diff --git "a/lr5e-4_total_batch_size20480_seq_len128/log2.txt" "b/lr5e-4_total_batch_size20480_seq_len128/log2.txt" --- "a/lr5e-4_total_batch_size20480_seq_len128/log2.txt" +++ "b/lr5e-4_total_batch_size20480_seq_len128/log2.txt" @@ -4,1040 +4,1040 @@ max_steps: 1000 0 train 11.700421 (lr=1.7483e-06) (hash(x)=5113283) 1 train 11.672960 (lr=3.4965e-06) (hash(x)=5534142) 2 train 11.695552 (lr=5.2448e-06) (hash(x)=6763231) -3 train 11.666068 (lr=6.9930e-06) (hash(x)=6328012) -4 train 11.654607 (lr=8.7413e-06) (hash(x)=7052161) -5 train 11.608361 (lr=1.0490e-05) (hash(x)=5556098) -6 train 11.570334 (lr=1.2238e-05) (hash(x)=4696943) -7 train 11.518970 (lr=1.3986e-05) (hash(x)=6219138) -8 train 11.462629 (lr=1.5734e-05) (hash(x)=6049878) -9 train 11.423951 (lr=1.7483e-05) (hash(x)=5491972) -10 train 11.366195 (lr=1.9231e-05) (hash(x)=8075458) -11 train 11.285904 (lr=2.0979e-05) (hash(x)=5917741) -12 train 11.237248 (lr=2.2727e-05) (hash(x)=5750403) -13 train 11.162921 (lr=2.4476e-05) (hash(x)=6112458) -14 train 11.094389 (lr=2.6224e-05) (hash(x)=5806490) -15 train 10.994961 (lr=2.7972e-05) (hash(x)=6568379) -16 train 10.910911 (lr=2.9720e-05) (hash(x)=7212403) -17 train 10.843513 (lr=3.1469e-05) (hash(x)=7386082) -18 train 10.781620 (lr=3.3217e-05) (hash(x)=6359743) -19 train 10.729923 (lr=3.4965e-05) (hash(x)=6151674) -20 train 10.690209 (lr=3.6713e-05) (hash(x)=7168704) -21 train 10.643327 (lr=3.8462e-05) (hash(x)=7859060) -22 train 10.557471 (lr=4.0210e-05) (hash(x)=6976239) -23 train 10.554563 (lr=4.1958e-05) (hash(x)=6391506) -24 train 10.531520 (lr=4.3706e-05) (hash(x)=5245999) -25 train 10.479081 (lr=4.5455e-05) (hash(x)=5985675) -26 train 10.392241 (lr=4.7203e-05) (hash(x)=4355733) -27 train 10.559300 (lr=4.8951e-05) (hash(x)=6984772) -28 train 10.405327 (lr=5.0699e-05) (hash(x)=6244096) -29 train 10.423216 (lr=5.2448e-05) (hash(x)=6603717) -30 train 10.325966 (lr=5.4196e-05) (hash(x)=5669522) -31 train 10.309162 (lr=5.5944e-05) (hash(x)=6190579) -32 train 10.370431 (lr=5.7692e-05) (hash(x)=4912983) -33 train 10.242783 (lr=5.9441e-05) (hash(x)=7276303) -34 train 10.306746 (lr=6.1189e-05) (hash(x)=5479947) -35 train 10.397912 (lr=6.2937e-05) (hash(x)=6630378) -36 train 10.329117 (lr=6.4685e-05) (hash(x)=8097010) -37 train 10.381491 (lr=6.6434e-05) (hash(x)=9989744) -38 train 10.252186 (lr=6.8182e-05) (hash(x)=6694932) -39 train 10.178607 (lr=6.9930e-05) (hash(x)=6317894) -40 train 10.088614 (lr=7.1678e-05) (hash(x)=5046327) -41 train 10.156977 (lr=7.3427e-05) (hash(x)=7947703) -42 train 10.015911 (lr=7.5175e-05) (hash(x)=5916068) -43 train 10.109138 (lr=7.6923e-05) (hash(x)=5777498) -44 train 10.032684 (lr=7.8671e-05) (hash(x)=5753092) -45 train 10.005583 (lr=8.0420e-05) (hash(x)=7723226) -46 train 9.986021 (lr=8.2168e-05) (hash(x)=7007016) -47 train 9.901617 (lr=8.3916e-05) (hash(x)=6491229) -48 train 9.931938 (lr=8.5664e-05) (hash(x)=6390752) -49 train 10.034129 (lr=8.7413e-05) (hash(x)=6019389) -50 val loss 9.8939 -50 val perplexity 19809.6738 -50 train 9.885399 (lr=8.9161e-05) (hash(x)=7662067) -51 train 9.873328 (lr=9.0909e-05) (hash(x)=4648609) -52 train 9.797134 (lr=9.2657e-05) (hash(x)=4725966) -53 train 9.742386 (lr=9.4406e-05) (hash(x)=5558355) -54 train 9.767694 (lr=9.6154e-05) (hash(x)=6524933) -55 train 9.704561 (lr=9.7902e-05) (hash(x)=6369326) -56 train 9.654732 (lr=9.9650e-05) (hash(x)=6022625) -57 train 9.575443 (lr=1.0140e-04) (hash(x)=4906853) -58 train 9.381954 (lr=1.0315e-04) (hash(x)=5589269) -59 train 9.489091 (lr=1.0490e-04) (hash(x)=6437376) -60 train 9.515290 (lr=1.0664e-04) (hash(x)=7304892) -61 train 9.461693 (lr=1.0839e-04) (hash(x)=7084093) -62 train 9.460057 (lr=1.1014e-04) (hash(x)=5908178) -63 train 9.228505 (lr=1.1189e-04) (hash(x)=7048804) -64 train 9.292789 (lr=1.1364e-04) (hash(x)=6085549) -65 train 9.291378 (lr=1.1538e-04) (hash(x)=5752594) -66 train 9.076304 (lr=1.1713e-04) (hash(x)=7662769) -67 train 8.918578 (lr=1.1888e-04) (hash(x)=6393520) -68 train 9.151848 (lr=1.2063e-04) (hash(x)=5942867) -69 train 9.127384 (lr=1.2238e-04) (hash(x)=6793550) -70 train 8.950273 (lr=1.2413e-04) (hash(x)=7105976) -71 train 8.967115 (lr=1.2587e-04) (hash(x)=6581348) -72 train 8.880000 (lr=1.2762e-04) (hash(x)=5555598) -73 train 8.822878 (lr=1.2937e-04) (hash(x)=6235837) -74 train 8.747945 (lr=1.3112e-04) (hash(x)=5591770) -75 train 8.946789 (lr=1.3287e-04) (hash(x)=7083021) -76 train 8.770114 (lr=1.3462e-04) (hash(x)=7281348) -77 train 8.808050 (lr=1.3636e-04) (hash(x)=6155821) -78 train 8.625364 (lr=1.3811e-04) (hash(x)=5736241) -79 train 8.525559 (lr=1.3986e-04) (hash(x)=5657123) -80 train 8.465181 (lr=1.4161e-04) (hash(x)=6452095) -81 train 8.402158 (lr=1.4336e-04) (hash(x)=5312267) -82 train 8.274101 (lr=1.4510e-04) (hash(x)=5434493) -83 train 8.474909 (lr=1.4685e-04) (hash(x)=6830813) -84 train 8.312563 (lr=1.4860e-04) (hash(x)=4752771) -85 train 8.389462 (lr=1.5035e-04) (hash(x)=6424933) -86 train 8.288081 (lr=1.5210e-04) (hash(x)=5786517) -87 train 8.339081 (lr=1.5385e-04) (hash(x)=6680023) -88 train 8.251625 (lr=1.5559e-04) (hash(x)=6474729) -89 train 8.267853 (lr=1.5734e-04) (hash(x)=7523279) -90 train 8.057953 (lr=1.5909e-04) (hash(x)=5508768) -91 train 8.231356 (lr=1.6084e-04) (hash(x)=6635925) -92 train 8.114038 (lr=1.6259e-04) (hash(x)=6663801) -93 train 8.085885 (lr=1.6434e-04) (hash(x)=5869441) -94 train 8.135342 (lr=1.6608e-04) (hash(x)=6698878) -95 train 8.047293 (lr=1.6783e-04) (hash(x)=6349004) -96 train 8.049777 (lr=1.6958e-04) (hash(x)=4986137) -97 train 7.831696 (lr=1.7133e-04) (hash(x)=6008454) -98 train 7.897891 (lr=1.7308e-04) (hash(x)=6550770) -99 train 8.033091 (lr=1.7483e-04) (hash(x)=7682741) -100 val loss 7.9831 -100 val perplexity 2930.9805 -100 train 8.090453 (lr=1.7657e-04) (hash(x)=7892158) -101 train 7.958868 (lr=1.7832e-04) (hash(x)=7794028) -102 train 7.949870 (lr=1.8007e-04) (hash(x)=7093523) -103 train 7.980931 (lr=1.8182e-04) (hash(x)=6166062) -104 train 7.919570 (lr=1.8357e-04) (hash(x)=6645781) -105 train 7.891222 (lr=1.8531e-04) (hash(x)=4811192) -106 train 7.811481 (lr=1.8706e-04) (hash(x)=5970866) -107 train 7.818060 (lr=1.8881e-04) (hash(x)=7822680) -108 train 7.777383 (lr=1.9056e-04) (hash(x)=6317317) -109 train 7.874724 (lr=1.9231e-04) (hash(x)=6431409) -110 train 7.892319 (lr=1.9406e-04) (hash(x)=6653337) -111 train 7.827804 (lr=1.9580e-04) (hash(x)=5323032) -112 train 7.717324 (lr=1.9755e-04) (hash(x)=5125339) -113 train 7.660126 (lr=1.9930e-04) (hash(x)=7363286) -114 train 8.018383 (lr=2.0105e-04) (hash(x)=7670050) -115 train 7.784950 (lr=2.0280e-04) (hash(x)=5616075) -116 train 7.829693 (lr=2.0455e-04) (hash(x)=6593764) -117 train 7.890211 (lr=2.0629e-04) (hash(x)=5672608) -118 train 7.730969 (lr=2.0804e-04) (hash(x)=6828653) -119 train 7.721272 (lr=2.0979e-04) (hash(x)=6839867) -120 train 7.846440 (lr=2.1154e-04) (hash(x)=8426992) -121 train 7.517550 (lr=2.1329e-04) (hash(x)=4916928) -122 train 7.730700 (lr=2.1503e-04) (hash(x)=6484050) -123 train 7.823503 (lr=2.1678e-04) (hash(x)=8353379) -124 train 7.734229 (lr=2.1853e-04) (hash(x)=6552510) -125 train 7.706458 (lr=2.2028e-04) (hash(x)=4838871) -126 train 7.446773 (lr=2.2203e-04) (hash(x)=3021697) -127 train 7.606452 (lr=2.2378e-04) (hash(x)=6795665) -128 train 7.620957 (lr=2.2552e-04) (hash(x)=5486935) -129 train 7.809128 (lr=2.2727e-04) (hash(x)=6678038) -130 train 7.825309 (lr=2.2902e-04) (hash(x)=6657714) -131 train 7.716088 (lr=2.3077e-04) (hash(x)=6112215) -132 train 7.758881 (lr=2.3252e-04) (hash(x)=8353143) -133 train 7.783720 (lr=2.3427e-04) (hash(x)=5915361) -134 train 7.680995 (lr=2.3601e-04) (hash(x)=6254885) -135 train 7.694855 (lr=2.3776e-04) (hash(x)=5771588) -136 train 7.677476 (lr=2.3951e-04) (hash(x)=5561507) -137 train 7.624990 (lr=2.4126e-04) (hash(x)=5688829) -138 train 7.621283 (lr=2.4301e-04) (hash(x)=5371951) -139 train 7.790312 (lr=2.4476e-04) (hash(x)=5443305) -140 train 7.751131 (lr=2.4650e-04) (hash(x)=5016757) -141 train 7.758002 (lr=2.4825e-04) (hash(x)=6901933) -142 train 7.730201 (lr=2.5000e-04) (hash(x)=6019085) -143 train 7.565399 (lr=2.5175e-04) (hash(x)=4294425) -144 train 7.673890 (lr=2.5350e-04) (hash(x)=6095229) -145 train 7.503168 (lr=2.5524e-04) (hash(x)=4363941) -146 train 7.580531 (lr=2.5699e-04) (hash(x)=4693798) -147 train 8.144917 (lr=2.5874e-04) (hash(x)=5486335) -148 train 7.948389 (lr=2.6049e-04) (hash(x)=7907450) -149 train 7.779182 (lr=2.6224e-04) (hash(x)=7295165) -150 val loss 7.6655 -150 val perplexity 2133.4790 -150 train 7.703281 (lr=2.6399e-04) (hash(x)=6814026) -151 train 7.792414 (lr=2.6573e-04) (hash(x)=6267424) -152 train 7.802181 (lr=2.6748e-04) (hash(x)=8086437) -153 train 7.851647 (lr=2.6923e-04) (hash(x)=5270452) -154 train 7.695092 (lr=2.7098e-04) (hash(x)=6420820) -155 train 7.593840 (lr=2.7273e-04) (hash(x)=6305297) -156 train 7.737329 (lr=2.7448e-04) (hash(x)=7889849) -157 train 8.117135 (lr=2.7622e-04) (hash(x)=6040077) -158 train 8.112368 (lr=2.7797e-04) (hash(x)=5652497) -159 train 7.692060 (lr=2.7972e-04) (hash(x)=7130251) -160 train 7.550304 (lr=2.8147e-04) (hash(x)=6610177) -161 train 7.612594 (lr=2.8322e-04) (hash(x)=6508350) -162 train 7.769850 (lr=2.8497e-04) (hash(x)=6994983) -163 train 7.727452 (lr=2.8671e-04) (hash(x)=5859576) -164 train 7.284773 (lr=2.8846e-04) (hash(x)=5487065) -165 train 7.532728 (lr=2.9021e-04) (hash(x)=4892065) -166 train 7.427954 (lr=2.9196e-04) (hash(x)=4933674) -167 train 7.690159 (lr=2.9371e-04) (hash(x)=7317289) -168 train 7.792884 (lr=2.9545e-04) (hash(x)=6811522) -169 train 7.619172 (lr=2.9720e-04) (hash(x)=5510218) -170 train 7.783511 (lr=2.9895e-04) (hash(x)=7304235) -171 train 7.934256 (lr=3.0070e-04) (hash(x)=6752265) -172 train 7.629849 (lr=3.0245e-04) (hash(x)=5994476) -173 train 7.600955 (lr=3.0420e-04) (hash(x)=6530867) -174 train 7.702915 (lr=3.0594e-04) (hash(x)=5746260) -175 train 7.658589 (lr=3.0769e-04) (hash(x)=5790078) -176 train 7.674985 (lr=3.0944e-04) (hash(x)=6430135) -177 train 7.746804 (lr=3.1119e-04) (hash(x)=7614023) -178 train 7.730116 (lr=3.1294e-04) (hash(x)=5244861) -179 train 7.712088 (lr=3.1469e-04) (hash(x)=5245146) -180 train 7.603346 (lr=3.1643e-04) (hash(x)=6415565) -181 train 7.655617 (lr=3.1818e-04) (hash(x)=5786972) -182 train 7.691521 (lr=3.1993e-04) (hash(x)=6131703) -183 train 7.712232 (lr=3.2168e-04) (hash(x)=6346459) -184 train 7.754544 (lr=3.2343e-04) (hash(x)=6504131) -185 train 7.744644 (lr=3.2517e-04) (hash(x)=5209234) -186 train 7.656458 (lr=3.2692e-04) (hash(x)=6163272) -187 train 7.648332 (lr=3.2867e-04) (hash(x)=5676768) -188 train 7.715640 (lr=3.3042e-04) (hash(x)=6090561) -189 train 7.867862 (lr=3.3217e-04) (hash(x)=5863092) -190 train 7.778335 (lr=3.3392e-04) (hash(x)=7201312) -191 train 7.853775 (lr=3.3566e-04) (hash(x)=7019489) -192 train 7.619477 (lr=3.3741e-04) (hash(x)=6225608) -193 train 7.712648 (lr=3.3916e-04) (hash(x)=5483019) -194 train 7.652710 (lr=3.4091e-04) (hash(x)=5903258) -195 train 7.691281 (lr=3.4266e-04) (hash(x)=5968716) -196 train 7.687555 (lr=3.4441e-04) (hash(x)=5778017) -197 train 7.410178 (lr=3.4615e-04) (hash(x)=7780194) -198 train 7.622293 (lr=3.4790e-04) (hash(x)=6140998) -199 train 7.609862 (lr=3.4965e-04) (hash(x)=3784321) -200 val loss 7.6258 -200 val perplexity 2050.3394 -200 train 7.632768 (lr=3.5140e-04) (hash(x)=5860821) -201 train 7.672125 (lr=3.5315e-04) (hash(x)=7774109) -202 train 7.835864 (lr=3.5490e-04) (hash(x)=7997664) -203 train 7.801472 (lr=3.5664e-04) (hash(x)=6576749) -204 train 7.720698 (lr=3.5839e-04) (hash(x)=7266655) -205 train 7.686074 (lr=3.6014e-04) (hash(x)=7072404) -206 train 7.599856 (lr=3.6189e-04) (hash(x)=6626459) -207 train 7.601377 (lr=3.6364e-04) (hash(x)=6556025) -208 train 7.638923 (lr=3.6538e-04) (hash(x)=5942129) -209 train 7.745492 (lr=3.6713e-04) (hash(x)=7325027) -210 train 7.741173 (lr=3.6888e-04) (hash(x)=7322467) -211 train 7.673203 (lr=3.7063e-04) (hash(x)=6373412) -212 train 7.465663 (lr=3.7238e-04) (hash(x)=7332255) -213 train 7.744501 (lr=3.7413e-04) (hash(x)=5262868) -214 train 7.456234 (lr=3.7587e-04) (hash(x)=5688247) -215 train 7.622649 (lr=3.7762e-04) (hash(x)=8055563) -216 train 7.651843 (lr=3.7937e-04) (hash(x)=5352405) -217 train 7.726893 (lr=3.8112e-04) (hash(x)=5932790) -218 train 7.666943 (lr=3.8287e-04) (hash(x)=6249312) -219 train 7.623081 (lr=3.8462e-04) (hash(x)=5680154) -220 train 7.722910 (lr=3.8636e-04) (hash(x)=8156280) -221 train 7.649165 (lr=3.8811e-04) (hash(x)=5914217) -222 train 7.484366 (lr=3.8986e-04) (hash(x)=7120215) -223 train 7.680924 (lr=3.9161e-04) (hash(x)=6424128) -224 train 7.432400 (lr=3.9336e-04) (hash(x)=4390027) -225 train 7.641574 (lr=3.9510e-04) (hash(x)=7804089) -226 train 7.717457 (lr=3.9685e-04) (hash(x)=7130267) -227 train 7.493531 (lr=3.9860e-04) (hash(x)=6490149) -228 train 7.587654 (lr=4.0035e-04) (hash(x)=9276378) -229 train 7.613081 (lr=4.0210e-04) (hash(x)=6283540) -230 train 7.594581 (lr=4.0385e-04) (hash(x)=5781680) -231 train 7.525056 (lr=4.0559e-04) (hash(x)=5728337) -232 train 7.519223 (lr=4.0734e-04) (hash(x)=6278202) -233 train 7.623920 (lr=4.0909e-04) (hash(x)=7400272) -234 train 7.590850 (lr=4.1084e-04) (hash(x)=5795128) -235 train 7.558988 (lr=4.1259e-04) (hash(x)=6473432) -236 train 7.579780 (lr=4.1434e-04) (hash(x)=5201502) -237 train 7.788270 (lr=4.1608e-04) (hash(x)=6922646) -238 train 7.499532 (lr=4.1783e-04) (hash(x)=5484641) -239 train 7.566568 (lr=4.1958e-04) (hash(x)=7277141) -240 train 7.573974 (lr=4.2133e-04) (hash(x)=5604614) -241 train 7.624212 (lr=4.2308e-04) (hash(x)=7443124) -242 train 7.636985 (lr=4.2483e-04) (hash(x)=5601968) -243 train 7.525299 (lr=4.2657e-04) (hash(x)=5632735) -244 train 7.536751 (lr=4.2832e-04) (hash(x)=5594810) -245 train 7.395719 (lr=4.3007e-04) (hash(x)=5881015) -246 train 7.534366 (lr=4.3182e-04) (hash(x)=6865361) -247 train 7.606976 (lr=4.3357e-04) (hash(x)=5809411) -248 train 7.598826 (lr=4.3531e-04) (hash(x)=6293025) -249 train 7.542069 (lr=4.3706e-04) (hash(x)=7232964) -250 val loss 7.5649 -250 val perplexity 1929.2784 -250 train 7.486119 (lr=4.3881e-04) (hash(x)=5646619) -251 train 7.601873 (lr=4.4056e-04) (hash(x)=6171829) -252 train 7.676800 (lr=4.4231e-04) (hash(x)=7787552) -253 train 7.609212 (lr=4.4406e-04) (hash(x)=5884456) -254 train 7.627812 (lr=4.4580e-04) (hash(x)=6752162) -255 train 7.541821 (lr=4.4755e-04) (hash(x)=5077031) -256 train 7.698488 (lr=4.4930e-04) (hash(x)=6883481) -257 train 7.584640 (lr=4.5105e-04) (hash(x)=6248895) -258 train 7.457194 (lr=4.5280e-04) (hash(x)=6636615) -259 train 7.646179 (lr=4.5455e-04) (hash(x)=6918004) -260 train 7.561431 (lr=4.5629e-04) (hash(x)=7302874) -261 train 7.669982 (lr=4.5804e-04) (hash(x)=6482466) -262 train 7.498110 (lr=4.5979e-04) (hash(x)=7298317) -263 train 7.533354 (lr=4.6154e-04) (hash(x)=6588573) -264 train 7.526618 (lr=4.6329e-04) (hash(x)=6229630) -265 train 7.600528 (lr=4.6503e-04) (hash(x)=6136939) -266 train 7.357875 (lr=4.6678e-04) (hash(x)=6394645) -267 train 7.592115 (lr=4.6853e-04) (hash(x)=7040157) -268 train 7.628303 (lr=4.7028e-04) (hash(x)=7041858) -269 train 7.529849 (lr=4.7203e-04) (hash(x)=6455595) -270 train 7.459441 (lr=4.7378e-04) (hash(x)=6480443) -271 train 7.647004 (lr=4.7552e-04) (hash(x)=4122983) -272 train 7.458611 (lr=4.7727e-04) (hash(x)=7672190) -273 train 7.485595 (lr=4.7902e-04) (hash(x)=4724052) -274 train 7.437414 (lr=4.8077e-04) (hash(x)=6654267) -275 train 7.420813 (lr=4.8252e-04) (hash(x)=6820797) -276 train 7.512196 (lr=4.8427e-04) (hash(x)=6458662) -277 train 7.917709 (lr=4.8601e-04) (hash(x)=7477594) -278 train 7.554106 (lr=4.8776e-04) (hash(x)=5876574) -279 train 7.277621 (lr=4.8951e-04) (hash(x)=6146305) -280 train 7.454937 (lr=4.9126e-04) (hash(x)=6162080) -281 train 7.411793 (lr=4.9301e-04) (hash(x)=6814831) -282 train 7.541778 (lr=4.9476e-04) (hash(x)=7138295) -283 train 7.317982 (lr=4.9650e-04) (hash(x)=5548298) -284 train 7.428448 (lr=4.9825e-04) (hash(x)=6265078) -285 train 7.801420 (lr=5.0000e-04) (hash(x)=7609416) -286 train 7.483164 (lr=5.0000e-04) (hash(x)=6909367) -287 train 7.597700 (lr=5.0000e-04) (hash(x)=7574342) -288 train 7.409695 (lr=4.9999e-04) (hash(x)=8859748) -289 train 7.362408 (lr=4.9998e-04) (hash(x)=5906937) -290 train 7.386526 (lr=4.9997e-04) (hash(x)=7243024) -291 train 7.502868 (lr=4.9995e-04) (hash(x)=8013471) -292 train 7.416108 (lr=4.9992e-04) (hash(x)=5659461) -293 train 7.455505 (lr=4.9989e-04) (hash(x)=6146213) -294 train 7.491917 (lr=4.9986e-04) (hash(x)=6602917) -295 train 7.399060 (lr=4.9982e-04) (hash(x)=6709902) -296 train 7.526380 (lr=4.9978e-04) (hash(x)=8154341) -297 train 7.667249 (lr=4.9974e-04) (hash(x)=6402571) -298 train 7.428350 (lr=4.9969e-04) (hash(x)=5605466) -299 train 7.383250 (lr=4.9963e-04) (hash(x)=7683614) -300 val loss 7.4516 -300 val perplexity 1722.6920 -300 train 7.500629 (lr=4.9957e-04) (hash(x)=5421572) -301 train 7.343226 (lr=4.9951e-04) (hash(x)=5453026) -302 train 7.402356 (lr=4.9944e-04) (hash(x)=6437746) -303 train 7.311347 (lr=4.9937e-04) (hash(x)=6260017) -304 train 7.410797 (lr=4.9929e-04) (hash(x)=6119053) -305 train 7.575393 (lr=4.9921e-04) (hash(x)=6591466) -306 train 7.485226 (lr=4.9913e-04) (hash(x)=5652701) -307 train 7.442460 (lr=4.9904e-04) (hash(x)=5501472) -308 train 7.624926 (lr=4.9895e-04) (hash(x)=6160695) -309 train 7.380640 (lr=4.9885e-04) (hash(x)=5871698) -310 train 7.343381 (lr=4.9875e-04) (hash(x)=7301184) -311 train 7.274087 (lr=4.9864e-04) (hash(x)=4282052) -312 train 7.481493 (lr=4.9853e-04) (hash(x)=5679330) -313 train 7.329782 (lr=4.9841e-04) (hash(x)=7824660) -314 train 7.376566 (lr=4.9829e-04) (hash(x)=4857318) -315 train 7.313642 (lr=4.9817e-04) (hash(x)=5954950) -316 train 7.372428 (lr=4.9804e-04) (hash(x)=5758178) -317 train 7.392262 (lr=4.9791e-04) (hash(x)=5484656) -318 train 7.383463 (lr=4.9777e-04) (hash(x)=6818913) -319 train 7.589435 (lr=4.9763e-04) (hash(x)=7031328) -320 train 7.416356 (lr=4.9749e-04) (hash(x)=6837621) -321 train 7.457081 (lr=4.9734e-04) (hash(x)=9157069) -322 train 7.698480 (lr=4.9718e-04) (hash(x)=6509536) -323 train 7.392669 (lr=4.9702e-04) (hash(x)=5996883) -324 train 7.647024 (lr=4.9686e-04) (hash(x)=6850868) -325 train 7.569314 (lr=4.9670e-04) (hash(x)=7645447) -326 train 7.580283 (lr=4.9652e-04) (hash(x)=6717515) -327 train 7.708749 (lr=4.9635e-04) (hash(x)=6336164) -328 train 7.413807 (lr=4.9617e-04) (hash(x)=6897445) -329 train 7.333851 (lr=4.9598e-04) (hash(x)=5224240) -330 train 7.483329 (lr=4.9580e-04) (hash(x)=6612945) -331 train 7.923858 (lr=4.9560e-04) (hash(x)=5447801) -332 train 7.465648 (lr=4.9541e-04) (hash(x)=7308579) -333 train 7.358824 (lr=4.9521e-04) (hash(x)=4155598) -334 train 7.355170 (lr=4.9500e-04) (hash(x)=6106773) -335 train 7.404686 (lr=4.9479e-04) (hash(x)=7482744) -336 train 7.500164 (lr=4.9458e-04) (hash(x)=6310687) -337 train 7.362833 (lr=4.9436e-04) (hash(x)=4733414) -338 train 7.462912 (lr=4.9414e-04) (hash(x)=6979734) -339 train 7.269539 (lr=4.9391e-04) (hash(x)=7806284) -340 train 7.276829 (lr=4.9368e-04) (hash(x)=5080536) -341 train 7.495099 (lr=4.9344e-04) (hash(x)=7236478) -342 train 7.432468 (lr=4.9320e-04) (hash(x)=6619318) -343 train 7.337922 (lr=4.9296e-04) (hash(x)=4656255) -344 train 7.276386 (lr=4.9271e-04) (hash(x)=5546888) -345 train 7.748324 (lr=4.9246e-04) (hash(x)=9298325) -346 train 7.459085 (lr=4.9220e-04) (hash(x)=5994232) -347 train 7.417453 (lr=4.9194e-04) (hash(x)=6287524) -348 train 7.540259 (lr=4.9168e-04) (hash(x)=6200049) -349 train 7.444436 (lr=4.9141e-04) (hash(x)=7895970) -350 val loss 7.3646 -350 val perplexity 1579.1465 -350 train 7.350061 (lr=4.9114e-04) (hash(x)=6051847) -351 train 7.506237 (lr=4.9086e-04) (hash(x)=8847992) -352 train 7.880729 (lr=4.9058e-04) (hash(x)=5123883) -353 train 7.464824 (lr=4.9029e-04) (hash(x)=6338998) -354 train 7.467878 (lr=4.9000e-04) (hash(x)=5765866) -355 train 7.813435 (lr=4.8971e-04) (hash(x)=7104011) -356 train 7.582506 (lr=4.8941e-04) (hash(x)=7438267) -357 train 7.317100 (lr=4.8911e-04) (hash(x)=5573214) -358 train 7.570335 (lr=4.8880e-04) (hash(x)=6897283) -359 train 7.362119 (lr=4.8849e-04) (hash(x)=6882897) -360 train 7.479269 (lr=4.8818e-04) (hash(x)=5343615) -361 train 7.388541 (lr=4.8786e-04) (hash(x)=5854242) -362 train 7.301569 (lr=4.8754e-04) (hash(x)=6317324) -363 train 7.239825 (lr=4.8721e-04) (hash(x)=6972494) -364 train 7.318973 (lr=4.8688e-04) (hash(x)=5661167) -365 train 7.332743 (lr=4.8654e-04) (hash(x)=6796805) -366 train 7.158183 (lr=4.8620e-04) (hash(x)=5817209) -367 train 7.233025 (lr=4.8586e-04) (hash(x)=6139120) -368 train 7.402174 (lr=4.8551e-04) (hash(x)=6121296) -369 train 7.376255 (lr=4.8516e-04) (hash(x)=6486796) -370 train 7.291081 (lr=4.8481e-04) (hash(x)=5514645) -371 train 7.235853 (lr=4.8445e-04) (hash(x)=5578797) -372 train 7.232906 (lr=4.8408e-04) (hash(x)=7651738) -373 train 7.441844 (lr=4.8372e-04) (hash(x)=6895326) -374 train 7.463004 (lr=4.8334e-04) (hash(x)=5490256) -375 train 7.318242 (lr=4.8297e-04) (hash(x)=7783160) -376 train 7.523637 (lr=4.8259e-04) (hash(x)=5608424) -377 train 7.289732 (lr=4.8220e-04) (hash(x)=4867625) -378 train 7.199661 (lr=4.8182e-04) (hash(x)=4655472) -379 train 7.258174 (lr=4.8142e-04) (hash(x)=6631123) -380 train 6.930998 (lr=4.8103e-04) (hash(x)=5751990) -381 train 7.244713 (lr=4.8063e-04) (hash(x)=6710965) -382 train 7.194671 (lr=4.8022e-04) (hash(x)=5293800) -383 train 7.221773 (lr=4.7982e-04) (hash(x)=6294657) -384 train 7.393067 (lr=4.7940e-04) (hash(x)=6999538) -385 train 7.381361 (lr=4.7899e-04) (hash(x)=5443606) -386 train 7.358816 (lr=4.7857e-04) (hash(x)=5650401) -387 train 7.354572 (lr=4.7815e-04) (hash(x)=7035770) -388 train 7.304999 (lr=4.7772e-04) (hash(x)=6678271) -389 train 7.499672 (lr=4.7729e-04) (hash(x)=4899541) -390 train 7.237353 (lr=4.7685e-04) (hash(x)=5359260) -391 train 7.232718 (lr=4.7641e-04) (hash(x)=6227120) -392 train 7.301436 (lr=4.7597e-04) (hash(x)=6643916) -393 train 7.356061 (lr=4.7552e-04) (hash(x)=5981648) -394 train 7.321610 (lr=4.7507e-04) (hash(x)=6467540) -395 train 7.252539 (lr=4.7462e-04) (hash(x)=5558993) -396 train 7.430574 (lr=4.7416e-04) (hash(x)=6698959) -397 train 7.227236 (lr=4.7369e-04) (hash(x)=7015671) -398 train 7.248781 (lr=4.7323e-04) (hash(x)=6800890) -399 train 7.412173 (lr=4.7276e-04) (hash(x)=5931234) -400 val loss 7.3167 -400 val perplexity 1505.2485 -400 train 7.409585 (lr=4.7228e-04) (hash(x)=3995070) -401 train 7.332630 (lr=4.7181e-04) (hash(x)=4582159) -402 train 7.372652 (lr=4.7132e-04) (hash(x)=7081906) -403 train 7.296834 (lr=4.7084e-04) (hash(x)=5029472) -404 train 7.319156 (lr=4.7035e-04) (hash(x)=3946232) -405 train 7.222072 (lr=4.6986e-04) (hash(x)=5434102) -406 train 7.960849 (lr=4.6936e-04) (hash(x)=5340646) -407 train 7.133418 (lr=4.6886e-04) (hash(x)=6810638) -408 train 7.384606 (lr=4.6835e-04) (hash(x)=6768026) -409 train 7.375993 (lr=4.6785e-04) (hash(x)=6521562) -410 train 7.327439 (lr=4.6733e-04) (hash(x)=4429434) -411 train 7.394525 (lr=4.6682e-04) (hash(x)=7226932) -412 train 7.169340 (lr=4.6630e-04) (hash(x)=5065932) -413 train 7.331411 (lr=4.6578e-04) (hash(x)=6957849) -414 train 7.329439 (lr=4.6525e-04) (hash(x)=6431457) -415 train 7.399717 (lr=4.6472e-04) (hash(x)=5334281) -416 train 7.406147 (lr=4.6418e-04) (hash(x)=5471747) -417 train 7.499147 (lr=4.6365e-04) (hash(x)=5887983) -418 train 7.404335 (lr=4.6311e-04) (hash(x)=5075909) -419 train 7.202665 (lr=4.6256e-04) (hash(x)=6393576) -420 train 7.296270 (lr=4.6201e-04) (hash(x)=6608979) -421 train 7.728078 (lr=4.6146e-04) (hash(x)=5057959) -422 train 7.663626 (lr=4.6090e-04) (hash(x)=6414858) -423 train 7.435847 (lr=4.6034e-04) (hash(x)=8595271) -424 train 7.300275 (lr=4.5978e-04) (hash(x)=6500949) -425 train 7.502699 (lr=4.5921e-04) (hash(x)=8395167) -426 train 7.632969 (lr=4.5864e-04) (hash(x)=6288420) -427 train 7.425904 (lr=4.5807e-04) (hash(x)=7634417) -428 train 7.306537 (lr=4.5749e-04) (hash(x)=6795561) -429 train 7.204391 (lr=4.5691e-04) (hash(x)=5257771) -430 train 7.367026 (lr=4.5633e-04) (hash(x)=7506860) -431 train 7.397141 (lr=4.5574e-04) (hash(x)=7674238) -432 train 7.503457 (lr=4.5515e-04) (hash(x)=5353794) -433 train 7.430412 (lr=4.5455e-04) (hash(x)=5300555) -434 train 7.117725 (lr=4.5396e-04) (hash(x)=5564419) -435 train 7.385005 (lr=4.5335e-04) (hash(x)=6066139) -436 train 7.363755 (lr=4.5275e-04) (hash(x)=6863709) -437 train 7.352476 (lr=4.5214e-04) (hash(x)=6688212) -438 train 7.504986 (lr=4.5153e-04) (hash(x)=7095090) -439 train 7.606781 (lr=4.5091e-04) (hash(x)=6642404) -440 train 7.314439 (lr=4.5029e-04) (hash(x)=6539227) -441 train 7.305208 (lr=4.4967e-04) (hash(x)=4961570) -442 train 7.246849 (lr=4.4905e-04) (hash(x)=6606391) -443 train 7.048862 (lr=4.4842e-04) (hash(x)=5105190) -444 train 7.646637 (lr=4.4778e-04) (hash(x)=5695997) -445 train 7.336450 (lr=4.4715e-04) (hash(x)=7155991) -446 train 7.309959 (lr=4.4651e-04) (hash(x)=7249727) -447 train 7.295984 (lr=4.4587e-04) (hash(x)=5132972) -448 train 7.292876 (lr=4.4522e-04) (hash(x)=5381802) -449 train 7.317535 (lr=4.4457e-04) (hash(x)=6269946) -450 val loss 7.2890 -450 val perplexity 1464.1219 -450 train 7.271142 (lr=4.4392e-04) (hash(x)=4976762) -451 train 7.361707 (lr=4.4326e-04) (hash(x)=5396133) -452 train 7.327783 (lr=4.4260e-04) (hash(x)=6173473) -453 train 7.296171 (lr=4.4194e-04) (hash(x)=6394083) -454 train 7.372822 (lr=4.4128e-04) (hash(x)=6436030) -455 train 7.211841 (lr=4.4061e-04) (hash(x)=5237804) -456 train 7.193060 (lr=4.3994e-04) (hash(x)=6540397) -457 train 7.444540 (lr=4.3926e-04) (hash(x)=5216638) -458 train 7.271979 (lr=4.3858e-04) (hash(x)=5750537) -459 train 7.259324 (lr=4.3790e-04) (hash(x)=6735565) -460 train 7.287656 (lr=4.3722e-04) (hash(x)=7297488) -461 train 7.463627 (lr=4.3653e-04) (hash(x)=5983575) -462 train 7.290742 (lr=4.3584e-04) (hash(x)=4808543) -463 train 7.405876 (lr=4.3515e-04) (hash(x)=5831619) -464 train 7.156505 (lr=4.3445e-04) (hash(x)=6280052) -465 train 7.171041 (lr=4.3375e-04) (hash(x)=9109083) -466 train 7.431561 (lr=4.3305e-04) (hash(x)=5848604) -467 train 7.372941 (lr=4.3234e-04) (hash(x)=6912967) -468 train 7.553815 (lr=4.3163e-04) (hash(x)=6615365) -469 train 7.607442 (lr=4.3092e-04) (hash(x)=5965674) -470 train 7.455511 (lr=4.3020e-04) (hash(x)=6879965) -471 train 7.419261 (lr=4.2948e-04) (hash(x)=5822533) -472 train 7.278405 (lr=4.2876e-04) (hash(x)=5794462) -473 train 7.372121 (lr=4.2804e-04) (hash(x)=5268216) -474 train 7.190698 (lr=4.2731e-04) (hash(x)=7058396) -475 train 7.303502 (lr=4.2658e-04) (hash(x)=6531900) -476 train 7.335746 (lr=4.2585e-04) (hash(x)=5878912) -477 train 7.136664 (lr=4.2511e-04) (hash(x)=5426499) -478 train 7.347939 (lr=4.2437e-04) (hash(x)=8107004) -479 train 8.073548 (lr=4.2363e-04) (hash(x)=7455372) -480 train 7.998034 (lr=4.2289e-04) (hash(x)=7727959) -481 train 7.919175 (lr=4.2214e-04) (hash(x)=8319119) -482 train 7.831254 (lr=4.2139e-04) (hash(x)=7581656) -483 train 7.897698 (lr=4.2064e-04) (hash(x)=7592128) -484 train 7.883114 (lr=4.1988e-04) (hash(x)=10506633) -485 train 7.835151 (lr=4.1912e-04) (hash(x)=8704170) -486 train 7.658167 (lr=4.1836e-04) (hash(x)=7461138) -487 train 7.588099 (lr=4.1759e-04) (hash(x)=7165037) -488 train 7.634685 (lr=4.1683e-04) (hash(x)=4976998) -489 train 7.399677 (lr=4.1606e-04) (hash(x)=7678000) -490 train 7.460315 (lr=4.1529e-04) (hash(x)=6299409) -491 train 7.390481 (lr=4.1451e-04) (hash(x)=7414788) -492 train 7.459745 (lr=4.1373e-04) (hash(x)=5063061) -493 train 7.374101 (lr=4.1295e-04) (hash(x)=7326216) -494 train 7.538434 (lr=4.1217e-04) (hash(x)=7492012) -495 train 7.500280 (lr=4.1138e-04) (hash(x)=5857162) -496 train 7.296118 (lr=4.1059e-04) (hash(x)=6169001) -497 train 9.308700 (lr=4.0980e-04) (hash(x)=14715669) -498 train 12.223278 (lr=4.0901e-04) (hash(x)=18256706) -499 train 11.954405 (lr=4.0821e-04) (hash(x)=16950560) -500 val loss 7.3852 -500 val perplexity 1611.9194 -500 train 8.109703 (lr=4.0741e-04) (hash(x)=6113563) -501 train 7.068744 (lr=4.0661e-04) (hash(x)=6159125) -502 train 7.454783 (lr=4.0581e-04) (hash(x)=5482303) -503 train 7.484365 (lr=4.0500e-04) (hash(x)=5908442) -504 train 7.354419 (lr=4.0419e-04) (hash(x)=4985045) -505 train 7.251081 (lr=4.0338e-04) (hash(x)=6668887) -506 train 7.330905 (lr=4.0256e-04) (hash(x)=6123910) -507 train 7.420095 (lr=4.0175e-04) (hash(x)=7662975) -508 train 7.364473 (lr=4.0093e-04) (hash(x)=7191898) -509 train 7.303823 (lr=4.0011e-04) (hash(x)=6669539) -510 train 7.355706 (lr=3.9928e-04) (hash(x)=6557481) -511 train 7.248978 (lr=3.9846e-04) (hash(x)=5015998) -512 train 7.317575 (lr=3.9763e-04) (hash(x)=4964540) -513 train 7.176949 (lr=3.9680e-04) (hash(x)=5458386) -514 train 7.554805 (lr=3.9596e-04) (hash(x)=6077616) -515 train 7.274286 (lr=3.9513e-04) (hash(x)=4849847) -516 train 7.352317 (lr=3.9429e-04) (hash(x)=5431422) -517 train 7.531367 (lr=3.9345e-04) (hash(x)=5125562) -518 train 7.447542 (lr=3.9260e-04) (hash(x)=5587715) -519 train 7.502025 (lr=3.9176e-04) (hash(x)=6012047) -520 train 7.332932 (lr=3.9091e-04) (hash(x)=5668436) -521 train 7.344112 (lr=3.9006e-04) (hash(x)=6079364) -522 train 7.462158 (lr=3.8921e-04) (hash(x)=5200504) -523 train 7.190444 (lr=3.8836e-04) (hash(x)=6030395) -524 train 7.433517 (lr=3.8750e-04) (hash(x)=6855319) -525 train 7.204855 (lr=3.8664e-04) (hash(x)=6781762) -526 train 7.350496 (lr=3.8578e-04) (hash(x)=6717939) -527 train 7.349863 (lr=3.8492e-04) (hash(x)=5238325) -528 train 7.255769 (lr=3.8405e-04) (hash(x)=5808069) -529 train 7.575129 (lr=3.8319e-04) (hash(x)=8611144) -530 train 7.260050 (lr=3.8232e-04) (hash(x)=6028738) -531 train 7.298766 (lr=3.8145e-04) (hash(x)=6901605) -532 train 7.252521 (lr=3.8057e-04) (hash(x)=6723307) -533 train 7.340546 (lr=3.7970e-04) (hash(x)=5499337) -534 train 7.275239 (lr=3.7882e-04) (hash(x)=6586372) -535 train 7.402943 (lr=3.7794e-04) (hash(x)=7134874) -536 train 7.293164 (lr=3.7706e-04) (hash(x)=8415623) -537 train 7.318466 (lr=3.7618e-04) (hash(x)=6149038) -538 train 7.356337 (lr=3.7529e-04) (hash(x)=6078325) -539 train 7.327504 (lr=3.7440e-04) (hash(x)=6609760) -540 train 7.226675 (lr=3.7351e-04) (hash(x)=6185253) -541 train 7.624069 (lr=3.7262e-04) (hash(x)=6652627) -542 train 7.410195 (lr=3.7173e-04) (hash(x)=7758536) -543 train 7.383860 (lr=3.7084e-04) (hash(x)=8618579) -544 train 7.341766 (lr=3.6994e-04) (hash(x)=6710226) -545 train 7.210335 (lr=3.6904e-04) (hash(x)=5896892) -546 train 7.228855 (lr=3.6814e-04) (hash(x)=6332995) -547 train 7.615961 (lr=3.6724e-04) (hash(x)=8945854) -548 train 7.197575 (lr=3.6633e-04) (hash(x)=4329129) -549 train 7.258995 (lr=3.6543e-04) (hash(x)=6775103) -550 val loss 7.2793 -550 val perplexity 1449.9744 -550 train 7.363537 (lr=3.6452e-04) (hash(x)=4465735) -551 train 7.254971 (lr=3.6361e-04) (hash(x)=6200024) -552 train 7.203400 (lr=3.6270e-04) (hash(x)=5520748) -553 train 7.216261 (lr=3.6179e-04) (hash(x)=5238139) -554 train 7.461508 (lr=3.6088e-04) (hash(x)=7639817) -555 train 7.217396 (lr=3.5996e-04) (hash(x)=5780948) -556 train 7.360391 (lr=3.5904e-04) (hash(x)=6733444) -557 train 7.305562 (lr=3.5812e-04) (hash(x)=6168407) -558 train 7.351892 (lr=3.5720e-04) (hash(x)=6680197) -559 train 7.215224 (lr=3.5628e-04) (hash(x)=3775881) -560 train 7.074762 (lr=3.5536e-04) (hash(x)=5784096) -561 train 7.505771 (lr=3.5443e-04) (hash(x)=6848709) -562 train 7.553386 (lr=3.5350e-04) (hash(x)=7449019) -563 train 7.653483 (lr=3.5257e-04) (hash(x)=6478113) -564 train 7.305277 (lr=3.5164e-04) (hash(x)=5925744) -565 train 7.367736 (lr=3.5071e-04) (hash(x)=6483914) -566 train 7.258492 (lr=3.4978e-04) (hash(x)=6010847) -567 train 7.337683 (lr=3.4885e-04) (hash(x)=5927795) -568 train 7.333642 (lr=3.4791e-04) (hash(x)=5896332) -569 train 7.307150 (lr=3.4697e-04) (hash(x)=8438033) -570 train 7.391054 (lr=3.4603e-04) (hash(x)=6081660) -571 train 7.320904 (lr=3.4509e-04) (hash(x)=5684788) -572 train 7.210525 (lr=3.4415e-04) (hash(x)=6272055) -573 train 7.157257 (lr=3.4321e-04) (hash(x)=5710182) -574 train 7.280805 (lr=3.4227e-04) (hash(x)=6219616) -575 train 7.237747 (lr=3.4132e-04) (hash(x)=6160063) -576 train 7.262324 (lr=3.4037e-04) (hash(x)=5710809) -577 train 7.014307 (lr=3.3943e-04) (hash(x)=5955100) -578 train 7.025233 (lr=3.3848e-04) (hash(x)=5356088) -579 train 7.067662 (lr=3.3753e-04) (hash(x)=6672309) -580 train 7.278050 (lr=3.3657e-04) (hash(x)=5841684) -581 train 7.612208 (lr=3.3562e-04) (hash(x)=9001564) -582 train 8.155598 (lr=3.3467e-04) (hash(x)=6897178) -583 train 7.391499 (lr=3.3371e-04) (hash(x)=5454654) -584 train 7.158257 (lr=3.3276e-04) (hash(x)=6391454) -585 train 7.242211 (lr=3.3180e-04) (hash(x)=5174062) -586 train 7.359061 (lr=3.3084e-04) (hash(x)=5197924) -587 train 7.319856 (lr=3.2988e-04) (hash(x)=6199203) -588 train 7.152327 (lr=3.2892e-04) (hash(x)=5786498) -589 train 7.270411 (lr=3.2796e-04) (hash(x)=8352747) -590 train 7.553372 (lr=3.2700e-04) (hash(x)=4829700) -591 train 7.089417 (lr=3.2603e-04) (hash(x)=4547106) -592 train 7.379088 (lr=3.2507e-04) (hash(x)=7686831) -593 train 7.255884 (lr=3.2410e-04) (hash(x)=6433099) -594 train 7.126493 (lr=3.2313e-04) (hash(x)=4826460) -595 train 7.209390 (lr=3.2217e-04) (hash(x)=6424428) -596 train 7.087097 (lr=3.2120e-04) (hash(x)=6073605) -597 train 7.446998 (lr=3.2023e-04) (hash(x)=5975712) -598 train 7.053827 (lr=3.1926e-04) (hash(x)=7030029) -599 train 7.345481 (lr=3.1829e-04) (hash(x)=5458532) -600 val loss 7.2723 -600 val perplexity 1439.8539 -600 train 7.193815 (lr=3.1732e-04) (hash(x)=7823919) -601 train 7.623002 (lr=3.1634e-04) (hash(x)=7002774) -602 train 7.425569 (lr=3.1537e-04) (hash(x)=7056399) -603 train 7.625144 (lr=3.1440e-04) (hash(x)=8206173) -604 train 7.478229 (lr=3.1342e-04) (hash(x)=8034846) -605 train 7.757761 (lr=3.1244e-04) (hash(x)=7784971) -606 train 7.867619 (lr=3.1147e-04) (hash(x)=7118076) -607 train 7.218085 (lr=3.1049e-04) (hash(x)=6001843) -608 train 7.324508 (lr=3.0951e-04) (hash(x)=5582437) -609 train 7.424302 (lr=3.0853e-04) (hash(x)=5698642) -610 train 7.278915 (lr=3.0756e-04) (hash(x)=6615301) -611 train 7.279538 (lr=3.0658e-04) (hash(x)=6600751) -612 train 7.184999 (lr=3.0559e-04) (hash(x)=6880955) -613 train 7.259321 (lr=3.0461e-04) (hash(x)=5804610) -614 train 7.177356 (lr=3.0363e-04) (hash(x)=6263347) -615 train 7.155849 (lr=3.0265e-04) (hash(x)=5162652) -616 train 7.209515 (lr=3.0167e-04) (hash(x)=6055710) -617 train 7.168361 (lr=3.0068e-04) (hash(x)=5297006) -618 train 7.190626 (lr=2.9970e-04) (hash(x)=5923648) -619 train 7.204132 (lr=2.9872e-04) (hash(x)=6728323) -620 train 7.214056 (lr=2.9773e-04) (hash(x)=6660239) -621 train 7.162459 (lr=2.9675e-04) (hash(x)=3964882) -622 train 7.224735 (lr=2.9576e-04) (hash(x)=5868942) -623 train 7.143094 (lr=2.9477e-04) (hash(x)=6735993) -624 train 7.470279 (lr=2.9379e-04) (hash(x)=5926190) -625 train 7.164414 (lr=2.9280e-04) (hash(x)=5150316) -626 train 7.176792 (lr=2.9181e-04) (hash(x)=7571467) -627 train 7.078360 (lr=2.9083e-04) (hash(x)=5220448) -628 train 7.119508 (lr=2.8984e-04) (hash(x)=6790397) -629 train 7.551075 (lr=2.8885e-04) (hash(x)=6971289) -630 train 7.489536 (lr=2.8786e-04) (hash(x)=7123359) -631 train 7.285959 (lr=2.8687e-04) (hash(x)=5012069) -632 train 7.283583 (lr=2.8589e-04) (hash(x)=6183574) -633 train 7.184519 (lr=2.8490e-04) (hash(x)=6576136) -634 train 7.193376 (lr=2.8391e-04) (hash(x)=6157346) -635 train 7.188956 (lr=2.8292e-04) (hash(x)=6077647) -636 train 7.419818 (lr=2.8193e-04) (hash(x)=8369488) -637 train 7.209139 (lr=2.8094e-04) (hash(x)=6032381) -638 train 7.156520 (lr=2.7995e-04) (hash(x)=5924756) -639 train 7.175603 (lr=2.7896e-04) (hash(x)=8410716) -640 train 7.185459 (lr=2.7797e-04) (hash(x)=5803440) -641 train 7.264145 (lr=2.7698e-04) (hash(x)=6212516) -642 train 7.332349 (lr=2.7599e-04) (hash(x)=7165945) -643 train 7.047024 (lr=2.7500e-04) (hash(x)=5298545) -644 train 7.316221 (lr=2.7401e-04) (hash(x)=6281739) -645 train 7.271581 (lr=2.7302e-04) (hash(x)=5779073) -646 train 7.132289 (lr=2.7203e-04) (hash(x)=5090107) -647 train 7.183856 (lr=2.7104e-04) (hash(x)=6340947) -648 train 6.944769 (lr=2.7005e-04) (hash(x)=4741418) -649 train 6.879519 (lr=2.6906e-04) (hash(x)=6530441) -650 val loss 7.2311 -650 val perplexity 1381.7054 -650 train 7.410245 (lr=2.6807e-04) (hash(x)=6396041) -651 train 7.086882 (lr=2.6708e-04) (hash(x)=7818007) -652 train 7.111167 (lr=2.6609e-04) (hash(x)=6478457) -653 train 7.172120 (lr=2.6510e-04) (hash(x)=6277435) -654 train 7.139045 (lr=2.6411e-04) (hash(x)=6042369) -655 train 7.153538 (lr=2.6313e-04) (hash(x)=6226320) -656 train 7.178140 (lr=2.6214e-04) (hash(x)=5826883) -657 train 7.282806 (lr=2.6115e-04) (hash(x)=5463751) -658 train 7.215002 (lr=2.6016e-04) (hash(x)=6433080) -659 train 7.074018 (lr=2.5917e-04) (hash(x)=6579329) -660 train 7.071548 (lr=2.5819e-04) (hash(x)=4724703) -661 train 7.422923 (lr=2.5720e-04) (hash(x)=6660540) -662 train 7.238236 (lr=2.5621e-04) (hash(x)=5918756) -663 train 7.157944 (lr=2.5523e-04) (hash(x)=6491272) -664 train 7.066785 (lr=2.5424e-04) (hash(x)=5452863) -665 train 7.276259 (lr=2.5325e-04) (hash(x)=6766947) -666 train 7.639463 (lr=2.5227e-04) (hash(x)=7459504) -667 train 7.289299 (lr=2.5128e-04) (hash(x)=3721218) -668 train 7.473959 (lr=2.5030e-04) (hash(x)=7929571) -669 train 7.159019 (lr=2.4932e-04) (hash(x)=5229898) -670 train 7.181027 (lr=2.4833e-04) (hash(x)=6083090) -671 train 7.037563 (lr=2.4735e-04) (hash(x)=6054428) -672 train 7.206755 (lr=2.4637e-04) (hash(x)=6072563) -673 train 7.296102 (lr=2.4539e-04) (hash(x)=6290464) -674 train 7.388740 (lr=2.4441e-04) (hash(x)=6314742) -675 train 7.059244 (lr=2.4342e-04) (hash(x)=6904498) -676 train 7.233764 (lr=2.4244e-04) (hash(x)=5378107) -677 train 7.344265 (lr=2.4147e-04) (hash(x)=7765805) -678 train 7.155362 (lr=2.4049e-04) (hash(x)=5871280) -679 train 7.307432 (lr=2.3951e-04) (hash(x)=6543764) -680 train 7.180436 (lr=2.3853e-04) (hash(x)=7369665) -681 train 7.267678 (lr=2.3756e-04) (hash(x)=7204955) -682 train 7.211934 (lr=2.3658e-04) (hash(x)=5856543) -683 train 7.088581 (lr=2.3560e-04) (hash(x)=4423711) -684 train 7.074786 (lr=2.3463e-04) (hash(x)=5818153) -685 train 7.169012 (lr=2.3366e-04) (hash(x)=5343477) -686 train 7.356835 (lr=2.3268e-04) (hash(x)=6581702) -687 train 7.190972 (lr=2.3171e-04) (hash(x)=6595856) -688 train 7.127554 (lr=2.3074e-04) (hash(x)=5325378) -689 train 7.055649 (lr=2.2977e-04) (hash(x)=7229015) -690 train 7.222462 (lr=2.2880e-04) (hash(x)=5918186) -691 train 7.098609 (lr=2.2783e-04) (hash(x)=5916034) -692 train 7.088319 (lr=2.2687e-04) (hash(x)=5280722) -693 train 7.493737 (lr=2.2590e-04) (hash(x)=6939521) -694 train 7.246545 (lr=2.2493e-04) (hash(x)=5172566) -695 train 7.089564 (lr=2.2397e-04) (hash(x)=5492185) -696 train 6.947562 (lr=2.2300e-04) (hash(x)=5779011) -697 train 7.236990 (lr=2.2204e-04) (hash(x)=6898006) -698 train 7.073624 (lr=2.2108e-04) (hash(x)=5779217) -699 train 6.940072 (lr=2.2012e-04) (hash(x)=5462008) -700 val loss 7.2242 -700 val perplexity 1372.1897 -700 train 7.088466 (lr=2.1916e-04) (hash(x)=6243843) -701 train 7.150336 (lr=2.1820e-04) (hash(x)=7821902) -702 train 7.209005 (lr=2.1724e-04) (hash(x)=5222501) -703 train 7.181474 (lr=2.1629e-04) (hash(x)=6608108) -704 train 7.262262 (lr=2.1533e-04) (hash(x)=7602879) -705 train 7.212751 (lr=2.1438e-04) (hash(x)=6295394) -706 train 7.171757 (lr=2.1343e-04) (hash(x)=6579907) -707 train 7.052801 (lr=2.1247e-04) (hash(x)=6803449) -708 train 7.131286 (lr=2.1152e-04) (hash(x)=5413733) -709 train 7.093498 (lr=2.1057e-04) (hash(x)=7444134) -710 train 7.252778 (lr=2.0963e-04) (hash(x)=7028652) -711 train 7.042346 (lr=2.0868e-04) (hash(x)=5361923) -712 train 7.152476 (lr=2.0773e-04) (hash(x)=5478293) -713 train 7.147458 (lr=2.0679e-04) (hash(x)=7803039) -714 train 7.329758 (lr=2.0585e-04) (hash(x)=6469017) -715 train 7.218033 (lr=2.0491e-04) (hash(x)=7042578) -716 train 7.283916 (lr=2.0397e-04) (hash(x)=6927957) -717 train 7.084883 (lr=2.0303e-04) (hash(x)=6647007) -718 train 7.057630 (lr=2.0209e-04) (hash(x)=6230888) -719 train 7.336038 (lr=2.0115e-04) (hash(x)=6303658) -720 train 7.361563 (lr=2.0022e-04) (hash(x)=6769880) -721 train 7.188929 (lr=1.9929e-04) (hash(x)=6158927) -722 train 7.204041 (lr=1.9836e-04) (hash(x)=5991631) -723 train 7.059233 (lr=1.9743e-04) (hash(x)=6419656) -724 train 7.062278 (lr=1.9650e-04) (hash(x)=7739209) -725 train 6.998619 (lr=1.9557e-04) (hash(x)=7891271) -726 train 7.352912 (lr=1.9464e-04) (hash(x)=7171433) -727 train 7.144310 (lr=1.9372e-04) (hash(x)=7099888) -728 train 7.159133 (lr=1.9280e-04) (hash(x)=6103730) -729 train 7.263193 (lr=1.9188e-04) (hash(x)=6352424) -730 train 7.150970 (lr=1.9096e-04) (hash(x)=4893671) -731 train 7.118305 (lr=1.9004e-04) (hash(x)=5863145) -732 train 7.217144 (lr=1.8912e-04) (hash(x)=5502233) -733 train 7.122712 (lr=1.8821e-04) (hash(x)=6844597) -734 train 7.143062 (lr=1.8730e-04) (hash(x)=6744526) -735 train 7.281025 (lr=1.8639e-04) (hash(x)=6009861) -736 train 7.146035 (lr=1.8548e-04) (hash(x)=6152358) -737 train 7.067510 (lr=1.8457e-04) (hash(x)=5374957) -738 train 7.099597 (lr=1.8367e-04) (hash(x)=6495309) -739 train 7.255993 (lr=1.8276e-04) (hash(x)=3923225) -740 train 7.023756 (lr=1.8186e-04) (hash(x)=6255243) -741 train 7.191382 (lr=1.8096e-04) (hash(x)=5848862) -742 train 7.196548 (lr=1.8006e-04) (hash(x)=4535000) -743 train 7.074863 (lr=1.7916e-04) (hash(x)=4440634) -744 train 7.076263 (lr=1.7827e-04) (hash(x)=5222077) -745 train 7.109241 (lr=1.7738e-04) (hash(x)=4788998) -746 train 7.111574 (lr=1.7649e-04) (hash(x)=6108350) -747 train 7.025684 (lr=1.7560e-04) (hash(x)=7378165) -748 train 7.102706 (lr=1.7471e-04) (hash(x)=5475646) -749 train 7.099395 (lr=1.7382e-04) (hash(x)=4771243) -750 val loss 7.2055 -750 val perplexity 1346.7758 -750 train 6.982396 (lr=1.7294e-04) (hash(x)=6668088) -751 train 7.221345 (lr=1.7206e-04) (hash(x)=5716089) -752 train 7.171526 (lr=1.7118e-04) (hash(x)=6991946) -753 train 7.078938 (lr=1.7030e-04) (hash(x)=7991009) -754 train 7.177859 (lr=1.6943e-04) (hash(x)=6037018) -755 train 7.160283 (lr=1.6855e-04) (hash(x)=5348607) -756 train 7.290399 (lr=1.6768e-04) (hash(x)=5190526) -757 train 7.169240 (lr=1.6681e-04) (hash(x)=6036146) -758 train 7.068059 (lr=1.6595e-04) (hash(x)=5329783) -759 train 7.157620 (lr=1.6508e-04) (hash(x)=6658718) -760 train 7.038643 (lr=1.6422e-04) (hash(x)=4820939) -761 train 7.053461 (lr=1.6336e-04) (hash(x)=6176253) -762 train 7.019988 (lr=1.6250e-04) (hash(x)=5316750) -763 train 7.120662 (lr=1.6164e-04) (hash(x)=4542895) -764 train 6.906596 (lr=1.6079e-04) (hash(x)=5395673) -765 train 7.007916 (lr=1.5994e-04) (hash(x)=5549073) -766 train 7.245580 (lr=1.5909e-04) (hash(x)=5233723) -767 train 7.308990 (lr=1.5824e-04) (hash(x)=5342783) -768 train 7.228425 (lr=1.5740e-04) (hash(x)=5552448) -769 train 7.369246 (lr=1.5655e-04) (hash(x)=6549546) -770 train 7.035216 (lr=1.5571e-04) (hash(x)=3816493) -771 train 7.084671 (lr=1.5487e-04) (hash(x)=6170599) -772 train 7.568273 (lr=1.5404e-04) (hash(x)=6708759) -773 train 7.173415 (lr=1.5320e-04) (hash(x)=8483134) -774 train 7.767962 (lr=1.5237e-04) (hash(x)=5583732) -775 train 7.164863 (lr=1.5154e-04) (hash(x)=4865036) -776 train 7.088977 (lr=1.5072e-04) (hash(x)=7234336) -777 train 7.149169 (lr=1.4989e-04) (hash(x)=4433890) -778 train 7.451601 (lr=1.4907e-04) (hash(x)=7484636) -779 train 7.903167 (lr=1.4825e-04) (hash(x)=6738597) -780 train 7.129013 (lr=1.4744e-04) (hash(x)=6752421) -781 train 7.321273 (lr=1.4662e-04) (hash(x)=5459620) -782 train 7.243683 (lr=1.4581e-04) (hash(x)=6718131) -783 train 7.223713 (lr=1.4500e-04) (hash(x)=4604074) -784 train 7.085139 (lr=1.4419e-04) (hash(x)=5946124) -785 train 7.362234 (lr=1.4339e-04) (hash(x)=8045501) -786 train 7.455173 (lr=1.4259e-04) (hash(x)=5712725) -787 train 7.190992 (lr=1.4179e-04) (hash(x)=6176464) -788 train 7.221046 (lr=1.4099e-04) (hash(x)=6276702) -789 train 7.047091 (lr=1.4020e-04) (hash(x)=6127317) -790 train 7.199562 (lr=1.3941e-04) (hash(x)=7221374) -791 train 7.174991 (lr=1.3862e-04) (hash(x)=5571462) -792 train 7.170771 (lr=1.3783e-04) (hash(x)=7518021) -793 train 7.174084 (lr=1.3705e-04) (hash(x)=6640755) -794 train 7.255888 (lr=1.3627e-04) (hash(x)=6870405) -795 train 7.233688 (lr=1.3549e-04) (hash(x)=6147295) -796 train 7.105479 (lr=1.3471e-04) (hash(x)=6782583) -797 train 7.243057 (lr=1.3394e-04) (hash(x)=6120461) -798 train 7.161384 (lr=1.3317e-04) (hash(x)=5893870) -799 train 7.109607 (lr=1.3241e-04) (hash(x)=5123928) -800 val loss 7.1876 -800 val perplexity 1322.9208 -800 train 7.179597 (lr=1.3164e-04) (hash(x)=7037251) -801 train 7.171445 (lr=1.3088e-04) (hash(x)=5428813) -802 train 7.102864 (lr=1.3012e-04) (hash(x)=5550387) -803 train 7.173723 (lr=1.2936e-04) (hash(x)=6448586) -804 train 7.321678 (lr=1.2861e-04) (hash(x)=5916934) -805 train 7.279310 (lr=1.2786e-04) (hash(x)=8116987) -806 train 7.256086 (lr=1.2711e-04) (hash(x)=6210899) -807 train 7.352948 (lr=1.2637e-04) (hash(x)=5974342) -808 train 7.345386 (lr=1.2563e-04) (hash(x)=7236199) -809 train 7.280527 (lr=1.2489e-04) (hash(x)=5261336) -810 train 7.103971 (lr=1.2415e-04) (hash(x)=6310720) -811 train 7.146641 (lr=1.2342e-04) (hash(x)=5307056) -812 train 6.992956 (lr=1.2269e-04) (hash(x)=7356633) -813 train 7.108308 (lr=1.2196e-04) (hash(x)=5865119) -814 train 7.009826 (lr=1.2124e-04) (hash(x)=5979205) -815 train 7.152751 (lr=1.2052e-04) (hash(x)=6672380) -816 train 7.140406 (lr=1.1980e-04) (hash(x)=5565030) -817 train 7.126254 (lr=1.1908e-04) (hash(x)=6886810) -818 train 7.190171 (lr=1.1837e-04) (hash(x)=5926478) -819 train 7.388689 (lr=1.1766e-04) (hash(x)=6564071) -820 train 7.011282 (lr=1.1695e-04) (hash(x)=5024280) -821 train 7.020510 (lr=1.1625e-04) (hash(x)=7705089) -822 train 6.995688 (lr=1.1555e-04) (hash(x)=4037371) -823 train 7.091742 (lr=1.1485e-04) (hash(x)=5773073) -824 train 7.114347 (lr=1.1416e-04) (hash(x)=7158139) -825 train 6.951860 (lr=1.1347e-04) (hash(x)=5905976) -826 train 7.375481 (lr=1.1278e-04) (hash(x)=13897369) -827 train 8.458034 (lr=1.1210e-04) (hash(x)=6936653) -828 train 7.153047 (lr=1.1142e-04) (hash(x)=6592246) -829 train 7.118033 (lr=1.1074e-04) (hash(x)=6592773) -830 train 7.169332 (lr=1.1006e-04) (hash(x)=5461178) -831 train 6.943568 (lr=1.0939e-04) (hash(x)=6796551) -832 train 7.177258 (lr=1.0872e-04) (hash(x)=4721691) -833 train 7.084432 (lr=1.0806e-04) (hash(x)=6151589) -834 train 7.238265 (lr=1.0740e-04) (hash(x)=7008995) -835 train 7.566961 (lr=1.0674e-04) (hash(x)=7045164) -836 train 7.159750 (lr=1.0608e-04) (hash(x)=6614221) -837 train 7.197012 (lr=1.0543e-04) (hash(x)=6650506) -838 train 7.005482 (lr=1.0478e-04) (hash(x)=6363762) -839 train 7.162179 (lr=1.0413e-04) (hash(x)=7839748) -840 train 7.087656 (lr=1.0349e-04) (hash(x)=5124077) -841 train 7.506143 (lr=1.0285e-04) (hash(x)=6028671) -842 train 7.023764 (lr=1.0222e-04) (hash(x)=5427175) -843 train 7.339113 (lr=1.0158e-04) (hash(x)=6118408) -844 train 7.129816 (lr=1.0095e-04) (hash(x)=6022552) -845 train 7.144388 (lr=1.0033e-04) (hash(x)=5757526) -846 train 7.568955 (lr=9.9707e-05) (hash(x)=6476549) -847 train 6.933665 (lr=9.9088e-05) (hash(x)=6030172) -848 train 7.300003 (lr=9.8472e-05) (hash(x)=5917229) -849 train 7.381317 (lr=9.7860e-05) (hash(x)=6719882) -850 val loss 7.1759 -850 val perplexity 1307.5314 -850 train 7.238054 (lr=9.7252e-05) (hash(x)=5441498) -851 train 7.101161 (lr=9.6646e-05) (hash(x)=5028050) -852 train 7.143072 (lr=9.6044e-05) (hash(x)=8487491) -853 train 7.154226 (lr=9.5446e-05) (hash(x)=5682910) -854 train 7.322289 (lr=9.4851e-05) (hash(x)=6781362) -855 train 7.147408 (lr=9.4260e-05) (hash(x)=5747891) -856 train 7.192365 (lr=9.3672e-05) (hash(x)=7627661) -857 train 6.864371 (lr=9.3088e-05) (hash(x)=5734208) -858 train 7.014743 (lr=9.2507e-05) (hash(x)=6162015) -859 train 7.229060 (lr=9.1929e-05) (hash(x)=7024381) -860 train 7.429635 (lr=9.1356e-05) (hash(x)=5198498) -861 train 7.423097 (lr=9.0785e-05) (hash(x)=7814361) -862 train 7.289762 (lr=9.0219e-05) (hash(x)=7394995) -863 train 7.173902 (lr=8.9656e-05) (hash(x)=5765893) -864 train 6.983388 (lr=8.9096e-05) (hash(x)=4990435) -865 train 7.139946 (lr=8.8540e-05) (hash(x)=5572048) -866 train 7.274060 (lr=8.7988e-05) (hash(x)=7093293) -867 train 7.173663 (lr=8.7439e-05) (hash(x)=5610058) -868 train 7.063409 (lr=8.6894e-05) (hash(x)=6771468) -869 train 7.102000 (lr=8.6353e-05) (hash(x)=4459483) -870 train 6.990169 (lr=8.5815e-05) (hash(x)=4926546) -871 train 7.109494 (lr=8.5281e-05) (hash(x)=6758411) -872 train 7.072481 (lr=8.4751e-05) (hash(x)=7394277) -873 train 7.198714 (lr=8.4224e-05) (hash(x)=6701381) -874 train 7.534401 (lr=8.3701e-05) (hash(x)=8120966) -875 train 7.049159 (lr=8.3182e-05) (hash(x)=5416400) -876 train 7.063768 (lr=8.2666e-05) (hash(x)=6292778) -877 train 7.003854 (lr=8.2154e-05) (hash(x)=5919569) -878 train 7.318653 (lr=8.1646e-05) (hash(x)=7561740) -879 train 7.060314 (lr=8.1142e-05) (hash(x)=5282870) -880 train 7.101182 (lr=8.0641e-05) (hash(x)=5473238) -881 train 6.974599 (lr=8.0144e-05) (hash(x)=8072181) -882 train 7.002427 (lr=7.9651e-05) (hash(x)=6757322) -883 train 6.970382 (lr=7.9162e-05) (hash(x)=7996770) -884 train 7.051551 (lr=7.8676e-05) (hash(x)=3181021) -885 train 7.077705 (lr=7.8195e-05) (hash(x)=5093519) -886 train 7.067791 (lr=7.7717e-05) (hash(x)=5391352) -887 train 7.110921 (lr=7.7243e-05) (hash(x)=6270917) -888 train 7.084269 (lr=7.6772e-05) (hash(x)=5818195) -889 train 6.834678 (lr=7.6306e-05) (hash(x)=5852780) -890 train 6.753691 (lr=7.5843e-05) (hash(x)=5777928) -891 train 6.957564 (lr=7.5384e-05) (hash(x)=5327728) -892 train 6.994030 (lr=7.4930e-05) (hash(x)=7651281) -893 train 7.197446 (lr=7.4479e-05) (hash(x)=6260765) -894 train 7.099965 (lr=7.4031e-05) (hash(x)=6265102) -895 train 7.242281 (lr=7.3588e-05) (hash(x)=6212894) -896 train 7.025801 (lr=7.3149e-05) (hash(x)=6901967) -897 train 7.093394 (lr=7.2714e-05) (hash(x)=6724010) -898 train 7.095313 (lr=7.2282e-05) (hash(x)=6299033) -899 train 7.249408 (lr=7.1854e-05) (hash(x)=6059934) -900 val loss 7.1696 -900 val perplexity 1299.2709 -900 train 6.956734 (lr=7.1431e-05) (hash(x)=6029696) -901 train 6.891285 (lr=7.1011e-05) (hash(x)=5587382) -902 train 7.093894 (lr=7.0595e-05) (hash(x)=5890076) -903 train 7.015258 (lr=7.0184e-05) (hash(x)=7274108) -904 train 7.089938 (lr=6.9776e-05) (hash(x)=7975528) -905 train 7.150680 (lr=6.9372e-05) (hash(x)=6085396) -906 train 7.027868 (lr=6.8972e-05) (hash(x)=6724496) -907 train 7.018924 (lr=6.8576e-05) (hash(x)=4784666) -908 train 7.031313 (lr=6.8184e-05) (hash(x)=7193845) -909 train 7.189034 (lr=6.7796e-05) (hash(x)=6288638) -910 train 7.163491 (lr=6.7412e-05) (hash(x)=5685285) -911 train 7.132307 (lr=6.7033e-05) (hash(x)=7714288) -912 train 7.220439 (lr=6.6657e-05) (hash(x)=5983679) -913 train 7.180109 (lr=6.6285e-05) (hash(x)=5534748) -914 train 7.109372 (lr=6.5917e-05) (hash(x)=6545471) -915 train 7.098323 (lr=6.5553e-05) (hash(x)=6361270) -916 train 7.098313 (lr=6.5194e-05) (hash(x)=6257744) -917 train 7.121905 (lr=6.4838e-05) (hash(x)=4682956) -918 train 7.005388 (lr=6.4487e-05) (hash(x)=4521756) -919 train 7.138700 (lr=6.4139e-05) (hash(x)=7568935) -920 train 7.063842 (lr=6.3796e-05) (hash(x)=7969353) -921 train 7.250971 (lr=6.3457e-05) (hash(x)=7973311) -922 train 6.977053 (lr=6.3121e-05) (hash(x)=4843937) -923 train 7.095287 (lr=6.2790e-05) (hash(x)=6987352) -924 train 7.233639 (lr=6.2463e-05) (hash(x)=7179418) -925 train 6.882221 (lr=6.2140e-05) (hash(x)=5413904) -926 train 7.293038 (lr=6.1822e-05) (hash(x)=6028105) -927 train 7.184164 (lr=6.1507e-05) (hash(x)=6732924) -928 train 7.079037 (lr=6.1197e-05) (hash(x)=4547651) -929 train 7.230199 (lr=6.0890e-05) (hash(x)=6219754) -930 train 7.019924 (lr=6.0588e-05) (hash(x)=7465186) -931 train 7.161325 (lr=6.0290e-05) (hash(x)=6839070) -932 train 7.043342 (lr=5.9996e-05) (hash(x)=5390324) -933 train 7.011817 (lr=5.9706e-05) (hash(x)=6090120) -934 train 7.653197 (lr=5.9421e-05) (hash(x)=7123181) -935 train 7.308783 (lr=5.9139e-05) (hash(x)=7115176) -936 train 7.297654 (lr=5.8862e-05) (hash(x)=7016990) -937 train 7.075312 (lr=5.8589e-05) (hash(x)=4989299) -938 train 7.101528 (lr=5.8320e-05) (hash(x)=6783311) -939 train 7.070540 (lr=5.8056e-05) (hash(x)=7497590) -940 train 7.288990 (lr=5.7795e-05) (hash(x)=6767514) -941 train 7.044348 (lr=5.7539e-05) (hash(x)=3977557) -942 train 7.166264 (lr=5.7287e-05) (hash(x)=4806492) -943 train 7.091781 (lr=5.7039e-05) (hash(x)=5524165) -944 train 7.135848 (lr=5.6796e-05) (hash(x)=4930752) -945 train 7.092951 (lr=5.6556e-05) (hash(x)=5124936) -946 train 6.994030 (lr=5.6321e-05) (hash(x)=6877351) -947 train 7.281543 (lr=5.6090e-05) (hash(x)=5522119) -948 train 7.080702 (lr=5.5864e-05) (hash(x)=6183512) -949 train 6.984340 (lr=5.5641e-05) (hash(x)=5030865) -950 val loss 7.1528 -950 val perplexity 1277.6420 -950 train 7.097123 (lr=5.5423e-05) (hash(x)=6619812) -951 train 7.098376 (lr=5.5209e-05) (hash(x)=6411783) -952 train 7.088872 (lr=5.4999e-05) (hash(x)=6748982) -953 train 7.000419 (lr=5.4794e-05) (hash(x)=6581937) -954 train 7.102852 (lr=5.4593e-05) (hash(x)=7881022) -955 train 7.066958 (lr=5.4396e-05) (hash(x)=5116910) -956 train 6.857338 (lr=5.4203e-05) (hash(x)=4880833) -957 train 6.900289 (lr=5.4015e-05) (hash(x)=7353459) -958 train 6.972719 (lr=5.3831e-05) (hash(x)=4951302) -959 train 6.879022 (lr=5.3651e-05) (hash(x)=6344535) -960 train 7.476079 (lr=5.3476e-05) (hash(x)=7411763) -961 train 7.066309 (lr=5.3305e-05) (hash(x)=5840169) -962 train 7.168903 (lr=5.3138e-05) (hash(x)=5784788) -963 train 6.974478 (lr=5.2975e-05) (hash(x)=6754290) -964 train 7.261588 (lr=5.2817e-05) (hash(x)=6369963) -965 train 7.335275 (lr=5.2663e-05) (hash(x)=6484573) -966 train 6.908237 (lr=5.2513e-05) (hash(x)=6516338) -967 train 6.942739 (lr=5.2368e-05) (hash(x)=5260125) -968 train 7.083892 (lr=5.2227e-05) (hash(x)=5781624) -969 train 6.876302 (lr=5.2090e-05) (hash(x)=4881179) -970 train 6.999709 (lr=5.1957e-05) (hash(x)=6707821) -971 train 7.147691 (lr=5.1829e-05) (hash(x)=5001634) -972 train 7.025114 (lr=5.1705e-05) (hash(x)=4402949) -973 train 7.027910 (lr=5.1586e-05) (hash(x)=7424810) -974 train 6.900013 (lr=5.1471e-05) (hash(x)=4814803) -975 train 6.823050 (lr=5.1360e-05) (hash(x)=5176431) -976 train 7.021018 (lr=5.1253e-05) (hash(x)=5769393) -977 train 6.965964 (lr=5.1151e-05) (hash(x)=5421624) -978 train 7.193567 (lr=5.1053e-05) (hash(x)=5999773) -979 train 6.874374 (lr=5.0960e-05) (hash(x)=5674439) -980 train 6.981283 (lr=5.0871e-05) (hash(x)=6345351) -981 train 6.917695 (lr=5.0786e-05) (hash(x)=5819157) -982 train 7.177959 (lr=5.0705e-05) (hash(x)=11159355) -983 train 7.118654 (lr=5.0629e-05) (hash(x)=6506856) -984 train 7.013239 (lr=5.0557e-05) (hash(x)=6331023) -985 train 6.918195 (lr=5.0490e-05) (hash(x)=6119124) -986 train 7.119637 (lr=5.0427e-05) (hash(x)=8142528) -987 train 7.305790 (lr=5.0368e-05) (hash(x)=6241669) -988 train 6.927010 (lr=5.0314e-05) (hash(x)=3852991) -989 train 6.660688 (lr=5.0263e-05) (hash(x)=4992756) -990 train 7.372957 (lr=5.0218e-05) (hash(x)=7097145) -991 train 7.146570 (lr=5.0176e-05) (hash(x)=7277927) -992 train 7.228550 (lr=5.0139e-05) (hash(x)=5661400) -993 train 7.135367 (lr=5.0107e-05) (hash(x)=6622097) -994 train 7.267321 (lr=5.0078e-05) (hash(x)=5016804) -995 train 7.375402 (lr=5.0054e-05) (hash(x)=7026582) -996 train 7.121544 (lr=5.0035e-05) (hash(x)=5639136) -997 train 7.285857 (lr=5.0020e-05) (hash(x)=5840987) -998 train 6.901052 (lr=5.0009e-05) (hash(x)=5265410) -999 val loss 7.1461 -999 val perplexity 1269.0940 -999 train 6.878165 (lr=5.0002e-05) (hash(x)=4351074) +3 train 11.666055 (lr=6.9930e-06) (hash(x)=6328012) +4 train 11.645175 (lr=8.7413e-06) (hash(x)=7052161) +5 train 11.619282 (lr=1.0490e-05) (hash(x)=5556098) +6 train 11.574085 (lr=1.2238e-05) (hash(x)=4696943) +7 train 11.522718 (lr=1.3986e-05) (hash(x)=6219138) +8 train 11.467787 (lr=1.5734e-05) (hash(x)=6049878) +9 train 11.429907 (lr=1.7483e-05) (hash(x)=5491972) +10 train 11.385011 (lr=1.9231e-05) (hash(x)=8075458) +11 train 11.275307 (lr=2.0979e-05) (hash(x)=5917741) +12 train 11.238571 (lr=2.2727e-05) (hash(x)=5750403) +13 train 11.161193 (lr=2.4476e-05) (hash(x)=6112458) +14 train 11.104759 (lr=2.6224e-05) (hash(x)=5806490) +15 train 11.001119 (lr=2.7972e-05) (hash(x)=6568379) +16 train 10.912309 (lr=2.9720e-05) (hash(x)=7212403) +17 train 10.832689 (lr=3.1469e-05) (hash(x)=7386082) +18 train 10.783924 (lr=3.3217e-05) (hash(x)=6359743) +19 train 10.718146 (lr=3.4965e-05) (hash(x)=6151674) +20 train 10.678718 (lr=3.6713e-05) (hash(x)=7168704) +21 train 10.633057 (lr=3.8462e-05) (hash(x)=7859060) +22 train 10.551099 (lr=4.0210e-05) (hash(x)=6976239) +23 train 10.546165 (lr=4.1958e-05) (hash(x)=6391506) +24 train 10.532306 (lr=4.3706e-05) (hash(x)=5245999) +25 train 10.475378 (lr=4.5455e-05) (hash(x)=5985675) +26 train 10.383001 (lr=4.7203e-05) (hash(x)=4355733) +27 train 10.548789 (lr=4.8951e-05) (hash(x)=6984772) +28 train 10.399026 (lr=5.0699e-05) (hash(x)=6244096) +29 train 10.413669 (lr=5.2448e-05) (hash(x)=6603717) +30 train 10.318188 (lr=5.4196e-05) (hash(x)=5669522) +31 train 10.303373 (lr=5.5944e-05) (hash(x)=6190579) +32 train 10.360798 (lr=5.7692e-05) (hash(x)=4912983) +33 train 10.234416 (lr=5.9441e-05) (hash(x)=7276303) +34 train 10.300045 (lr=6.1189e-05) (hash(x)=5479947) +35 train 10.394086 (lr=6.2937e-05) (hash(x)=6630378) +36 train 10.322168 (lr=6.4685e-05) (hash(x)=8097010) +37 train 10.373155 (lr=6.6434e-05) (hash(x)=9989744) +38 train 10.245996 (lr=6.8182e-05) (hash(x)=6694932) +39 train 10.169633 (lr=6.9930e-05) (hash(x)=6317894) +40 train 10.077536 (lr=7.1678e-05) (hash(x)=5046327) +41 train 10.146451 (lr=7.3427e-05) (hash(x)=7947703) +42 train 10.004020 (lr=7.5175e-05) (hash(x)=5916068) +43 train 10.094974 (lr=7.6923e-05) (hash(x)=5777498) +44 train 10.013888 (lr=7.8671e-05) (hash(x)=5753092) +45 train 9.985736 (lr=8.0420e-05) (hash(x)=7723226) +46 train 9.960760 (lr=8.2168e-05) (hash(x)=7007016) +47 train 9.873100 (lr=8.3916e-05) (hash(x)=6491229) +48 train 9.903370 (lr=8.5664e-05) (hash(x)=6390752) +49 train 10.005838 (lr=8.7413e-05) (hash(x)=6019389) +50 val loss 9.8617 +50 val perplexity 19181.0508 +50 train 9.854578 (lr=8.9161e-05) (hash(x)=7662067) +51 train 9.837037 (lr=9.0909e-05) (hash(x)=4648609) +52 train 9.756139 (lr=9.2657e-05) (hash(x)=4725966) +53 train 9.699567 (lr=9.4406e-05) (hash(x)=5558355) +54 train 9.725101 (lr=9.6154e-05) (hash(x)=6524933) +55 train 9.657341 (lr=9.7902e-05) (hash(x)=6369326) +56 train 9.607556 (lr=9.9650e-05) (hash(x)=6022625) +57 train 9.528498 (lr=1.0140e-04) (hash(x)=4906853) +58 train 9.329304 (lr=1.0315e-04) (hash(x)=5589269) +59 train 9.436498 (lr=1.0490e-04) (hash(x)=6437376) +60 train 9.463205 (lr=1.0664e-04) (hash(x)=7304892) +61 train 9.403612 (lr=1.0839e-04) (hash(x)=7084093) +62 train 9.401078 (lr=1.1014e-04) (hash(x)=5908178) +63 train 9.165181 (lr=1.1189e-04) (hash(x)=7048804) +64 train 9.223444 (lr=1.1364e-04) (hash(x)=6085549) +65 train 9.224805 (lr=1.1538e-04) (hash(x)=5752594) +66 train 9.002790 (lr=1.1713e-04) (hash(x)=7662769) +67 train 8.845735 (lr=1.1888e-04) (hash(x)=6393520) +68 train 9.073675 (lr=1.2063e-04) (hash(x)=5942867) +69 train 9.050341 (lr=1.2238e-04) (hash(x)=6793550) +70 train 8.869069 (lr=1.2413e-04) (hash(x)=7105976) +71 train 8.882218 (lr=1.2587e-04) (hash(x)=6581348) +72 train 8.790711 (lr=1.2762e-04) (hash(x)=5555598) +73 train 8.737088 (lr=1.2937e-04) (hash(x)=6235837) +74 train 8.651990 (lr=1.3112e-04) (hash(x)=5591770) +75 train 8.864938 (lr=1.3287e-04) (hash(x)=7083021) +76 train 8.684290 (lr=1.3462e-04) (hash(x)=7281348) +77 train 8.723883 (lr=1.3636e-04) (hash(x)=6155821) +78 train 8.530906 (lr=1.3811e-04) (hash(x)=5736241) +79 train 8.432609 (lr=1.3986e-04) (hash(x)=5657123) +80 train 8.382647 (lr=1.4161e-04) (hash(x)=6452095) +81 train 8.309020 (lr=1.4336e-04) (hash(x)=5312267) +82 train 8.158272 (lr=1.4510e-04) (hash(x)=5434493) +83 train 8.382386 (lr=1.4685e-04) (hash(x)=6830813) +84 train 8.202319 (lr=1.4860e-04) (hash(x)=4752771) +85 train 8.299712 (lr=1.5035e-04) (hash(x)=6424933) +86 train 8.198415 (lr=1.5210e-04) (hash(x)=5786517) +87 train 8.263995 (lr=1.5385e-04) (hash(x)=6680023) +88 train 8.168283 (lr=1.5559e-04) (hash(x)=6474729) +89 train 8.174347 (lr=1.5734e-04) (hash(x)=7523279) +90 train 7.964462 (lr=1.5909e-04) (hash(x)=5508768) +91 train 8.147779 (lr=1.6084e-04) (hash(x)=6635925) +92 train 8.020328 (lr=1.6259e-04) (hash(x)=6663801) +93 train 7.997099 (lr=1.6434e-04) (hash(x)=5869441) +94 train 8.055408 (lr=1.6608e-04) (hash(x)=6698878) +95 train 7.954882 (lr=1.6783e-04) (hash(x)=6349004) +96 train 7.957451 (lr=1.6958e-04) (hash(x)=4986137) +97 train 7.736154 (lr=1.7133e-04) (hash(x)=6008454) +98 train 7.805086 (lr=1.7308e-04) (hash(x)=6550770) +99 train 7.950117 (lr=1.7483e-04) (hash(x)=7682741) +100 val loss 7.8950 +100 val perplexity 2683.8577 +100 train 8.008267 (lr=1.7657e-04) (hash(x)=7892158) +101 train 7.866814 (lr=1.7832e-04) (hash(x)=7794028) +102 train 7.858949 (lr=1.8007e-04) (hash(x)=7093523) +103 train 7.906054 (lr=1.8182e-04) (hash(x)=6166062) +104 train 7.840604 (lr=1.8357e-04) (hash(x)=6645781) +105 train 7.812424 (lr=1.8531e-04) (hash(x)=4811192) +106 train 7.727083 (lr=1.8706e-04) (hash(x)=5970866) +107 train 7.732053 (lr=1.8881e-04) (hash(x)=7822680) +108 train 7.706115 (lr=1.9056e-04) (hash(x)=6317317) +109 train 7.812702 (lr=1.9231e-04) (hash(x)=6431409) +110 train 7.825748 (lr=1.9406e-04) (hash(x)=6653337) +111 train 7.759559 (lr=1.9580e-04) (hash(x)=5323032) +112 train 7.641473 (lr=1.9755e-04) (hash(x)=5125339) +113 train 7.569887 (lr=1.9930e-04) (hash(x)=7363286) +114 train 7.982043 (lr=2.0105e-04) (hash(x)=7670050) +115 train 7.722515 (lr=2.0280e-04) (hash(x)=5616075) +116 train 7.775238 (lr=2.0455e-04) (hash(x)=6593764) +117 train 7.849370 (lr=2.0629e-04) (hash(x)=5672608) +118 train 7.661986 (lr=2.0804e-04) (hash(x)=6828653) +119 train 7.664970 (lr=2.0979e-04) (hash(x)=6839867) +120 train 7.816816 (lr=2.1154e-04) (hash(x)=8426992) +121 train 7.473126 (lr=2.1329e-04) (hash(x)=4916928) +122 train 7.689544 (lr=2.1503e-04) (hash(x)=6484050) +123 train 7.798779 (lr=2.1678e-04) (hash(x)=8353379) +124 train 7.709025 (lr=2.1853e-04) (hash(x)=6552510) +125 train 7.678270 (lr=2.2028e-04) (hash(x)=4838871) +126 train 7.421080 (lr=2.2203e-04) (hash(x)=3021697) +127 train 7.580019 (lr=2.2378e-04) (hash(x)=6795665) +128 train 7.599019 (lr=2.2552e-04) (hash(x)=5486935) +129 train 7.789984 (lr=2.2727e-04) (hash(x)=6678038) +130 train 7.820652 (lr=2.2902e-04) (hash(x)=6657714) +131 train 7.689227 (lr=2.3077e-04) (hash(x)=6112215) +132 train 7.742520 (lr=2.3252e-04) (hash(x)=8353143) +133 train 7.793004 (lr=2.3427e-04) (hash(x)=5915361) +134 train 7.683446 (lr=2.3601e-04) (hash(x)=6254885) +135 train 7.695318 (lr=2.3776e-04) (hash(x)=5771588) +136 train 7.670632 (lr=2.3951e-04) (hash(x)=5561507) +137 train 7.608744 (lr=2.4126e-04) (hash(x)=5688829) +138 train 7.615840 (lr=2.4301e-04) (hash(x)=5371951) +139 train 7.785644 (lr=2.4476e-04) (hash(x)=5443305) +140 train 7.750953 (lr=2.4650e-04) (hash(x)=5016757) +141 train 7.749409 (lr=2.4825e-04) (hash(x)=6901933) +142 train 7.726532 (lr=2.5000e-04) (hash(x)=6019085) +143 train 7.562340 (lr=2.5175e-04) (hash(x)=4294425) +144 train 7.673570 (lr=2.5350e-04) (hash(x)=6095229) +145 train 7.497625 (lr=2.5524e-04) (hash(x)=4363941) +146 train 7.578037 (lr=2.5699e-04) (hash(x)=4693798) +147 train 8.139331 (lr=2.5874e-04) (hash(x)=5486335) +148 train 7.949450 (lr=2.6049e-04) (hash(x)=7907450) +149 train 7.777784 (lr=2.6224e-04) (hash(x)=7295165) +150 val loss 7.6588 +150 val perplexity 2119.2546 +150 train 7.710848 (lr=2.6399e-04) (hash(x)=6814026) +151 train 7.788910 (lr=2.6573e-04) (hash(x)=6267424) +152 train 7.813081 (lr=2.6748e-04) (hash(x)=8086437) +153 train 7.856061 (lr=2.6923e-04) (hash(x)=5270452) +154 train 7.696571 (lr=2.7098e-04) (hash(x)=6420820) +155 train 7.598413 (lr=2.7273e-04) (hash(x)=6305297) +156 train 7.735969 (lr=2.7448e-04) (hash(x)=7889849) +157 train 8.112687 (lr=2.7622e-04) (hash(x)=6040077) +158 train 8.113515 (lr=2.7797e-04) (hash(x)=5652497) +159 train 7.693543 (lr=2.7972e-04) (hash(x)=7130251) +160 train 7.560094 (lr=2.8147e-04) (hash(x)=6610177) +161 train 7.608335 (lr=2.8322e-04) (hash(x)=6508350) +162 train 7.768837 (lr=2.8497e-04) (hash(x)=6994983) +163 train 7.714787 (lr=2.8671e-04) (hash(x)=5859576) +164 train 7.289391 (lr=2.8846e-04) (hash(x)=5487065) +165 train 7.524610 (lr=2.9021e-04) (hash(x)=4892065) +166 train 7.421996 (lr=2.9196e-04) (hash(x)=4933674) +167 train 7.688111 (lr=2.9371e-04) (hash(x)=7317289) +168 train 7.790551 (lr=2.9545e-04) (hash(x)=6811522) +169 train 7.619090 (lr=2.9720e-04) (hash(x)=5510218) +170 train 7.776705 (lr=2.9895e-04) (hash(x)=7304235) +171 train 7.929608 (lr=3.0070e-04) (hash(x)=6752265) +172 train 7.633643 (lr=3.0245e-04) (hash(x)=5994476) +173 train 7.600718 (lr=3.0420e-04) (hash(x)=6530867) +174 train 7.706640 (lr=3.0594e-04) (hash(x)=5746260) +175 train 7.654285 (lr=3.0769e-04) (hash(x)=5790078) +176 train 7.686028 (lr=3.0944e-04) (hash(x)=6430135) +177 train 7.753693 (lr=3.1119e-04) (hash(x)=7614023) +178 train 7.744906 (lr=3.1294e-04) (hash(x)=5244861) +179 train 7.718095 (lr=3.1469e-04) (hash(x)=5245146) +180 train 7.615874 (lr=3.1643e-04) (hash(x)=6415565) +181 train 7.678169 (lr=3.1818e-04) (hash(x)=5786972) +182 train 7.703015 (lr=3.1993e-04) (hash(x)=6131703) +183 train 7.729957 (lr=3.2168e-04) (hash(x)=6346459) +184 train 7.765361 (lr=3.2343e-04) (hash(x)=6504131) +185 train 7.730519 (lr=3.2517e-04) (hash(x)=5209234) +186 train 7.649171 (lr=3.2692e-04) (hash(x)=6163272) +187 train 7.658487 (lr=3.2867e-04) (hash(x)=5676768) +188 train 7.723412 (lr=3.3042e-04) (hash(x)=6090561) +189 train 7.854752 (lr=3.3217e-04) (hash(x)=5863092) +190 train 7.771751 (lr=3.3392e-04) (hash(x)=7201312) +191 train 7.853581 (lr=3.3566e-04) (hash(x)=7019489) +192 train 7.615558 (lr=3.3741e-04) (hash(x)=6225608) +193 train 7.700966 (lr=3.3916e-04) (hash(x)=5483019) +194 train 7.647720 (lr=3.4091e-04) (hash(x)=5903258) +195 train 7.685577 (lr=3.4266e-04) (hash(x)=5968716) +196 train 7.677250 (lr=3.4441e-04) (hash(x)=5778017) +197 train 7.405304 (lr=3.4615e-04) (hash(x)=7780194) +198 train 7.611497 (lr=3.4790e-04) (hash(x)=6140998) +199 train 7.595297 (lr=3.4965e-04) (hash(x)=3784321) +200 val loss 7.6274 +200 val perplexity 2053.6846 +200 train 7.624048 (lr=3.5140e-04) (hash(x)=5860821) +201 train 7.677978 (lr=3.5315e-04) (hash(x)=7774109) +202 train 7.844927 (lr=3.5490e-04) (hash(x)=7997664) +203 train 7.804366 (lr=3.5664e-04) (hash(x)=6576749) +204 train 7.717428 (lr=3.5839e-04) (hash(x)=7266655) +205 train 7.683898 (lr=3.6014e-04) (hash(x)=7072404) +206 train 7.618389 (lr=3.6189e-04) (hash(x)=6626459) +207 train 7.615627 (lr=3.6364e-04) (hash(x)=6556025) +208 train 7.649898 (lr=3.6538e-04) (hash(x)=5942129) +209 train 7.784403 (lr=3.6713e-04) (hash(x)=7325027) +210 train 7.784254 (lr=3.6888e-04) (hash(x)=7322467) +211 train 7.716784 (lr=3.7063e-04) (hash(x)=6373412) +212 train 7.491305 (lr=3.7238e-04) (hash(x)=7332255) +213 train 7.758969 (lr=3.7413e-04) (hash(x)=5262868) +214 train 7.516233 (lr=3.7587e-04) (hash(x)=5688247) +215 train 7.667155 (lr=3.7762e-04) (hash(x)=8055563) +216 train 7.670269 (lr=3.7937e-04) (hash(x)=5352405) +217 train 7.726042 (lr=3.8112e-04) (hash(x)=5932790) +218 train 7.687083 (lr=3.8287e-04) (hash(x)=6249312) +219 train 7.619506 (lr=3.8462e-04) (hash(x)=5680154) +220 train 7.718568 (lr=3.8636e-04) (hash(x)=8156280) +221 train 7.652415 (lr=3.8811e-04) (hash(x)=5914217) +222 train 7.513154 (lr=3.8986e-04) (hash(x)=7120215) +223 train 7.681170 (lr=3.9161e-04) (hash(x)=6424128) +224 train 7.448785 (lr=3.9336e-04) (hash(x)=4390027) +225 train 7.633909 (lr=3.9510e-04) (hash(x)=7804089) +226 train 7.734452 (lr=3.9685e-04) (hash(x)=7130267) +227 train 7.524920 (lr=3.9860e-04) (hash(x)=6490149) +228 train 7.599020 (lr=4.0035e-04) (hash(x)=9276378) +229 train 7.612488 (lr=4.0210e-04) (hash(x)=6283540) +230 train 7.589837 (lr=4.0385e-04) (hash(x)=5781680) +231 train 7.540930 (lr=4.0559e-04) (hash(x)=5728337) +232 train 7.518760 (lr=4.0734e-04) (hash(x)=6278202) +233 train 7.611977 (lr=4.0909e-04) (hash(x)=7400272) +234 train 7.578421 (lr=4.1084e-04) (hash(x)=5795128) +235 train 7.565903 (lr=4.1259e-04) (hash(x)=6473432) +236 train 7.570687 (lr=4.1434e-04) (hash(x)=5201502) +237 train 7.800767 (lr=4.1608e-04) (hash(x)=6922646) +238 train 7.507735 (lr=4.1783e-04) (hash(x)=5484641) +239 train 7.572129 (lr=4.1958e-04) (hash(x)=7277141) +240 train 7.592578 (lr=4.2133e-04) (hash(x)=5604614) +241 train 7.639655 (lr=4.2308e-04) (hash(x)=7443124) +242 train 7.648936 (lr=4.2483e-04) (hash(x)=5601968) +243 train 7.535066 (lr=4.2657e-04) (hash(x)=5632735) +244 train 7.558194 (lr=4.2832e-04) (hash(x)=5594810) +245 train 7.395972 (lr=4.3007e-04) (hash(x)=5881015) +246 train 7.522896 (lr=4.3182e-04) (hash(x)=6865361) +247 train 7.633927 (lr=4.3357e-04) (hash(x)=5809411) +248 train 7.605800 (lr=4.3531e-04) (hash(x)=6293025) +249 train 7.549047 (lr=4.3706e-04) (hash(x)=7232964) +250 val loss 7.5480 +250 val perplexity 1896.9547 +250 train 7.482858 (lr=4.3881e-04) (hash(x)=5646619) +251 train 7.602551 (lr=4.4056e-04) (hash(x)=6171829) +252 train 7.659615 (lr=4.4231e-04) (hash(x)=7787552) +253 train 7.608674 (lr=4.4406e-04) (hash(x)=5884456) +254 train 7.634095 (lr=4.4580e-04) (hash(x)=6752162) +255 train 7.533070 (lr=4.4755e-04) (hash(x)=5077031) +256 train 7.725801 (lr=4.4930e-04) (hash(x)=6883481) +257 train 7.587954 (lr=4.5105e-04) (hash(x)=6248895) +258 train 7.451650 (lr=4.5280e-04) (hash(x)=6636615) +259 train 7.657730 (lr=4.5455e-04) (hash(x)=6918004) +260 train 7.561597 (lr=4.5629e-04) (hash(x)=7302874) +261 train 7.659683 (lr=4.5804e-04) (hash(x)=6482466) +262 train 7.508364 (lr=4.5979e-04) (hash(x)=7298317) +263 train 7.547161 (lr=4.6154e-04) (hash(x)=6588573) +264 train 7.531609 (lr=4.6329e-04) (hash(x)=6229630) +265 train 7.604511 (lr=4.6503e-04) (hash(x)=6136939) +266 train 7.369548 (lr=4.6678e-04) (hash(x)=6394645) +267 train 7.599665 (lr=4.6853e-04) (hash(x)=7040157) +268 train 7.638434 (lr=4.7028e-04) (hash(x)=7041858) +269 train 7.541422 (lr=4.7203e-04) (hash(x)=6455595) +270 train 7.482071 (lr=4.7378e-04) (hash(x)=6480443) +271 train 7.655662 (lr=4.7552e-04) (hash(x)=4122983) +272 train 7.471832 (lr=4.7727e-04) (hash(x)=7672190) +273 train 7.503120 (lr=4.7902e-04) (hash(x)=4724052) +274 train 7.440013 (lr=4.8077e-04) (hash(x)=6654267) +275 train 7.436909 (lr=4.8252e-04) (hash(x)=6820797) +276 train 7.507745 (lr=4.8427e-04) (hash(x)=6458662) +277 train 7.920717 (lr=4.8601e-04) (hash(x)=7477594) +278 train 7.567708 (lr=4.8776e-04) (hash(x)=5876574) +279 train 7.287622 (lr=4.8951e-04) (hash(x)=6146305) +280 train 7.460553 (lr=4.9126e-04) (hash(x)=6162080) +281 train 7.412753 (lr=4.9301e-04) (hash(x)=6814831) +282 train 7.543858 (lr=4.9476e-04) (hash(x)=7138295) +283 train 7.323990 (lr=4.9650e-04) (hash(x)=5548298) +284 train 7.421038 (lr=4.9825e-04) (hash(x)=6265078) +285 train 7.811182 (lr=5.0000e-04) (hash(x)=7609416) +286 train 7.490105 (lr=5.0000e-04) (hash(x)=6909367) +287 train 7.610667 (lr=5.0000e-04) (hash(x)=7574342) +288 train 7.403266 (lr=4.9999e-04) (hash(x)=8859748) +289 train 7.357216 (lr=4.9998e-04) (hash(x)=5906937) +290 train 7.397072 (lr=4.9997e-04) (hash(x)=7243024) +291 train 7.503991 (lr=4.9995e-04) (hash(x)=8013471) +292 train 7.404248 (lr=4.9992e-04) (hash(x)=5659461) +293 train 7.474968 (lr=4.9989e-04) (hash(x)=6146213) +294 train 7.506311 (lr=4.9986e-04) (hash(x)=6602917) +295 train 7.407012 (lr=4.9982e-04) (hash(x)=6709902) +296 train 7.509507 (lr=4.9978e-04) (hash(x)=8154341) +297 train 7.662838 (lr=4.9974e-04) (hash(x)=6402571) +298 train 7.420599 (lr=4.9969e-04) (hash(x)=5605466) +299 train 7.394629 (lr=4.9963e-04) (hash(x)=7683614) +300 val loss 7.4446 +300 val perplexity 1710.5594 +300 train 7.484637 (lr=4.9957e-04) (hash(x)=5421572) +301 train 7.326612 (lr=4.9951e-04) (hash(x)=5453026) +302 train 7.397893 (lr=4.9944e-04) (hash(x)=6437746) +303 train 7.308720 (lr=4.9937e-04) (hash(x)=6260017) +304 train 7.406430 (lr=4.9929e-04) (hash(x)=6119053) +305 train 7.580610 (lr=4.9921e-04) (hash(x)=6591466) +306 train 7.484182 (lr=4.9913e-04) (hash(x)=5652701) +307 train 7.449085 (lr=4.9904e-04) (hash(x)=5501472) +308 train 7.619984 (lr=4.9895e-04) (hash(x)=6160695) +309 train 7.396847 (lr=4.9885e-04) (hash(x)=5871698) +310 train 7.351732 (lr=4.9875e-04) (hash(x)=7301184) +311 train 7.279935 (lr=4.9864e-04) (hash(x)=4282052) +312 train 7.503771 (lr=4.9853e-04) (hash(x)=5679330) +313 train 7.355653 (lr=4.9841e-04) (hash(x)=7824660) +314 train 7.413687 (lr=4.9829e-04) (hash(x)=4857318) +315 train 7.329000 (lr=4.9817e-04) (hash(x)=5954950) +316 train 7.395568 (lr=4.9804e-04) (hash(x)=5758178) +317 train 7.406400 (lr=4.9791e-04) (hash(x)=5484656) +318 train 7.398585 (lr=4.9777e-04) (hash(x)=6818913) +319 train 7.610539 (lr=4.9763e-04) (hash(x)=7031328) +320 train 7.449712 (lr=4.9749e-04) (hash(x)=6837621) +321 train 7.475561 (lr=4.9734e-04) (hash(x)=9157069) +322 train 7.703325 (lr=4.9718e-04) (hash(x)=6509536) +323 train 7.411084 (lr=4.9702e-04) (hash(x)=5996883) +324 train 7.669407 (lr=4.9686e-04) (hash(x)=6850868) +325 train 7.593994 (lr=4.9670e-04) (hash(x)=7645447) +326 train 7.608600 (lr=4.9652e-04) (hash(x)=6717515) +327 train 7.727924 (lr=4.9635e-04) (hash(x)=6336164) +328 train 7.437611 (lr=4.9617e-04) (hash(x)=6897445) +329 train 7.341949 (lr=4.9598e-04) (hash(x)=5224240) +330 train 7.495986 (lr=4.9580e-04) (hash(x)=6612945) +331 train 7.955403 (lr=4.9560e-04) (hash(x)=5447801) +332 train 7.488016 (lr=4.9541e-04) (hash(x)=7308579) +333 train 7.359042 (lr=4.9521e-04) (hash(x)=4155598) +334 train 7.363286 (lr=4.9500e-04) (hash(x)=6106773) +335 train 7.423721 (lr=4.9479e-04) (hash(x)=7482744) +336 train 7.494067 (lr=4.9458e-04) (hash(x)=6310687) +337 train 7.365700 (lr=4.9436e-04) (hash(x)=4733414) +338 train 7.475525 (lr=4.9414e-04) (hash(x)=6979734) +339 train 7.272816 (lr=4.9391e-04) (hash(x)=7806284) +340 train 7.275695 (lr=4.9368e-04) (hash(x)=5080536) +341 train 7.469730 (lr=4.9344e-04) (hash(x)=7236478) +342 train 7.423913 (lr=4.9320e-04) (hash(x)=6619318) +343 train 7.327144 (lr=4.9296e-04) (hash(x)=4656255) +344 train 7.271228 (lr=4.9271e-04) (hash(x)=5546888) +345 train 7.720705 (lr=4.9246e-04) (hash(x)=9298325) +346 train 7.414561 (lr=4.9220e-04) (hash(x)=5994232) +347 train 7.394266 (lr=4.9194e-04) (hash(x)=6287524) +348 train 7.510101 (lr=4.9168e-04) (hash(x)=6200049) +349 train 7.418662 (lr=4.9141e-04) (hash(x)=7895970) +350 val loss 7.3536 +350 val perplexity 1561.8104 +350 train 7.328287 (lr=4.9114e-04) (hash(x)=6051847) +351 train 7.486687 (lr=4.9086e-04) (hash(x)=8847992) +352 train 7.859628 (lr=4.9058e-04) (hash(x)=5123883) +353 train 7.450664 (lr=4.9029e-04) (hash(x)=6338998) +354 train 7.444146 (lr=4.9000e-04) (hash(x)=5765866) +355 train 7.772780 (lr=4.8971e-04) (hash(x)=7104011) +356 train 7.550044 (lr=4.8941e-04) (hash(x)=7438267) +357 train 7.264985 (lr=4.8911e-04) (hash(x)=5573214) +358 train 7.550290 (lr=4.8880e-04) (hash(x)=6897283) +359 train 7.356629 (lr=4.8849e-04) (hash(x)=6882897) +360 train 7.454725 (lr=4.8818e-04) (hash(x)=5343615) +361 train 7.375886 (lr=4.8786e-04) (hash(x)=5854242) +362 train 7.312562 (lr=4.8754e-04) (hash(x)=6317324) +363 train 7.236091 (lr=4.8721e-04) (hash(x)=6972494) +364 train 7.306662 (lr=4.8688e-04) (hash(x)=5661167) +365 train 7.341830 (lr=4.8654e-04) (hash(x)=6796805) +366 train 7.157329 (lr=4.8620e-04) (hash(x)=5817209) +367 train 7.246288 (lr=4.8586e-04) (hash(x)=6139120) +368 train 7.403800 (lr=4.8551e-04) (hash(x)=6121296) +369 train 7.364226 (lr=4.8516e-04) (hash(x)=6486796) +370 train 7.281477 (lr=4.8481e-04) (hash(x)=5514645) +371 train 7.215428 (lr=4.8445e-04) (hash(x)=5578797) +372 train 7.216171 (lr=4.8408e-04) (hash(x)=7651738) +373 train 7.406281 (lr=4.8372e-04) (hash(x)=6895326) +374 train 7.429514 (lr=4.8334e-04) (hash(x)=5490256) +375 train 7.314692 (lr=4.8297e-04) (hash(x)=7783160) +376 train 7.503982 (lr=4.8259e-04) (hash(x)=5608424) +377 train 7.280173 (lr=4.8220e-04) (hash(x)=4867625) +378 train 7.184649 (lr=4.8182e-04) (hash(x)=4655472) +379 train 7.253836 (lr=4.8142e-04) (hash(x)=6631123) +380 train 6.923525 (lr=4.8103e-04) (hash(x)=5751990) +381 train 7.210806 (lr=4.8063e-04) (hash(x)=6710965) +382 train 7.182482 (lr=4.8022e-04) (hash(x)=5293800) +383 train 7.210277 (lr=4.7982e-04) (hash(x)=6294657) +384 train 7.374399 (lr=4.7940e-04) (hash(x)=6999538) +385 train 7.352964 (lr=4.7899e-04) (hash(x)=5443606) +386 train 7.323287 (lr=4.7857e-04) (hash(x)=5650401) +387 train 7.334792 (lr=4.7815e-04) (hash(x)=7035770) +388 train 7.287696 (lr=4.7772e-04) (hash(x)=6678271) +389 train 7.477417 (lr=4.7729e-04) (hash(x)=4899541) +390 train 7.232618 (lr=4.7685e-04) (hash(x)=5359260) +391 train 7.236198 (lr=4.7641e-04) (hash(x)=6227120) +392 train 7.290464 (lr=4.7597e-04) (hash(x)=6643916) +393 train 7.355058 (lr=4.7552e-04) (hash(x)=5981648) +394 train 7.311389 (lr=4.7507e-04) (hash(x)=6467540) +395 train 7.259229 (lr=4.7462e-04) (hash(x)=5558993) +396 train 7.411689 (lr=4.7416e-04) (hash(x)=6698959) +397 train 7.215295 (lr=4.7369e-04) (hash(x)=7015671) +398 train 7.243164 (lr=4.7323e-04) (hash(x)=6800890) +399 train 7.394808 (lr=4.7276e-04) (hash(x)=5931234) +400 val loss 7.3279 +400 val perplexity 1522.2522 +400 train 7.372487 (lr=4.7228e-04) (hash(x)=3995070) +401 train 7.324036 (lr=4.7181e-04) (hash(x)=4582159) +402 train 7.381629 (lr=4.7132e-04) (hash(x)=7081906) +403 train 7.276715 (lr=4.7084e-04) (hash(x)=5029472) +404 train 7.281701 (lr=4.7035e-04) (hash(x)=3946232) +405 train 7.200863 (lr=4.6986e-04) (hash(x)=5434102) +406 train 7.944567 (lr=4.6936e-04) (hash(x)=5340646) +407 train 7.108198 (lr=4.6886e-04) (hash(x)=6810638) +408 train 7.320922 (lr=4.6835e-04) (hash(x)=6768026) +409 train 7.320460 (lr=4.6785e-04) (hash(x)=6521562) +410 train 7.321039 (lr=4.6733e-04) (hash(x)=4429434) +411 train 7.386598 (lr=4.6682e-04) (hash(x)=7226932) +412 train 7.167847 (lr=4.6630e-04) (hash(x)=5065932) +413 train 7.312317 (lr=4.6578e-04) (hash(x)=6957849) +414 train 7.322593 (lr=4.6525e-04) (hash(x)=6431457) +415 train 7.413438 (lr=4.6472e-04) (hash(x)=5334281) +416 train 7.407595 (lr=4.6418e-04) (hash(x)=5471747) +417 train 7.483612 (lr=4.6365e-04) (hash(x)=5887983) +418 train 7.380519 (lr=4.6311e-04) (hash(x)=5075909) +419 train 7.185901 (lr=4.6256e-04) (hash(x)=6393576) +420 train 7.318250 (lr=4.6201e-04) (hash(x)=6608979) +421 train 7.726437 (lr=4.6146e-04) (hash(x)=5057959) +422 train 7.651789 (lr=4.6090e-04) (hash(x)=6414858) +423 train 7.445477 (lr=4.6034e-04) (hash(x)=8595271) +424 train 7.308368 (lr=4.5978e-04) (hash(x)=6500949) +425 train 7.487451 (lr=4.5921e-04) (hash(x)=8395167) +426 train 7.620287 (lr=4.5864e-04) (hash(x)=6288420) +427 train 7.446658 (lr=4.5807e-04) (hash(x)=7634417) +428 train 7.303462 (lr=4.5749e-04) (hash(x)=6795561) +429 train 7.206491 (lr=4.5691e-04) (hash(x)=5257771) +430 train 7.363413 (lr=4.5633e-04) (hash(x)=7506860) +431 train 7.412990 (lr=4.5574e-04) (hash(x)=7674238) +432 train 7.524159 (lr=4.5515e-04) (hash(x)=5353794) +433 train 7.438557 (lr=4.5455e-04) (hash(x)=5300555) +434 train 7.114783 (lr=4.5396e-04) (hash(x)=5564419) +435 train 7.358934 (lr=4.5335e-04) (hash(x)=6066139) +436 train 7.337205 (lr=4.5275e-04) (hash(x)=6863709) +437 train 7.358753 (lr=4.5214e-04) (hash(x)=6688212) +438 train 7.509358 (lr=4.5153e-04) (hash(x)=7095090) +439 train 7.578953 (lr=4.5091e-04) (hash(x)=6642404) +440 train 7.321925 (lr=4.5029e-04) (hash(x)=6539227) +441 train 7.292851 (lr=4.4967e-04) (hash(x)=4961570) +442 train 7.241978 (lr=4.4905e-04) (hash(x)=6606391) +443 train 7.074153 (lr=4.4842e-04) (hash(x)=5105190) +444 train 7.605476 (lr=4.4778e-04) (hash(x)=5695997) +445 train 7.329309 (lr=4.4715e-04) (hash(x)=7155991) +446 train 7.283907 (lr=4.4651e-04) (hash(x)=7249727) +447 train 7.277253 (lr=4.4587e-04) (hash(x)=5132972) +448 train 7.279430 (lr=4.4522e-04) (hash(x)=5381802) +449 train 7.323202 (lr=4.4457e-04) (hash(x)=6269946) +450 val loss 7.2899 +450 val perplexity 1465.4833 +450 train 7.270376 (lr=4.4392e-04) (hash(x)=4976762) +451 train 7.357784 (lr=4.4326e-04) (hash(x)=5396133) +452 train 7.311365 (lr=4.4260e-04) (hash(x)=6173473) +453 train 7.289800 (lr=4.4194e-04) (hash(x)=6394083) +454 train 7.348038 (lr=4.4128e-04) (hash(x)=6436030) +455 train 7.196606 (lr=4.4061e-04) (hash(x)=5237804) +456 train 7.195276 (lr=4.3994e-04) (hash(x)=6540397) +457 train 7.440486 (lr=4.3926e-04) (hash(x)=5216638) +458 train 7.258152 (lr=4.3858e-04) (hash(x)=5750537) +459 train 7.248807 (lr=4.3790e-04) (hash(x)=6735565) +460 train 7.280071 (lr=4.3722e-04) (hash(x)=7297488) +461 train 7.459930 (lr=4.3653e-04) (hash(x)=5983575) +462 train 7.281603 (lr=4.3584e-04) (hash(x)=4808543) +463 train 7.400100 (lr=4.3515e-04) (hash(x)=5831619) +464 train 7.165792 (lr=4.3445e-04) (hash(x)=6280052) +465 train 7.187557 (lr=4.3375e-04) (hash(x)=9109083) +466 train 7.453741 (lr=4.3305e-04) (hash(x)=5848604) +467 train 7.363054 (lr=4.3234e-04) (hash(x)=6912967) +468 train 7.545842 (lr=4.3163e-04) (hash(x)=6615365) +469 train 7.592494 (lr=4.3092e-04) (hash(x)=5965674) +470 train 7.431085 (lr=4.3020e-04) (hash(x)=6879965) +471 train 7.418310 (lr=4.2948e-04) (hash(x)=5822533) +472 train 7.284165 (lr=4.2876e-04) (hash(x)=5794462) +473 train 7.357923 (lr=4.2804e-04) (hash(x)=5268216) +474 train 7.178822 (lr=4.2731e-04) (hash(x)=7058396) +475 train 7.272190 (lr=4.2658e-04) (hash(x)=6531900) +476 train 7.302053 (lr=4.2585e-04) (hash(x)=5878912) +477 train 7.118084 (lr=4.2511e-04) (hash(x)=5426499) +478 train 7.321150 (lr=4.2437e-04) (hash(x)=8107004) +479 train 8.043603 (lr=4.2363e-04) (hash(x)=7455372) +480 train 7.958918 (lr=4.2289e-04) (hash(x)=7727959) +481 train 7.869405 (lr=4.2214e-04) (hash(x)=8319119) +482 train 7.796440 (lr=4.2139e-04) (hash(x)=7581656) +483 train 7.859143 (lr=4.2064e-04) (hash(x)=7592128) +484 train 7.851507 (lr=4.1988e-04) (hash(x)=10506633) +485 train 7.820150 (lr=4.1912e-04) (hash(x)=8704170) +486 train 7.597719 (lr=4.1836e-04) (hash(x)=7461138) +487 train 7.542131 (lr=4.1759e-04) (hash(x)=7165037) +488 train 7.589431 (lr=4.1683e-04) (hash(x)=4976998) +489 train 7.333087 (lr=4.1606e-04) (hash(x)=7678000) +490 train 7.371785 (lr=4.1529e-04) (hash(x)=6299409) +491 train 7.314082 (lr=4.1451e-04) (hash(x)=7414788) +492 train 7.383027 (lr=4.1373e-04) (hash(x)=5063061) +493 train 7.304886 (lr=4.1295e-04) (hash(x)=7326216) +494 train 7.463638 (lr=4.1217e-04) (hash(x)=7492012) +495 train 7.448625 (lr=4.1138e-04) (hash(x)=5857162) +496 train 7.240193 (lr=4.1059e-04) (hash(x)=6169001) +497 train 9.057885 (lr=4.0980e-04) (hash(x)=14715669) +498 train 11.606592 (lr=4.0901e-04) (hash(x)=18256706) +499 train 11.324938 (lr=4.0821e-04) (hash(x)=16950560) +500 val loss 7.4028 +500 val perplexity 1640.5240 +500 train 8.012500 (lr=4.0741e-04) (hash(x)=6113563) +501 train 7.118929 (lr=4.0661e-04) (hash(x)=6159125) +502 train 7.505335 (lr=4.0581e-04) (hash(x)=5482303) +503 train 7.492241 (lr=4.0500e-04) (hash(x)=5908442) +504 train 7.327708 (lr=4.0419e-04) (hash(x)=4985045) +505 train 7.202794 (lr=4.0338e-04) (hash(x)=6668887) +506 train 7.250021 (lr=4.0256e-04) (hash(x)=6123910) +507 train 7.348025 (lr=4.0175e-04) (hash(x)=7662975) +508 train 7.329094 (lr=4.0093e-04) (hash(x)=7191898) +509 train 7.275278 (lr=4.0011e-04) (hash(x)=6669539) +510 train 7.366440 (lr=3.9928e-04) (hash(x)=6557481) +511 train 7.265127 (lr=3.9846e-04) (hash(x)=5015998) +512 train 7.339677 (lr=3.9763e-04) (hash(x)=4964540) +513 train 7.160976 (lr=3.9680e-04) (hash(x)=5458386) +514 train 7.550523 (lr=3.9596e-04) (hash(x)=6077616) +515 train 7.254044 (lr=3.9513e-04) (hash(x)=4849847) +516 train 7.315500 (lr=3.9429e-04) (hash(x)=5431422) +517 train 7.495736 (lr=3.9345e-04) (hash(x)=5125562) +518 train 7.399670 (lr=3.9260e-04) (hash(x)=5587715) +519 train 7.438242 (lr=3.9176e-04) (hash(x)=6012047) +520 train 7.285417 (lr=3.9091e-04) (hash(x)=5668436) +521 train 7.298543 (lr=3.9006e-04) (hash(x)=6079364) +522 train 7.424856 (lr=3.8921e-04) (hash(x)=5200504) +523 train 7.194755 (lr=3.8836e-04) (hash(x)=6030395) +524 train 7.410457 (lr=3.8750e-04) (hash(x)=6855319) +525 train 7.217526 (lr=3.8664e-04) (hash(x)=6781762) +526 train 7.332098 (lr=3.8578e-04) (hash(x)=6717939) +527 train 7.317234 (lr=3.8492e-04) (hash(x)=5238325) +528 train 7.225211 (lr=3.8405e-04) (hash(x)=5808069) +529 train 7.550049 (lr=3.8319e-04) (hash(x)=8611144) +530 train 7.216195 (lr=3.8232e-04) (hash(x)=6028738) +531 train 7.238579 (lr=3.8145e-04) (hash(x)=6901605) +532 train 7.219437 (lr=3.8057e-04) (hash(x)=6723307) +533 train 7.313085 (lr=3.7970e-04) (hash(x)=5499337) +534 train 7.227896 (lr=3.7882e-04) (hash(x)=6586372) +535 train 7.340302 (lr=3.7794e-04) (hash(x)=7134874) +536 train 7.241990 (lr=3.7706e-04) (hash(x)=8415623) +537 train 7.274408 (lr=3.7618e-04) (hash(x)=6149038) +538 train 7.304252 (lr=3.7529e-04) (hash(x)=6078325) +539 train 7.270723 (lr=3.7440e-04) (hash(x)=6609760) +540 train 7.188707 (lr=3.7351e-04) (hash(x)=6185253) +541 train 7.508142 (lr=3.7262e-04) (hash(x)=6652627) +542 train 7.350823 (lr=3.7173e-04) (hash(x)=7758536) +543 train 7.322165 (lr=3.7084e-04) (hash(x)=8618579) +544 train 7.283743 (lr=3.6994e-04) (hash(x)=6710226) +545 train 7.185863 (lr=3.6904e-04) (hash(x)=5896892) +546 train 7.190402 (lr=3.6814e-04) (hash(x)=6332995) +547 train 7.597643 (lr=3.6724e-04) (hash(x)=8945854) +548 train 7.161655 (lr=3.6633e-04) (hash(x)=4329129) +549 train 7.225268 (lr=3.6543e-04) (hash(x)=6775103) +550 val loss 7.2318 +550 val perplexity 1382.7369 +550 train 7.340587 (lr=3.6452e-04) (hash(x)=4465735) +551 train 7.199905 (lr=3.6361e-04) (hash(x)=6200024) +552 train 7.180590 (lr=3.6270e-04) (hash(x)=5520748) +553 train 7.206614 (lr=3.6179e-04) (hash(x)=5238139) +554 train 7.464119 (lr=3.6088e-04) (hash(x)=7639817) +555 train 7.205936 (lr=3.5996e-04) (hash(x)=5780948) +556 train 7.326672 (lr=3.5904e-04) (hash(x)=6733444) +557 train 7.274657 (lr=3.5812e-04) (hash(x)=6168407) +558 train 7.317760 (lr=3.5720e-04) (hash(x)=6680197) +559 train 7.181390 (lr=3.5628e-04) (hash(x)=3775881) +560 train 7.052334 (lr=3.5536e-04) (hash(x)=5784096) +561 train 7.497858 (lr=3.5443e-04) (hash(x)=6848709) +562 train 7.546772 (lr=3.5350e-04) (hash(x)=7449019) +563 train 7.608180 (lr=3.5257e-04) (hash(x)=6478113) +564 train 7.294013 (lr=3.5164e-04) (hash(x)=5925744) +565 train 7.362743 (lr=3.5071e-04) (hash(x)=6483914) +566 train 7.236003 (lr=3.4978e-04) (hash(x)=6010847) +567 train 7.326846 (lr=3.4885e-04) (hash(x)=5927795) +568 train 7.302283 (lr=3.4791e-04) (hash(x)=5896332) +569 train 7.267607 (lr=3.4697e-04) (hash(x)=8438033) +570 train 7.354639 (lr=3.4603e-04) (hash(x)=6081660) +571 train 7.276875 (lr=3.4509e-04) (hash(x)=5684788) +572 train 7.181964 (lr=3.4415e-04) (hash(x)=6272055) +573 train 7.125742 (lr=3.4321e-04) (hash(x)=5710182) +574 train 7.240862 (lr=3.4227e-04) (hash(x)=6219616) +575 train 7.210860 (lr=3.4132e-04) (hash(x)=6160063) +576 train 7.232080 (lr=3.4037e-04) (hash(x)=5710809) +577 train 6.994545 (lr=3.3943e-04) (hash(x)=5955100) +578 train 7.014284 (lr=3.3848e-04) (hash(x)=5356088) +579 train 7.055608 (lr=3.3753e-04) (hash(x)=6672309) +580 train 7.261271 (lr=3.3657e-04) (hash(x)=5841684) +581 train 7.551422 (lr=3.3562e-04) (hash(x)=9001564) +582 train 8.100646 (lr=3.3467e-04) (hash(x)=6897178) +583 train 7.340374 (lr=3.3371e-04) (hash(x)=5454654) +584 train 7.114398 (lr=3.3276e-04) (hash(x)=6391454) +585 train 7.168121 (lr=3.3180e-04) (hash(x)=5174062) +586 train 7.286976 (lr=3.3084e-04) (hash(x)=5197924) +587 train 7.275974 (lr=3.2988e-04) (hash(x)=6199203) +588 train 7.117282 (lr=3.2892e-04) (hash(x)=5786498) +589 train 7.241289 (lr=3.2796e-04) (hash(x)=8352747) +590 train 7.498503 (lr=3.2700e-04) (hash(x)=4829700) +591 train 7.067603 (lr=3.2603e-04) (hash(x)=4547106) +592 train 7.336035 (lr=3.2507e-04) (hash(x)=7686831) +593 train 7.225210 (lr=3.2410e-04) (hash(x)=6433099) +594 train 7.092546 (lr=3.2313e-04) (hash(x)=4826460) +595 train 7.166202 (lr=3.2217e-04) (hash(x)=6424428) +596 train 7.051532 (lr=3.2120e-04) (hash(x)=6073605) +597 train 7.401325 (lr=3.2023e-04) (hash(x)=5975712) +598 train 7.024569 (lr=3.1926e-04) (hash(x)=7030029) +599 train 7.303596 (lr=3.1829e-04) (hash(x)=5458532) +600 val loss 7.2336 +600 val perplexity 1385.2269 +600 train 7.170733 (lr=3.1732e-04) (hash(x)=7823919) +601 train 7.592966 (lr=3.1634e-04) (hash(x)=7002774) +602 train 7.391923 (lr=3.1537e-04) (hash(x)=7056399) +603 train 7.583635 (lr=3.1440e-04) (hash(x)=8206173) +604 train 7.453058 (lr=3.1342e-04) (hash(x)=8034846) +605 train 7.753613 (lr=3.1244e-04) (hash(x)=7784971) +606 train 7.897100 (lr=3.1147e-04) (hash(x)=7118076) +607 train 7.149109 (lr=3.1049e-04) (hash(x)=6001843) +608 train 7.265481 (lr=3.0951e-04) (hash(x)=5582437) +609 train 7.382948 (lr=3.0853e-04) (hash(x)=5698642) +610 train 7.252756 (lr=3.0756e-04) (hash(x)=6615301) +611 train 7.246986 (lr=3.0658e-04) (hash(x)=6600751) +612 train 7.193204 (lr=3.0559e-04) (hash(x)=6880955) +613 train 7.247636 (lr=3.0461e-04) (hash(x)=5804610) +614 train 7.155735 (lr=3.0363e-04) (hash(x)=6263347) +615 train 7.131412 (lr=3.0265e-04) (hash(x)=5162652) +616 train 7.181210 (lr=3.0167e-04) (hash(x)=6055710) +617 train 7.140581 (lr=3.0068e-04) (hash(x)=5297006) +618 train 7.153012 (lr=2.9970e-04) (hash(x)=5923648) +619 train 7.165670 (lr=2.9872e-04) (hash(x)=6728323) +620 train 7.169304 (lr=2.9773e-04) (hash(x)=6660239) +621 train 7.139369 (lr=2.9675e-04) (hash(x)=3964882) +622 train 7.186901 (lr=2.9576e-04) (hash(x)=5868942) +623 train 7.112548 (lr=2.9477e-04) (hash(x)=6735993) +624 train 7.428791 (lr=2.9379e-04) (hash(x)=5926190) +625 train 7.126852 (lr=2.9280e-04) (hash(x)=5150316) +626 train 7.131873 (lr=2.9181e-04) (hash(x)=7571467) +627 train 7.054023 (lr=2.9083e-04) (hash(x)=5220448) +628 train 7.079872 (lr=2.8984e-04) (hash(x)=6790397) +629 train 7.512336 (lr=2.8885e-04) (hash(x)=6971289) +630 train 7.467366 (lr=2.8786e-04) (hash(x)=7123359) +631 train 7.260921 (lr=2.8687e-04) (hash(x)=5012069) +632 train 7.230923 (lr=2.8589e-04) (hash(x)=6183574) +633 train 7.142000 (lr=2.8490e-04) (hash(x)=6576136) +634 train 7.168055 (lr=2.8391e-04) (hash(x)=6157346) +635 train 7.149889 (lr=2.8292e-04) (hash(x)=6077647) +636 train 7.385414 (lr=2.8193e-04) (hash(x)=8369488) +637 train 7.180794 (lr=2.8094e-04) (hash(x)=6032381) +638 train 7.129543 (lr=2.7995e-04) (hash(x)=5924756) +639 train 7.145929 (lr=2.7896e-04) (hash(x)=8410716) +640 train 7.131887 (lr=2.7797e-04) (hash(x)=5803440) +641 train 7.224884 (lr=2.7698e-04) (hash(x)=6212516) +642 train 7.297716 (lr=2.7599e-04) (hash(x)=7165945) +643 train 7.017425 (lr=2.7500e-04) (hash(x)=5298545) +644 train 7.283959 (lr=2.7401e-04) (hash(x)=6281739) +645 train 7.232979 (lr=2.7302e-04) (hash(x)=5779073) +646 train 7.122484 (lr=2.7203e-04) (hash(x)=5090107) +647 train 7.154592 (lr=2.7104e-04) (hash(x)=6340947) +648 train 6.947502 (lr=2.7005e-04) (hash(x)=4741418) +649 train 6.872756 (lr=2.6906e-04) (hash(x)=6530441) +650 val loss 7.2037 +650 val perplexity 1344.4575 +650 train 7.367408 (lr=2.6807e-04) (hash(x)=6396041) +651 train 7.059503 (lr=2.6708e-04) (hash(x)=7818007) +652 train 7.085327 (lr=2.6609e-04) (hash(x)=6478457) +653 train 7.139442 (lr=2.6510e-04) (hash(x)=6277435) +654 train 7.107744 (lr=2.6411e-04) (hash(x)=6042369) +655 train 7.133445 (lr=2.6313e-04) (hash(x)=6226320) +656 train 7.163586 (lr=2.6214e-04) (hash(x)=5826883) +657 train 7.260682 (lr=2.6115e-04) (hash(x)=5463751) +658 train 7.171949 (lr=2.6016e-04) (hash(x)=6433080) +659 train 7.026829 (lr=2.5917e-04) (hash(x)=6579329) +660 train 7.045075 (lr=2.5819e-04) (hash(x)=4724703) +661 train 7.392688 (lr=2.5720e-04) (hash(x)=6660540) +662 train 7.206363 (lr=2.5621e-04) (hash(x)=5918756) +663 train 7.142970 (lr=2.5523e-04) (hash(x)=6491272) +664 train 7.056121 (lr=2.5424e-04) (hash(x)=5452863) +665 train 7.262488 (lr=2.5325e-04) (hash(x)=6766947) +666 train 7.607103 (lr=2.5227e-04) (hash(x)=7459504) +667 train 7.274706 (lr=2.5128e-04) (hash(x)=3721218) +668 train 7.447508 (lr=2.5030e-04) (hash(x)=7929571) +669 train 7.141531 (lr=2.4932e-04) (hash(x)=5229898) +670 train 7.177824 (lr=2.4833e-04) (hash(x)=6083090) +671 train 7.026249 (lr=2.4735e-04) (hash(x)=6054428) +672 train 7.191954 (lr=2.4637e-04) (hash(x)=6072563) +673 train 7.281960 (lr=2.4539e-04) (hash(x)=6290464) +674 train 7.401324 (lr=2.4441e-04) (hash(x)=6314742) +675 train 7.054433 (lr=2.4342e-04) (hash(x)=6904498) +676 train 7.232555 (lr=2.4244e-04) (hash(x)=5378107) +677 train 7.341599 (lr=2.4147e-04) (hash(x)=7765805) +678 train 7.158114 (lr=2.4049e-04) (hash(x)=5871280) +679 train 7.296226 (lr=2.3951e-04) (hash(x)=6543764) +680 train 7.187054 (lr=2.3853e-04) (hash(x)=7369665) +681 train 7.256405 (lr=2.3756e-04) (hash(x)=7204955) +682 train 7.204233 (lr=2.3658e-04) (hash(x)=5856543) +683 train 7.083048 (lr=2.3560e-04) (hash(x)=4423711) +684 train 7.053214 (lr=2.3463e-04) (hash(x)=5818153) +685 train 7.164416 (lr=2.3366e-04) (hash(x)=5343477) +686 train 7.341728 (lr=2.3268e-04) (hash(x)=6581702) +687 train 7.172156 (lr=2.3171e-04) (hash(x)=6595856) +688 train 7.113365 (lr=2.3074e-04) (hash(x)=5325378) +689 train 7.030375 (lr=2.2977e-04) (hash(x)=7229015) +690 train 7.191414 (lr=2.2880e-04) (hash(x)=5918186) +691 train 7.079477 (lr=2.2783e-04) (hash(x)=5916034) +692 train 7.085675 (lr=2.2687e-04) (hash(x)=5280722) +693 train 7.464597 (lr=2.2590e-04) (hash(x)=6939521) +694 train 7.236353 (lr=2.2493e-04) (hash(x)=5172566) +695 train 7.085230 (lr=2.2397e-04) (hash(x)=5492185) +696 train 6.950496 (lr=2.2300e-04) (hash(x)=5779011) +697 train 7.217097 (lr=2.2204e-04) (hash(x)=6898006) +698 train 7.064927 (lr=2.2108e-04) (hash(x)=5779217) +699 train 6.930017 (lr=2.2012e-04) (hash(x)=5462008) +700 val loss 7.2030 +700 val perplexity 1343.4436 +700 train 7.080348 (lr=2.1916e-04) (hash(x)=6243843) +701 train 7.130294 (lr=2.1820e-04) (hash(x)=7821902) +702 train 7.202125 (lr=2.1724e-04) (hash(x)=5222501) +703 train 7.154733 (lr=2.1629e-04) (hash(x)=6608108) +704 train 7.259069 (lr=2.1533e-04) (hash(x)=7602879) +705 train 7.189792 (lr=2.1438e-04) (hash(x)=6295394) +706 train 7.164328 (lr=2.1343e-04) (hash(x)=6579907) +707 train 7.043313 (lr=2.1247e-04) (hash(x)=6803449) +708 train 7.120936 (lr=2.1152e-04) (hash(x)=5413733) +709 train 7.086606 (lr=2.1057e-04) (hash(x)=7444134) +710 train 7.217830 (lr=2.0963e-04) (hash(x)=7028652) +711 train 7.029326 (lr=2.0868e-04) (hash(x)=5361923) +712 train 7.141841 (lr=2.0773e-04) (hash(x)=5478293) +713 train 7.125812 (lr=2.0679e-04) (hash(x)=7803039) +714 train 7.310772 (lr=2.0585e-04) (hash(x)=6469017) +715 train 7.198825 (lr=2.0491e-04) (hash(x)=7042578) +716 train 7.265806 (lr=2.0397e-04) (hash(x)=6927957) +717 train 7.063830 (lr=2.0303e-04) (hash(x)=6647007) +718 train 7.031882 (lr=2.0209e-04) (hash(x)=6230888) +719 train 7.298119 (lr=2.0115e-04) (hash(x)=6303658) +720 train 7.333447 (lr=2.0022e-04) (hash(x)=6769880) +721 train 7.171665 (lr=1.9929e-04) (hash(x)=6158927) +722 train 7.185044 (lr=1.9836e-04) (hash(x)=5991631) +723 train 7.036589 (lr=1.9743e-04) (hash(x)=6419656) +724 train 7.043666 (lr=1.9650e-04) (hash(x)=7739209) +725 train 6.989378 (lr=1.9557e-04) (hash(x)=7891271) +726 train 7.329946 (lr=1.9464e-04) (hash(x)=7171433) +727 train 7.109214 (lr=1.9372e-04) (hash(x)=7099888) +728 train 7.132068 (lr=1.9280e-04) (hash(x)=6103730) +729 train 7.228476 (lr=1.9188e-04) (hash(x)=6352424) +730 train 7.128138 (lr=1.9096e-04) (hash(x)=4893671) +731 train 7.070363 (lr=1.9004e-04) (hash(x)=5863145) +732 train 7.178476 (lr=1.8912e-04) (hash(x)=5502233) +733 train 7.097033 (lr=1.8821e-04) (hash(x)=6844597) +734 train 7.111217 (lr=1.8730e-04) (hash(x)=6744526) +735 train 7.245788 (lr=1.8639e-04) (hash(x)=6009861) +736 train 7.120891 (lr=1.8548e-04) (hash(x)=6152358) +737 train 7.041088 (lr=1.8457e-04) (hash(x)=5374957) +738 train 7.061660 (lr=1.8367e-04) (hash(x)=6495309) +739 train 7.229872 (lr=1.8276e-04) (hash(x)=3923225) +740 train 6.993084 (lr=1.8186e-04) (hash(x)=6255243) +741 train 7.151180 (lr=1.8096e-04) (hash(x)=5848862) +742 train 7.164347 (lr=1.8006e-04) (hash(x)=4535000) +743 train 7.048220 (lr=1.7916e-04) (hash(x)=4440634) +744 train 7.040949 (lr=1.7827e-04) (hash(x)=5222077) +745 train 7.071302 (lr=1.7738e-04) (hash(x)=4788998) +746 train 7.077866 (lr=1.7649e-04) (hash(x)=6108350) +747 train 6.994192 (lr=1.7560e-04) (hash(x)=7378165) +748 train 7.071881 (lr=1.7471e-04) (hash(x)=5475646) +749 train 7.066017 (lr=1.7382e-04) (hash(x)=4771243) +750 val loss 7.1755 +750 val perplexity 1306.9722 +750 train 6.969173 (lr=1.7294e-04) (hash(x)=6668088) +751 train 7.197128 (lr=1.7206e-04) (hash(x)=5716089) +752 train 7.130735 (lr=1.7118e-04) (hash(x)=6991946) +753 train 7.051327 (lr=1.7030e-04) (hash(x)=7991009) +754 train 7.142888 (lr=1.6943e-04) (hash(x)=6037018) +755 train 7.120643 (lr=1.6855e-04) (hash(x)=5348607) +756 train 7.271412 (lr=1.6768e-04) (hash(x)=5190526) +757 train 7.147381 (lr=1.6681e-04) (hash(x)=6036146) +758 train 7.030255 (lr=1.6595e-04) (hash(x)=5329783) +759 train 7.144168 (lr=1.6508e-04) (hash(x)=6658718) +760 train 7.039481 (lr=1.6422e-04) (hash(x)=4820939) +761 train 7.040227 (lr=1.6336e-04) (hash(x)=6176253) +762 train 7.002691 (lr=1.6250e-04) (hash(x)=5316750) +763 train 7.096122 (lr=1.6164e-04) (hash(x)=4542895) +764 train 6.901529 (lr=1.6079e-04) (hash(x)=5395673) +765 train 6.987905 (lr=1.5994e-04) (hash(x)=5549073) +766 train 7.213568 (lr=1.5909e-04) (hash(x)=5233723) +767 train 7.287885 (lr=1.5824e-04) (hash(x)=5342783) +768 train 7.200521 (lr=1.5740e-04) (hash(x)=5552448) +769 train 7.333962 (lr=1.5655e-04) (hash(x)=6549546) +770 train 7.030944 (lr=1.5571e-04) (hash(x)=3816493) +771 train 7.051879 (lr=1.5487e-04) (hash(x)=6170599) +772 train 7.530505 (lr=1.5404e-04) (hash(x)=6708759) +773 train 7.150365 (lr=1.5320e-04) (hash(x)=8483134) +774 train 7.712167 (lr=1.5237e-04) (hash(x)=5583732) +775 train 7.148433 (lr=1.5154e-04) (hash(x)=4865036) +776 train 7.065294 (lr=1.5072e-04) (hash(x)=7234336) +777 train 7.122308 (lr=1.4989e-04) (hash(x)=4433890) +778 train 7.431165 (lr=1.4907e-04) (hash(x)=7484636) +779 train 7.765922 (lr=1.4825e-04) (hash(x)=6738597) +780 train 7.115509 (lr=1.4744e-04) (hash(x)=6752421) +781 train 7.284620 (lr=1.4662e-04) (hash(x)=5459620) +782 train 7.217221 (lr=1.4581e-04) (hash(x)=6718131) +783 train 7.192764 (lr=1.4500e-04) (hash(x)=4604074) +784 train 7.053667 (lr=1.4419e-04) (hash(x)=5946124) +785 train 7.322965 (lr=1.4339e-04) (hash(x)=8045501) +786 train 7.430284 (lr=1.4259e-04) (hash(x)=5712725) +787 train 7.142458 (lr=1.4179e-04) (hash(x)=6176464) +788 train 7.199960 (lr=1.4099e-04) (hash(x)=6276702) +789 train 7.009469 (lr=1.4020e-04) (hash(x)=6127317) +790 train 7.175450 (lr=1.3941e-04) (hash(x)=7221374) +791 train 7.154131 (lr=1.3862e-04) (hash(x)=5571462) +792 train 7.145968 (lr=1.3783e-04) (hash(x)=7518021) +793 train 7.147912 (lr=1.3705e-04) (hash(x)=6640755) +794 train 7.230053 (lr=1.3627e-04) (hash(x)=6870405) +795 train 7.207945 (lr=1.3549e-04) (hash(x)=6147295) +796 train 7.096144 (lr=1.3471e-04) (hash(x)=6782583) +797 train 7.212864 (lr=1.3394e-04) (hash(x)=6120461) +798 train 7.148787 (lr=1.3317e-04) (hash(x)=5893870) +799 train 7.096112 (lr=1.3241e-04) (hash(x)=5123928) +800 val loss 7.1756 +800 val perplexity 1307.2084 +800 train 7.150401 (lr=1.3164e-04) (hash(x)=7037251) +801 train 7.150720 (lr=1.3088e-04) (hash(x)=5428813) +802 train 7.090047 (lr=1.3012e-04) (hash(x)=5550387) +803 train 7.158418 (lr=1.2936e-04) (hash(x)=6448586) +804 train 7.290930 (lr=1.2861e-04) (hash(x)=5916934) +805 train 7.267348 (lr=1.2786e-04) (hash(x)=8116987) +806 train 7.225321 (lr=1.2711e-04) (hash(x)=6210899) +807 train 7.339539 (lr=1.2637e-04) (hash(x)=5974342) +808 train 7.331194 (lr=1.2563e-04) (hash(x)=7236199) +809 train 7.256968 (lr=1.2489e-04) (hash(x)=5261336) +810 train 7.093021 (lr=1.2415e-04) (hash(x)=6310720) +811 train 7.130575 (lr=1.2342e-04) (hash(x)=5307056) +812 train 6.961190 (lr=1.2269e-04) (hash(x)=7356633) +813 train 7.093193 (lr=1.2196e-04) (hash(x)=5865119) +814 train 6.997390 (lr=1.2124e-04) (hash(x)=5979205) +815 train 7.137850 (lr=1.2052e-04) (hash(x)=6672380) +816 train 7.127195 (lr=1.1980e-04) (hash(x)=5565030) +817 train 7.101686 (lr=1.1908e-04) (hash(x)=6886810) +818 train 7.164133 (lr=1.1837e-04) (hash(x)=5926478) +819 train 7.367997 (lr=1.1766e-04) (hash(x)=6564071) +820 train 6.997451 (lr=1.1695e-04) (hash(x)=5024280) +821 train 6.993600 (lr=1.1625e-04) (hash(x)=7705089) +822 train 6.985338 (lr=1.1555e-04) (hash(x)=4037371) +823 train 7.086132 (lr=1.1485e-04) (hash(x)=5773073) +824 train 7.100038 (lr=1.1416e-04) (hash(x)=7158139) +825 train 6.934294 (lr=1.1347e-04) (hash(x)=5905976) +826 train 7.339707 (lr=1.1278e-04) (hash(x)=13897369) +827 train 8.364253 (lr=1.1210e-04) (hash(x)=6936653) +828 train 7.101104 (lr=1.1142e-04) (hash(x)=6592246) +829 train 7.105082 (lr=1.1074e-04) (hash(x)=6592773) +830 train 7.160076 (lr=1.1006e-04) (hash(x)=5461178) +831 train 6.933063 (lr=1.0939e-04) (hash(x)=6796551) +832 train 7.151640 (lr=1.0872e-04) (hash(x)=4721691) +833 train 7.066098 (lr=1.0806e-04) (hash(x)=6151589) +834 train 7.203424 (lr=1.0740e-04) (hash(x)=7008995) +835 train 7.544888 (lr=1.0674e-04) (hash(x)=7045164) +836 train 7.137199 (lr=1.0608e-04) (hash(x)=6614221) +837 train 7.163367 (lr=1.0543e-04) (hash(x)=6650506) +838 train 6.974346 (lr=1.0478e-04) (hash(x)=6363762) +839 train 7.130906 (lr=1.0413e-04) (hash(x)=7839748) +840 train 7.062234 (lr=1.0349e-04) (hash(x)=5124077) +841 train 7.502398 (lr=1.0285e-04) (hash(x)=6028671) +842 train 7.007654 (lr=1.0222e-04) (hash(x)=5427175) +843 train 7.328398 (lr=1.0158e-04) (hash(x)=6118408) +844 train 7.103365 (lr=1.0095e-04) (hash(x)=6022552) +845 train 7.128020 (lr=1.0033e-04) (hash(x)=5757526) +846 train 7.552039 (lr=9.9707e-05) (hash(x)=6476549) +847 train 6.917031 (lr=9.9088e-05) (hash(x)=6030172) +848 train 7.301168 (lr=9.8472e-05) (hash(x)=5917229) +849 train 7.370104 (lr=9.7860e-05) (hash(x)=6719882) +850 val loss 7.1587 +850 val perplexity 1285.1992 +850 train 7.225770 (lr=9.7252e-05) (hash(x)=5441498) +851 train 7.090196 (lr=9.6646e-05) (hash(x)=5028050) +852 train 7.128417 (lr=9.6044e-05) (hash(x)=8487491) +853 train 7.126094 (lr=9.5446e-05) (hash(x)=5682910) +854 train 7.313828 (lr=9.4851e-05) (hash(x)=6781362) +855 train 7.139297 (lr=9.4260e-05) (hash(x)=5747891) +856 train 7.172555 (lr=9.3672e-05) (hash(x)=7627661) +857 train 6.852248 (lr=9.3088e-05) (hash(x)=5734208) +858 train 6.991792 (lr=9.2507e-05) (hash(x)=6162015) +859 train 7.218524 (lr=9.1929e-05) (hash(x)=7024381) +860 train 7.422373 (lr=9.1356e-05) (hash(x)=5198498) +861 train 7.389331 (lr=9.0785e-05) (hash(x)=7814361) +862 train 7.259416 (lr=9.0219e-05) (hash(x)=7394995) +863 train 7.136432 (lr=8.9656e-05) (hash(x)=5765893) +864 train 6.953266 (lr=8.9096e-05) (hash(x)=4990435) +865 train 7.097276 (lr=8.8540e-05) (hash(x)=5572048) +866 train 7.240610 (lr=8.7988e-05) (hash(x)=7093293) +867 train 7.144871 (lr=8.7439e-05) (hash(x)=5610058) +868 train 7.025204 (lr=8.6894e-05) (hash(x)=6771468) +869 train 7.082045 (lr=8.6353e-05) (hash(x)=4459483) +870 train 6.963592 (lr=8.5815e-05) (hash(x)=4926546) +871 train 7.064310 (lr=8.5281e-05) (hash(x)=6758411) +872 train 7.049325 (lr=8.4751e-05) (hash(x)=7394277) +873 train 7.170132 (lr=8.4224e-05) (hash(x)=6701381) +874 train 7.513340 (lr=8.3701e-05) (hash(x)=8120966) +875 train 7.032025 (lr=8.3182e-05) (hash(x)=5416400) +876 train 7.038291 (lr=8.2666e-05) (hash(x)=6292778) +877 train 6.968759 (lr=8.2154e-05) (hash(x)=5919569) +878 train 7.298956 (lr=8.1646e-05) (hash(x)=7561740) +879 train 7.039161 (lr=8.1142e-05) (hash(x)=5282870) +880 train 7.076750 (lr=8.0641e-05) (hash(x)=5473238) +881 train 6.951123 (lr=8.0144e-05) (hash(x)=8072181) +882 train 6.986775 (lr=7.9651e-05) (hash(x)=6757322) +883 train 6.938721 (lr=7.9162e-05) (hash(x)=7996770) +884 train 7.017838 (lr=7.8676e-05) (hash(x)=3181021) +885 train 7.077095 (lr=7.8195e-05) (hash(x)=5093519) +886 train 7.038786 (lr=7.7717e-05) (hash(x)=5391352) +887 train 7.074209 (lr=7.7243e-05) (hash(x)=6270917) +888 train 7.069191 (lr=7.6772e-05) (hash(x)=5818195) +889 train 6.843506 (lr=7.6306e-05) (hash(x)=5852780) +890 train 6.775005 (lr=7.5843e-05) (hash(x)=5777928) +891 train 6.944767 (lr=7.5384e-05) (hash(x)=5327728) +892 train 6.976420 (lr=7.4930e-05) (hash(x)=7651281) +893 train 7.181395 (lr=7.4479e-05) (hash(x)=6260765) +894 train 7.067991 (lr=7.4031e-05) (hash(x)=6265102) +895 train 7.223037 (lr=7.3588e-05) (hash(x)=6212894) +896 train 7.006706 (lr=7.3149e-05) (hash(x)=6901967) +897 train 7.078855 (lr=7.2714e-05) (hash(x)=6724010) +898 train 7.068458 (lr=7.2282e-05) (hash(x)=6299033) +899 train 7.224230 (lr=7.1854e-05) (hash(x)=6059934) +900 val loss 7.1495 +900 val perplexity 1273.4417 +900 train 6.938208 (lr=7.1431e-05) (hash(x)=6029696) +901 train 6.863510 (lr=7.1011e-05) (hash(x)=5587382) +902 train 7.058921 (lr=7.0595e-05) (hash(x)=5890076) +903 train 6.984908 (lr=7.0184e-05) (hash(x)=7274108) +904 train 7.065307 (lr=6.9776e-05) (hash(x)=7975528) +905 train 7.131458 (lr=6.9372e-05) (hash(x)=6085396) +906 train 7.014284 (lr=6.8972e-05) (hash(x)=6724496) +907 train 7.007479 (lr=6.8576e-05) (hash(x)=4784666) +908 train 7.010525 (lr=6.8184e-05) (hash(x)=7193845) +909 train 7.173096 (lr=6.7796e-05) (hash(x)=6288638) +910 train 7.143156 (lr=6.7412e-05) (hash(x)=5685285) +911 train 7.118443 (lr=6.7033e-05) (hash(x)=7714288) +912 train 7.204838 (lr=6.6657e-05) (hash(x)=5983679) +913 train 7.153268 (lr=6.6285e-05) (hash(x)=5534748) +914 train 7.085438 (lr=6.5917e-05) (hash(x)=6545471) +915 train 7.081078 (lr=6.5553e-05) (hash(x)=6361270) +916 train 7.082535 (lr=6.5194e-05) (hash(x)=6257744) +917 train 7.088195 (lr=6.4838e-05) (hash(x)=4682956) +918 train 6.986125 (lr=6.4487e-05) (hash(x)=4521756) +919 train 7.122678 (lr=6.4139e-05) (hash(x)=7568935) +920 train 7.044667 (lr=6.3796e-05) (hash(x)=7969353) +921 train 7.242951 (lr=6.3457e-05) (hash(x)=7973311) +922 train 6.944165 (lr=6.3121e-05) (hash(x)=4843937) +923 train 7.071736 (lr=6.2790e-05) (hash(x)=6987352) +924 train 7.200426 (lr=6.2463e-05) (hash(x)=7179418) +925 train 6.855283 (lr=6.2140e-05) (hash(x)=5413904) +926 train 7.276327 (lr=6.1822e-05) (hash(x)=6028105) +927 train 7.173356 (lr=6.1507e-05) (hash(x)=6732924) +928 train 7.059677 (lr=6.1197e-05) (hash(x)=4547651) +929 train 7.211281 (lr=6.0890e-05) (hash(x)=6219754) +930 train 6.990976 (lr=6.0588e-05) (hash(x)=7465186) +931 train 7.144866 (lr=6.0290e-05) (hash(x)=6839070) +932 train 7.010251 (lr=5.9996e-05) (hash(x)=5390324) +933 train 6.991083 (lr=5.9706e-05) (hash(x)=6090120) +934 train 7.616641 (lr=5.9421e-05) (hash(x)=7123181) +935 train 7.273526 (lr=5.9139e-05) (hash(x)=7115176) +936 train 7.296881 (lr=5.8862e-05) (hash(x)=7016990) +937 train 7.058184 (lr=5.8589e-05) (hash(x)=4989299) +938 train 7.073798 (lr=5.8320e-05) (hash(x)=6783311) +939 train 7.052233 (lr=5.8056e-05) (hash(x)=7497590) +940 train 7.281614 (lr=5.7795e-05) (hash(x)=6767514) +941 train 7.035194 (lr=5.7539e-05) (hash(x)=3977557) +942 train 7.162869 (lr=5.7287e-05) (hash(x)=4806492) +943 train 7.067997 (lr=5.7039e-05) (hash(x)=5524165) +944 train 7.112118 (lr=5.6796e-05) (hash(x)=4930752) +945 train 7.074996 (lr=5.6556e-05) (hash(x)=5124936) +946 train 6.971954 (lr=5.6321e-05) (hash(x)=6877351) +947 train 7.257543 (lr=5.6090e-05) (hash(x)=5522119) +948 train 7.062779 (lr=5.5864e-05) (hash(x)=6183512) +949 train 6.978442 (lr=5.5641e-05) (hash(x)=5030865) +950 val loss 7.1423 +950 val perplexity 1264.2904 +950 train 7.086110 (lr=5.5423e-05) (hash(x)=6619812) +951 train 7.082719 (lr=5.5209e-05) (hash(x)=6411783) +952 train 7.064824 (lr=5.4999e-05) (hash(x)=6748982) +953 train 6.989625 (lr=5.4794e-05) (hash(x)=6581937) +954 train 7.079334 (lr=5.4593e-05) (hash(x)=7881022) +955 train 7.051720 (lr=5.4396e-05) (hash(x)=5116910) +956 train 6.848124 (lr=5.4203e-05) (hash(x)=4880833) +957 train 6.889359 (lr=5.4015e-05) (hash(x)=7353459) +958 train 6.970458 (lr=5.3831e-05) (hash(x)=4951302) +959 train 6.875148 (lr=5.3651e-05) (hash(x)=6344535) +960 train 7.445865 (lr=5.3476e-05) (hash(x)=7411763) +961 train 7.050831 (lr=5.3305e-05) (hash(x)=5840169) +962 train 7.157571 (lr=5.3138e-05) (hash(x)=5784788) +963 train 6.964265 (lr=5.2975e-05) (hash(x)=6754290) +964 train 7.238569 (lr=5.2817e-05) (hash(x)=6369963) +965 train 7.312208 (lr=5.2663e-05) (hash(x)=6484573) +966 train 6.905547 (lr=5.2513e-05) (hash(x)=6516338) +967 train 6.932100 (lr=5.2368e-05) (hash(x)=5260125) +968 train 7.068916 (lr=5.2227e-05) (hash(x)=5781624) +969 train 6.864578 (lr=5.2090e-05) (hash(x)=4881179) +970 train 6.981455 (lr=5.1957e-05) (hash(x)=6707821) +971 train 7.115916 (lr=5.1829e-05) (hash(x)=5001634) +972 train 7.000066 (lr=5.1705e-05) (hash(x)=4402949) +973 train 7.013063 (lr=5.1586e-05) (hash(x)=7424810) +974 train 6.891196 (lr=5.1471e-05) (hash(x)=4814803) +975 train 6.813814 (lr=5.1360e-05) (hash(x)=5176431) +976 train 7.008841 (lr=5.1253e-05) (hash(x)=5769393) +977 train 6.944740 (lr=5.1151e-05) (hash(x)=5421624) +978 train 7.156435 (lr=5.1053e-05) (hash(x)=5999773) +979 train 6.863198 (lr=5.0960e-05) (hash(x)=5674439) +980 train 6.959261 (lr=5.0871e-05) (hash(x)=6345351) +981 train 6.922173 (lr=5.0786e-05) (hash(x)=5819157) +982 train 7.106555 (lr=5.0705e-05) (hash(x)=11159355) +983 train 7.081688 (lr=5.0629e-05) (hash(x)=6506856) +984 train 7.006543 (lr=5.0557e-05) (hash(x)=6331023) +985 train 6.903501 (lr=5.0490e-05) (hash(x)=6119124) +986 train 7.097688 (lr=5.0427e-05) (hash(x)=8142528) +987 train 7.290154 (lr=5.0368e-05) (hash(x)=6241669) +988 train 6.921596 (lr=5.0314e-05) (hash(x)=3852991) +989 train 6.673730 (lr=5.0263e-05) (hash(x)=4992756) +990 train 7.355527 (lr=5.0218e-05) (hash(x)=7097145) +991 train 7.128623 (lr=5.0176e-05) (hash(x)=7277927) +992 train 7.219755 (lr=5.0139e-05) (hash(x)=5661400) +993 train 7.122837 (lr=5.0107e-05) (hash(x)=6622097) +994 train 7.259983 (lr=5.0078e-05) (hash(x)=5016804) +995 train 7.339842 (lr=5.0054e-05) (hash(x)=7026582) +996 train 7.107574 (lr=5.0035e-05) (hash(x)=5639136) +997 train 7.263753 (lr=5.0020e-05) (hash(x)=5840987) +998 train 6.883562 (lr=5.0009e-05) (hash(x)=5265410) +999 val loss 7.1431 +999 val perplexity 1265.3368 +999 train 6.887639 (lr=5.0002e-05) (hash(x)=4351074)