)=6108350) -747 train 7.002780 (lr=1.4048e-04) (hash(x)=7378165) -748 train 7.083867 (lr=1.3977e-04) (hash(x)=5475646) -749 train 7.081274 (lr=1.3906e-04) (hash(x)=4771243) -750 val loss 7.1958 -750 val perplexity 1333.7659 -750 train 6.975585 (lr=1.3835e-04) (hash(x)=6668088) -751 train 7.192849 (lr=1.3765e-04) (hash(x)=5716089) -752 train 7.151796 (lr=1.3694e-04) (hash(x)=6991946) -753 train 7.062603 (lr=1.3624e-04) (hash(x)=7991009) -754 train 7.149424 (lr=1.3554e-04) (hash(x)=6037018) -755 train 7.115553 (lr=1.3484e-04) (hash(x)=5348607) -756 train 7.266709 (lr=1.3415e-04) (hash(x)=5190526) -757 train 7.138197 (lr=1.3345e-04) (hash(x)=6036146) -758 train 7.033880 (lr=1.3276e-04) (hash(x)=5329783) -759 train 7.137833 (lr=1.3207e-04) (hash(x)=6658718) -760 train 7.036718 (lr=1.3138e-04) (hash(x)=4820939) -761 train 7.045386 (lr=1.3069e-04) (hash(x)=6176253) -762 train 7.003334 (lr=1.3000e-04) (hash(x)=5316750) -763 train 7.104775 (lr=1.2931e-04) (hash(x)=4542895) -764 train 6.868597 (lr=1.2863e-04) (hash(x)=5395673) -765 train 6.986865 (lr=1.2795e-04) (hash(x)=5549073) -766 train 7.255738 (lr=1.2727e-04) (hash(x)=5233723) -767 train 7.305648 (lr=1.2659e-04) (hash(x)=5342783) -768 train 7.237090 (lr=1.2592e-04) (hash(x)=5552448) -769 train 7.376866 (lr=1.2524e-04) (hash(x)=6549546) -770 train 7.020038 (lr=1.2457e-04) (hash(x)=3816493) -771 train 7.054595 (lr=1.2390e-04) (hash(x)=6170599) -772 train 7.553206 (lr=1.2323e-04) (hash(x)=6708759) -773 train 7.161798 (lr=1.2256e-04) (hash(x)=8483134) -774 train 7.740232 (lr=1.2190e-04) (hash(x)=5583732) -775 train 7.171287 (lr=1.2124e-04) (hash(x)=4865036) -776 train 7.080164 (lr=1.2057e-04) (hash(x)=7234336) -777 train 7.157468 (lr=1.1992e-04) (hash(x)=4433890) -778 train 7.468447 (lr=1.1926e-04) (hash(x)=7484636) -779 train 7.882348 (lr=1.1860e-04) (hash(x)=6738597) -780 train 7.116121 (lr=1.1795e-04) (hash(x)=6752421) -781 train 7.308029 (lr=1.1730e-04) (hash(x)=5459620) -782 train 7.220198 (lr=1.1665e-04) (hash(x)=6718131) -783 train 7.192760 (lr=1.1600e-04) (hash(x)=4604074) -784 train 7.066220 (lr=1.1536e-04) (hash(x)=5946124) -785 train 7.350662 (lr=1.1471e-04) (hash(x)=8045501) -786 train 7.442341 (lr=1.1407e-04) (hash(x)=5712725) -787 train 7.169938 (lr=1.1343e-04) (hash(x)=6176464) -788 train 7.217295 (lr=1.1279e-04) (hash(x)=6276702) -789 train 7.029304 (lr=1.1216e-04) (hash(x)=6127317) -790 train 7.185762 (lr=1.1153e-04) (hash(x)=7221374) -791 train 7.154645 (lr=1.1089e-04) (hash(x)=5571462) -792 train 7.176119 (lr=1.1027e-04) (hash(x)=7518021) -793 train 7.164327 (lr=1.0964e-04) (hash(x)=6640755) -794 train 7.236927 (lr=1.0901e-04) (hash(x)=6870405) -795 train 7.213480 (lr=1.0839e-04) (hash(x)=6147295) -796 train 7.096205 (lr=1.0777e-04) (hash(x)=6782583) -797 train 7.221269 (lr=1.0715e-04) (hash(x)=6120461) -798 train 7.153096 (lr=1.0654e-04) (hash(x)=5893870) -799 train 7.097794 (lr=1.0592e-04) (hash(x)=5123928) -800 val loss 7.1858 -800 val perplexity 1320.5674 -800 train 7.167883 (lr=1.0531e-04) (hash(x)=7037251) -801 train 7.153453 (lr=1.0470e-04) (hash(x)=5428813) -802 train 7.104988 (lr=1.0410e-04) (hash(x)=5550387) -803 train 7.164821 (lr=1.0349e-04) (hash(x)=6448586) -804 train 7.310443 (lr=1.0289e-04) (hash(x)=5916934) -805 train 7.270067 (lr=1.0229e-04) (hash(x)=8116987) -806 train 7.249178 (lr=1.0169e-04) (hash(x)=6210899) -807 train 7.352675 (lr=1.0109e-04) (hash(x)=5974342) -808 train 7.341385 (lr=1.0050e-04) (hash(x)=7236199) -809 train 7.272756 (lr=9.9910e-05) (hash(x)=5261336) -810 train 7.091850 (lr=9.9321e-05) (hash(x)=6310720) -811 train 7.140950 (lr=9.8735e-05) (hash(x)=5307056) -812 train 6.960600 (lr=9.8151e-05) (hash(x)=7356633) -813 train 7.095349 (lr=9.7569e-05) (hash(x)=5865119) -814 train 6.991228 (lr=9.6990e-05) (hash(x)=5979205) -815 train 7.159368 (lr=9.6413e-05) (hash(x)=6672380) -816 train 7.143548 (lr=9.5838e-05) (hash(x)=5565030) -817 train 7.114964 (lr=9.5266e-05) (hash(x)=6886810) -818 train 7.167445 (lr=9.4696e-05) (hash(x)=5926478) -819 train 7.377586 (lr=9.4129e-05) (hash(x)=6564071) -820 train 6.997161 (lr=9.3564e-05) (hash(x)=5024280) -821 train 6.998382 (lr=9.3001e-05) (hash(x)=7705089) -822 train 6.974398 (lr=9.2441e-05) (hash(x)=4037371) -823 train 7.087169 (lr=9.1884e-05) (hash(x)=5773073) -824 train 7.102084 (lr=9.1328e-05) (hash(x)=7158139) -825 train 6.941420 (lr=9.0776e-05) (hash(x)=5905976) -826 train 7.371319 (lr=9.0226e-05) (hash(x)=13897369) -827 train 8.487906 (lr=8.9678e-05) (hash(x)=6936653) -828 train 7.124721 (lr=8.9133e-05) (hash(x)=6592246) -829 train 7.107628 (lr=8.8591e-05) (hash(x)=6592773) -830 train 7.165405 (lr=8.8051e-05) (hash(x)=5461178) -831 train 6.931377 (lr=8.7513e-05) (hash(x)=6796551) -832 train 7.151716 (lr=8.6978e-05) (hash(x)=4721691) -833 train 7.071537 (lr=8.6446e-05) (hash(x)=6151589) -834 train 7.216248 (lr=8.5916e-05) (hash(x)=7008995) -835 train 7.537697 (lr=8.5389e-05) (hash(x)=7045164) -836 train 7.138468 (lr=8.4865e-05) (hash(x)=6614221) -837 train 7.166931 (lr=8.4343e-05) (hash(x)=6650506) -838 train 6.991625 (lr=8.3824e-05) (hash(x)=6363762) -839 train 7.156168 (lr=8.3307e-05) (hash(x)=7839748) -840 train 7.092438 (lr=8.2793e-05) (hash(x)=5124077) -841 train 7.521439 (lr=8.2282e-05) (hash(x)=6028671) -842 train 7.002462 (lr=8.1773e-05) (hash(x)=5427175) -843 train 7.344855 (lr=8.1267e-05) (hash(x)=6118408) -844 train 7.103992 (lr=8.0764e-05) (hash(x)=6022552) -845 train 7.126197 (lr=8.0263e-05) (hash(x)=5757526) -846 train 7.593597 (lr=7.9765e-05) (hash(x)=6476549) -847 train 6.912841 (lr=7.9270e-05) (hash(x)=6030172) -848 train 7.301657 (lr=7.8778e-05) (hash(x)=5917229) -849 train 7.360444 (lr=7.8288e-05) (hash(x)=6719882) -850 val loss 7.1740 -850 val perplexity 1305.0623 -850 train 7.220369 (lr=7.7801e-05) (hash(x)=5441498) -851 train 7.072789 (lr=7.7317e-05) (hash(x)=5028050) -852 train 7.136975 (lr=7.6836e-05) (hash(x)=8487491) -853 train 7.131804 (lr=7.6357e-05) (hash(x)=5682910) -854 train 7.330167 (lr=7.5881e-05) (hash(x)=6781362) -855 train 7.146786 (lr=7.5408e-05) (hash(x)=5747891) -856 train 7.178394 (lr=7.4938e-05) (hash(x)=7627661) -857 train 6.840408 (lr=7.4470e-05) (hash(x)=5734208) -858 train 7.005817 (lr=7.4005e-05) (hash(x)=6162015) -859 train 7.214223 (lr=7.3544e-05) (hash(x)=7024381) -860 train 7.427608 (lr=7.3085e-05) (hash(x)=5198498) -861 train 7.415044 (lr=7.2628e-05) (hash(x)=7814361) -862 train 7.261909 (lr=7.2175e-05) (hash(x)=7394995) -863 train 7.165792 (lr=7.1725e-05) (hash(x)=5765893) -864 train 6.968561 (lr=7.1277e-05) (hash(x)=4990435) -865 train 7.116785 (lr=7.0832e-05) (hash(x)=5572048) -866 train 7.261439 (lr=7.0390e-05) (hash(x)=7093293) -867 train 7.137643 (lr=6.9952e-05) (hash(x)=5610058) -868 train 7.045588 (lr=6.9516e-05) (hash(x)=6771468) -869 train 7.076818 (lr=6.9082e-05) (hash(x)=4459483) -870 train 6.974629 (lr=6.8652e-05) (hash(x)=4926546) -871 train 7.073829 (lr=6.8225e-05) (hash(x)=6758411) -872 train 7.050490 (lr=6.7801e-05) (hash(x)=7394277) -873 train 7.176453 (lr=6.7379e-05) (hash(x)=6701381) -874 train 7.527780 (lr=6.6961e-05) (hash(x)=8120966) -875 train 7.029181 (lr=6.6545e-05) (hash(x)=5416400) -876 train 7.045394 (lr=6.6133e-05) (hash(x)=6292778) -877 train 6.982659 (lr=6.5723e-05) (hash(x)=5919569) -878 train 7.292915 (lr=6.5317e-05) (hash(x)=7561740) -879 train 7.048343 (lr=6.4913e-05) (hash(x)=5282870) -880 train 7.077844 (lr=6.4513e-05) (hash(x)=5473238) -881 train 6.951062 (lr=6.4115e-05) (hash(x)=8072181) -882 train 6.977979 (lr=6.3721e-05) (hash(x)=6757322) -883 train 6.942024 (lr=6.3329e-05) (hash(x)=7996770) -884 train 7.021532 (lr=6.2941e-05) (hash(x)=3181021) -885 train 7.057776 (lr=6.2556e-05) (hash(x)=5093519) -886 train 7.053750 (lr=6.2173e-05) (hash(x)=5391352) -887 train 7.087307 (lr=6.1794e-05) (hash(x)=6270917) -888 train 7.082528 (lr=6.1418e-05) (hash(x)=5818195) -889 train 6.850028 (lr=6.1045e-05) (hash(x)=5852780) -890 train 6.771029 (lr=6.0675e-05) (hash(x)=5777928) -891 train 6.941120 (lr=6.0308e-05) (hash(x)=5327728) -892 train 6.976896 (lr=5.9944e-05) (hash(x)=7651281) -893 train 7.194061 (lr=5.9583e-05) (hash(x)=6260765) -894 train 7.064901 (lr=5.9225e-05) (hash(x)=6265102) -895 train 7.251947 (lr=5.8871e-05) (hash(x)=6212894) -896 train 7.007589 (lr=5.8519e-05) (hash(x)=6901967) -897 train 7.082289 (lr=5.8171e-05) (hash(x)=6724010) -898 train 7.069149 (lr=5.7826e-05) (hash(x)=6299033) -899 train 7.237507 (lr=5.7484e-05) (hash(x)=6059934) -900 val loss 7.1657 -900 val perplexity 1294.3068 -900 train 6.943421 (lr=5.7145e-05) (hash(x)=6029696) -901 train 6.854955 (lr=5.6809e-05) (hash(x)=5587382) -902 train 7.071787 (lr=5.6476e-05) (hash(x)=5890076) -903 train 6.993479 (lr=5.6147e-05) (hash(x)=7274108) -904 train 7.086677 (lr=5.5821e-05) (hash(x)=7975528) -905 train 7.135279 (lr=5.5497e-05) (hash(x)=6085396) -906 train 7.020583 (lr=5.5178e-05) (hash(x)=6724496) -907 train 7.017730 (lr=5.4861e-05) (hash(x)=4784666) -908 train 7.009595 (lr=5.4547e-05) (hash(x)=7193845) -909 train 7.177256 (lr=5.4237e-05) (hash(x)=6288638) -910 train 7.141451 (lr=5.3930e-05) (hash(x)=5685285) -911 train 7.123322 (lr=5.3626e-05) (hash(x)=7714288) -912 train 7.217126 (lr=5.3325e-05) (hash(x)=5983679) -913 train 7.159458 (lr=5.3028e-05) (hash(x)=5534748) -914 train 7.093553 (lr=5.2734e-05) (hash(x)=6545471) -915 train 7.090096 (lr=5.2443e-05) (hash(x)=6361270) -916 train 7.092950 (lr=5.2155e-05) (hash(x)=6257744) -917 train 7.096164 (lr=5.1871e-05) (hash(x)=4682956) -918 train 6.988361 (lr=5.1589e-05) (hash(x)=4521756) -919 train 7.126476 (lr=5.1311e-05) (hash(x)=7568935) -920 train 7.045220 (lr=5.1037e-05) (hash(x)=7969353) -921 train 7.253804 (lr=5.0765e-05) (hash(x)=7973311) -922 train 6.916569 (lr=5.0497e-05) (hash(x)=4843937) -923 train 7.070973 (lr=5.0232e-05) (hash(x)=6987352) -924 train 7.215007 (lr=4.9971e-05) (hash(x)=7179418) -925 train 6.840687 (lr=4.9712e-05) (hash(x)=5413904) -926 train 7.272241 (lr=4.9457e-05) (hash(x)=6028105) -927 train 7.176475 (lr=4.9206e-05) (hash(x)=6732924) -928 train 7.066581 (lr=4.8957e-05) (hash(x)=4547651) -929 train 7.206191 (lr=4.8712e-05) (hash(x)=6219754) -930 train 6.977387 (lr=4.8470e-05) (hash(x)=7465186) -931 train 7.135737 (lr=4.8232e-05) (hash(x)=6839070) -932 train 7.015966 (lr=4.7997e-05) (hash(x)=5390324) -933 train 6.991179 (lr=4.7765e-05) (hash(x)=6090120) -934 train 7.602218 (lr=4.7537e-05) (hash(x)=7123181) -935 train 7.291836 (lr=4.7312e-05) (hash(x)=7115176) -936 train 7.265821 (lr=4.7090e-05) (hash(x)=7016990) -937 train 7.070276 (lr=4.6871e-05) (hash(x)=4989299) -938 train 7.080413 (lr=4.6656e-05) (hash(x)=6783311) -939 train 7.054582 (lr=4.6445e-05) (hash(x)=7497590) -940 train 7.281096 (lr=4.6236e-05) (hash(x)=6767514) -941 train 7.032323 (lr=4.6031e-05) (hash(x)=3977557) -942 train 7.171589 (lr=4.5830e-05) (hash(x)=4806492) -943 train 7.065566 (lr=4.5631e-05) (hash(x)=5524165) -944 train 7.119200 (lr=4.5437e-05) (hash(x)=4930752) -945 train 7.072712 (lr=4.5245e-05) (hash(x)=5124936) -946 train 6.970873 (lr=4.5057e-05) (hash(x)=6877351) -947 train 7.258476 (lr=4.4872e-05) (hash(x)=5522119) -948 train 7.072148 (lr=4.4691e-05) (hash(x)=6183512) -949 train 6.988660 (lr=4.4513e-05) (hash(x)=5030865) -950 val loss 7.1565 -950 val perplexity 1282.4493 -950 train 7.080802 (lr=4.4338e-05) (hash(x)=6619812) -951 train 7.092521 (lr=4.4167e-05) (hash(x)=6411783) -952 train 7.075318 (lr=4.4000e-05) (hash(x)=6748982) -953 train 6.979934 (lr=4.3835e-05) (hash(x)=6581937) -954 train 7.094067 (lr=4.3674e-05) (hash(x)=7881022) -955 train 7.049211 (lr=4.3517e-05) (hash(x)=5116910) -956 train 6.840390 (lr=4.3363e-05) (hash(x)=4880833) -957 train 6.897750 (lr=4.3212e-05) (hash(x)=7353459) -958 train 6.958652 (lr=4.3065e-05) (hash(x)=4951302) -959 train 6.859964 (lr=4.2921e-05) (hash(x)=6344535) -960 train 7.482074 (lr=4.2781e-05) (hash(x)=7411763) -961 train 7.056205 (lr=4.2644e-05) (hash(x)=5840169) -962 train 7.154108 (lr=4.2510e-05) (hash(x)=5784788) -963 train 6.964046 (lr=4.2380e-05) (hash(x)=6754290) -964 train 7.243752 (lr=4.2253e-05) (hash(x)=6369963) -965 train 7.322361 (lr=4.2130e-05) (hash(x)=6484573) -966 train 6.894042 (lr=4.2010e-05) (hash(x)=6516338) -967 train 6.932183 (lr=4.1894e-05) (hash(x)=5260125) -968 train 7.070291 (lr=4.1781e-05) (hash(x)=5781624) -969 train 6.851396 (lr=4.1672e-05) (hash(x)=4881179) -970 train 6.993733 (lr=4.1566e-05) (hash(x)=6707821) -971 train 7.134998 (lr=4.1463e-05) (hash(x)=5001634) -972 train 6.999440 (lr=4.1364e-05) (hash(x)=4402949) -973 train 7.020264 (lr=4.1269e-05) (hash(x)=7424810) -974 train 6.895786 (lr=4.1177e-05) (hash(x)=4814803) -975 train 6.816129 (lr=4.1088e-05) (hash(x)=5176431) -976 train 7.014992 (lr=4.1003e-05) (hash(x)=5769393) -977 train 6.951116 (lr=4.0921e-05) (hash(x)=5421624) -978 train 7.168338 (lr=4.0843e-05) (hash(x)=5999773) -979 train 6.877117 (lr=4.0768e-05) (hash(x)=5674439) -980 train 6.972448 (lr=4.0697e-05) (hash(x)=6345351) -981 train 6.912955 (lr=4.0629e-05) (hash(x)=5819157) -982 train 7.121727 (lr=4.0564e-05) (hash(x)=11159355) -983 train 7.088211 (lr=4.0503e-05) (hash(x)=6506856) -984 train 7.000676 (lr=4.0446e-05) (hash(x)=6331023) -985 train 6.903489 (lr=4.0392e-05) (hash(x)=6119124) -986 train 7.111833 (lr=4.0341e-05) (hash(x)=8142528) -987 train 7.293222 (lr=4.0294e-05) (hash(x)=6241669) -988 train 6.915487 (lr=4.0251e-05) (hash(x)=3852991) -989 train 6.638735 (lr=4.0211e-05) (hash(x)=4992756) -990 train 7.366664 (lr=4.0174e-05) (hash(x)=7097145) -991 train 7.150247 (lr=4.0141e-05) (hash(x)=7277927) -992 train 7.241073 (lr=4.0112e-05) (hash(x)=5661400) -993 train 7.138251 (lr=4.0085e-05) (hash(x)=6622097) -994 train 7.261961 (lr=4.0063e-05) (hash(x)=5016804) -995 train 7.346981 (lr=4.0044e-05) (hash(x)=7026582) -996 train 7.134982 (lr=4.0028e-05) (hash(x)=5639136) -997 train 7.260903 (lr=4.0016e-05) (hash(x)=5840987) -998 train 6.904773 (lr=4.0007e-05) (hash(x)=5265410) -999 val loss 7.1602 -999 val perplexity 1287.1317 -999 train 6.898254 (lr=4.0002e-05) (hash(x)=4351074) +3 train 11.668599 (lr=5.5944e-06) (hash(x)=6328012) +4 train 11.663975 (lr=6.9930e-06) (hash(x)=7052161) +5 train 11.642254 (lr=8.3916e-06) (hash(x)=5556098) +6 train 11.612977 (lr=9.7902e-06) (hash(x)=4696943) +7 train 11.566650 (lr=1.1189e-05) (hash(x)=6219138) +8 train 11.502043 (lr=1.2587e-05) (hash(x)=6049878) +9 train 11.492296 (lr=1.3986e-05) (hash(x)=5491972) +10 train 11.453333 (lr=1.5385e-05) (hash(x)=8075458) +11 train 11.373230 (lr=1.6783e-05) (hash(x)=5917741) +12 train 11.346788 (lr=1.8182e-05) (hash(x)=5750403) +13 train 11.285571 (lr=1.9580e-05) (hash(x)=6112458) +14 train 11.230989 (lr=2.0979e-05) (hash(x)=5806490) +15 train 11.139845 (lr=2.2378e-05) (hash(x)=6568379) +16 train 11.057432 (lr=2.3776e-05) (hash(x)=7212403) +17 train 10.986838 (lr=2.5175e-05) (hash(x)=7386082) +18 train 10.942245 (lr=2.6573e-05) (hash(x)=6359743) +19 train 10.871616 (lr=2.7972e-05) (hash(x)=6151674) +20 train 10.837899 (lr=2.9371e-05) (hash(x)=7168704) +21 train 10.784581 (lr=3.0769e-05) (hash(x)=7859060) +22 train 10.694351 (lr=3.2168e-05) (hash(x)=6976239) +23 train 10.671911 (lr=3.3566e-05) (hash(x)=6391506) +24 train 10.644014 (lr=3.4965e-05) (hash(x)=5245999) +25 train 10.582640 (lr=3.6364e-05) (hash(x)=5985675) +26 train 10.488470 (lr=3.7762e-05) (hash(x)=4355733) +27 train 10.626515 (lr=3.9161e-05) (hash(x)=6984772) +28 train 10.492462 (lr=4.0559e-05) (hash(x)=6244096) +29 train 10.491182 (lr=4.1958e-05) (hash(x)=6603717) +30 train 10.396413 (lr=4.3357e-05) (hash(x)=5669522) +31 train 10.378435 (lr=4.4755e-05) (hash(x)=6190579) +32 train 10.431861 (lr=4.6154e-05) (hash(x)=4912983) +33 train 10.308258 (lr=4.7552e-05) (hash(x)=7276303) +34 train 10.367301 (lr=4.8951e-05) (hash(x)=5479947) +35 train 10.453874 (lr=5.0350e-05) (hash(x)=6630378) +36 train 10.395393 (lr=5.1748e-05) (hash(x)=8097010) +37 train 10.445938 (lr=5.3147e-05) (hash(x)=9989744) +38 train 10.327421 (lr=5.4545e-05) (hash(x)=6694932) +39 train 10.256737 (lr=5.5944e-05) (hash(x)=6317894) +40 train 10.177275 (lr=5.7343e-05) (hash(x)=5046327) +41 train 10.252541 (lr=5.8741e-05) (hash(x)=7947703) +42 train 10.124130 (lr=6.0140e-05) (hash(x)=5916068) +43 train 10.215006 (lr=6.1538e-05) (hash(x)=5777498) +44 train 10.147282 (lr=6.2937e-05) (hash(x)=5753092) +45 train 10.135040 (lr=6.4336e-05) (hash(x)=7723226) +46 train 10.122688 (lr=6.5734e-05) (hash(x)=7007016) +47 train 10.054515 (lr=6.7133e-05) (hash(x)=6491229) +48 train 10.100163 (lr=6.8531e-05) (hash(x)=6390752) +49 train 10.210835 (lr=6.9930e-05) (hash(x)=6019389) +50 val loss 10.0889 +50 val perplexity 24074.9297 +50 train 10.081839 (lr=7.1329e-05) (hash(x)=7662067) +51 train 10.082613 (lr=7.2727e-05) (hash(x)=4648609) +52 train 10.019441 (lr=7.4126e-05) (hash(x)=4725966) +53 train 9.983593 (lr=7.5524e-05) (hash(x)=5558355) +54 train 10.021416 (lr=7.6923e-05) (hash(x)=6524933) +55 train 9.972417 (lr=7.8322e-05) (hash(x)=6369326) +56 train 9.941675 (lr=7.9720e-05) (hash(x)=6022625) +57 train 9.886727 (lr=8.1119e-05) (hash(x)=4906853) +58 train 9.723225 (lr=8.2517e-05) (hash(x)=5589269) +59 train 9.838627 (lr=8.3916e-05) (hash(x)=6437376) +60 train 9.870028 (lr=8.5315e-05) (hash(x)=7304892) +61 train 9.823192 (lr=8.6713e-05) (hash(x)=7084093) +62 train 9.840137 (lr=8.8112e-05) (hash(x)=5908178) +63 train 9.638361 (lr=8.9510e-05) (hash(x)=7048804) +64 train 9.715075 (lr=9.0909e-05) (hash(x)=6085549) +65 train 9.715473 (lr=9.2308e-05) (hash(x)=5752594) +66 train 9.527724 (lr=9.3706e-05) (hash(x)=7662769) +67 train 9.388057 (lr=9.5105e-05) (hash(x)=6393520) +68 train 9.635707 (lr=9.6503e-05) (hash(x)=5942867) +69 train 9.620716 (lr=9.7902e-05) (hash(x)=6793550) +70 train 9.476423 (lr=9.9301e-05) (hash(x)=7105976) +71 train 9.504151 (lr=1.0070e-04) (hash(x)=6581348) +72 train 9.443439 (lr=1.0210e-04) (hash(x)=5555598) +73 train 9.372897 (lr=1.0350e-04) (hash(x)=6235837) +74 train 9.315989 (lr=1.0490e-04) (hash(x)=5591770) +75 train 9.504561 (lr=1.0629e-04) (hash(x)=7083021) +76 train 9.340022 (lr=1.0769e-04) (hash(x)=7281348) +77 train 9.369104 (lr=1.0909e-04) (hash(x)=6155821) +78 train 9.217697 (lr=1.1049e-04) (hash(x)=5736241) +79 train 9.136160 (lr=1.1189e-04) (hash(x)=5657123) +80 train 9.023884 (lr=1.1329e-04) (hash(x)=6452095) +81 train 9.029348 (lr=1.1469e-04) (hash(x)=5312267) +82 train 8.980440 (lr=1.1608e-04) (hash(x)=5434493) +83 train 9.088493 (lr=1.1748e-04) (hash(x)=6830813) +84 train 8.973318 (lr=1.1888e-04) (hash(x)=4752771) +85 train 8.990337 (lr=1.2028e-04) (hash(x)=6424933) +86 train 8.898154 (lr=1.2168e-04) (hash(x)=5786517) +87 train 8.911846 (lr=1.2308e-04) (hash(x)=6680023) +88 train 8.803731 (lr=1.2448e-04) (hash(x)=6474729) +89 train 8.852645 (lr=1.2587e-04) (hash(x)=7523279) +90 train 8.656075 (lr=1.2727e-04) (hash(x)=5508768) +91 train 8.763476 (lr=1.2867e-04) (hash(x)=6635925) +92 train 8.700764 (lr=1.3007e-04) (hash(x)=6663801) +93 train 8.665603 (lr=1.3147e-04) (hash(x)=5869441) +94 train 8.663618 (lr=1.3287e-04) (hash(x)=6698878) +95 train 8.607197 (lr=1.3427e-04) (hash(x)=6349004) +96 train 8.598606 (lr=1.3566e-04) (hash(x)=4986137) +97 train 8.390861 (lr=1.3706e-04) (hash(x)=6008454) +98 train 8.429855 (lr=1.3846e-04) (hash(x)=6550770) +99 train 8.521902 (lr=1.3986e-04) (hash(x)=7682741) +100 val loss 8.4879 +100 val perplexity 4855.6479 +100 train 8.560909 (lr=1.4126e-04) (hash(x)=7892158) +101 train 8.443310 (lr=1.4266e-04) (hash(x)=7794028) +102 train 8.444137 (lr=1.4406e-04) (hash(x)=7093523) +103 train 8.424159 (lr=1.4545e-04) (hash(x)=6166062) +104 train 8.361854 (lr=1.4685e-04) (hash(x)=6645781) +105 train 8.344572 (lr=1.4825e-04) (hash(x)=4811192) +106 train 8.256047 (lr=1.4965e-04) (hash(x)=5970866) +107 train 8.287255 (lr=1.5105e-04) (hash(x)=7822680) +108 train 8.204074 (lr=1.5245e-04) (hash(x)=6317317) +109 train 8.260469 (lr=1.5385e-04) (hash(x)=6431409) +110 train 8.277518 (lr=1.5524e-04) (hash(x)=6653337) +111 train 8.199308 (lr=1.5664e-04) (hash(x)=5323032) +112 train 8.115597 (lr=1.5804e-04) (hash(x)=5125339) +113 train 8.083223 (lr=1.5944e-04) (hash(x)=7363286) +114 train 8.332310 (lr=1.6084e-04) (hash(x)=7670050) +115 train 8.133595 (lr=1.6224e-04) (hash(x)=5616075) +116 train 8.169359 (lr=1.6364e-04) (hash(x)=6593764) +117 train 8.204596 (lr=1.6503e-04) (hash(x)=5672608) +118 train 8.097459 (lr=1.6643e-04) (hash(x)=6828653) +119 train 8.064495 (lr=1.6783e-04) (hash(x)=6839867) +120 train 8.146966 (lr=1.6923e-04) (hash(x)=8426992) +121 train 7.851494 (lr=1.7063e-04) (hash(x)=4916928) +122 train 8.044436 (lr=1.7203e-04) (hash(x)=6484050) +123 train 8.102897 (lr=1.7343e-04) (hash(x)=8353379) +124 train 7.995897 (lr=1.7483e-04) (hash(x)=6552510) +125 train 7.994003 (lr=1.7622e-04) (hash(x)=4838871) +126 train 7.752324 (lr=1.7762e-04) (hash(x)=3021697) +127 train 7.857156 (lr=1.7902e-04) (hash(x)=6795665) +128 train 7.848892 (lr=1.8042e-04) (hash(x)=5486935) +129 train 8.026804 (lr=1.8182e-04) (hash(x)=6678038) +130 train 8.026256 (lr=1.8322e-04) (hash(x)=6657714) +131 train 7.945943 (lr=1.8462e-04) (hash(x)=6112215) +132 train 7.953169 (lr=1.8601e-04) (hash(x)=8353143) +133 train 7.956581 (lr=1.8741e-04) (hash(x)=5915361) +134 train 7.848178 (lr=1.8881e-04) (hash(x)=6254885) +135 train 7.880404 (lr=1.9021e-04) (hash(x)=5771588) +136 train 7.843487 (lr=1.9161e-04) (hash(x)=5561507) +137 train 7.807485 (lr=1.9301e-04) (hash(x)=5688829) +138 train 7.767586 (lr=1.9441e-04) (hash(x)=5371951) +139 train 7.907703 (lr=1.9580e-04) (hash(x)=5443305) +140 train 7.914382 (lr=1.9720e-04) (hash(x)=5016757) +141 train 7.898002 (lr=1.9860e-04) (hash(x)=6901933) +142 train 7.858418 (lr=2.0000e-04) (hash(x)=6019085) +143 train 7.723762 (lr=2.0140e-04) (hash(x)=4294425) +144 train 7.804673 (lr=2.0280e-04) (hash(x)=6095229) +145 train 7.646305 (lr=2.0420e-04) (hash(x)=4363941) +146 train 7.722137 (lr=2.0559e-04) (hash(x)=4693798) +147 train 8.213309 (lr=2.0699e-04) (hash(x)=5486335) +148 train 8.029712 (lr=2.0839e-04) (hash(x)=7907450) +149 train 7.872520 (lr=2.0979e-04) (hash(x)=7295165) +150 val loss 7.7626 +150 val perplexity 2351.0942 +150 train 7.801119 (lr=2.1119e-04) (hash(x)=6814026) +151 train 7.881440 (lr=2.1259e-04) (hash(x)=6267424) +152 train 7.872754 (lr=2.1399e-04) (hash(x)=8086437) +153 train 7.916137 (lr=2.1538e-04) (hash(x)=5270452) +154 train 7.756899 (lr=2.1678e-04) (hash(x)=6420820) +155 train 7.664027 (lr=2.1818e-04) (hash(x)=6305297) +156 train 7.830265 (lr=2.1958e-04) (hash(x)=7889849) +157 train 8.169842 (lr=2.2098e-04) (hash(x)=6040077) +158 train 8.172132 (lr=2.2238e-04) (hash(x)=5652497) +159 train 7.742303 (lr=2.2378e-04) (hash(x)=7130251) +160 train 7.614914 (lr=2.2517e-04) (hash(x)=6610177) +161 train 7.666033 (lr=2.2657e-04) (hash(x)=6508350) +162 train 7.820766 (lr=2.2797e-04) (hash(x)=6994983) +163 train 7.770495 (lr=2.2937e-04) (hash(x)=5859576) +164 train 7.340787 (lr=2.3077e-04) (hash(x)=5487065) +165 train 7.572525 (lr=2.3217e-04) (hash(x)=4892065) +166 train 7.460403 (lr=2.3357e-04) (hash(x)=4933674) +167 train 7.740736 (lr=2.3497e-04) (hash(x)=7317289) +168 train 7.831223 (lr=2.3636e-04) (hash(x)=6811522) +169 train 7.669032 (lr=2.3776e-04) (hash(x)=5510218) +170 train 7.821404 (lr=2.3916e-04) (hash(x)=7304235) +171 train 7.972172 (lr=2.4056e-04) (hash(x)=6752265) +172 train 7.662764 (lr=2.4196e-04) (hash(x)=5994476) +173 train 7.639644 (lr=2.4336e-04) (hash(x)=6530867) +174 train 7.748015 (lr=2.4476e-04) (hash(x)=5746260) +175 train 7.695560 (lr=2.4615e-04) (hash(x)=5790078) +176 train 7.714489 (lr=2.4755e-04) (hash(x)=6430135) +177 train 7.769151 (lr=2.4895e-04) (hash(x)=7614023) +178 train 7.759392 (lr=2.5035e-04) (hash(x)=5244861) +179 train 7.748844 (lr=2.5175e-04) (hash(x)=5245146) +180 train 7.641789 (lr=2.5315e-04) (hash(x)=6415565) +181 train 7.698789 (lr=2.5455e-04) (hash(x)=5786972) +182 train 7.736896 (lr=2.5594e-04) (hash(x)=6131703) +183 train 7.744957 (lr=2.5734e-04) (hash(x)=6346459) +184 train 7.785090 (lr=2.5874e-04) (hash(x)=6504131) +185 train 7.766044 (lr=2.6014e-04) (hash(x)=5209234) +186 train 7.676859 (lr=2.6154e-04) (hash(x)=6163272) +187 train 7.677661 (lr=2.6294e-04) (hash(x)=5676768) +188 train 7.754196 (lr=2.6434e-04) (hash(x)=6090561) +189 train 7.888874 (lr=2.6573e-04) (hash(x)=5863092) +190 train 7.808018 (lr=2.6713e-04) (hash(x)=7201312) +191 train 7.883904 (lr=2.6853e-04) (hash(x)=7019489) +192 train 7.651485 (lr=2.6993e-04) (hash(x)=6225608) +193 train 7.729876 (lr=2.7133e-04) (hash(x)=5483019) +194 train 7.682510 (lr=2.7273e-04) (hash(x)=5903258) +195 train 7.727228 (lr=2.7413e-04) (hash(x)=5968716) +196 train 7.717389 (lr=2.7552e-04) (hash(x)=5778017) +197 train 7.458175 (lr=2.7692e-04) (hash(x)=7780194) +198 train 7.648131 (lr=2.7832e-04) (hash(x)=6140998) +199 train 7.638054 (lr=2.7972e-04) (hash(x)=3784321) +200 val loss 7.6668 +200 val perplexity 2136.3303 +200 train 7.665111 (lr=2.8112e-04) (hash(x)=5860821) +201 train 7.714205 (lr=2.8252e-04) (hash(x)=7774109) +202 train 7.874697 (lr=2.8392e-04) (hash(x)=7997664) +203 train 7.847374 (lr=2.8531e-04) (hash(x)=6576749) +204 train 7.770347 (lr=2.8671e-04) (hash(x)=7266655) +205 train 7.731509 (lr=2.8811e-04) (hash(x)=7072404) +206 train 7.642121 (lr=2.8951e-04) (hash(x)=6626459) +207 train 7.675529 (lr=2.9091e-04) (hash(x)=6556025) +208 train 7.696689 (lr=2.9231e-04) (hash(x)=5942129) +209 train 7.799453 (lr=2.9371e-04) (hash(x)=7325027) +210 train 7.807098 (lr=2.9510e-04) (hash(x)=7322467) +211 train 7.731977 (lr=2.9650e-04) (hash(x)=6373412) +212 train 7.531200 (lr=2.9790e-04) (hash(x)=7332255) +213 train 7.793663 (lr=2.9930e-04) (hash(x)=5262868) +214 train 7.525547 (lr=3.0070e-04) (hash(x)=5688247) +215 train 7.713514 (lr=3.0210e-04) (hash(x)=8055563) +216 train 7.708601 (lr=3.0350e-04) (hash(x)=5352405) +217 train 7.758339 (lr=3.0490e-04) (hash(x)=5932790) +218 train 7.716666 (lr=3.0629e-04) (hash(x)=6249312) +219 train 7.656990 (lr=3.0769e-04) (hash(x)=5680154) +220 train 7.767953 (lr=3.0909e-04) (hash(x)=8156280) +221 train 7.716599 (lr=3.1049e-04) (hash(x)=5914217) +222 train 7.559160 (lr=3.1189e-04) (hash(x)=7120215) +223 train 7.735987 (lr=3.1329e-04) (hash(x)=6424128) +224 train 7.493481 (lr=3.1469e-04) (hash(x)=4390027) +225 train 7.696038 (lr=3.1608e-04) (hash(x)=7804089) +226 train 7.819855 (lr=3.1748e-04) (hash(x)=7130267) +227 train 7.661702 (lr=3.1888e-04) (hash(x)=6490149) +228 train 7.648042 (lr=3.2028e-04) (hash(x)=9276378) +229 train 7.679459 (lr=3.2168e-04) (hash(x)=6283540) +230 train 7.660205 (lr=3.2308e-04) (hash(x)=5781680) +231 train 7.598940 (lr=3.2448e-04) (hash(x)=5728337) +232 train 7.581058 (lr=3.2587e-04) (hash(x)=6278202) +233 train 7.684605 (lr=3.2727e-04) (hash(x)=7400272) +234 train 7.667821 (lr=3.2867e-04) (hash(x)=5795128) +235 train 7.635843 (lr=3.3007e-04) (hash(x)=6473432) +236 train 7.638198 (lr=3.3147e-04) (hash(x)=5201502) +237 train 7.851905 (lr=3.3287e-04) (hash(x)=6922646) +238 train 7.582545 (lr=3.3427e-04) (hash(x)=5484641) +239 train 7.641405 (lr=3.3566e-04) (hash(x)=7277141) +240 train 7.652216 (lr=3.3706e-04) (hash(x)=5604614) +241 train 7.710049 (lr=3.3846e-04) (hash(x)=7443124) +242 train 7.723013 (lr=3.3986e-04) (hash(x)=5601968) +243 train 7.618766 (lr=3.4126e-04) (hash(x)=5632735) +244 train 7.615646 (lr=3.4266e-04) (hash(x)=5594810) +245 train 7.451205 (lr=3.4406e-04) (hash(x)=5881015) +246 train 7.622200 (lr=3.4545e-04) (hash(x)=6865361) +247 train 7.705945 (lr=3.4685e-04) (hash(x)=5809411) +248 train 7.700913 (lr=3.4825e-04) (hash(x)=6293025) +249 train 7.635019 (lr=3.4965e-04) (hash(x)=7232964) +250 val loss 7.6329 +250 val perplexity 2065.0815 +250 train 7.569902 (lr=3.5105e-04) (hash(x)=5646619) +251 train 7.691182 (lr=3.5245e-04) (hash(x)=6171829) +252 train 7.754964 (lr=3.5385e-04) (hash(x)=7787552) +253 train 7.704890 (lr=3.5524e-04) (hash(x)=5884456) +254 train 7.732307 (lr=3.5664e-04) (hash(x)=6752162) +255 train 7.625611 (lr=3.5804e-04) (hash(x)=5077031) +256 train 7.804005 (lr=3.5944e-04) (hash(x)=6883481) +257 train 7.695967 (lr=3.6084e-04) (hash(x)=6248895) +258 train 7.565556 (lr=3.6224e-04) (hash(x)=6636615) +259 train 7.753356 (lr=3.6364e-04) (hash(x)=6918004) +260 train 7.658677 (lr=3.6503e-04) (hash(x)=7302874) +261 train 7.773692 (lr=3.6643e-04) (hash(x)=6482466) +262 train 7.620600 (lr=3.6783e-04) (hash(x)=7298317) +263 train 7.653758 (lr=3.6923e-04) (hash(x)=6588573) +264 train 7.650673 (lr=3.7063e-04) (hash(x)=6229630) +265 train 7.697197 (lr=3.7203e-04) (hash(x)=6136939) +266 train 7.468801 (lr=3.7343e-04) (hash(x)=6394645) +267 train 7.706978 (lr=3.7483e-04) (hash(x)=7040157) +268 train 7.733478 (lr=3.7622e-04) (hash(x)=7041858) +269 train 7.659576 (lr=3.7762e-04) (hash(x)=6455595) +270 train 7.594198 (lr=3.7902e-04) (hash(x)=6480443) +271 train 7.757108 (lr=3.8042e-04) (hash(x)=4122983) +272 train 7.581870 (lr=3.8182e-04) (hash(x)=7672190) +273 train 7.618864 (lr=3.8322e-04) (hash(x)=4724052) +274 train 7.573687 (lr=3.8462e-04) (hash(x)=6654267) +275 train 7.567622 (lr=3.8601e-04) (hash(x)=6820797) +276 train 7.635229 (lr=3.8741e-04) (hash(x)=6458662) +277 train 8.026220 (lr=3.8881e-04) (hash(x)=7477594) +278 train 7.698599 (lr=3.9021e-04) (hash(x)=5876574) +279 train 7.417127 (lr=3.9161e-04) (hash(x)=6146305) +280 train 7.599573 (lr=3.9301e-04) (hash(x)=6162080) +281 train 7.546029 (lr=3.9441e-04) (hash(x)=6814831) +282 train 7.689419 (lr=3.9580e-04) (hash(x)=7138295) +283 train 7.465721 (lr=3.9720e-04) (hash(x)=5548298) +284 train 7.566527 (lr=3.9860e-04) (hash(x)=6265078) +285 train 7.941619 (lr=4.0000e-04) (hash(x)=7609416) +286 train 7.642284 (lr=4.0000e-04) (hash(x)=6909367) +287 train 7.742813 (lr=4.0000e-04) (hash(x)=7574342) +288 train 7.561686 (lr=3.9999e-04) (hash(x)=8859748) +289 train 7.507805 (lr=3.9998e-04) (hash(x)=5906937) +290 train 7.532437 (lr=3.9997e-04) (hash(x)=7243024) +291 train 7.638661 (lr=3.9996e-04) (hash(x)=8013471) +292 train 7.563684 (lr=3.9994e-04) (hash(x)=5659461) +293 train 7.602683 (lr=3.9991e-04) (hash(x)=6146213) +294 train 7.640275 (lr=3.9989e-04) (hash(x)=6602917) +295 train 7.560316 (lr=3.9986e-04) (hash(x)=6709902) +296 train 7.672884 (lr=3.9983e-04) (hash(x)=8154341) +297 train 7.823232 (lr=3.9979e-04) (hash(x)=6402571) +298 train 7.583462 (lr=3.9975e-04) (hash(x)=5605466) +299 train 7.535816 (lr=3.9971e-04) (hash(x)=7683614) +300 val loss 7.5887 +300 val perplexity 1975.6564 +300 train 7.625172 (lr=3.9966e-04) (hash(x)=5421572) +301 train 7.472358 (lr=3.9961e-04) (hash(x)=5453026) +302 train 7.550536 (lr=3.9955e-04) (hash(x)=6437746) +303 train 7.447942 (lr=3.9950e-04) (hash(x)=6260017) +304 train 7.549609 (lr=3.9944e-04) (hash(x)=6119053) +305 train 7.697911 (lr=3.9937e-04) (hash(x)=6591466) +306 train 7.609343 (lr=3.9930e-04) (hash(x)=5652701) +307 train 7.587608 (lr=3.9923e-04) (hash(x)=5501472) +308 train 7.775560 (lr=3.9916e-04) (hash(x)=6160695) +309 train 7.524661 (lr=3.9908e-04) (hash(x)=5871698) +310 train 7.508925 (lr=3.9900e-04) (hash(x)=7301184) +311 train 7.425855 (lr=3.9891e-04) (hash(x)=4282052) +312 train 7.629645 (lr=3.9882e-04) (hash(x)=5679330) +313 train 7.499234 (lr=3.9873e-04) (hash(x)=7824660) +314 train 7.531750 (lr=3.9864e-04) (hash(x)=4857318) +315 train 7.460138 (lr=3.9854e-04) (hash(x)=5954950) +316 train 7.545074 (lr=3.9843e-04) (hash(x)=5758178) +317 train 7.559426 (lr=3.9833e-04) (hash(x)=5484656) +318 train 7.560868 (lr=3.9822e-04) (hash(x)=6818913) +319 train 7.743922 (lr=3.9811e-04) (hash(x)=7031328) +320 train 7.600710 (lr=3.9799e-04) (hash(x)=6837621) +321 train 7.625903 (lr=3.9787e-04) (hash(x)=9157069) +322 train 7.864896 (lr=3.9775e-04) (hash(x)=6509536) +323 train 7.560966 (lr=3.9762e-04) (hash(x)=5996883) +324 train 7.798395 (lr=3.9749e-04) (hash(x)=6850868) +325 train 7.744821 (lr=3.9736e-04) (hash(x)=7645447) +326 train 7.756393 (lr=3.9722e-04) (hash(x)=6717515) +327 train 7.859602 (lr=3.9708e-04) (hash(x)=6336164) +328 train 7.576122 (lr=3.9694e-04) (hash(x)=6897445) +329 train 7.499548 (lr=3.9679e-04) (hash(x)=5224240) +330 train 7.635642 (lr=3.9664e-04) (hash(x)=6612945) +331 train 8.100457 (lr=3.9648e-04) (hash(x)=5447801) +332 train 7.636302 (lr=3.9633e-04) (hash(x)=7308579) +333 train 7.509712 (lr=3.9616e-04) (hash(x)=4155598) +334 train 7.546395 (lr=3.9600e-04) (hash(x)=6106773) +335 train 7.582079 (lr=3.9583e-04) (hash(x)=7482744) +336 train 7.634215 (lr=3.9566e-04) (hash(x)=6310687) +337 train 7.516341 (lr=3.9549e-04) (hash(x)=4733414) +338 train 7.642998 (lr=3.9531e-04) (hash(x)=6979734) +339 train 7.441540 (lr=3.9513e-04) (hash(x)=7806284) +340 train 7.449180 (lr=3.9494e-04) (hash(x)=5080536) +341 train 7.661563 (lr=3.9475e-04) (hash(x)=7236478) +342 train 7.603889 (lr=3.9456e-04) (hash(x)=6619318) +343 train 7.544798 (lr=3.9437e-04) (hash(x)=4656255) +344 train 7.462327 (lr=3.9417e-04) (hash(x)=5546888) +345 train 7.876224 (lr=3.9397e-04) (hash(x)=9298325) +346 train 7.602437 (lr=3.9376e-04) (hash(x)=5994232) +347 train 7.578405 (lr=3.9356e-04) (hash(x)=6287524) +348 train 7.681384 (lr=3.9334e-04) (hash(x)=6200049) +349 train 7.598798 (lr=3.9313e-04) (hash(x)=7895970) +350 val loss 7.5419 +350 val perplexity 1885.3993 +350 train 7.519921 (lr=3.9291e-04) (hash(x)=6051847) +351 train 7.660943 (lr=3.9269e-04) (hash(x)=8847992) +352 train 8.006535 (lr=3.9246e-04) (hash(x)=5123883) +353 train 7.636000 (lr=3.9223e-04) (hash(x)=6338998) +354 train 7.635743 (lr=3.9200e-04) (hash(x)=5765866) +355 train 7.966119 (lr=3.9177e-04) (hash(x)=7104011) +356 train 7.728853 (lr=3.9153e-04) (hash(x)=7438267) +357 train 7.470283 (lr=3.9129e-04) (hash(x)=5573214) +358 train 7.769766 (lr=3.9104e-04) (hash(x)=6897283) +359 train 7.548629 (lr=3.9079e-04) (hash(x)=6882897) +360 train 7.657766 (lr=3.9054e-04) (hash(x)=5343615) +361 train 7.546317 (lr=3.9029e-04) (hash(x)=5854242) +362 train 7.458848 (lr=3.9003e-04) (hash(x)=6317324) +363 train 7.409717 (lr=3.8977e-04) (hash(x)=6972494) +364 train 7.471271 (lr=3.8950e-04) (hash(x)=5661167) +365 train 7.488361 (lr=3.8923e-04) (hash(x)=6796805) +366 train 7.341200 (lr=3.8896e-04) (hash(x)=5817209) +367 train 7.402862 (lr=3.8869e-04) (hash(x)=6139120) +368 train 7.586423 (lr=3.8841e-04) (hash(x)=6121296) +369 train 7.532811 (lr=3.8813e-04) (hash(x)=6486796) +370 train 7.452713 (lr=3.8785e-04) (hash(x)=5514645) +371 train 7.381469 (lr=3.8756e-04) (hash(x)=5578797) +372 train 7.406301 (lr=3.8727e-04) (hash(x)=7651738) +373 train 7.612904 (lr=3.8697e-04) (hash(x)=6895326) +374 train 7.620765 (lr=3.8667e-04) (hash(x)=5490256) +375 train 7.512875 (lr=3.8637e-04) (hash(x)=7783160) +376 train 7.686960 (lr=3.8607e-04) (hash(x)=5608424) +377 train 7.449463 (lr=3.8576e-04) (hash(x)=4867625) +378 train 7.367590 (lr=3.8545e-04) (hash(x)=4655472) +379 train 7.434838 (lr=3.8514e-04) (hash(x)=6631123) +380 train 7.101231 (lr=3.8482e-04) (hash(x)=5751990) +381 train 7.395020 (lr=3.8450e-04) (hash(x)=6710965) +382 train 7.377497 (lr=3.8418e-04) (hash(x)=5293800) +383 train 7.432155 (lr=3.8385e-04) (hash(x)=6294657) +384 train 7.603856 (lr=3.8352e-04) (hash(x)=6999538) +385 train 7.564030 (lr=3.8319e-04) (hash(x)=5443606) +386 train 7.552951 (lr=3.8286e-04) (hash(x)=5650401) +387 train 7.532697 (lr=3.8252e-04) (hash(x)=7035770) +388 train 7.477146 (lr=3.8217e-04) (hash(x)=6678271) +389 train 7.662197 (lr=3.8183e-04) (hash(x)=4899541) +390 train 7.419435 (lr=3.8148e-04) (hash(x)=5359260) +391 train 7.430234 (lr=3.8113e-04) (hash(x)=6227120) +392 train 7.476434 (lr=3.8077e-04) (hash(x)=6643916) +393 train 7.556436 (lr=3.8042e-04) (hash(x)=5981648) +394 train 7.525835 (lr=3.8006e-04) (hash(x)=6467540) +395 train 7.457469 (lr=3.7969e-04) (hash(x)=5558993) +396 train 7.623603 (lr=3.7933e-04) (hash(x)=6698959) +397 train 7.434885 (lr=3.7896e-04) (hash(x)=7015671) +398 train 7.434843 (lr=3.7858e-04) (hash(x)=6800890) +399 train 7.570840 (lr=3.7821e-04) (hash(x)=5931234) +400 val loss 7.4818 +400 val perplexity 1775.4008 +400 train 7.505006 (lr=3.7783e-04) (hash(x)=3995070) +401 train 7.446759 (lr=3.7744e-04) (hash(x)=4582159) +402 train 7.501878 (lr=3.7706e-04) (hash(x)=7081906) +403 train 7.500100 (lr=3.7667e-04) (hash(x)=5029472) +404 train 7.463895 (lr=3.7628e-04) (hash(x)=3946232) +405 train 7.369647 (lr=3.7588e-04) (hash(x)=5434102) +406 train 8.088981 (lr=3.7549e-04) (hash(x)=5340646) +407 train 7.277464 (lr=3.7509e-04) (hash(x)=6810638) +408 train 7.527253 (lr=3.7468e-04) (hash(x)=6768026) +409 train 7.523851 (lr=3.7428e-04) (hash(x)=6521562) +410 train 7.480124 (lr=3.7387e-04) (hash(x)=4429434) +411 train 7.548787 (lr=3.7345e-04) (hash(x)=7226932) +412 train 7.328004 (lr=3.7304e-04) (hash(x)=5065932) +413 train 7.491096 (lr=3.7262e-04) (hash(x)=6957849) +414 train 7.472599 (lr=3.7220e-04) (hash(x)=6431457) +415 train 7.540831 (lr=3.7177e-04) (hash(x)=5334281) +416 train 7.552095 (lr=3.7135e-04) (hash(x)=5471747) +417 train 7.653757 (lr=3.7092e-04) (hash(x)=5887983) +418 train 7.567940 (lr=3.7048e-04) (hash(x)=5075909) +419 train 7.353391 (lr=3.7005e-04) (hash(x)=6393576) +420 train 7.471872 (lr=3.6961e-04) (hash(x)=6608979) +421 train 7.882187 (lr=3.6917e-04) (hash(x)=5057959) +422 train 7.793412 (lr=3.6872e-04) (hash(x)=6414858) +423 train 7.575715 (lr=3.6828e-04) (hash(x)=8595271) +424 train 7.445928 (lr=3.6782e-04) (hash(x)=6500949) +425 train 7.598707 (lr=3.6737e-04) (hash(x)=8395167) +426 train 7.703246 (lr=3.6692e-04) (hash(x)=6288420) +427 train 7.565794 (lr=3.6646e-04) (hash(x)=7634417) +428 train 7.452353 (lr=3.6599e-04) (hash(x)=6795561) +429 train 7.366128 (lr=3.6553e-04) (hash(x)=5257771) +430 train 7.534714 (lr=3.6506e-04) (hash(x)=7506860) +431 train 7.562077 (lr=3.6459e-04) (hash(x)=7674238) +432 train 7.621844 (lr=3.6412e-04) (hash(x)=5353794) +433 train 7.561383 (lr=3.6364e-04) (hash(x)=5300555) +434 train 7.311060 (lr=3.6316e-04) (hash(x)=5564419) +435 train 7.534441 (lr=3.6268e-04) (hash(x)=6066139) +436 train 7.513524 (lr=3.6220e-04) (hash(x)=6863709) +437 train 7.511140 (lr=3.6171e-04) (hash(x)=6688212) +438 train 7.672241 (lr=3.6122e-04) (hash(x)=7095090) +439 train 7.753230 (lr=3.6073e-04) (hash(x)=6642404) +440 train 7.479750 (lr=3.6023e-04) (hash(x)=6539227) +441 train 7.474813 (lr=3.5974e-04) (hash(x)=4961570) +442 train 7.419219 (lr=3.5924e-04) (hash(x)=6606391) +443 train 7.233069 (lr=3.5873e-04) (hash(x)=5105190) +444 train 7.788304 (lr=3.5823e-04) (hash(x)=5695997) +445 train 7.476083 (lr=3.5772e-04) (hash(x)=7155991) +446 train 7.461076 (lr=3.5721e-04) (hash(x)=7249727) +447 train 7.447714 (lr=3.5669e-04) (hash(x)=5132972) +448 train 7.436718 (lr=3.5618e-04) (hash(x)=5381802) +449 train 7.468949 (lr=3.5566e-04) (hash(x)=6269946) +450 val loss 7.4324 +450 val perplexity 1689.8700 +450 train 7.409864 (lr=3.5514e-04) (hash(x)=4976762) +451 train 7.512599 (lr=3.5461e-04) (hash(x)=5396133) +452 train 7.474947 (lr=3.5408e-04) (hash(x)=6173473) +453 train 7.458471 (lr=3.5355e-04) (hash(x)=6394083) +454 train 7.511147 (lr=3.5302e-04) (hash(x)=6436030) +455 train 7.372351 (lr=3.5249e-04) (hash(x)=5237804) +456 train 7.354269 (lr=3.5195e-04) (hash(x)=6540397) +457 train 7.599018 (lr=3.5141e-04) (hash(x)=5216638) +458 train 7.426204 (lr=3.5087e-04) (hash(x)=5750537) +459 train 7.408210 (lr=3.5032e-04) (hash(x)=6735565) +460 train 7.423842 (lr=3.4977e-04) (hash(x)=7297488) +461 train 7.590972 (lr=3.4922e-04) (hash(x)=5983575) +462 train 7.436912 (lr=3.4867e-04) (hash(x)=4808543) +463 train 7.532351 (lr=3.4812e-04) (hash(x)=5831619) +464 train 7.304359 (lr=3.4756e-04) (hash(x)=6280052) +465 train 7.317745 (lr=3.4700e-04) (hash(x)=9109083) +466 train 7.574814 (lr=3.4644e-04) (hash(x)=5848604) +467 train 7.516620 (lr=3.4587e-04) (hash(x)=6912967) +468 train 7.664823 (lr=3.4530e-04) (hash(x)=6615365) +469 train 7.698574 (lr=3.4473e-04) (hash(x)=5965674) +470 train 7.577804 (lr=3.4416e-04) (hash(x)=6879965) +471 train 7.566149 (lr=3.4359e-04) (hash(x)=5822533) +472 train 7.414194 (lr=3.4301e-04) (hash(x)=5794462) +473 train 7.515330 (lr=3.4243e-04) (hash(x)=5268216) +474 train 7.320827 (lr=3.4185e-04) (hash(x)=7058396) +475 train 7.413641 (lr=3.4127e-04) (hash(x)=6531900) +476 train 7.436832 (lr=3.4068e-04) (hash(x)=5878912) +477 train 7.273552 (lr=3.4009e-04) (hash(x)=5426499) +478 train 7.477423 (lr=3.3950e-04) (hash(x)=8107004) +479 train 8.170026 (lr=3.3891e-04) (hash(x)=7455372) +480 train 8.097099 (lr=3.3831e-04) (hash(x)=7727959) +481 train 8.020588 (lr=3.3771e-04) (hash(x)=8319119) +482 train 7.945535 (lr=3.3711e-04) (hash(x)=7581656) +483 train 8.009356 (lr=3.3651e-04) (hash(x)=7592128) +484 train 7.977788 (lr=3.3590e-04) (hash(x)=10506633) +485 train 7.935920 (lr=3.3530e-04) (hash(x)=8704170) +486 train 7.772789 (lr=3.3469e-04) (hash(x)=7461138) +487 train 7.675597 (lr=3.3408e-04) (hash(x)=7165037) +488 train 7.705663 (lr=3.3346e-04) (hash(x)=4976998) +489 train 7.442335 (lr=3.3285e-04) (hash(x)=7678000) +490 train 7.486555 (lr=3.3223e-04) (hash(x)=6299409) +491 train 7.461079 (lr=3.3161e-04) (hash(x)=7414788) +492 train 7.529131 (lr=3.3099e-04) (hash(x)=5063061) +493 train 7.475542 (lr=3.3036e-04) (hash(x)=7326216) +494 train 7.600051 (lr=3.2973e-04) (hash(x)=7492012) +495 train 7.585319 (lr=3.2911e-04) (hash(x)=5857162) +496 train 7.385015 (lr=3.2847e-04) (hash(x)=6169001) +497 train 9.503296 (lr=3.2784e-04) (hash(x)=14715669) +498 train 12.628654 (lr=3.2721e-04) (hash(x)=18256706) +499 train 12.423527 (lr=3.2657e-04) (hash(x)=16950560) +500 val loss 7.4695 +500 val perplexity 1753.8151 +500 train 8.282737 (lr=3.2593e-04) (hash(x)=6113563) +501 train 7.135665 (lr=3.2529e-04) (hash(x)=6159125) +502 train 7.562279 (lr=3.2464e-04) (hash(x)=5482303) +503 train 7.626824 (lr=3.2400e-04) (hash(x)=5908442) +504 train 7.513757 (lr=3.2335e-04) (hash(x)=4985045) +505 train 7.434715 (lr=3.2270e-04) (hash(x)=6668887) +506 train 7.484407 (lr=3.2205e-04) (hash(x)=6123910) +507 train 7.554261 (lr=3.2140e-04) (hash(x)=7662975) +508 train 7.488832 (lr=3.2074e-04) (hash(x)=7191898) +509 train 7.429835 (lr=3.2008e-04) (hash(x)=6669539) +510 train 7.479131 (lr=3.1943e-04) (hash(x)=6557481) +511 train 7.386092 (lr=3.1876e-04) (hash(x)=5015998) +512 train 7.444901 (lr=3.1810e-04) (hash(x)=4964540) +513 train 7.301023 (lr=3.1744e-04) (hash(x)=5458386) +514 train 7.672542 (lr=3.1677e-04) (hash(x)=6077616) +515 train 7.417021 (lr=3.1610e-04) (hash(x)=4849847) +516 train 7.477108 (lr=3.1543e-04) (hash(x)=5431422) +517 train 7.643063 (lr=3.1476e-04) (hash(x)=5125562) +518 train 7.575170 (lr=3.1408e-04) (hash(x)=5587715) +519 train 7.587160 (lr=3.1341e-04) (hash(x)=6012047) +520 train 7.430419 (lr=3.1273e-04) (hash(x)=5668436) +521 train 7.444870 (lr=3.1205e-04) (hash(x)=6079364) +522 train 7.578581 (lr=3.1137e-04) (hash(x)=5200504) +523 train 7.325253 (lr=3.1069e-04) (hash(x)=6030395) +524 train 7.542663 (lr=3.1000e-04) (hash(x)=6855319) +525 train 7.343051 (lr=3.0931e-04) (hash(x)=6781762) +526 train 7.485873 (lr=3.0862e-04) (hash(x)=6717939) +527 train 7.480980 (lr=3.0793e-04) (hash(x)=5238325) +528 train 7.387571 (lr=3.0724e-04) (hash(x)=5808069) +529 train 7.660790 (lr=3.0655e-04) (hash(x)=8611144) +530 train 7.371555 (lr=3.0585e-04) (hash(x)=6028738) +531 train 7.413113 (lr=3.0516e-04) (hash(x)=6901605) +532 train 7.367253 (lr=3.0446e-04) (hash(x)=6723307) +533 train 7.460772 (lr=3.0376e-04) (hash(x)=5499337) +534 train 7.389361 (lr=3.0306e-04) (hash(x)=6586372) +535 train 7.501397 (lr=3.0235e-04) (hash(x)=7134874) +536 train 7.410165 (lr=3.0165e-04) (hash(x)=8415623) +537 train 7.422731 (lr=3.0094e-04) (hash(x)=6149038) +538 train 7.490672 (lr=3.0023e-04) (hash(x)=6078325) +539 train 7.439776 (lr=2.9952e-04) (hash(x)=6609760) +540 train 7.333106 (lr=2.9881e-04) (hash(x)=6185253) +541 train 7.755735 (lr=2.9810e-04) (hash(x)=6652627) +542 train 7.490166 (lr=2.9738e-04) (hash(x)=7758536) +543 train 7.497404 (lr=2.9667e-04) (hash(x)=8618579) +544 train 7.451189 (lr=2.9595e-04) (hash(x)=6710226) +545 train 7.328456 (lr=2.9523e-04) (hash(x)=5896892) +546 train 7.338814 (lr=2.9451e-04) (hash(x)=6332995) +547 train 7.721033 (lr=2.9379e-04) (hash(x)=8945854) +548 train 7.300228 (lr=2.9307e-04) (hash(x)=4329129) +549 train 7.352046 (lr=2.9234e-04) (hash(x)=6775103) +550 val loss 7.3670 +550 val perplexity 1582.9507 +550 train 7.451190 (lr=2.9162e-04) (hash(x)=4465735) +551 train 7.341278 (lr=2.9089e-04) (hash(x)=6200024) +552 train 7.285071 (lr=2.9016e-04) (hash(x)=5520748) +553 train 7.306071 (lr=2.8943e-04) (hash(x)=5238139) +554 train 7.572120 (lr=2.8870e-04) (hash(x)=7639817) +555 train 7.320476 (lr=2.8797e-04) (hash(x)=5780948) +556 train 7.448494 (lr=2.8723e-04) (hash(x)=6733444) +557 train 7.388828 (lr=2.8650e-04) (hash(x)=6168407) +558 train 7.425199 (lr=2.8576e-04) (hash(x)=6680197) +559 train 7.325930 (lr=2.8502e-04) (hash(x)=3775881) +560 train 7.170143 (lr=2.8428e-04) (hash(x)=5784096) +561 train 7.606311 (lr=2.8354e-04) (hash(x)=6848709) +562 train 7.656246 (lr=2.8280e-04) (hash(x)=7449019) +563 train 7.760560 (lr=2.8206e-04) (hash(x)=6478113) +564 train 7.382689 (lr=2.8132e-04) (hash(x)=5925744) +565 train 7.443940 (lr=2.8057e-04) (hash(x)=6483914) +566 train 7.346461 (lr=2.7982e-04) (hash(x)=6010847) +567 train 7.431954 (lr=2.7908e-04) (hash(x)=5927795) +568 train 7.419445 (lr=2.7833e-04) (hash(x)=5896332) +569 train 7.383034 (lr=2.7758e-04) (hash(x)=8438033) +570 train 7.486923 (lr=2.7683e-04) (hash(x)=6081660) +571 train 7.393309 (lr=2.7607e-04) (hash(x)=5684788) +572 train 7.281616 (lr=2.7532e-04) (hash(x)=6272055) +573 train 7.251824 (lr=2.7457e-04) (hash(x)=5710182) +574 train 7.358568 (lr=2.7381e-04) (hash(x)=6219616) +575 train 7.330452 (lr=2.7306e-04) (hash(x)=6160063) +576 train 7.347513 (lr=2.7230e-04) (hash(x)=5710809) +577 train 7.082848 (lr=2.7154e-04) (hash(x)=5955100) +578 train 7.080400 (lr=2.7078e-04) (hash(x)=5356088) +579 train 7.149458 (lr=2.7002e-04) (hash(x)=6672309) +580 train 7.380894 (lr=2.6926e-04) (hash(x)=5841684) +581 train 7.699202 (lr=2.6850e-04) (hash(x)=9001564) +582 train 8.254947 (lr=2.6773e-04) (hash(x)=6897178) +583 train 7.473521 (lr=2.6697e-04) (hash(x)=5454654) +584 train 7.228654 (lr=2.6620e-04) (hash(x)=6391454) +585 train 7.313796 (lr=2.6544e-04) (hash(x)=5174062) +586 train 7.436153 (lr=2.6467e-04) (hash(x)=5197924) +587 train 7.386438 (lr=2.6390e-04) (hash(x)=6199203) +588 train 7.230528 (lr=2.6314e-04) (hash(x)=5786498) +589 train 7.348143 (lr=2.6237e-04) (hash(x)=8352747) +590 train 7.623299 (lr=2.6160e-04) (hash(x)=4829700) +591 train 7.160744 (lr=2.6083e-04) (hash(x)=4547106) +592 train 7.451963 (lr=2.6005e-04) (hash(x)=7686831) +593 train 7.326598 (lr=2.5928e-04) (hash(x)=6433099) +594 train 7.198521 (lr=2.5851e-04) (hash(x)=4826460) +595 train 7.291193 (lr=2.5773e-04) (hash(x)=6424428) +596 train 7.171371 (lr=2.5696e-04) (hash(x)=6073605) +597 train 7.512160 (lr=2.5618e-04) (hash(x)=5975712) +598 train 7.132048 (lr=2.5541e-04) (hash(x)=7030029) +599 train 7.429355 (lr=2.5463e-04) (hash(x)=5458532) +600 val loss 7.3354 +600 val perplexity 1533.5659 +600 train 7.275058 (lr=2.5385e-04) (hash(x)=7823919) +601 train 7.696326 (lr=2.5307e-04) (hash(x)=7002774) +602 train 7.489892 (lr=2.5230e-04) (hash(x)=7056399) +603 train 7.687265 (lr=2.5152e-04) (hash(x)=8206173) +604 train 7.547617 (lr=2.5074e-04) (hash(x)=8034846) +605 train 7.844244 (lr=2.4996e-04) (hash(x)=7784971) +606 train 7.970962 (lr=2.4917e-04) (hash(x)=7118076) +607 train 7.295692 (lr=2.4839e-04) (hash(x)=6001843) +608 train 7.403044 (lr=2.4761e-04) (hash(x)=5582437) +609 train 7.486993 (lr=2.4683e-04) (hash(x)=5698642) +610 train 7.364911 (lr=2.4604e-04) (hash(x)=6615301) +611 train 7.352203 (lr=2.4526e-04) (hash(x)=6600751) +612 train 7.262407 (lr=2.4448e-04) (hash(x)=6880955) +613 train 7.325389 (lr=2.4369e-04) (hash(x)=5804610) +614 train 7.244720 (lr=2.4291e-04) (hash(x)=6263347) +615 train 7.225625 (lr=2.4212e-04) (hash(x)=5162652) +616 train 7.272368 (lr=2.4133e-04) (hash(x)=6055710) +617 train 7.228276 (lr=2.4055e-04) (hash(x)=5297006) +618 train 7.244278 (lr=2.3976e-04) (hash(x)=5923648) +619 train 7.268196 (lr=2.3897e-04) (hash(x)=6728323) +620 train 7.273649 (lr=2.3818e-04) (hash(x)=6660239) +621 train 7.232489 (lr=2.3740e-04) (hash(x)=3964882) +622 train 7.280426 (lr=2.3661e-04) (hash(x)=5868942) +623 train 7.208530 (lr=2.3582e-04) (hash(x)=6735993) +624 train 7.536401 (lr=2.3503e-04) (hash(x)=5926190) +625 train 7.226804 (lr=2.3424e-04) (hash(x)=5150316) +626 train 7.243620 (lr=2.3345e-04) (hash(x)=7571467) +627 train 7.146760 (lr=2.3266e-04) (hash(x)=5220448) +628 train 7.177813 (lr=2.3187e-04) (hash(x)=6790397) +629 train 7.620047 (lr=2.3108e-04) (hash(x)=6971289) +630 train 7.564197 (lr=2.3029e-04) (hash(x)=7123359) +631 train 7.344495 (lr=2.2950e-04) (hash(x)=5012069) +632 train 7.327092 (lr=2.2871e-04) (hash(x)=6183574) +633 train 7.218500 (lr=2.2792e-04) (hash(x)=6576136) +634 train 7.244624 (lr=2.2713e-04) (hash(x)=6157346) +635 train 7.241570 (lr=2.2633e-04) (hash(x)=6077647) +636 train 7.464887 (lr=2.2554e-04) (hash(x)=8369488) +637 train 7.259305 (lr=2.2475e-04) (hash(x)=6032381) +638 train 7.208690 (lr=2.2396e-04) (hash(x)=5924756) +639 train 7.220105 (lr=2.2317e-04) (hash(x)=8410716) +640 train 7.226849 (lr=2.2238e-04) (hash(x)=5803440) +641 train 7.318607 (lr=2.2158e-04) (hash(x)=6212516) +642 train 7.371354 (lr=2.2079e-04) (hash(x)=7165945) +643 train 7.110163 (lr=2.2000e-04) (hash(x)=5298545) +644 train 7.368158 (lr=2.1921e-04) (hash(x)=6281739) +645 train 7.335451 (lr=2.1842e-04) (hash(x)=5779073) +646 train 7.180093 (lr=2.1762e-04) (hash(x)=5090107) +647 train 7.250807 (lr=2.1683e-04) (hash(x)=6340947) +648 train 7.005602 (lr=2.1604e-04) (hash(x)=4741418) +649 train 6.941532 (lr=2.1525e-04) (hash(x)=6530441) +650 val loss 7.2794 +650 val perplexity 1450.1272 +650 train 7.463500 (lr=2.1446e-04) (hash(x)=6396041) +651 train 7.153759 (lr=2.1367e-04) (hash(x)=7818007) +652 train 7.170884 (lr=2.1287e-04) (hash(x)=6478457) +653 train 7.218959 (lr=2.1208e-04) (hash(x)=6277435) +654 train 7.200498 (lr=2.1129e-04) (hash(x)=6042369) +655 train 7.219680 (lr=2.1050e-04) (hash(x)=6226320) +656 train 7.225859 (lr=2.0971e-04) (hash(x)=5826883) +657 train 7.339520 (lr=2.0892e-04) (hash(x)=5463751) +658 train 7.273391 (lr=2.0813e-04) (hash(x)=6433080) +659 train 7.121003 (lr=2.0734e-04) (hash(x)=6579329) +660 train 7.133976 (lr=2.0655e-04) (hash(x)=4724703) +661 train 7.473115 (lr=2.0576e-04) (hash(x)=6660540) +662 train 7.284691 (lr=2.0497e-04) (hash(x)=5918756) +663 train 7.226702 (lr=2.0418e-04) (hash(x)=6491272) +664 train 7.130912 (lr=2.0339e-04) (hash(x)=5452863) +665 train 7.328146 (lr=2.0260e-04) (hash(x)=6766947) +666 train 7.689554 (lr=2.0182e-04) (hash(x)=7459504) +667 train 7.334201 (lr=2.0103e-04) (hash(x)=3721218) +668 train 7.530101 (lr=2.0024e-04) (hash(x)=7929571) +669 train 7.209186 (lr=1.9945e-04) (hash(x)=5229898) +670 train 7.242120 (lr=1.9867e-04) (hash(x)=6083090) +671 train 7.083554 (lr=1.9788e-04) (hash(x)=6054428) +672 train 7.248810 (lr=1.9709e-04) (hash(x)=6072563) +673 train 7.356581 (lr=1.9631e-04) (hash(x)=6290464) +674 train 7.448825 (lr=1.9552e-04) (hash(x)=6314742) +675 train 7.113656 (lr=1.9474e-04) (hash(x)=6904498) +676 train 7.286090 (lr=1.9396e-04) (hash(x)=5378107) +677 train 7.376834 (lr=1.9317e-04) (hash(x)=7765805) +678 train 7.209204 (lr=1.9239e-04) (hash(x)=5871280) +679 train 7.358083 (lr=1.9161e-04) (hash(x)=6543764) +680 train 7.243546 (lr=1.9083e-04) (hash(x)=7369665) +681 train 7.322464 (lr=1.9004e-04) (hash(x)=7204955) +682 train 7.267771 (lr=1.8926e-04) (hash(x)=5856543) +683 train 7.143608 (lr=1.8848e-04) (hash(x)=4423711) +684 train 7.115523 (lr=1.8770e-04) (hash(x)=5818153) +685 train 7.221832 (lr=1.8693e-04) (hash(x)=5343477) +686 train 7.414406 (lr=1.8615e-04) (hash(x)=6581702) +687 train 7.241409 (lr=1.8537e-04) (hash(x)=6595856) +688 train 7.168486 (lr=1.8459e-04) (hash(x)=5325378) +689 train 7.098573 (lr=1.8382e-04) (hash(x)=7229015) +690 train 7.272418 (lr=1.8304e-04) (hash(x)=5918186) +691 train 7.156876 (lr=1.8227e-04) (hash(x)=5916034) +692 train 7.146904 (lr=1.8149e-04) (hash(x)=5280722) +693 train 7.547509 (lr=1.8072e-04) (hash(x)=6939521) +694 train 7.295873 (lr=1.7995e-04) (hash(x)=5172566) +695 train 7.141894 (lr=1.7917e-04) (hash(x)=5492185) +696 train 7.017113 (lr=1.7840e-04) (hash(x)=5779011) +697 train 7.279517 (lr=1.7763e-04) (hash(x)=6898006) +698 train 7.120196 (lr=1.7686e-04) (hash(x)=5779217) +699 train 6.995289 (lr=1.7610e-04) (hash(x)=5462008) +700 val loss 7.2622 +700 val perplexity 1425.4296 +700 train 7.132263 (lr=1.7533e-04) (hash(x)=6243843) +701 train 7.191575 (lr=1.7456e-04) (hash(x)=7821902) +702 train 7.261506 (lr=1.7380e-04) (hash(x)=5222501) +703 train 7.221681 (lr=1.7303e-04) (hash(x)=6608108) +704 train 7.324085 (lr=1.7227e-04) (hash(x)=7602879) +705 train 7.258575 (lr=1.7150e-04) (hash(x)=6295394) +706 train 7.216912 (lr=1.7074e-04) (hash(x)=6579907) +707 train 7.110833 (lr=1.6998e-04) (hash(x)=6803449) +708 train 7.187553 (lr=1.6922e-04) (hash(x)=5413733) +709 train 7.156728 (lr=1.6846e-04) (hash(x)=7444134) +710 train 7.312540 (lr=1.6770e-04) (hash(x)=7028652) +711 train 7.100245 (lr=1.6694e-04) (hash(x)=5361923) +712 train 7.219955 (lr=1.6619e-04) (hash(x)=5478293) +713 train 7.204009 (lr=1.6543e-04) (hash(x)=7803039) +714 train 7.376867 (lr=1.6468e-04) (hash(x)=6469017) +715 train 7.273723 (lr=1.6393e-04) (hash(x)=7042578) +716 train 7.321140 (lr=1.6317e-04) (hash(x)=6927957) +717 train 7.135811 (lr=1.6242e-04) (hash(x)=6647007) +718 train 7.107846 (lr=1.6167e-04) (hash(x)=6230888) +719 train 7.372190 (lr=1.6092e-04) (hash(x)=6303658) +720 train 7.402132 (lr=1.6018e-04) (hash(x)=6769880) +721 train 7.238507 (lr=1.5943e-04) (hash(x)=6158927) +722 train 7.254570 (lr=1.5868e-04) (hash(x)=5991631) +723 train 7.101628 (lr=1.5794e-04) (hash(x)=6419656) +724 train 7.110524 (lr=1.5720e-04) (hash(x)=7739209) +725 train 7.057066 (lr=1.5646e-04) (hash(x)=7891271) +726 train 7.402411 (lr=1.5572e-04) (hash(x)=7171433) +727 train 7.190579 (lr=1.5498e-04) (hash(x)=7099888) +728 train 7.208033 (lr=1.5424e-04) (hash(x)=6103730) +729 train 7.315645 (lr=1.5350e-04) (hash(x)=6352424) +730 train 7.197739 (lr=1.5277e-04) (hash(x)=4893671) +731 train 7.143514 (lr=1.5203e-04) (hash(x)=5863145) +732 train 7.269551 (lr=1.5130e-04) (hash(x)=5502233) +733 train 7.166574 (lr=1.5057e-04) (hash(x)=6844597) +734 train 7.185538 (lr=1.4984e-04) (hash(x)=6744526) +735 train 7.328297 (lr=1.4911e-04) (hash(x)=6009861) +736 train 7.203203 (lr=1.4838e-04) (hash(x)=6152358) +737 train 7.110647 (lr=1.4766e-04) (hash(x)=5374957) +738 train 7.142003 (lr=1.4693e-04) (hash(x)=6495309) +739 train 7.298958 (lr=1.4621e-04) (hash(x)=3923225) +740 train 7.067060 (lr=1.4549e-04) (hash(x)=6255243) +741 train 7.235266 (lr=1.4477e-04) (hash(x)=5848862) +742 train 7.242447 (lr=1.4405e-04) (hash(x)=4535000) +743 train 7.115075 (lr=1.4333e-04) (hash(x)=4440634) +744 train 7.119870 (lr=1.4262e-04) (hash(x)=5222077) +745 train 7.143877 (lr=1.4190e-04) (hash(x)=4788998) +746 train 7.156085 (lr=1.4119e-04) (hash(x)=6108350) +747 train 7.072492 (lr=1.4048e-04) (hash(x)=7378165) +748 train 7.149367 (lr=1.3977e-04) (hash(x)=5475646) +749 train 7.154236 (lr=1.3906e-04) (hash(x)=4771243) +750 val loss 7.2383 +750 val perplexity 1391.7517 +750 train 7.044060 (lr=1.3835e-04) (hash(x)=6668088) +751 train 7.269045 (lr=1.3765e-04) (hash(x)=5716089) +752 train 7.213087 (lr=1.3694e-04) (hash(x)=6991946) +753 train 7.118353 (lr=1.3624e-04) (hash(x)=7991009) +754 train 7.221117 (lr=1.3554e-04) (hash(x)=6037018) +755 train 7.198998 (lr=1.3484e-04) (hash(x)=5348607) +756 train 7.329817 (lr=1.3415e-04) (hash(x)=5190526) +757 train 7.209009 (lr=1.3345e-04) (hash(x)=6036146) +758 train 7.110222 (lr=1.3276e-04) (hash(x)=5329783) +759 train 7.208671 (lr=1.3207e-04) (hash(x)=6658718) +760 train 7.104613 (lr=1.3138e-04) (hash(x)=4820939) +761 train 7.096487 (lr=1.3069e-04) (hash(x)=6176253) +762 train 7.071394 (lr=1.3000e-04) (hash(x)=5316750) +763 train 7.161713 (lr=1.2931e-04) (hash(x)=4542895) +764 train 6.977513 (lr=1.2863e-04) (hash(x)=5395673) +765 train 7.053274 (lr=1.2795e-04) (hash(x)=5549073) +766 train 7.292261 (lr=1.2727e-04) (hash(x)=5233723) +767 train 7.358769 (lr=1.2659e-04) (hash(x)=5342783) +768 train 7.276813 (lr=1.2592e-04) (hash(x)=5552448) +769 train 7.408619 (lr=1.2524e-04) (hash(x)=6549546) +770 train 7.084890 (lr=1.2457e-04) (hash(x)=3816493) +771 train 7.138319 (lr=1.2390e-04) (hash(x)=6170599) +772 train 7.609827 (lr=1.2323e-04) (hash(x)=6708759) +773 train 7.226921 (lr=1.2256e-04) (hash(x)=8483134) +774 train 7.799468 (lr=1.2190e-04) (hash(x)=5583732) +775 train 7.222649 (lr=1.2124e-04) (hash(x)=4865036) +776 train 7.154861 (lr=1.2057e-04) (hash(x)=7234336) +777 train 7.182988 (lr=1.1992e-04) (hash(x)=4433890) +778 train 7.507464 (lr=1.1926e-04) (hash(x)=7484636) +779 train 7.933812 (lr=1.1860e-04) (hash(x)=6738597) +780 train 7.176251 (lr=1.1795e-04) (hash(x)=6752421) +781 train 7.366491 (lr=1.1730e-04) (hash(x)=5459620) +782 train 7.275759 (lr=1.1665e-04) (hash(x)=6718131) +783 train 7.252876 (lr=1.1600e-04) (hash(x)=4604074) +784 train 7.119261 (lr=1.1536e-04) (hash(x)=5946124) +785 train 7.386425 (lr=1.1471e-04) (hash(x)=8045501) +786 train 7.508865 (lr=1.1407e-04) (hash(x)=5712725) +787 train 7.225373 (lr=1.1343e-04) (hash(x)=6176464) +788 train 7.275974 (lr=1.1279e-04) (hash(x)=6276702) +789 train 7.093797 (lr=1.1216e-04) (hash(x)=6127317) +790 train 7.245023 (lr=1.1153e-04) (hash(x)=7221374) +791 train 7.219378 (lr=1.1089e-04) (hash(x)=5571462) +792 train 7.216733 (lr=1.1027e-04) (hash(x)=7518021) +793 train 7.218337 (lr=1.0964e-04) (hash(x)=6640755) +794 train 7.301258 (lr=1.0901e-04) (hash(x)=6870405) +795 train 7.273545 (lr=1.0839e-04) (hash(x)=6147295) +796 train 7.156823 (lr=1.0777e-04) (hash(x)=6782583) +797 train 7.280247 (lr=1.0715e-04) (hash(x)=6120461) +798 train 7.202295 (lr=1.0654e-04) (hash(x)=5893870) +799 train 7.153700 (lr=1.0592e-04) (hash(x)=5123928) +800 val loss 7.2274 +800 val perplexity 1376.5905 +800 train 7.229641 (lr=1.0531e-04) (hash(x)=7037251) +801 train 7.220909 (lr=1.0470e-04) (hash(x)=5428813) +802 train 7.150929 (lr=1.0410e-04) (hash(x)=5550387) +803 train 7.228024 (lr=1.0349e-04) (hash(x)=6448586) +804 train 7.378293 (lr=1.0289e-04) (hash(x)=5916934) +805 train 7.325979 (lr=1.0229e-04) (hash(x)=8116987) +806 train 7.298142 (lr=1.0169e-04) (hash(x)=6210899) +807 train 7.405035 (lr=1.0109e-04) (hash(x)=5974342) +808 train 7.392243 (lr=1.0050e-04) (hash(x)=7236199) +809 train 7.319428 (lr=9.9910e-05) (hash(x)=5261336) +810 train 7.158749 (lr=9.9321e-05) (hash(x)=6310720) +811 train 7.188274 (lr=9.8735e-05) (hash(x)=5307056) +812 train 7.032549 (lr=9.8151e-05) (hash(x)=7356633) +813 train 7.159448 (lr=9.7569e-05) (hash(x)=5865119) +814 train 7.056686 (lr=9.6990e-05) (hash(x)=5979205) +815 train 7.193457 (lr=9.6413e-05) (hash(x)=6672380) +816 train 7.190723 (lr=9.5838e-05) (hash(x)=5565030) +817 train 7.172619 (lr=9.5266e-05) (hash(x)=6886810) +818 train 7.223519 (lr=9.4696e-05) (hash(x)=5926478) +819 train 7.432525 (lr=9.4129e-05) (hash(x)=6564071) +820 train 7.069888 (lr=9.3564e-05) (hash(x)=5024280) +821 train 7.065514 (lr=9.3001e-05) (hash(x)=7705089) +822 train 7.049113 (lr=9.2441e-05) (hash(x)=4037371) +823 train 7.149962 (lr=9.1884e-05) (hash(x)=5773073) +824 train 7.167453 (lr=9.1328e-05) (hash(x)=7158139) +825 train 7.006561 (lr=9.0776e-05) (hash(x)=5905976) +826 train 7.432954 (lr=9.0226e-05) (hash(x)=13897369) +827 train 8.530783 (lr=8.9678e-05) (hash(x)=6936653) +828 train 7.203353 (lr=8.9133e-05) (hash(x)=6592246) +829 train 7.169111 (lr=8.8591e-05) (hash(x)=6592773) +830 train 7.226086 (lr=8.8051e-05) (hash(x)=5461178) +831 train 7.010349 (lr=8.7513e-05) (hash(x)=6796551) +832 train 7.230725 (lr=8.6978e-05) (hash(x)=4721691) +833 train 7.137772 (lr=8.6446e-05) (hash(x)=6151589) +834 train 7.277274 (lr=8.5916e-05) (hash(x)=7008995) +835 train 7.583528 (lr=8.5389e-05) (hash(x)=7045164) +836 train 7.203821 (lr=8.4865e-05) (hash(x)=6614221) +837 train 7.243589 (lr=8.4343e-05) (hash(x)=6650506) +838 train 7.056056 (lr=8.3824e-05) (hash(x)=6363762) +839 train 7.205100 (lr=8.3307e-05) (hash(x)=7839748) +840 train 7.138793 (lr=8.2793e-05) (hash(x)=5124077) +841 train 7.587353 (lr=8.2282e-05) (hash(x)=6028671) +842 train 7.063087 (lr=8.1773e-05) (hash(x)=5427175) +843 train 7.402686 (lr=8.1267e-05) (hash(x)=6118408) +844 train 7.175012 (lr=8.0764e-05) (hash(x)=6022552) +845 train 7.184048 (lr=8.0263e-05) (hash(x)=5757526) +846 train 7.650795 (lr=7.9765e-05) (hash(x)=6476549) +847 train 6.980637 (lr=7.9270e-05) (hash(x)=6030172) +848 train 7.354448 (lr=7.8778e-05) (hash(x)=5917229) +849 train 7.433615 (lr=7.8288e-05) (hash(x)=6719882) +850 val loss 7.2150 +850 val perplexity 1359.6350 +850 train 7.285114 (lr=7.7801e-05) (hash(x)=5441498) +851 train 7.157188 (lr=7.7317e-05) (hash(x)=5028050) +852 train 7.192585 (lr=7.6836e-05) (hash(x)=8487491) +853 train 7.203831 (lr=7.6357e-05) (hash(x)=5682910) +854 train 7.394411 (lr=7.5881e-05) (hash(x)=6781362) +855 train 7.193308 (lr=7.5408e-05) (hash(x)=5747891) +856 train 7.238395 (lr=7.4938e-05) (hash(x)=7627661) +857 train 6.909959 (lr=7.4470e-05) (hash(x)=5734208) +858 train 7.056494 (lr=7.4005e-05) (hash(x)=6162015) +859 train 7.273399 (lr=7.3544e-05) (hash(x)=7024381) +860 train 7.479629 (lr=7.3085e-05) (hash(x)=5198498) +861 train 7.465922 (lr=7.2628e-05) (hash(x)=7814361) +862 train 7.344965 (lr=7.2175e-05) (hash(x)=7394995) +863 train 7.222353 (lr=7.1725e-05) (hash(x)=5765893) +864 train 7.027587 (lr=7.1277e-05) (hash(x)=4990435) +865 train 7.174835 (lr=7.0832e-05) (hash(x)=5572048) +866 train 7.329129 (lr=7.0390e-05) (hash(x)=7093293) +867 train 7.223151 (lr=6.9952e-05) (hash(x)=5610058) +868 train 7.105561 (lr=6.9516e-05) (hash(x)=6771468) +869 train 7.150793 (lr=6.9082e-05) (hash(x)=4459483) +870 train 7.053327 (lr=6.8652e-05) (hash(x)=4926546) +871 train 7.158035 (lr=6.8225e-05) (hash(x)=6758411) +872 train 7.108824 (lr=6.7801e-05) (hash(x)=7394277) +873 train 7.246135 (lr=6.7379e-05) (hash(x)=6701381) +874 train 7.581738 (lr=6.6961e-05) (hash(x)=8120966) +875 train 7.101703 (lr=6.6545e-05) (hash(x)=5416400) +876 train 7.107294 (lr=6.6133e-05) (hash(x)=6292778) +877 train 7.044969 (lr=6.5723e-05) (hash(x)=5919569) +878 train 7.359562 (lr=6.5317e-05) (hash(x)=7561740) +879 train 7.101764 (lr=6.4913e-05) (hash(x)=5282870) +880 train 7.139434 (lr=6.4513e-05) (hash(x)=5473238) +881 train 7.033217 (lr=6.4115e-05) (hash(x)=8072181) +882 train 7.053913 (lr=6.3721e-05) (hash(x)=6757322) +883 train 7.012833 (lr=6.3329e-05) (hash(x)=7996770) +884 train 7.093047 (lr=6.2941e-05) (hash(x)=3181021) +885 train 7.132130 (lr=6.2556e-05) (hash(x)=5093519) +886 train 7.107012 (lr=6.2173e-05) (hash(x)=5391352) +887 train 7.156550 (lr=6.1794e-05) (hash(x)=6270917) +888 train 7.143846 (lr=6.1418e-05) (hash(x)=5818195) +889 train 6.889523 (lr=6.1045e-05) (hash(x)=5852780) +890 train 6.814914 (lr=6.0675e-05) (hash(x)=5777928) +891 train 7.012060 (lr=6.0308e-05) (hash(x)=5327728) +892 train 7.049720 (lr=5.9944e-05) (hash(x)=7651281) +893 train 7.250639 (lr=5.9583e-05) (hash(x)=6260765) +894 train 7.141496 (lr=5.9225e-05) (hash(x)=6265102) +895 train 7.303749 (lr=5.8871e-05) (hash(x)=6212894) +896 train 7.075490 (lr=5.8519e-05) (hash(x)=6901967) +897 train 7.142359 (lr=5.8171e-05) (hash(x)=6724010) +898 train 7.131633 (lr=5.7826e-05) (hash(x)=6299033) +899 train 7.300793 (lr=5.7484e-05) (hash(x)=6059934) +900 val loss 7.2094 +900 val perplexity 1352.0785 +900 train 7.003590 (lr=5.7145e-05) (hash(x)=6029696) +901 train 6.933363 (lr=5.6809e-05) (hash(x)=5587382) +902 train 7.135447 (lr=5.6476e-05) (hash(x)=5890076) +903 train 7.056733 (lr=5.6147e-05) (hash(x)=7274108) +904 train 7.150995 (lr=5.5821e-05) (hash(x)=7975528) +905 train 7.184387 (lr=5.5497e-05) (hash(x)=6085396) +906 train 7.071656 (lr=5.5178e-05) (hash(x)=6724496) +907 train 7.073547 (lr=5.4861e-05) (hash(x)=4784666) +908 train 7.074179 (lr=5.4547e-05) (hash(x)=7193845) +909 train 7.242885 (lr=5.4237e-05) (hash(x)=6288638) +910 train 7.207493 (lr=5.3930e-05) (hash(x)=5685285) +911 train 7.184367 (lr=5.3626e-05) (hash(x)=7714288) +912 train 7.278225 (lr=5.3325e-05) (hash(x)=5983679) +913 train 7.226754 (lr=5.3028e-05) (hash(x)=5534748) +914 train 7.160311 (lr=5.2734e-05) (hash(x)=6545471) +915 train 7.141065 (lr=5.2443e-05) (hash(x)=6361270) +916 train 7.155121 (lr=5.2155e-05) (hash(x)=6257744) +917 train 7.170340 (lr=5.1871e-05) (hash(x)=4682956) +918 train 7.055867 (lr=5.1589e-05) (hash(x)=4521756) +919 train 7.185217 (lr=5.1311e-05) (hash(x)=7568935) +920 train 7.102146 (lr=5.1037e-05) (hash(x)=7969353) +921 train 7.301379 (lr=5.0765e-05) (hash(x)=7973311) +922 train 7.020391 (lr=5.0497e-05) (hash(x)=4843937) +923 train 7.146888 (lr=5.0232e-05) (hash(x)=6987352) +924 train 7.266483 (lr=4.9971e-05) (hash(x)=7179418) +925 train 6.925049 (lr=4.9712e-05) (hash(x)=5413904) +926 train 7.326685 (lr=4.9457e-05) (hash(x)=6028105) +927 train 7.240430 (lr=4.9206e-05) (hash(x)=6732924) +928 train 7.130965 (lr=4.8957e-05) (hash(x)=4547651) +929 train 7.277041 (lr=4.8712e-05) (hash(x)=6219754) +930 train 7.070505 (lr=4.8470e-05) (hash(x)=7465186) +931 train 7.216633 (lr=4.8232e-05) (hash(x)=6839070) +932 train 7.091709 (lr=4.7997e-05) (hash(x)=5390324) +933 train 7.065251 (lr=4.7765e-05) (hash(x)=6090120) +934 train 7.696120 (lr=4.7537e-05) (hash(x)=7123181) +935 train 7.356413 (lr=4.7312e-05) (hash(x)=7115176) +936 train 7.365523 (lr=4.7090e-05) (hash(x)=7016990) +937 train 7.129372 (lr=4.6871e-05) (hash(x)=4989299) +938 train 7.156030 (lr=4.6656e-05) (hash(x)=6783311) +939 train 7.126403 (lr=4.6445e-05) (hash(x)=7497590) +940 train 7.345727 (lr=4.6236e-05) (hash(x)=6767514) +941 train 7.109758 (lr=4.6031e-05) (hash(x)=3977557) +942 train 7.227119 (lr=4.5830e-05) (hash(x)=4806492) +943 train 7.145763 (lr=4.5631e-05) (hash(x)=5524165) +944 train 7.190461 (lr=4.5437e-05) (hash(x)=4930752) +945 train 7.158647 (lr=4.5245e-05) (hash(x)=5124936) +946 train 7.045914 (lr=4.5057e-05) (hash(x)=6877351) +947 train 7.337680 (lr=4.4872e-05) (hash(x)=5522119) +948 train 7.134319 (lr=4.4691e-05) (hash(x)=6183512) +949 train 7.050566 (lr=4.4513e-05) (hash(x)=5030865) +950 val loss 7.1976 +950 val perplexity 1336.2561 +950 train 7.151243 (lr=4.4338e-05) (hash(x)=6619812) +951 train 7.152121 (lr=4.4167e-05) (hash(x)=6411783) +952 train 7.144426 (lr=4.4000e-05) (hash(x)=6748982) +953 train 7.052294 (lr=4.3835e-05) (hash(x)=6581937) +954 train 7.146032 (lr=4.3674e-05) (hash(x)=7881022) +955 train 7.111592 (lr=4.3517e-05) (hash(x)=5116910) +956 train 6.909661 (lr=4.3363e-05) (hash(x)=4880833) +957 train 6.959412 (lr=4.3212e-05) (hash(x)=7353459) +958 train 7.009448 (lr=4.3065e-05) (hash(x)=4951302) +959 train 6.934485 (lr=4.2921e-05) (hash(x)=6344535) +960 train 7.554094 (lr=4.2781e-05) (hash(x)=7411763) +961 train 7.119178 (lr=4.2644e-05) (hash(x)=5840169) +962 train 7.215100 (lr=4.2510e-05) (hash(x)=5784788) +963 train 7.032366 (lr=4.2380e-05) (hash(x)=6754290) +964 train 7.302464 (lr=4.2253e-05) (hash(x)=6369963) +965 train 7.384223 (lr=4.2130e-05) (hash(x)=6484573) +966 train 6.969843 (lr=4.2010e-05) (hash(x)=6516338) +967 train 7.001606 (lr=4.1894e-05) (hash(x)=5260125) +968 train 7.124123 (lr=4.1781e-05) (hash(x)=5781624) +969 train 6.933152 (lr=4.1672e-05) (hash(x)=4881179) +970 train 7.044945 (lr=4.1566e-05) (hash(x)=6707821) +971 train 7.179349 (lr=4.1463e-05) (hash(x)=5001634) +972 train 7.069664 (lr=4.1364e-05) (hash(x)=4402949) +973 train 7.078676 (lr=4.1269e-05) (hash(x)=7424810) +974 train 6.961133 (lr=4.1177e-05) (hash(x)=4814803) +975 train 6.877477 (lr=4.1088e-05) (hash(x)=5176431) +976 train 7.073682 (lr=4.1003e-05) (hash(x)=5769393) +977 train 7.016310 (lr=4.0921e-05) (hash(x)=5421624) +978 train 7.228631 (lr=4.0843e-05) (hash(x)=5999773) +979 train 6.938479 (lr=4.0768e-05) (hash(x)=5674439) +980 train 7.031736 (lr=4.0697e-05) (hash(x)=6345351) +981 train 6.970438 (lr=4.0629e-05) (hash(x)=5819157) +982 train 7.190891 (lr=4.0564e-05) (hash(x)=11159355) +983 train 7.154009 (lr=4.0503e-05) (hash(x)=6506856) +984 train 7.067500 (lr=4.0446e-05) (hash(x)=6331023) +985 train 6.969358 (lr=4.0392e-05) (hash(x)=6119124) +986 train 7.180532 (lr=4.0341e-05) (hash(x)=8142528) +987 train 7.351092 (lr=4.0294e-05) (hash(x)=6241669) +988 train 6.980901 (lr=4.0251e-05) (hash(x)=3852991) +989 train 6.724988 (lr=4.0211e-05) (hash(x)=4992756) +990 train 7.436276 (lr=4.0174e-05) (hash(x)=7097145) +991 train 7.210177 (lr=4.0141e-05) (hash(x)=7277927) +992 train 7.280996 (lr=4.0112e-05) (hash(x)=5661400) +993 train 7.192758 (lr=4.0085e-05) (hash(x)=6622097) +994 train 7.332208 (lr=4.0063e-05) (hash(x)=5016804) +995 train 7.406902 (lr=4.0044e-05) (hash(x)=7026582) +996 train 7.166484 (lr=4.0028e-05) (hash(x)=5639136) +997 train 7.339573 (lr=4.0016e-05) (hash(x)=5840987) +998 train 6.944027 (lr=4.0007e-05) (hash(x)=5265410) +999 val loss 7.1913 +999 val perplexity 1327.7983 +999 train 6.943222 (lr=4.0002e-05) (hash(x)=4351074)