diff --git "a/lr6e-4_total_batch_size20480_seq_len128/log2.txt" "b/lr6e-4_total_batch_size20480_seq_len128/log2.txt" --- "a/lr6e-4_total_batch_size20480_seq_len128/log2.txt" +++ "b/lr6e-4_total_batch_size20480_seq_len128/log2.txt" @@ -10,1034 +10,1034 @@ max_steps: 1000 6 train 11.556558 (lr=1.4685e-05) (hash(x)=4696943) 7 train 11.504883 (lr=1.6783e-05) (hash(x)=6219138) 8 train 11.424795 (lr=1.8881e-05) (hash(x)=6049878) -9 train 11.399450 (lr=2.0979e-05) (hash(x)=5491972) -10 train 11.321382 (lr=2.3077e-05) (hash(x)=8075458) -11 train 11.218025 (lr=2.5175e-05) (hash(x)=5917741) -12 train 11.168683 (lr=2.7273e-05) (hash(x)=5750403) -13 train 11.092779 (lr=2.9371e-05) (hash(x)=6112458) -14 train 11.031763 (lr=3.1469e-05) (hash(x)=5806490) -15 train 10.914715 (lr=3.3566e-05) (hash(x)=6568379) -16 train 10.824193 (lr=3.5664e-05) (hash(x)=7212403) -17 train 10.762385 (lr=3.7762e-05) (hash(x)=7386082) -18 train 10.689731 (lr=3.9860e-05) (hash(x)=6359743) -19 train 10.633512 (lr=4.1958e-05) (hash(x)=6151674) -20 train 10.609541 (lr=4.4056e-05) (hash(x)=7168704) -21 train 10.560685 (lr=4.6154e-05) (hash(x)=7859060) -22 train 10.487794 (lr=4.8252e-05) (hash(x)=6976239) -23 train 10.479760 (lr=5.0350e-05) (hash(x)=6391506) -24 train 10.468954 (lr=5.2448e-05) (hash(x)=5245999) -25 train 10.421699 (lr=5.4545e-05) (hash(x)=5985675) -26 train 10.332866 (lr=5.6643e-05) (hash(x)=4355733) -27 train 10.504283 (lr=5.8741e-05) (hash(x)=6984772) -28 train 10.353855 (lr=6.0839e-05) (hash(x)=6244096) -29 train 10.374558 (lr=6.2937e-05) (hash(x)=6603717) -30 train 10.280658 (lr=6.5035e-05) (hash(x)=5669522) -31 train 10.258889 (lr=6.7133e-05) (hash(x)=6190579) -32 train 10.318835 (lr=6.9231e-05) (hash(x)=4912983) -33 train 10.189525 (lr=7.1329e-05) (hash(x)=7276303) -34 train 10.252820 (lr=7.3427e-05) (hash(x)=5479947) -35 train 10.347001 (lr=7.5524e-05) (hash(x)=6630378) -36 train 10.270600 (lr=7.7622e-05) (hash(x)=8097010) -37 train 10.325130 (lr=7.9720e-05) (hash(x)=9989744) -38 train 10.191603 (lr=8.1818e-05) (hash(x)=6694932) -39 train 10.117285 (lr=8.3916e-05) (hash(x)=6317894) -40 train 10.018936 (lr=8.6014e-05) (hash(x)=5046327) -41 train 10.081988 (lr=8.8112e-05) (hash(x)=7947703) -42 train 9.935648 (lr=9.0210e-05) (hash(x)=5916068) -43 train 10.025830 (lr=9.2308e-05) (hash(x)=5777498) -44 train 9.942770 (lr=9.4406e-05) (hash(x)=5753092) -45 train 9.906315 (lr=9.6503e-05) (hash(x)=7723226) -46 train 9.879588 (lr=9.8601e-05) (hash(x)=7007016) -47 train 9.786048 (lr=1.0070e-04) (hash(x)=6491229) -48 train 9.814020 (lr=1.0280e-04) (hash(x)=6390752) -49 train 9.911051 (lr=1.0490e-04) (hash(x)=6019389) -50 val loss 9.7619 -50 val perplexity 17359.5156 -50 train 9.756538 (lr=1.0699e-04) (hash(x)=7662067) -51 train 9.734842 (lr=1.0909e-04) (hash(x)=4648609) -52 train 9.649823 (lr=1.1119e-04) (hash(x)=4725966) -53 train 9.586785 (lr=1.1329e-04) (hash(x)=5558355) -54 train 9.607746 (lr=1.1538e-04) (hash(x)=6524933) -55 train 9.544440 (lr=1.1748e-04) (hash(x)=6369326) -56 train 9.485706 (lr=1.1958e-04) (hash(x)=6022625) -57 train 9.400290 (lr=1.2168e-04) (hash(x)=4906853) -58 train 9.194029 (lr=1.2378e-04) (hash(x)=5589269) -59 train 9.299592 (lr=1.2587e-04) (hash(x)=6437376) -60 train 9.329102 (lr=1.2797e-04) (hash(x)=7304892) -61 train 9.268149 (lr=1.3007e-04) (hash(x)=7084093) -62 train 9.262506 (lr=1.3217e-04) (hash(x)=5908178) -63 train 9.017707 (lr=1.3427e-04) (hash(x)=7048804) -64 train 9.079869 (lr=1.3636e-04) (hash(x)=6085549) -65 train 9.080568 (lr=1.3846e-04) (hash(x)=5752594) -66 train 8.854486 (lr=1.4056e-04) (hash(x)=7662769) -67 train 8.702577 (lr=1.4266e-04) (hash(x)=6393520) -68 train 8.934906 (lr=1.4476e-04) (hash(x)=5942867) -69 train 8.912291 (lr=1.4685e-04) (hash(x)=6793550) -70 train 8.729600 (lr=1.4895e-04) (hash(x)=7105976) -71 train 8.747009 (lr=1.5105e-04) (hash(x)=6581348) -72 train 8.656689 (lr=1.5315e-04) (hash(x)=5555598) -73 train 8.614600 (lr=1.5524e-04) (hash(x)=6235837) -74 train 8.536751 (lr=1.5734e-04) (hash(x)=5591770) -75 train 8.758008 (lr=1.5944e-04) (hash(x)=7083021) -76 train 8.594731 (lr=1.6154e-04) (hash(x)=7281348) -77 train 8.643272 (lr=1.6364e-04) (hash(x)=6155821) -78 train 8.458706 (lr=1.6573e-04) (hash(x)=5736241) -79 train 8.366180 (lr=1.6783e-04) (hash(x)=5657123) -80 train 8.340291 (lr=1.6993e-04) (hash(x)=6452095) -81 train 8.261395 (lr=1.7203e-04) (hash(x)=5312267) -82 train 8.100721 (lr=1.7413e-04) (hash(x)=5434493) -83 train 8.352497 (lr=1.7622e-04) (hash(x)=6830813) -84 train 8.178012 (lr=1.7832e-04) (hash(x)=4752771) -85 train 8.282215 (lr=1.8042e-04) (hash(x)=6424933) -86 train 8.196641 (lr=1.8252e-04) (hash(x)=5786517) -87 train 8.275944 (lr=1.8462e-04) (hash(x)=6680023) -88 train 8.183519 (lr=1.8671e-04) (hash(x)=6474729) -89 train 8.204452 (lr=1.8881e-04) (hash(x)=7523279) -90 train 7.996569 (lr=1.9091e-04) (hash(x)=5508768) -91 train 8.188123 (lr=1.9301e-04) (hash(x)=6635925) -92 train 8.069695 (lr=1.9510e-04) (hash(x)=6663801) -93 train 8.044952 (lr=1.9720e-04) (hash(x)=5869441) -94 train 8.103032 (lr=1.9930e-04) (hash(x)=6698878) -95 train 8.019039 (lr=2.0140e-04) (hash(x)=6349004) -96 train 8.017328 (lr=2.0350e-04) (hash(x)=4986137) -97 train 7.808747 (lr=2.0559e-04) (hash(x)=6008454) -98 train 7.879772 (lr=2.0769e-04) (hash(x)=6550770) -99 train 8.014522 (lr=2.0979e-04) (hash(x)=7682741) -100 val loss 7.9707 -100 val perplexity 2894.9226 -100 train 8.070560 (lr=2.1189e-04) (hash(x)=7892158) -101 train 7.940425 (lr=2.1399e-04) (hash(x)=7794028) -102 train 7.933344 (lr=2.1608e-04) (hash(x)=7093523) -103 train 7.980068 (lr=2.1818e-04) (hash(x)=6166062) -104 train 7.918315 (lr=2.2028e-04) (hash(x)=6645781) -105 train 7.886864 (lr=2.2238e-04) (hash(x)=4811192) -106 train 7.809242 (lr=2.2448e-04) (hash(x)=5970866) -107 train 7.818639 (lr=2.2657e-04) (hash(x)=7822680) -108 train 7.782276 (lr=2.2867e-04) (hash(x)=6317317) -109 train 7.880509 (lr=2.3077e-04) (hash(x)=6431409) -110 train 7.896371 (lr=2.3287e-04) (hash(x)=6653337) -111 train 7.825218 (lr=2.3497e-04) (hash(x)=5323032) -112 train 7.722114 (lr=2.3706e-04) (hash(x)=5125339) -113 train 7.667290 (lr=2.3916e-04) (hash(x)=7363286) -114 train 8.025681 (lr=2.4126e-04) (hash(x)=7670050) -115 train 7.791495 (lr=2.4336e-04) (hash(x)=5616075) -116 train 7.844471 (lr=2.4545e-04) (hash(x)=6593764) -117 train 7.914949 (lr=2.4755e-04) (hash(x)=5672608) -118 train 7.744909 (lr=2.4965e-04) (hash(x)=6828653) -119 train 7.746331 (lr=2.5175e-04) (hash(x)=6839867) -120 train 7.873523 (lr=2.5385e-04) (hash(x)=8426992) -121 train 7.546752 (lr=2.5594e-04) (hash(x)=4916928) -122 train 7.755312 (lr=2.5804e-04) (hash(x)=6484050) -123 train 7.837285 (lr=2.6014e-04) (hash(x)=8353379) -124 train 7.757292 (lr=2.6224e-04) (hash(x)=6552510) -125 train 7.735661 (lr=2.6434e-04) (hash(x)=4838871) -126 train 7.468061 (lr=2.6643e-04) (hash(x)=3021697) -127 train 7.626331 (lr=2.6853e-04) (hash(x)=6795665) -128 train 7.649026 (lr=2.7063e-04) (hash(x)=5486935) -129 train 7.834298 (lr=2.7273e-04) (hash(x)=6678038) -130 train 7.862762 (lr=2.7483e-04) (hash(x)=6657714) -131 train 7.731431 (lr=2.7692e-04) (hash(x)=6112215) -132 train 7.785623 (lr=2.7902e-04) (hash(x)=8353143) -133 train 7.810211 (lr=2.8112e-04) (hash(x)=5915361) -134 train 7.724842 (lr=2.8322e-04) (hash(x)=6254885) -135 train 7.725986 (lr=2.8531e-04) (hash(x)=5771588) -136 train 7.697923 (lr=2.8741e-04) (hash(x)=5561507) -137 train 7.665032 (lr=2.8951e-04) (hash(x)=5688829) -138 train 7.640872 (lr=2.9161e-04) (hash(x)=5371951) -139 train 7.810389 (lr=2.9371e-04) (hash(x)=5443305) -140 train 7.785834 (lr=2.9580e-04) (hash(x)=5016757) -141 train 7.787242 (lr=2.9790e-04) (hash(x)=6901933) -142 train 7.758804 (lr=3.0000e-04) (hash(x)=6019085) -143 train 7.603468 (lr=3.0210e-04) (hash(x)=4294425) -144 train 7.699917 (lr=3.0420e-04) (hash(x)=6095229) -145 train 7.537947 (lr=3.0629e-04) (hash(x)=4363941) -146 train 7.617387 (lr=3.0839e-04) (hash(x)=4693798) -147 train 8.164754 (lr=3.1049e-04) (hash(x)=5486335) -148 train 7.974043 (lr=3.1259e-04) (hash(x)=7907450) -149 train 7.805943 (lr=3.1469e-04) (hash(x)=7295165) -150 val loss 7.6933 -150 val perplexity 2193.6753 -150 train 7.738387 (lr=3.1678e-04) (hash(x)=6814026) -151 train 7.818550 (lr=3.1888e-04) (hash(x)=6267424) -152 train 7.825542 (lr=3.2098e-04) (hash(x)=8086437) -153 train 7.876915 (lr=3.2308e-04) (hash(x)=5270452) -154 train 7.717978 (lr=3.2517e-04) (hash(x)=6420820) -155 train 7.604784 (lr=3.2727e-04) (hash(x)=6305297) -156 train 7.771953 (lr=3.2937e-04) (hash(x)=7889849) -157 train 8.124987 (lr=3.3147e-04) (hash(x)=6040077) -158 train 8.112553 (lr=3.3357e-04) (hash(x)=5652497) -159 train 7.707443 (lr=3.3566e-04) (hash(x)=7130251) -160 train 7.572378 (lr=3.3776e-04) (hash(x)=6610177) -161 train 7.636499 (lr=3.3986e-04) (hash(x)=6508350) -162 train 7.788102 (lr=3.4196e-04) (hash(x)=6994983) -163 train 7.744952 (lr=3.4406e-04) (hash(x)=5859576) -164 train 7.304287 (lr=3.4615e-04) (hash(x)=5487065) -165 train 7.537818 (lr=3.4825e-04) (hash(x)=4892065) -166 train 7.439801 (lr=3.5035e-04) (hash(x)=4933674) -167 train 7.709087 (lr=3.5245e-04) (hash(x)=7317289) -168 train 7.810067 (lr=3.5455e-04) (hash(x)=6811522) -169 train 7.639495 (lr=3.5664e-04) (hash(x)=5510218) -170 train 7.800025 (lr=3.5874e-04) (hash(x)=7304235) -171 train 7.956987 (lr=3.6084e-04) (hash(x)=6752265) -172 train 7.660645 (lr=3.6294e-04) (hash(x)=5994476) -173 train 7.622958 (lr=3.6503e-04) (hash(x)=6530867) -174 train 7.724622 (lr=3.6713e-04) (hash(x)=5746260) -175 train 7.680183 (lr=3.6923e-04) (hash(x)=5790078) -176 train 7.700298 (lr=3.7133e-04) (hash(x)=6430135) -177 train 7.769589 (lr=3.7343e-04) (hash(x)=7614023) -178 train 7.755341 (lr=3.7552e-04) (hash(x)=5244861) -179 train 7.741224 (lr=3.7762e-04) (hash(x)=5245146) -180 train 7.632860 (lr=3.7972e-04) (hash(x)=6415565) -181 train 7.684500 (lr=3.8182e-04) (hash(x)=5786972) -182 train 7.722946 (lr=3.8392e-04) (hash(x)=6131703) -183 train 7.754008 (lr=3.8601e-04) (hash(x)=6346459) -184 train 7.784397 (lr=3.8811e-04) (hash(x)=6504131) -185 train 7.767685 (lr=3.9021e-04) (hash(x)=5209234) -186 train 7.668563 (lr=3.9231e-04) (hash(x)=6163272) -187 train 7.676054 (lr=3.9441e-04) (hash(x)=5676768) -188 train 7.745142 (lr=3.9650e-04) (hash(x)=6090561) -189 train 7.885430 (lr=3.9860e-04) (hash(x)=5863092) -190 train 7.799054 (lr=4.0070e-04) (hash(x)=7201312) -191 train 7.888859 (lr=4.0280e-04) (hash(x)=7019489) -192 train 7.651678 (lr=4.0490e-04) (hash(x)=6225608) -193 train 7.722473 (lr=4.0699e-04) (hash(x)=5483019) -194 train 7.673765 (lr=4.0909e-04) (hash(x)=5903258) -195 train 7.713775 (lr=4.1119e-04) (hash(x)=5968716) -196 train 7.700187 (lr=4.1329e-04) (hash(x)=5778017) -197 train 7.435637 (lr=4.1538e-04) (hash(x)=7780194) -198 train 7.640100 (lr=4.1748e-04) (hash(x)=6140998) -199 train 7.632166 (lr=4.1958e-04) (hash(x)=3784321) -200 val loss 7.6571 -200 val perplexity 2115.7114 -200 train 7.650524 (lr=4.2168e-04) (hash(x)=5860821) -201 train 7.712367 (lr=4.2378e-04) (hash(x)=7774109) -202 train 7.875457 (lr=4.2587e-04) (hash(x)=7997664) -203 train 7.848608 (lr=4.2797e-04) (hash(x)=6576749) -204 train 7.761374 (lr=4.3007e-04) (hash(x)=7266655) -205 train 7.724911 (lr=4.3217e-04) (hash(x)=7072404) -206 train 7.627774 (lr=4.3427e-04) (hash(x)=6626459) -207 train 7.647211 (lr=4.3636e-04) (hash(x)=6556025) -208 train 7.682404 (lr=4.3846e-04) (hash(x)=5942129) -209 train 7.794866 (lr=4.4056e-04) (hash(x)=7325027) -210 train 7.780463 (lr=4.4266e-04) (hash(x)=7322467) -211 train 7.711524 (lr=4.4476e-04) (hash(x)=6373412) -212 train 7.501585 (lr=4.4685e-04) (hash(x)=7332255) -213 train 7.783019 (lr=4.4895e-04) (hash(x)=5262868) -214 train 7.489666 (lr=4.5105e-04) (hash(x)=5688247) -215 train 7.653491 (lr=4.5315e-04) (hash(x)=8055563) -216 train 7.696162 (lr=4.5524e-04) (hash(x)=5352405) -217 train 7.738225 (lr=4.5734e-04) (hash(x)=5932790) -218 train 7.673267 (lr=4.5944e-04) (hash(x)=6249312) -219 train 7.632036 (lr=4.6154e-04) (hash(x)=5680154) -220 train 7.737161 (lr=4.6364e-04) (hash(x)=8156280) -221 train 7.684314 (lr=4.6573e-04) (hash(x)=5914217) -222 train 7.527965 (lr=4.6783e-04) (hash(x)=7120215) -223 train 7.698344 (lr=4.6993e-04) (hash(x)=6424128) -224 train 7.462379 (lr=4.7203e-04) (hash(x)=4390027) -225 train 7.670824 (lr=4.7413e-04) (hash(x)=7804089) -226 train 7.782909 (lr=4.7622e-04) (hash(x)=7130267) -227 train 7.552779 (lr=4.7832e-04) (hash(x)=6490149) -228 train 7.619543 (lr=4.8042e-04) (hash(x)=9276378) -229 train 7.649869 (lr=4.8252e-04) (hash(x)=6283540) -230 train 7.624301 (lr=4.8462e-04) (hash(x)=5781680) -231 train 7.572819 (lr=4.8671e-04) (hash(x)=5728337) -232 train 7.556737 (lr=4.8881e-04) (hash(x)=6278202) -233 train 7.643196 (lr=4.9091e-04) (hash(x)=7400272) -234 train 7.610126 (lr=4.9301e-04) (hash(x)=5795128) -235 train 7.590264 (lr=4.9510e-04) (hash(x)=6473432) -236 train 7.608821 (lr=4.9720e-04) (hash(x)=5201502) -237 train 7.847617 (lr=4.9930e-04) (hash(x)=6922646) -238 train 7.564544 (lr=5.0140e-04) (hash(x)=5484641) -239 train 7.620001 (lr=5.0350e-04) (hash(x)=7277141) -240 train 7.646079 (lr=5.0559e-04) (hash(x)=5604614) -241 train 7.685642 (lr=5.0769e-04) (hash(x)=7443124) -242 train 7.688267 (lr=5.0979e-04) (hash(x)=5601968) -243 train 7.573340 (lr=5.1189e-04) (hash(x)=5632735) -244 train 7.594320 (lr=5.1399e-04) (hash(x)=5594810) -245 train 7.434153 (lr=5.1608e-04) (hash(x)=5881015) -246 train 7.561196 (lr=5.1818e-04) (hash(x)=6865361) -247 train 7.664344 (lr=5.2028e-04) (hash(x)=5809411) -248 train 7.645874 (lr=5.2238e-04) (hash(x)=6293025) -249 train 7.589986 (lr=5.2448e-04) (hash(x)=7232964) -250 val loss 7.5984 -250 val perplexity 1995.0034 -250 train 7.527665 (lr=5.2657e-04) (hash(x)=5646619) -251 train 7.642452 (lr=5.2867e-04) (hash(x)=6171829) -252 train 7.694654 (lr=5.3077e-04) (hash(x)=7787552) -253 train 7.642994 (lr=5.3287e-04) (hash(x)=5884456) -254 train 7.670448 (lr=5.3497e-04) (hash(x)=6752162) -255 train 7.585383 (lr=5.3706e-04) (hash(x)=5077031) -256 train 7.768045 (lr=5.3916e-04) (hash(x)=6883481) -257 train 7.629124 (lr=5.4126e-04) (hash(x)=6248895) -258 train 7.514213 (lr=5.4336e-04) (hash(x)=6636615) -259 train 7.706795 (lr=5.4545e-04) (hash(x)=6918004) -260 train 7.621819 (lr=5.4755e-04) (hash(x)=7302874) -261 train 7.727994 (lr=5.4965e-04) (hash(x)=6482466) -262 train 7.571028 (lr=5.5175e-04) (hash(x)=7298317) -263 train 7.595658 (lr=5.5385e-04) (hash(x)=6588573) -264 train 7.590421 (lr=5.5594e-04) (hash(x)=6229630) -265 train 7.654818 (lr=5.5804e-04) (hash(x)=6136939) -266 train 7.409466 (lr=5.6014e-04) (hash(x)=6394645) -267 train 7.650968 (lr=5.6224e-04) (hash(x)=7040157) -268 train 7.685484 (lr=5.6434e-04) (hash(x)=7041858) -269 train 7.590397 (lr=5.6643e-04) (hash(x)=6455595) -270 train 7.526274 (lr=5.6853e-04) (hash(x)=6480443) -271 train 7.717497 (lr=5.7063e-04) (hash(x)=4122983) -272 train 7.519444 (lr=5.7273e-04) (hash(x)=7672190) -273 train 7.560659 (lr=5.7483e-04) (hash(x)=4724052) -274 train 7.504530 (lr=5.7692e-04) (hash(x)=6654267) -275 train 7.497781 (lr=5.7902e-04) (hash(x)=6820797) -276 train 7.565026 (lr=5.8112e-04) (hash(x)=6458662) -277 train 7.988827 (lr=5.8322e-04) (hash(x)=7477594) -278 train 7.661254 (lr=5.8531e-04) (hash(x)=5876574) -279 train 7.362312 (lr=5.8741e-04) (hash(x)=6146305) -280 train 7.524668 (lr=5.8951e-04) (hash(x)=6162080) -281 train 7.482239 (lr=5.9161e-04) (hash(x)=6814831) -282 train 7.626757 (lr=5.9371e-04) (hash(x)=7138295) -283 train 7.402195 (lr=5.9580e-04) (hash(x)=5548298) -284 train 7.490658 (lr=5.9790e-04) (hash(x)=6265078) -285 train 7.874024 (lr=6.0000e-04) (hash(x)=7609416) -286 train 7.555768 (lr=6.0000e-04) (hash(x)=6909367) -287 train 7.676691 (lr=6.0000e-04) (hash(x)=7574342) -288 train 7.471145 (lr=5.9999e-04) (hash(x)=8859748) -289 train 7.437964 (lr=5.9998e-04) (hash(x)=5906937) -290 train 7.475700 (lr=5.9996e-04) (hash(x)=7243024) -291 train 7.579866 (lr=5.9993e-04) (hash(x)=8013471) -292 train 7.490800 (lr=5.9991e-04) (hash(x)=5659461) -293 train 7.555206 (lr=5.9987e-04) (hash(x)=6146213) -294 train 7.571939 (lr=5.9983e-04) (hash(x)=6602917) -295 train 7.492304 (lr=5.9979e-04) (hash(x)=6709902) -296 train 7.608312 (lr=5.9974e-04) (hash(x)=8154341) -297 train 7.744592 (lr=5.9968e-04) (hash(x)=6402571) -298 train 7.495922 (lr=5.9962e-04) (hash(x)=5605466) -299 train 7.456540 (lr=5.9956e-04) (hash(x)=7683614) -300 val loss 7.5021 -300 val perplexity 1811.8381 -300 train 7.545509 (lr=5.9949e-04) (hash(x)=5421572) -301 train 7.393278 (lr=5.9941e-04) (hash(x)=5453026) -302 train 7.454529 (lr=5.9933e-04) (hash(x)=6437746) -303 train 7.384210 (lr=5.9925e-04) (hash(x)=6260017) -304 train 7.468595 (lr=5.9915e-04) (hash(x)=6119053) -305 train 7.639496 (lr=5.9906e-04) (hash(x)=6591466) -306 train 7.565525 (lr=5.9896e-04) (hash(x)=5652701) -307 train 7.521061 (lr=5.9885e-04) (hash(x)=5501472) -308 train 7.706266 (lr=5.9874e-04) (hash(x)=6160695) -309 train 7.445512 (lr=5.9862e-04) (hash(x)=5871698) -310 train 7.426938 (lr=5.9850e-04) (hash(x)=7301184) -311 train 7.362667 (lr=5.9837e-04) (hash(x)=4282052) -312 train 7.575198 (lr=5.9824e-04) (hash(x)=5679330) -313 train 7.427068 (lr=5.9810e-04) (hash(x)=7824660) -314 train 7.480555 (lr=5.9795e-04) (hash(x)=4857318) -315 train 7.393532 (lr=5.9780e-04) (hash(x)=5954950) -316 train 7.460410 (lr=5.9765e-04) (hash(x)=5758178) -317 train 7.485731 (lr=5.9749e-04) (hash(x)=5484656) -318 train 7.496554 (lr=5.9733e-04) (hash(x)=6818913) -319 train 7.690413 (lr=5.9716e-04) (hash(x)=7031328) -320 train 7.540304 (lr=5.9698e-04) (hash(x)=6837621) -321 train 7.554158 (lr=5.9680e-04) (hash(x)=9157069) -322 train 7.795562 (lr=5.9662e-04) (hash(x)=6509536) -323 train 7.489796 (lr=5.9643e-04) (hash(x)=5996883) -324 train 7.722128 (lr=5.9623e-04) (hash(x)=6850868) -325 train 7.660053 (lr=5.9603e-04) (hash(x)=7645447) -326 train 7.658932 (lr=5.9583e-04) (hash(x)=6717515) -327 train 7.763359 (lr=5.9562e-04) (hash(x)=6336164) -328 train 7.496643 (lr=5.9540e-04) (hash(x)=6897445) -329 train 7.418449 (lr=5.9518e-04) (hash(x)=5224240) -330 train 7.554682 (lr=5.9496e-04) (hash(x)=6612945) -331 train 7.998134 (lr=5.9472e-04) (hash(x)=5447801) -332 train 7.550564 (lr=5.9449e-04) (hash(x)=7308579) -333 train 7.430622 (lr=5.9425e-04) (hash(x)=4155598) -334 train 7.454174 (lr=5.9400e-04) (hash(x)=6106773) -335 train 7.510879 (lr=5.9375e-04) (hash(x)=7482744) -336 train 7.552884 (lr=5.9349e-04) (hash(x)=6310687) -337 train 7.433215 (lr=5.9323e-04) (hash(x)=4733414) -338 train 7.544614 (lr=5.9296e-04) (hash(x)=6979734) -339 train 7.365823 (lr=5.9269e-04) (hash(x)=7806284) -340 train 7.376942 (lr=5.9241e-04) (hash(x)=5080536) -341 train 7.578179 (lr=5.9213e-04) (hash(x)=7236478) -342 train 7.517932 (lr=5.9185e-04) (hash(x)=6619318) -343 train 7.446670 (lr=5.9155e-04) (hash(x)=4656255) -344 train 7.389146 (lr=5.9126e-04) (hash(x)=5546888) -345 train 7.812582 (lr=5.9095e-04) (hash(x)=9298325) -346 train 7.525166 (lr=5.9065e-04) (hash(x)=5994232) -347 train 7.501871 (lr=5.9033e-04) (hash(x)=6287524) -348 train 7.623867 (lr=5.9002e-04) (hash(x)=6200049) -349 train 7.513824 (lr=5.8969e-04) (hash(x)=7895970) -350 val loss 7.4525 -350 val perplexity 1724.0956 -350 train 7.429665 (lr=5.8937e-04) (hash(x)=6051847) -351 train 7.600766 (lr=5.8903e-04) (hash(x)=8847992) -352 train 7.969036 (lr=5.8869e-04) (hash(x)=5123883) -353 train 7.567740 (lr=5.8835e-04) (hash(x)=6338998) -354 train 7.541628 (lr=5.8800e-04) (hash(x)=5765866) -355 train 7.858485 (lr=5.8765e-04) (hash(x)=7104011) -356 train 7.639140 (lr=5.8729e-04) (hash(x)=7438267) -357 train 7.351393 (lr=5.8693e-04) (hash(x)=5573214) -358 train 7.638958 (lr=5.8656e-04) (hash(x)=6897283) -359 train 7.435463 (lr=5.8619e-04) (hash(x)=6882897) -360 train 7.536877 (lr=5.8581e-04) (hash(x)=5343615) -361 train 7.447063 (lr=5.8543e-04) (hash(x)=5854242) -362 train 7.363630 (lr=5.8504e-04) (hash(x)=6317324) -363 train 7.303843 (lr=5.8465e-04) (hash(x)=6972494) -364 train 7.378379 (lr=5.8425e-04) (hash(x)=5661167) -365 train 7.406442 (lr=5.8385e-04) (hash(x)=6796805) -366 train 7.236358 (lr=5.8345e-04) (hash(x)=5817209) -367 train 7.316934 (lr=5.8303e-04) (hash(x)=6139120) -368 train 7.468953 (lr=5.8262e-04) (hash(x)=6121296) -369 train 7.448250 (lr=5.8219e-04) (hash(x)=6486796) -370 train 7.379686 (lr=5.8177e-04) (hash(x)=5514645) -371 train 7.305516 (lr=5.8134e-04) (hash(x)=5578797) -372 train 7.298994 (lr=5.8090e-04) (hash(x)=7651738) -373 train 7.493082 (lr=5.8046e-04) (hash(x)=6895326) -374 train 7.509957 (lr=5.8001e-04) (hash(x)=5490256) -375 train 7.409189 (lr=5.7956e-04) (hash(x)=7783160) -376 train 7.629080 (lr=5.7911e-04) (hash(x)=5608424) -377 train 7.391338 (lr=5.7864e-04) (hash(x)=4867625) -378 train 7.285182 (lr=5.7818e-04) (hash(x)=4655472) -379 train 7.368536 (lr=5.7771e-04) (hash(x)=6631123) -380 train 7.065244 (lr=5.7723e-04) (hash(x)=5751990) -381 train 7.326099 (lr=5.7675e-04) (hash(x)=6710965) -382 train 7.294798 (lr=5.7627e-04) (hash(x)=5293800) -383 train 7.311748 (lr=5.7578e-04) (hash(x)=6294657) -384 train 7.457703 (lr=5.7529e-04) (hash(x)=6999538) -385 train 7.446897 (lr=5.7479e-04) (hash(x)=5443606) -386 train 7.431631 (lr=5.7428e-04) (hash(x)=5650401) -387 train 7.419811 (lr=5.7377e-04) (hash(x)=7035770) -388 train 7.378371 (lr=5.7326e-04) (hash(x)=6678271) -389 train 7.578262 (lr=5.7274e-04) (hash(x)=4899541) -390 train 7.334831 (lr=5.7222e-04) (hash(x)=5359260) -391 train 7.347326 (lr=5.7169e-04) (hash(x)=6227120) -392 train 7.409576 (lr=5.7116e-04) (hash(x)=6643916) -393 train 7.482464 (lr=5.7063e-04) (hash(x)=5981648) -394 train 7.415128 (lr=5.7008e-04) (hash(x)=6467540) -395 train 7.344954 (lr=5.6954e-04) (hash(x)=5558993) -396 train 7.518650 (lr=5.6899e-04) (hash(x)=6698959) -397 train 7.346379 (lr=5.6843e-04) (hash(x)=7015671) -398 train 7.336495 (lr=5.6787e-04) (hash(x)=6800890) -399 train 7.492150 (lr=5.6731e-04) (hash(x)=5931234) -400 val loss 7.4163 -400 val perplexity 1662.9097 -400 train 7.473899 (lr=5.6674e-04) (hash(x)=3995070) -401 train 7.405529 (lr=5.6617e-04) (hash(x)=4582159) -402 train 7.444661 (lr=5.6559e-04) (hash(x)=7081906) -403 train 7.383349 (lr=5.6501e-04) (hash(x)=5029472) -404 train 7.406818 (lr=5.6442e-04) (hash(x)=3946232) -405 train 7.324516 (lr=5.6383e-04) (hash(x)=5434102) -406 train 8.035899 (lr=5.6323e-04) (hash(x)=5340646) -407 train 7.208325 (lr=5.6263e-04) (hash(x)=6810638) -408 train 7.441220 (lr=5.6202e-04) (hash(x)=6768026) -409 train 7.444545 (lr=5.6141e-04) (hash(x)=6521562) -410 train 7.406030 (lr=5.6080e-04) (hash(x)=4429434) -411 train 7.473647 (lr=5.6018e-04) (hash(x)=7226932) -412 train 7.224082 (lr=5.5956e-04) (hash(x)=5065932) -413 train 7.402736 (lr=5.5893e-04) (hash(x)=6957849) -414 train 7.380407 (lr=5.5830e-04) (hash(x)=6431457) -415 train 7.463393 (lr=5.5766e-04) (hash(x)=5334281) -416 train 7.471122 (lr=5.5702e-04) (hash(x)=5471747) -417 train 7.560372 (lr=5.5638e-04) (hash(x)=5887983) -418 train 7.458456 (lr=5.5573e-04) (hash(x)=5075909) -419 train 7.284758 (lr=5.5507e-04) (hash(x)=6393576) -420 train 7.388631 (lr=5.5441e-04) (hash(x)=6608979) -421 train 7.799415 (lr=5.5375e-04) (hash(x)=5057959) -422 train 7.733308 (lr=5.5308e-04) (hash(x)=6414858) -423 train 7.501235 (lr=5.5241e-04) (hash(x)=8595271) -424 train 7.355200 (lr=5.5174e-04) (hash(x)=6500949) -425 train 7.530478 (lr=5.5106e-04) (hash(x)=8395167) -426 train 7.651070 (lr=5.5037e-04) (hash(x)=6288420) -427 train 7.482823 (lr=5.4968e-04) (hash(x)=7634417) -428 train 7.365458 (lr=5.4899e-04) (hash(x)=6795561) -429 train 7.265526 (lr=5.4829e-04) (hash(x)=5257771) -430 train 7.415299 (lr=5.4759e-04) (hash(x)=7506860) -431 train 7.477797 (lr=5.4689e-04) (hash(x)=7674238) -432 train 7.571830 (lr=5.4618e-04) (hash(x)=5353794) -433 train 7.498618 (lr=5.4546e-04) (hash(x)=5300555) -434 train 7.222622 (lr=5.4475e-04) (hash(x)=5564419) -435 train 7.468519 (lr=5.4402e-04) (hash(x)=6066139) -436 train 7.445884 (lr=5.4330e-04) (hash(x)=6863709) -437 train 7.445212 (lr=5.4257e-04) (hash(x)=6688212) -438 train 7.601372 (lr=5.4183e-04) (hash(x)=7095090) -439 train 7.693650 (lr=5.4109e-04) (hash(x)=6642404) -440 train 7.403536 (lr=5.4035e-04) (hash(x)=6539227) -441 train 7.387924 (lr=5.3960e-04) (hash(x)=4961570) -442 train 7.336418 (lr=5.3885e-04) (hash(x)=6606391) -443 train 7.152795 (lr=5.3810e-04) (hash(x)=5105190) -444 train 7.710122 (lr=5.3734e-04) (hash(x)=5695997) -445 train 7.412235 (lr=5.3658e-04) (hash(x)=7155991) -446 train 7.391785 (lr=5.3581e-04) (hash(x)=7249727) -447 train 7.382384 (lr=5.3504e-04) (hash(x)=5132972) -448 train 7.379567 (lr=5.3426e-04) (hash(x)=5381802) -449 train 7.402682 (lr=5.3349e-04) (hash(x)=6269946) -450 val loss 7.3813 -450 val perplexity 1605.5961 -450 train 7.348353 (lr=5.3270e-04) (hash(x)=4976762) -451 train 7.441354 (lr=5.3192e-04) (hash(x)=5396133) -452 train 7.399624 (lr=5.3113e-04) (hash(x)=6173473) -453 train 7.373999 (lr=5.3033e-04) (hash(x)=6394083) -454 train 7.434234 (lr=5.2953e-04) (hash(x)=6436030) -455 train 7.304087 (lr=5.2873e-04) (hash(x)=5237804) -456 train 7.287929 (lr=5.2792e-04) (hash(x)=6540397) -457 train 7.531482 (lr=5.2711e-04) (hash(x)=5216638) -458 train 7.341828 (lr=5.2630e-04) (hash(x)=5750537) -459 train 7.325881 (lr=5.2548e-04) (hash(x)=6735565) -460 train 7.355223 (lr=5.2466e-04) (hash(x)=7297488) -461 train 7.519494 (lr=5.2384e-04) (hash(x)=5983575) -462 train 7.353300 (lr=5.2301e-04) (hash(x)=4808543) -463 train 7.451389 (lr=5.2217e-04) (hash(x)=5831619) -464 train 7.222446 (lr=5.2134e-04) (hash(x)=6280052) -465 train 7.237765 (lr=5.2050e-04) (hash(x)=9109083) -466 train 7.515056 (lr=5.1965e-04) (hash(x)=5848604) -467 train 7.420091 (lr=5.1881e-04) (hash(x)=6912967) -468 train 7.590788 (lr=5.1796e-04) (hash(x)=6615365) -469 train 7.629678 (lr=5.1710e-04) (hash(x)=5965674) -470 train 7.471103 (lr=5.1624e-04) (hash(x)=6879965) -471 train 7.474340 (lr=5.1538e-04) (hash(x)=5822533) -472 train 7.322839 (lr=5.1452e-04) (hash(x)=5794462) -473 train 7.402553 (lr=5.1365e-04) (hash(x)=5268216) -474 train 7.223906 (lr=5.1277e-04) (hash(x)=7058396) -475 train 7.320179 (lr=5.1190e-04) (hash(x)=6531900) -476 train 7.352033 (lr=5.1102e-04) (hash(x)=5878912) -477 train 7.165132 (lr=5.1013e-04) (hash(x)=5426499) -478 train 7.382191 (lr=5.0925e-04) (hash(x)=8107004) -479 train 8.164145 (lr=5.0836e-04) (hash(x)=7455372) -480 train 8.072473 (lr=5.0746e-04) (hash(x)=7727959) -481 train 7.992570 (lr=5.0657e-04) (hash(x)=8319119) -482 train 7.894061 (lr=5.0567e-04) (hash(x)=7581656) -483 train 7.942920 (lr=5.0476e-04) (hash(x)=7592128) -484 train 7.911593 (lr=5.0386e-04) (hash(x)=10506633) -485 train 7.855330 (lr=5.0295e-04) (hash(x)=8704170) -486 train 7.704393 (lr=5.0203e-04) (hash(x)=7461138) -487 train 7.667949 (lr=5.0111e-04) (hash(x)=7165037) -488 train 7.703639 (lr=5.0019e-04) (hash(x)=4976998) -489 train 7.457592 (lr=4.9927e-04) (hash(x)=7678000) -490 train 7.521662 (lr=4.9834e-04) (hash(x)=6299409) -491 train 7.461071 (lr=4.9741e-04) (hash(x)=7414788) -492 train 7.513994 (lr=4.9648e-04) (hash(x)=5063061) -493 train 7.405411 (lr=4.9554e-04) (hash(x)=7326216) -494 train 7.547427 (lr=4.9460e-04) (hash(x)=7492012) -495 train 7.518259 (lr=4.9366e-04) (hash(x)=5857162) -496 train 7.316451 (lr=4.9271e-04) (hash(x)=6169001) -497 train 9.262093 (lr=4.9176e-04) (hash(x)=14715669) -498 train 12.040575 (lr=4.9081e-04) (hash(x)=18256706) -499 train 11.780813 (lr=4.8985e-04) (hash(x)=16950560) -500 val loss 7.4213 -500 val perplexity 1671.1719 -500 train 8.108996 (lr=4.8889e-04) (hash(x)=6113563) -501 train 7.123283 (lr=4.8793e-04) (hash(x)=6159125) -502 train 7.496033 (lr=4.8697e-04) (hash(x)=5482303) -503 train 7.545724 (lr=4.8600e-04) (hash(x)=5908442) -504 train 7.393165 (lr=4.8503e-04) (hash(x)=4985045) -505 train 7.299108 (lr=4.8405e-04) (hash(x)=6668887) -506 train 7.349122 (lr=4.8308e-04) (hash(x)=6123910) -507 train 7.432206 (lr=4.8210e-04) (hash(x)=7662975) -508 train 7.376202 (lr=4.8111e-04) (hash(x)=7191898) -509 train 7.326754 (lr=4.8013e-04) (hash(x)=6669539) -510 train 7.402351 (lr=4.7914e-04) (hash(x)=6557481) -511 train 7.294858 (lr=4.7815e-04) (hash(x)=5015998) -512 train 7.359859 (lr=4.7715e-04) (hash(x)=4964540) -513 train 7.199244 (lr=4.7615e-04) (hash(x)=5458386) -514 train 7.597562 (lr=4.7515e-04) (hash(x)=6077616) -515 train 7.312298 (lr=4.7415e-04) (hash(x)=4849847) -516 train 7.373060 (lr=4.7315e-04) (hash(x)=5431422) -517 train 7.567559 (lr=4.7214e-04) (hash(x)=5125562) -518 train 7.465059 (lr=4.7113e-04) (hash(x)=5587715) -519 train 7.523211 (lr=4.7011e-04) (hash(x)=6012047) -520 train 7.347685 (lr=4.6909e-04) (hash(x)=5668436) -521 train 7.361018 (lr=4.6807e-04) (hash(x)=6079364) -522 train 7.491480 (lr=4.6705e-04) (hash(x)=5200504) -523 train 7.251234 (lr=4.6603e-04) (hash(x)=6030395) -524 train 7.475100 (lr=4.6500e-04) (hash(x)=6855319) -525 train 7.252298 (lr=4.6397e-04) (hash(x)=6781762) -526 train 7.397111 (lr=4.6294e-04) (hash(x)=6717939) -527 train 7.390493 (lr=4.6190e-04) (hash(x)=5238325) -528 train 7.305761 (lr=4.6086e-04) (hash(x)=5808069) -529 train 7.629593 (lr=4.5982e-04) (hash(x)=8611144) -530 train 7.293363 (lr=4.5878e-04) (hash(x)=6028738) -531 train 7.320099 (lr=4.5774e-04) (hash(x)=6901605) -532 train 7.285803 (lr=4.5669e-04) (hash(x)=6723307) -533 train 7.392346 (lr=4.5564e-04) (hash(x)=5499337) -534 train 7.317383 (lr=4.5458e-04) (hash(x)=6586372) -535 train 7.436609 (lr=4.5353e-04) (hash(x)=7134874) -536 train 7.328908 (lr=4.5247e-04) (hash(x)=8415623) -537 train 7.356822 (lr=4.5141e-04) (hash(x)=6149038) -538 train 7.395509 (lr=4.5035e-04) (hash(x)=6078325) -539 train 7.368484 (lr=4.4928e-04) (hash(x)=6609760) -540 train 7.260230 (lr=4.4822e-04) (hash(x)=6185253) -541 train 7.607190 (lr=4.4715e-04) (hash(x)=6652627) -542 train 7.451065 (lr=4.4608e-04) (hash(x)=7758536) -543 train 7.432088 (lr=4.4500e-04) (hash(x)=8618579) -544 train 7.384881 (lr=4.4393e-04) (hash(x)=6710226) -545 train 7.240624 (lr=4.4285e-04) (hash(x)=5896892) -546 train 7.258795 (lr=4.4177e-04) (hash(x)=6332995) -547 train 7.687635 (lr=4.4069e-04) (hash(x)=8945854) -548 train 7.238194 (lr=4.3960e-04) (hash(x)=4329129) -549 train 7.280193 (lr=4.3852e-04) (hash(x)=6775103) -550 val loss 7.2985 -550 val perplexity 1478.1306 -550 train 7.394739 (lr=4.3743e-04) (hash(x)=4465735) -551 train 7.258584 (lr=4.3634e-04) (hash(x)=6200024) -552 train 7.218898 (lr=4.3524e-04) (hash(x)=5520748) -553 train 7.240789 (lr=4.3415e-04) (hash(x)=5238139) -554 train 7.508582 (lr=4.3305e-04) (hash(x)=7639817) -555 train 7.255368 (lr=4.3195e-04) (hash(x)=5780948) -556 train 7.379350 (lr=4.3085e-04) (hash(x)=6733444) -557 train 7.327758 (lr=4.2975e-04) (hash(x)=6168407) -558 train 7.368332 (lr=4.2864e-04) (hash(x)=6680197) -559 train 7.252237 (lr=4.2754e-04) (hash(x)=3775881) -560 train 7.098436 (lr=4.2643e-04) (hash(x)=5784096) -561 train 7.550383 (lr=4.2532e-04) (hash(x)=6848709) -562 train 7.601026 (lr=4.2420e-04) (hash(x)=7449019) -563 train 7.701544 (lr=4.2309e-04) (hash(x)=6478113) -564 train 7.335200 (lr=4.2197e-04) (hash(x)=5925744) -565 train 7.400020 (lr=4.2086e-04) (hash(x)=6483914) -566 train 7.276992 (lr=4.1974e-04) (hash(x)=6010847) -567 train 7.368370 (lr=4.1861e-04) (hash(x)=5927795) -568 train 7.358539 (lr=4.1749e-04) (hash(x)=5896332) -569 train 7.321370 (lr=4.1637e-04) (hash(x)=8438033) -570 train 7.427846 (lr=4.1524e-04) (hash(x)=6081660) -571 train 7.340557 (lr=4.1411e-04) (hash(x)=5684788) -572 train 7.233648 (lr=4.1298e-04) (hash(x)=6272055) -573 train 7.190294 (lr=4.1185e-04) (hash(x)=5710182) -574 train 7.295902 (lr=4.1072e-04) (hash(x)=6219616) -575 train 7.259150 (lr=4.0958e-04) (hash(x)=6160063) -576 train 7.281532 (lr=4.0845e-04) (hash(x)=5710809) -577 train 7.027317 (lr=4.0731e-04) (hash(x)=5955100) -578 train 7.036273 (lr=4.0617e-04) (hash(x)=5356088) -579 train 7.096804 (lr=4.0503e-04) (hash(x)=6672309) -580 train 7.316266 (lr=4.0389e-04) (hash(x)=5841684) -581 train 7.673600 (lr=4.0275e-04) (hash(x)=9001564) -582 train 8.262786 (lr=4.0160e-04) (hash(x)=6897178) -583 train 7.422684 (lr=4.0045e-04) (hash(x)=5454654) -584 train 7.163071 (lr=3.9931e-04) (hash(x)=6391454) -585 train 7.222925 (lr=3.9816e-04) (hash(x)=5174062) -586 train 7.356100 (lr=3.9701e-04) (hash(x)=5197924) -587 train 7.333878 (lr=3.9586e-04) (hash(x)=6199203) -588 train 7.165671 (lr=3.9470e-04) (hash(x)=5786498) -589 train 7.305725 (lr=3.9355e-04) (hash(x)=8352747) -590 train 7.589388 (lr=3.9239e-04) (hash(x)=4829700) -591 train 7.135007 (lr=3.9124e-04) (hash(x)=4547106) -592 train 7.408190 (lr=3.9008e-04) (hash(x)=7686831) -593 train 7.281416 (lr=3.8892e-04) (hash(x)=6433099) -594 train 7.147138 (lr=3.8776e-04) (hash(x)=4826460) -595 train 7.231416 (lr=3.8660e-04) (hash(x)=6424428) -596 train 7.110586 (lr=3.8544e-04) (hash(x)=6073605) -597 train 7.457087 (lr=3.8428e-04) (hash(x)=5975712) -598 train 7.083070 (lr=3.8311e-04) (hash(x)=7030029) -599 train 7.378308 (lr=3.8195e-04) (hash(x)=5458532) -600 val loss 7.2907 -600 val perplexity 1466.6221 -600 train 7.221822 (lr=3.8078e-04) (hash(x)=7823919) -601 train 7.660409 (lr=3.7961e-04) (hash(x)=7002774) -602 train 7.456349 (lr=3.7844e-04) (hash(x)=7056399) -603 train 7.667455 (lr=3.7727e-04) (hash(x)=8206173) -604 train 7.484560 (lr=3.7610e-04) (hash(x)=8034846) -605 train 7.794947 (lr=3.7493e-04) (hash(x)=7784971) -606 train 8.001055 (lr=3.7376e-04) (hash(x)=7118076) -607 train 7.238340 (lr=3.7259e-04) (hash(x)=6001843) -608 train 7.328465 (lr=3.7142e-04) (hash(x)=5582437) -609 train 7.435714 (lr=3.7024e-04) (hash(x)=5698642) -610 train 7.306168 (lr=3.6907e-04) (hash(x)=6615301) -611 train 7.306557 (lr=3.6789e-04) (hash(x)=6600751) -612 train 7.223703 (lr=3.6671e-04) (hash(x)=6880955) -613 train 7.293599 (lr=3.6554e-04) (hash(x)=5804610) -614 train 7.200863 (lr=3.6436e-04) (hash(x)=6263347) -615 train 7.191039 (lr=3.6318e-04) (hash(x)=5162652) -616 train 7.244071 (lr=3.6200e-04) (hash(x)=6055710) -617 train 7.204926 (lr=3.6082e-04) (hash(x)=5297006) -618 train 7.209697 (lr=3.5964e-04) (hash(x)=5923648) -619 train 7.236640 (lr=3.5846e-04) (hash(x)=6728323) -620 train 7.244182 (lr=3.5728e-04) (hash(x)=6660239) -621 train 7.209693 (lr=3.5610e-04) (hash(x)=3964882) -622 train 7.266714 (lr=3.5491e-04) (hash(x)=5868942) -623 train 7.194851 (lr=3.5373e-04) (hash(x)=6735993) -624 train 7.519069 (lr=3.5255e-04) (hash(x)=5926190) -625 train 7.199207 (lr=3.5136e-04) (hash(x)=5150316) -626 train 7.213357 (lr=3.5018e-04) (hash(x)=7571467) -627 train 7.117115 (lr=3.4899e-04) (hash(x)=5220448) -628 train 7.148256 (lr=3.4781e-04) (hash(x)=6790397) -629 train 7.605984 (lr=3.4662e-04) (hash(x)=6971289) -630 train 7.542478 (lr=3.4544e-04) (hash(x)=7123359) -631 train 7.333251 (lr=3.4425e-04) (hash(x)=5012069) -632 train 7.304112 (lr=3.4306e-04) (hash(x)=6183574) -633 train 7.219798 (lr=3.4188e-04) (hash(x)=6576136) -634 train 7.243553 (lr=3.4069e-04) (hash(x)=6157346) -635 train 7.246114 (lr=3.3950e-04) (hash(x)=6077647) -636 train 7.469715 (lr=3.3831e-04) (hash(x)=8369488) -637 train 7.258065 (lr=3.3713e-04) (hash(x)=6032381) -638 train 7.215828 (lr=3.3594e-04) (hash(x)=5924756) -639 train 7.233202 (lr=3.3475e-04) (hash(x)=8410716) -640 train 7.225166 (lr=3.3356e-04) (hash(x)=5803440) -641 train 7.311962 (lr=3.3238e-04) (hash(x)=6212516) -642 train 7.378681 (lr=3.3119e-04) (hash(x)=7165945) -643 train 7.109223 (lr=3.3000e-04) (hash(x)=5298545) -644 train 7.354257 (lr=3.2881e-04) (hash(x)=6281739) -645 train 7.327255 (lr=3.2762e-04) (hash(x)=5779073) -646 train 7.199654 (lr=3.2644e-04) (hash(x)=5090107) -647 train 7.245661 (lr=3.2525e-04) (hash(x)=6340947) -648 train 6.996275 (lr=3.2406e-04) (hash(x)=4741418) -649 train 6.933474 (lr=3.2287e-04) (hash(x)=6530441) -650 val loss 7.2791 -650 val perplexity 1449.6439 -650 train 7.456884 (lr=3.2169e-04) (hash(x)=6396041) -651 train 7.136638 (lr=3.2050e-04) (hash(x)=7818007) -652 train 7.147539 (lr=3.1931e-04) (hash(x)=6478457) -653 train 7.209266 (lr=3.1812e-04) (hash(x)=6277435) -654 train 7.184879 (lr=3.1694e-04) (hash(x)=6042369) -655 train 7.198368 (lr=3.1575e-04) (hash(x)=6226320) -656 train 7.217704 (lr=3.1456e-04) (hash(x)=5826883) -657 train 7.348736 (lr=3.1338e-04) (hash(x)=5463751) -658 train 7.266311 (lr=3.1219e-04) (hash(x)=6433080) -659 train 7.115076 (lr=3.1101e-04) (hash(x)=6579329) -660 train 7.121492 (lr=3.0982e-04) (hash(x)=4724703) -661 train 7.460013 (lr=3.0864e-04) (hash(x)=6660540) -662 train 7.267281 (lr=3.0745e-04) (hash(x)=5918756) -663 train 7.206376 (lr=3.0627e-04) (hash(x)=6491272) -664 train 7.130589 (lr=3.0509e-04) (hash(x)=5452863) -665 train 7.333635 (lr=3.0390e-04) (hash(x)=6766947) -666 train 7.698385 (lr=3.0272e-04) (hash(x)=7459504) -667 train 7.339298 (lr=3.0154e-04) (hash(x)=3721218) -668 train 7.514933 (lr=3.0036e-04) (hash(x)=7929571) -669 train 7.195997 (lr=2.9918e-04) (hash(x)=5229898) -670 train 7.219360 (lr=2.9800e-04) (hash(x)=6083090) -671 train 7.084272 (lr=2.9682e-04) (hash(x)=6054428) -672 train 7.240918 (lr=2.9564e-04) (hash(x)=6072563) -673 train 7.347969 (lr=2.9446e-04) (hash(x)=6290464) -674 train 7.423286 (lr=2.9329e-04) (hash(x)=6314742) -675 train 7.103764 (lr=2.9211e-04) (hash(x)=6904498) -676 train 7.284342 (lr=2.9093e-04) (hash(x)=5378107) -677 train 7.379695 (lr=2.8976e-04) (hash(x)=7765805) -678 train 7.209647 (lr=2.8858e-04) (hash(x)=5871280) -679 train 7.352811 (lr=2.8741e-04) (hash(x)=6543764) -680 train 7.244007 (lr=2.8624e-04) (hash(x)=7369665) -681 train 7.327340 (lr=2.8507e-04) (hash(x)=7204955) -682 train 7.268192 (lr=2.8390e-04) (hash(x)=5856543) -683 train 7.142976 (lr=2.8273e-04) (hash(x)=4423711) -684 train 7.114275 (lr=2.8156e-04) (hash(x)=5818153) -685 train 7.214947 (lr=2.8039e-04) (hash(x)=5343477) -686 train 7.409268 (lr=2.7922e-04) (hash(x)=6581702) -687 train 7.236282 (lr=2.7805e-04) (hash(x)=6595856) -688 train 7.174536 (lr=2.7689e-04) (hash(x)=5325378) -689 train 7.094116 (lr=2.7572e-04) (hash(x)=7229015) -690 train 7.262506 (lr=2.7456e-04) (hash(x)=5918186) -691 train 7.146507 (lr=2.7340e-04) (hash(x)=5916034) -692 train 7.164917 (lr=2.7224e-04) (hash(x)=5280722) -693 train 7.570690 (lr=2.7108e-04) (hash(x)=6939521) -694 train 7.298468 (lr=2.6992e-04) (hash(x)=5172566) -695 train 7.147656 (lr=2.6876e-04) (hash(x)=5492185) -696 train 7.028531 (lr=2.6761e-04) (hash(x)=5779011) -697 train 7.283820 (lr=2.6645e-04) (hash(x)=6898006) -698 train 7.136384 (lr=2.6530e-04) (hash(x)=5779217) -699 train 7.003380 (lr=2.6414e-04) (hash(x)=5462008) -700 val loss 7.2763 -700 val perplexity 1445.6913 -700 train 7.133677 (lr=2.6299e-04) (hash(x)=6243843) -701 train 7.201668 (lr=2.6184e-04) (hash(x)=7821902) -702 train 7.263968 (lr=2.6069e-04) (hash(x)=5222501) -703 train 7.229538 (lr=2.5955e-04) (hash(x)=6608108) -704 train 7.353471 (lr=2.5840e-04) (hash(x)=7602879) -705 train 7.283667 (lr=2.5725e-04) (hash(x)=6295394) -706 train 7.240102 (lr=2.5611e-04) (hash(x)=6579907) -707 train 7.131851 (lr=2.5497e-04) (hash(x)=6803449) -708 train 7.206299 (lr=2.5383e-04) (hash(x)=5413733) -709 train 7.156231 (lr=2.5269e-04) (hash(x)=7444134) -710 train 7.320212 (lr=2.5155e-04) (hash(x)=7028652) -711 train 7.103862 (lr=2.5042e-04) (hash(x)=5361923) -712 train 7.224922 (lr=2.4928e-04) (hash(x)=5478293) -713 train 7.201499 (lr=2.4815e-04) (hash(x)=7803039) -714 train 7.387799 (lr=2.4702e-04) (hash(x)=6469017) -715 train 7.281194 (lr=2.4589e-04) (hash(x)=7042578) -716 train 7.329437 (lr=2.4476e-04) (hash(x)=6927957) -717 train 7.153640 (lr=2.4363e-04) (hash(x)=6647007) -718 train 7.122975 (lr=2.4251e-04) (hash(x)=6230888) -719 train 7.378871 (lr=2.4139e-04) (hash(x)=6303658) -720 train 7.415677 (lr=2.4026e-04) (hash(x)=6769880) -721 train 7.258996 (lr=2.3914e-04) (hash(x)=6158927) -722 train 7.277626 (lr=2.3803e-04) (hash(x)=5991631) -723 train 7.130712 (lr=2.3691e-04) (hash(x)=6419656) -724 train 7.158002 (lr=2.3580e-04) (hash(x)=7739209) -725 train 7.116948 (lr=2.3468e-04) (hash(x)=7891271) -726 train 7.466895 (lr=2.3357e-04) (hash(x)=7171433) -727 train 7.247159 (lr=2.3246e-04) (hash(x)=7099888) -728 train 7.271505 (lr=2.3136e-04) (hash(x)=6103730) -729 train 7.385959 (lr=2.3025e-04) (hash(x)=6352424) -730 train 7.266267 (lr=2.2915e-04) (hash(x)=4893671) -731 train 7.211841 (lr=2.2805e-04) (hash(x)=5863145) -732 train 7.324223 (lr=2.2695e-04) (hash(x)=5502233) -733 train 7.219761 (lr=2.2585e-04) (hash(x)=6844597) -734 train 7.230278 (lr=2.2476e-04) (hash(x)=6744526) -735 train 7.369040 (lr=2.2366e-04) (hash(x)=6009861) -736 train 7.245226 (lr=2.2257e-04) (hash(x)=6152358) -737 train 7.159678 (lr=2.2148e-04) (hash(x)=5374957) -738 train 7.172276 (lr=2.2040e-04) (hash(x)=6495309) -739 train 7.342313 (lr=2.1931e-04) (hash(x)=3923225) -740 train 7.127966 (lr=2.1823e-04) (hash(x)=6255243) -741 train 7.260824 (lr=2.1715e-04) (hash(x)=5848862) -742 train 7.277327 (lr=2.1607e-04) (hash(x)=4535000) -743 train 7.176571 (lr=2.1500e-04) (hash(x)=4440634) -744 train 7.163837 (lr=2.1392e-04) (hash(x)=5222077) -745 train 7.177392 (lr=2.1285e-04) (hash(x)=4788998) -746 train 7.183031 (lr=2.1178e-04) (hash(x)=6108350) -747 train 7.096934 (lr=2.1072e-04) (hash(x)=7378165) -748 train 7.179675 (lr=2.0965e-04) (hash(x)=5475646) -749 train 7.192242 (lr=2.0859e-04) (hash(x)=4771243) -750 val loss 7.2765 -750 val perplexity 1445.8718 -750 train 7.071801 (lr=2.0753e-04) (hash(x)=6668088) -751 train 7.283248 (lr=2.0647e-04) (hash(x)=5716089) -752 train 7.241159 (lr=2.0542e-04) (hash(x)=6991946) -753 train 7.142903 (lr=2.0436e-04) (hash(x)=7991009) -754 train 7.257631 (lr=2.0331e-04) (hash(x)=6037018) -755 train 7.224583 (lr=2.0226e-04) (hash(x)=5348607) -756 train 7.348554 (lr=2.0122e-04) (hash(x)=5190526) -757 train 7.239732 (lr=2.0018e-04) (hash(x)=6036146) -758 train 7.129354 (lr=1.9914e-04) (hash(x)=5329783) -759 train 7.226395 (lr=1.9810e-04) (hash(x)=6658718) -760 train 7.139090 (lr=1.9706e-04) (hash(x)=4820939) -761 train 7.118741 (lr=1.9603e-04) (hash(x)=6176253) -762 train 7.102529 (lr=1.9500e-04) (hash(x)=5316750) -763 train 7.180678 (lr=1.9397e-04) (hash(x)=4542895) -764 train 7.026456 (lr=1.9295e-04) (hash(x)=5395673) -765 train 7.069162 (lr=1.9193e-04) (hash(x)=5549073) -766 train 7.290985 (lr=1.9091e-04) (hash(x)=5233723) -767 train 7.365542 (lr=1.8989e-04) (hash(x)=5342783) -768 train 7.304257 (lr=1.8887e-04) (hash(x)=5552448) -769 train 7.426475 (lr=1.8786e-04) (hash(x)=6549546) -770 train 7.121472 (lr=1.8685e-04) (hash(x)=3816493) -771 train 7.160312 (lr=1.8585e-04) (hash(x)=6170599) -772 train 7.608524 (lr=1.8485e-04) (hash(x)=6708759) -773 train 7.244777 (lr=1.8385e-04) (hash(x)=8483134) -774 train 7.804720 (lr=1.8285e-04) (hash(x)=5583732) -775 train 7.228591 (lr=1.8185e-04) (hash(x)=4865036) -776 train 7.161191 (lr=1.8086e-04) (hash(x)=7234336) -777 train 7.200143 (lr=1.7987e-04) (hash(x)=4433890) -778 train 7.512131 (lr=1.7889e-04) (hash(x)=7484636) -779 train 7.926641 (lr=1.7790e-04) (hash(x)=6738597) -780 train 7.212890 (lr=1.7692e-04) (hash(x)=6752421) -781 train 7.392477 (lr=1.7595e-04) (hash(x)=5459620) -782 train 7.297678 (lr=1.7497e-04) (hash(x)=6718131) -783 train 7.289261 (lr=1.7400e-04) (hash(x)=4604074) -784 train 7.152444 (lr=1.7303e-04) (hash(x)=5946124) -785 train 7.419847 (lr=1.7207e-04) (hash(x)=8045501) -786 train 7.536399 (lr=1.7111e-04) (hash(x)=5712725) -787 train 7.256878 (lr=1.7015e-04) (hash(x)=6176464) -788 train 7.292347 (lr=1.6919e-04) (hash(x)=6276702) -789 train 7.115613 (lr=1.6824e-04) (hash(x)=6127317) -790 train 7.273091 (lr=1.6729e-04) (hash(x)=7221374) -791 train 7.248471 (lr=1.6634e-04) (hash(x)=5571462) -792 train 7.249466 (lr=1.6540e-04) (hash(x)=7518021) -793 train 7.248608 (lr=1.6446e-04) (hash(x)=6640755) -794 train 7.330340 (lr=1.6352e-04) (hash(x)=6870405) -795 train 7.290612 (lr=1.6259e-04) (hash(x)=6147295) -796 train 7.187652 (lr=1.6166e-04) (hash(x)=6782583) -797 train 7.304230 (lr=1.6073e-04) (hash(x)=6120461) -798 train 7.238538 (lr=1.5981e-04) (hash(x)=5893870) -799 train 7.175369 (lr=1.5889e-04) (hash(x)=5123928) -800 val loss 7.2628 -800 val perplexity 1426.1842 -800 train 7.238575 (lr=1.5797e-04) (hash(x)=7037251) -801 train 7.240525 (lr=1.5705e-04) (hash(x)=5428813) -802 train 7.165471 (lr=1.5614e-04) (hash(x)=5550387) -803 train 7.245495 (lr=1.5524e-04) (hash(x)=6448586) -804 train 7.384059 (lr=1.5433e-04) (hash(x)=5916934) -805 train 7.335072 (lr=1.5343e-04) (hash(x)=8116987) -806 train 7.318943 (lr=1.5254e-04) (hash(x)=6210899) -807 train 7.430175 (lr=1.5164e-04) (hash(x)=5974342) -808 train 7.420037 (lr=1.5075e-04) (hash(x)=7236199) -809 train 7.347103 (lr=1.4987e-04) (hash(x)=5261336) -810 train 7.184433 (lr=1.4898e-04) (hash(x)=6310720) -811 train 7.213087 (lr=1.4810e-04) (hash(x)=5307056) -812 train 7.075014 (lr=1.4723e-04) (hash(x)=7356633) -813 train 7.190030 (lr=1.4635e-04) (hash(x)=5865119) -814 train 7.088152 (lr=1.4548e-04) (hash(x)=5979205) -815 train 7.239465 (lr=1.4462e-04) (hash(x)=6672380) -816 train 7.222394 (lr=1.4376e-04) (hash(x)=5565030) -817 train 7.206617 (lr=1.4290e-04) (hash(x)=6886810) -818 train 7.270175 (lr=1.4204e-04) (hash(x)=5926478) -819 train 7.487834 (lr=1.4119e-04) (hash(x)=6564071) -820 train 7.114408 (lr=1.4035e-04) (hash(x)=5024280) -821 train 7.104883 (lr=1.3950e-04) (hash(x)=7705089) -822 train 7.086552 (lr=1.3866e-04) (hash(x)=4037371) -823 train 7.180008 (lr=1.3783e-04) (hash(x)=5773073) -824 train 7.194257 (lr=1.3699e-04) (hash(x)=7158139) -825 train 7.046433 (lr=1.3616e-04) (hash(x)=5905976) -826 train 7.471286 (lr=1.3534e-04) (hash(x)=13897369) -827 train 8.557480 (lr=1.3452e-04) (hash(x)=6936653) -828 train 7.230253 (lr=1.3370e-04) (hash(x)=6592246) -829 train 7.204882 (lr=1.3289e-04) (hash(x)=6592773) -830 train 7.249508 (lr=1.3208e-04) (hash(x)=5461178) -831 train 7.038263 (lr=1.3127e-04) (hash(x)=6796551) -832 train 7.265030 (lr=1.3047e-04) (hash(x)=4721691) -833 train 7.162796 (lr=1.2967e-04) (hash(x)=6151589) -834 train 7.321404 (lr=1.2887e-04) (hash(x)=7008995) -835 train 7.637057 (lr=1.2808e-04) (hash(x)=7045164) -836 train 7.237843 (lr=1.2730e-04) (hash(x)=6614221) -837 train 7.277291 (lr=1.2651e-04) (hash(x)=6650506) -838 train 7.078917 (lr=1.2574e-04) (hash(x)=6363762) -839 train 7.249407 (lr=1.2496e-04) (hash(x)=7839748) -840 train 7.154269 (lr=1.2419e-04) (hash(x)=5124077) -841 train 7.618376 (lr=1.2342e-04) (hash(x)=6028671) -842 train 7.123517 (lr=1.2266e-04) (hash(x)=5427175) -843 train 7.441318 (lr=1.2190e-04) (hash(x)=6118408) -844 train 7.220417 (lr=1.2115e-04) (hash(x)=6022552) -845 train 7.221863 (lr=1.2040e-04) (hash(x)=5757526) -846 train 7.683441 (lr=1.1965e-04) (hash(x)=6476549) -847 train 7.029605 (lr=1.1891e-04) (hash(x)=6030172) -848 train 7.395398 (lr=1.1817e-04) (hash(x)=5917229) -849 train 7.497690 (lr=1.1743e-04) (hash(x)=6719882) -850 val loss 7.2594 -850 val perplexity 1421.3531 -850 train 7.322224 (lr=1.1670e-04) (hash(x)=5441498) -851 train 7.221459 (lr=1.1598e-04) (hash(x)=5028050) -852 train 7.235754 (lr=1.1525e-04) (hash(x)=8487491) -853 train 7.227039 (lr=1.1454e-04) (hash(x)=5682910) -854 train 7.414336 (lr=1.1382e-04) (hash(x)=6781362) -855 train 7.230700 (lr=1.1311e-04) (hash(x)=5747891) -856 train 7.278474 (lr=1.1241e-04) (hash(x)=7627661) -857 train 6.966769 (lr=1.1171e-04) (hash(x)=5734208) -858 train 7.106152 (lr=1.1101e-04) (hash(x)=6162015) -859 train 7.304794 (lr=1.1032e-04) (hash(x)=7024381) -860 train 7.513941 (lr=1.0963e-04) (hash(x)=5198498) -861 train 7.495351 (lr=1.0894e-04) (hash(x)=7814361) -862 train 7.365499 (lr=1.0826e-04) (hash(x)=7394995) -863 train 7.259632 (lr=1.0759e-04) (hash(x)=5765893) -864 train 7.064799 (lr=1.0692e-04) (hash(x)=4990435) -865 train 7.197665 (lr=1.0625e-04) (hash(x)=5572048) -866 train 7.365871 (lr=1.0559e-04) (hash(x)=7093293) -867 train 7.245916 (lr=1.0493e-04) (hash(x)=5610058) -868 train 7.142777 (lr=1.0427e-04) (hash(x)=6771468) -869 train 7.187006 (lr=1.0362e-04) (hash(x)=4459483) -870 train 7.074708 (lr=1.0298e-04) (hash(x)=4926546) -871 train 7.193995 (lr=1.0234e-04) (hash(x)=6758411) -872 train 7.149498 (lr=1.0170e-04) (hash(x)=7394277) -873 train 7.278939 (lr=1.0107e-04) (hash(x)=6701381) -874 train 7.607490 (lr=1.0044e-04) (hash(x)=8120966) -875 train 7.140362 (lr=9.9818e-05) (hash(x)=5416400) -876 train 7.140898 (lr=9.9199e-05) (hash(x)=6292778) -877 train 7.078300 (lr=9.8585e-05) (hash(x)=5919569) -878 train 7.399718 (lr=9.7975e-05) (hash(x)=7561740) -879 train 7.143291 (lr=9.7370e-05) (hash(x)=5282870) -880 train 7.186507 (lr=9.6769e-05) (hash(x)=5473238) -881 train 7.086699 (lr=9.6173e-05) (hash(x)=8072181) -882 train 7.101425 (lr=9.5581e-05) (hash(x)=6757322) -883 train 7.067219 (lr=9.4994e-05) (hash(x)=7996770) -884 train 7.166949 (lr=9.4412e-05) (hash(x)=3181021) -885 train 7.211201 (lr=9.3833e-05) (hash(x)=5093519) -886 train 7.172001 (lr=9.3260e-05) (hash(x)=5391352) -887 train 7.211829 (lr=9.2691e-05) (hash(x)=6270917) -888 train 7.215734 (lr=9.2127e-05) (hash(x)=5818195) -889 train 6.975936 (lr=9.1567e-05) (hash(x)=5852780) -890 train 6.901105 (lr=9.1012e-05) (hash(x)=5777928) -891 train 7.089032 (lr=9.0461e-05) (hash(x)=5327728) -892 train 7.121693 (lr=8.9916e-05) (hash(x)=7651281) -893 train 7.317436 (lr=8.9374e-05) (hash(x)=6260765) -894 train 7.196193 (lr=8.8838e-05) (hash(x)=6265102) -895 train 7.354897 (lr=8.8306e-05) (hash(x)=6212894) -896 train 7.137350 (lr=8.7779e-05) (hash(x)=6901967) -897 train 7.201009 (lr=8.7256e-05) (hash(x)=6724010) -898 train 7.199869 (lr=8.6738e-05) (hash(x)=6299033) -899 train 7.367983 (lr=8.6225e-05) (hash(x)=6059934) -900 val loss 7.2706 -900 val perplexity 1437.3446 -900 train 7.058852 (lr=8.5717e-05) (hash(x)=6029696) -901 train 6.981483 (lr=8.5213e-05) (hash(x)=5587382) -902 train 7.180746 (lr=8.4714e-05) (hash(x)=5890076) -903 train 7.108450 (lr=8.4220e-05) (hash(x)=7274108) -904 train 7.201891 (lr=8.3731e-05) (hash(x)=7975528) -905 train 7.241421 (lr=8.3246e-05) (hash(x)=6085396) -906 train 7.133669 (lr=8.2766e-05) (hash(x)=6724496) -907 train 7.130234 (lr=8.2291e-05) (hash(x)=4784666) -908 train 7.145245 (lr=8.1821e-05) (hash(x)=7193845) -909 train 7.300814 (lr=8.1356e-05) (hash(x)=6288638) -910 train 7.286870 (lr=8.0895e-05) (hash(x)=5685285) -911 train 7.265322 (lr=8.0439e-05) (hash(x)=7714288) -912 train 7.338243 (lr=7.9988e-05) (hash(x)=5983679) -913 train 7.293921 (lr=7.9542e-05) (hash(x)=5534748) -914 train 7.239863 (lr=7.9101e-05) (hash(x)=6545471) -915 train 7.222851 (lr=7.8664e-05) (hash(x)=6361270) -916 train 7.217522 (lr=7.8232e-05) (hash(x)=6257744) -917 train 7.232538 (lr=7.7806e-05) (hash(x)=4682956) -918 train 7.116433 (lr=7.7384e-05) (hash(x)=4521756) -919 train 7.261102 (lr=7.6967e-05) (hash(x)=7568935) -920 train 7.169036 (lr=7.6555e-05) (hash(x)=7969353) -921 train 7.351889 (lr=7.6148e-05) (hash(x)=7973311) -922 train 7.057231 (lr=7.5746e-05) (hash(x)=4843937) -923 train 7.203022 (lr=7.5348e-05) (hash(x)=6987352) -924 train 7.316325 (lr=7.4956e-05) (hash(x)=7179418) -925 train 6.981483 (lr=7.4568e-05) (hash(x)=5413904) -926 train 7.367393 (lr=7.4186e-05) (hash(x)=6028105) -927 train 7.275677 (lr=7.3808e-05) (hash(x)=6732924) -928 train 7.167045 (lr=7.3436e-05) (hash(x)=4547651) -929 train 7.338727 (lr=7.3068e-05) (hash(x)=6219754) -930 train 7.117935 (lr=7.2706e-05) (hash(x)=7465186) -931 train 7.254127 (lr=7.2348e-05) (hash(x)=6839070) -932 train 7.124338 (lr=7.1995e-05) (hash(x)=5390324) -933 train 7.100323 (lr=7.1648e-05) (hash(x)=6090120) -934 train 7.719783 (lr=7.1305e-05) (hash(x)=7123181) -935 train 7.401228 (lr=7.0967e-05) (hash(x)=7115176) -936 train 7.405222 (lr=7.0635e-05) (hash(x)=7016990) -937 train 7.167251 (lr=7.0307e-05) (hash(x)=4989299) -938 train 7.187303 (lr=6.9984e-05) (hash(x)=6783311) -939 train 7.153462 (lr=6.9667e-05) (hash(x)=7497590) -940 train 7.370980 (lr=6.9354e-05) (hash(x)=6767514) -941 train 7.134829 (lr=6.9047e-05) (hash(x)=3977557) -942 train 7.244173 (lr=6.8744e-05) (hash(x)=4806492) -943 train 7.177331 (lr=6.8447e-05) (hash(x)=5524165) -944 train 7.236280 (lr=6.8155e-05) (hash(x)=4930752) -945 train 7.208829 (lr=6.7868e-05) (hash(x)=5124936) -946 train 7.091607 (lr=6.7585e-05) (hash(x)=6877351) -947 train 7.375976 (lr=6.7308e-05) (hash(x)=5522119) -948 train 7.168471 (lr=6.7036e-05) (hash(x)=6183512) -949 train 7.099660 (lr=6.6769e-05) (hash(x)=5030865) -950 val loss 7.2418 -950 val perplexity 1396.6221 -950 train 7.184534 (lr=6.6508e-05) (hash(x)=6619812) -951 train 7.195469 (lr=6.6251e-05) (hash(x)=6411783) -952 train 7.184252 (lr=6.5999e-05) (hash(x)=6748982) -953 train 7.088627 (lr=6.5753e-05) (hash(x)=6581937) -954 train 7.188861 (lr=6.5511e-05) (hash(x)=7881022) -955 train 7.157289 (lr=6.5275e-05) (hash(x)=5116910) -956 train 6.949575 (lr=6.5044e-05) (hash(x)=4880833) -957 train 6.997415 (lr=6.4818e-05) (hash(x)=7353459) -958 train 7.074324 (lr=6.4597e-05) (hash(x)=4951302) -959 train 6.977889 (lr=6.4382e-05) (hash(x)=6344535) -960 train 7.595117 (lr=6.4171e-05) (hash(x)=7411763) -961 train 7.153414 (lr=6.3966e-05) (hash(x)=5840169) -962 train 7.257590 (lr=6.3765e-05) (hash(x)=5784788) -963 train 7.068092 (lr=6.3570e-05) (hash(x)=6754290) -964 train 7.341851 (lr=6.3380e-05) (hash(x)=6369963) -965 train 7.421086 (lr=6.3195e-05) (hash(x)=6484573) -966 train 7.015618 (lr=6.3016e-05) (hash(x)=6516338) -967 train 7.039011 (lr=6.2841e-05) (hash(x)=5260125) -968 train 7.170541 (lr=6.2672e-05) (hash(x)=5781624) -969 train 6.965876 (lr=6.2508e-05) (hash(x)=4881179) -970 train 7.078770 (lr=6.2349e-05) (hash(x)=6707821) -971 train 7.228146 (lr=6.2195e-05) (hash(x)=5001634) -972 train 7.092967 (lr=6.2046e-05) (hash(x)=4402949) -973 train 7.117911 (lr=6.1903e-05) (hash(x)=7424810) -974 train 7.009636 (lr=6.1765e-05) (hash(x)=4814803) -975 train 6.924478 (lr=6.1632e-05) (hash(x)=5176431) -976 train 7.129508 (lr=6.1504e-05) (hash(x)=5769393) -977 train 7.071016 (lr=6.1381e-05) (hash(x)=5421624) -978 train 7.266103 (lr=6.1264e-05) (hash(x)=5999773) -979 train 6.982728 (lr=6.1152e-05) (hash(x)=5674439) -980 train 7.075795 (lr=6.1045e-05) (hash(x)=6345351) -981 train 7.013047 (lr=6.0943e-05) (hash(x)=5819157) -982 train 7.228723 (lr=6.0846e-05) (hash(x)=11159355) -983 train 7.189655 (lr=6.0755e-05) (hash(x)=6506856) -984 train 7.098700 (lr=6.0669e-05) (hash(x)=6331023) -985 train 7.012566 (lr=6.0588e-05) (hash(x)=6119124) -986 train 7.222008 (lr=6.0512e-05) (hash(x)=8142528) -987 train 7.398296 (lr=6.0442e-05) (hash(x)=6241669) -988 train 7.019189 (lr=6.0376e-05) (hash(x)=3852991) -989 train 6.764310 (lr=6.0316e-05) (hash(x)=4992756) -990 train 7.469626 (lr=6.0261e-05) (hash(x)=7097145) -991 train 7.224168 (lr=6.0212e-05) (hash(x)=7277927) -992 train 7.309268 (lr=6.0167e-05) (hash(x)=5661400) -993 train 7.233738 (lr=6.0128e-05) (hash(x)=6622097) -994 train 7.360166 (lr=6.0094e-05) (hash(x)=5016804) -995 train 7.464649 (lr=6.0065e-05) (hash(x)=7026582) -996 train 7.222393 (lr=6.0042e-05) (hash(x)=5639136) -997 train 7.373614 (lr=6.0024e-05) (hash(x)=5840987) -998 train 6.998946 (lr=6.0010e-05) (hash(x)=5265410) -999 val loss 7.2390 -999 val perplexity 1392.6698 -999 train 6.987595 (lr=6.0003e-05) (hash(x)=4351074) +9 train 11.400119 (lr=2.0979e-05) (hash(x)=5491972) +10 train 11.321334 (lr=2.3077e-05) (hash(x)=8075458) +11 train 11.223132 (lr=2.5175e-05) (hash(x)=5917741) +12 train 11.175581 (lr=2.7273e-05) (hash(x)=5750403) +13 train 11.092654 (lr=2.9371e-05) (hash(x)=6112458) +14 train 11.029594 (lr=3.1469e-05) (hash(x)=5806490) +15 train 10.915752 (lr=3.3566e-05) (hash(x)=6568379) +16 train 10.815973 (lr=3.5664e-05) (hash(x)=7212403) +17 train 10.754658 (lr=3.7762e-05) (hash(x)=7386082) +18 train 10.683637 (lr=3.9860e-05) (hash(x)=6359743) +19 train 10.628126 (lr=4.1958e-05) (hash(x)=6151674) +20 train 10.602698 (lr=4.4056e-05) (hash(x)=7168704) +21 train 10.553164 (lr=4.6154e-05) (hash(x)=7859060) +22 train 10.481210 (lr=4.8252e-05) (hash(x)=6976239) +23 train 10.480682 (lr=5.0350e-05) (hash(x)=6391506) +24 train 10.464776 (lr=5.2448e-05) (hash(x)=5245999) +25 train 10.422801 (lr=5.4545e-05) (hash(x)=5985675) +26 train 10.333903 (lr=5.6643e-05) (hash(x)=4355733) +27 train 10.505949 (lr=5.8741e-05) (hash(x)=6984772) +28 train 10.351595 (lr=6.0839e-05) (hash(x)=6244096) +29 train 10.374977 (lr=6.2937e-05) (hash(x)=6603717) +30 train 10.276633 (lr=6.5035e-05) (hash(x)=5669522) +31 train 10.260938 (lr=6.7133e-05) (hash(x)=6190579) +32 train 10.318028 (lr=6.9231e-05) (hash(x)=4912983) +33 train 10.191436 (lr=7.1329e-05) (hash(x)=7276303) +34 train 10.254468 (lr=7.3427e-05) (hash(x)=5479947) +35 train 10.345053 (lr=7.5524e-05) (hash(x)=6630378) +36 train 10.270501 (lr=7.7622e-05) (hash(x)=8097010) +37 train 10.323310 (lr=7.9720e-05) (hash(x)=9989744) +38 train 10.193913 (lr=8.1818e-05) (hash(x)=6694932) +39 train 10.112976 (lr=8.3916e-05) (hash(x)=6317894) +40 train 10.019819 (lr=8.6014e-05) (hash(x)=5046327) +41 train 10.086580 (lr=8.8112e-05) (hash(x)=7947703) +42 train 9.940279 (lr=9.0210e-05) (hash(x)=5916068) +43 train 10.029654 (lr=9.2308e-05) (hash(x)=5777498) +44 train 9.949553 (lr=9.4406e-05) (hash(x)=5753092) +45 train 9.917521 (lr=9.6503e-05) (hash(x)=7723226) +46 train 9.893804 (lr=9.8601e-05) (hash(x)=7007016) +47 train 9.804452 (lr=1.0070e-04) (hash(x)=6491229) +48 train 9.834908 (lr=1.0280e-04) (hash(x)=6390752) +49 train 9.937786 (lr=1.0490e-04) (hash(x)=6019389) +50 val loss 9.7943 +50 val perplexity 17932.1191 +50 train 9.788495 (lr=1.0699e-04) (hash(x)=7662067) +51 train 9.770037 (lr=1.0909e-04) (hash(x)=4648609) +52 train 9.690557 (lr=1.1119e-04) (hash(x)=4725966) +53 train 9.632469 (lr=1.1329e-04) (hash(x)=5558355) +54 train 9.657883 (lr=1.1538e-04) (hash(x)=6524933) +55 train 9.596804 (lr=1.1748e-04) (hash(x)=6369326) +56 train 9.545423 (lr=1.1958e-04) (hash(x)=6022625) +57 train 9.460669 (lr=1.2168e-04) (hash(x)=4906853) +58 train 9.264319 (lr=1.2378e-04) (hash(x)=5589269) +59 train 9.371090 (lr=1.2587e-04) (hash(x)=6437376) +60 train 9.400900 (lr=1.2797e-04) (hash(x)=7304892) +61 train 9.346132 (lr=1.3007e-04) (hash(x)=7084093) +62 train 9.347330 (lr=1.3217e-04) (hash(x)=5908178) +63 train 9.107050 (lr=1.3427e-04) (hash(x)=7048804) +64 train 9.169471 (lr=1.3636e-04) (hash(x)=6085549) +65 train 9.175297 (lr=1.3846e-04) (hash(x)=5752594) +66 train 8.949560 (lr=1.4056e-04) (hash(x)=7662769) +67 train 8.796184 (lr=1.4266e-04) (hash(x)=6393520) +68 train 9.031766 (lr=1.4476e-04) (hash(x)=5942867) +69 train 9.007526 (lr=1.4685e-04) (hash(x)=6793550) +70 train 8.830093 (lr=1.4895e-04) (hash(x)=7105976) +71 train 8.845319 (lr=1.5105e-04) (hash(x)=6581348) +72 train 8.749852 (lr=1.5315e-04) (hash(x)=5555598) +73 train 8.701643 (lr=1.5524e-04) (hash(x)=6235837) +74 train 8.617724 (lr=1.5734e-04) (hash(x)=5591770) +75 train 8.830299 (lr=1.5944e-04) (hash(x)=7083021) +76 train 8.654346 (lr=1.6154e-04) (hash(x)=7281348) +77 train 8.695653 (lr=1.6364e-04) (hash(x)=6155821) +78 train 8.502962 (lr=1.6573e-04) (hash(x)=5736241) +79 train 8.408897 (lr=1.6783e-04) (hash(x)=5657123) +80 train 8.356319 (lr=1.6993e-04) (hash(x)=6452095) +81 train 8.289348 (lr=1.7203e-04) (hash(x)=5312267) +82 train 8.144321 (lr=1.7413e-04) (hash(x)=5434493) +83 train 8.369704 (lr=1.7622e-04) (hash(x)=6830813) +84 train 8.183750 (lr=1.7832e-04) (hash(x)=4752771) +85 train 8.287519 (lr=1.8042e-04) (hash(x)=6424933) +86 train 8.188684 (lr=1.8252e-04) (hash(x)=5786517) +87 train 8.251399 (lr=1.8462e-04) (hash(x)=6680023) +88 train 8.168158 (lr=1.8671e-04) (hash(x)=6474729) +89 train 8.165698 (lr=1.8881e-04) (hash(x)=7523279) +90 train 7.951312 (lr=1.9091e-04) (hash(x)=5508768) +91 train 8.151656 (lr=1.9301e-04) (hash(x)=6635925) +92 train 8.011524 (lr=1.9510e-04) (hash(x)=6663801) +93 train 7.984674 (lr=1.9720e-04) (hash(x)=5869441) +94 train 8.050040 (lr=1.9930e-04) (hash(x)=6698878) +95 train 7.948261 (lr=2.0140e-04) (hash(x)=6349004) +96 train 7.951228 (lr=2.0350e-04) (hash(x)=4986137) +97 train 7.728497 (lr=2.0559e-04) (hash(x)=6008454) +98 train 7.799539 (lr=2.0769e-04) (hash(x)=6550770) +99 train 7.952554 (lr=2.0979e-04) (hash(x)=7682741) +100 val loss 7.8974 +100 val perplexity 2690.4128 +100 train 7.999499 (lr=2.1189e-04) (hash(x)=7892158) +101 train 7.864366 (lr=2.1399e-04) (hash(x)=7794028) +102 train 7.854183 (lr=2.1608e-04) (hash(x)=7093523) +103 train 7.904255 (lr=2.1818e-04) (hash(x)=6166062) +104 train 7.837919 (lr=2.2028e-04) (hash(x)=6645781) +105 train 7.800285 (lr=2.2238e-04) (hash(x)=4811192) +106 train 7.718511 (lr=2.2448e-04) (hash(x)=5970866) +107 train 7.729679 (lr=2.2657e-04) (hash(x)=7822680) +108 train 7.713760 (lr=2.2867e-04) (hash(x)=6317317) +109 train 7.813911 (lr=2.3077e-04) (hash(x)=6431409) +110 train 7.819135 (lr=2.3287e-04) (hash(x)=6653337) +111 train 7.770240 (lr=2.3497e-04) (hash(x)=5323032) +112 train 7.647367 (lr=2.3706e-04) (hash(x)=5125339) +113 train 7.580951 (lr=2.3916e-04) (hash(x)=7363286) +114 train 7.981218 (lr=2.4126e-04) (hash(x)=7670050) +115 train 7.725863 (lr=2.4336e-04) (hash(x)=5616075) +116 train 7.784916 (lr=2.4545e-04) (hash(x)=6593764) +117 train 7.856988 (lr=2.4755e-04) (hash(x)=5672608) +118 train 7.683552 (lr=2.4965e-04) (hash(x)=6828653) +119 train 7.674746 (lr=2.5175e-04) (hash(x)=6839867) +120 train 7.826398 (lr=2.5385e-04) (hash(x)=8426992) +121 train 7.494661 (lr=2.5594e-04) (hash(x)=4916928) +122 train 7.694818 (lr=2.5804e-04) (hash(x)=6484050) +123 train 7.784313 (lr=2.6014e-04) (hash(x)=8353379) +124 train 7.710339 (lr=2.6224e-04) (hash(x)=6552510) +125 train 7.685604 (lr=2.6434e-04) (hash(x)=4838871) +126 train 7.431924 (lr=2.6643e-04) (hash(x)=3021697) +127 train 7.589997 (lr=2.6853e-04) (hash(x)=6795665) +128 train 7.600587 (lr=2.7063e-04) (hash(x)=5486935) +129 train 7.785960 (lr=2.7273e-04) (hash(x)=6678038) +130 train 7.834836 (lr=2.7483e-04) (hash(x)=6657714) +131 train 7.685847 (lr=2.7692e-04) (hash(x)=6112215) +132 train 7.747384 (lr=2.7902e-04) (hash(x)=8353143) +133 train 7.800886 (lr=2.8112e-04) (hash(x)=5915361) +134 train 7.704382 (lr=2.8322e-04) (hash(x)=6254885) +135 train 7.705235 (lr=2.8531e-04) (hash(x)=5771588) +136 train 7.692060 (lr=2.8741e-04) (hash(x)=5561507) +137 train 7.624603 (lr=2.8951e-04) (hash(x)=5688829) +138 train 7.629492 (lr=2.9161e-04) (hash(x)=5371951) +139 train 7.798805 (lr=2.9371e-04) (hash(x)=5443305) +140 train 7.758296 (lr=2.9580e-04) (hash(x)=5016757) +141 train 7.760416 (lr=2.9790e-04) (hash(x)=6901933) +142 train 7.739495 (lr=3.0000e-04) (hash(x)=6019085) +143 train 7.578549 (lr=3.0210e-04) (hash(x)=4294425) +144 train 7.684919 (lr=3.0420e-04) (hash(x)=6095229) +145 train 7.513330 (lr=3.0629e-04) (hash(x)=4363941) +146 train 7.599327 (lr=3.0839e-04) (hash(x)=4693798) +147 train 8.163743 (lr=3.1049e-04) (hash(x)=5486335) +148 train 7.958571 (lr=3.1259e-04) (hash(x)=7907450) +149 train 7.774135 (lr=3.1469e-04) (hash(x)=7295165) +150 val loss 7.6689 +150 val perplexity 2140.8171 +150 train 7.716048 (lr=3.1678e-04) (hash(x)=6814026) +151 train 7.800571 (lr=3.1888e-04) (hash(x)=6267424) +152 train 7.801202 (lr=3.2098e-04) (hash(x)=8086437) +153 train 7.856976 (lr=3.2308e-04) (hash(x)=5270452) +154 train 7.690909 (lr=3.2517e-04) (hash(x)=6420820) +155 train 7.602250 (lr=3.2727e-04) (hash(x)=6305297) +156 train 7.748369 (lr=3.2937e-04) (hash(x)=7889849) +157 train 8.138862 (lr=3.3147e-04) (hash(x)=6040077) +158 train 8.117600 (lr=3.3357e-04) (hash(x)=5652497) +159 train 7.702460 (lr=3.3566e-04) (hash(x)=7130251) +160 train 7.564566 (lr=3.3776e-04) (hash(x)=6610177) +161 train 7.622563 (lr=3.3986e-04) (hash(x)=6508350) +162 train 7.780531 (lr=3.4196e-04) (hash(x)=6994983) +163 train 7.735390 (lr=3.4406e-04) (hash(x)=5859576) +164 train 7.322190 (lr=3.4615e-04) (hash(x)=5487065) +165 train 7.525076 (lr=3.4825e-04) (hash(x)=4892065) +166 train 7.444222 (lr=3.5035e-04) (hash(x)=4933674) +167 train 7.707693 (lr=3.5245e-04) (hash(x)=7317289) +168 train 7.806633 (lr=3.5455e-04) (hash(x)=6811522) +169 train 7.641271 (lr=3.5664e-04) (hash(x)=5510218) +170 train 7.799200 (lr=3.5874e-04) (hash(x)=7304235) +171 train 7.961283 (lr=3.6084e-04) (hash(x)=6752265) +172 train 7.652269 (lr=3.6294e-04) (hash(x)=5994476) +173 train 7.608574 (lr=3.6503e-04) (hash(x)=6530867) +174 train 7.717165 (lr=3.6713e-04) (hash(x)=5746260) +175 train 7.673892 (lr=3.6923e-04) (hash(x)=5790078) +176 train 7.700000 (lr=3.7133e-04) (hash(x)=6430135) +177 train 7.755785 (lr=3.7343e-04) (hash(x)=7614023) +178 train 7.750881 (lr=3.7552e-04) (hash(x)=5244861) +179 train 7.738803 (lr=3.7762e-04) (hash(x)=5245146) +180 train 7.621737 (lr=3.7972e-04) (hash(x)=6415565) +181 train 7.670055 (lr=3.8182e-04) (hash(x)=5786972) +182 train 7.704283 (lr=3.8392e-04) (hash(x)=6131703) +183 train 7.747603 (lr=3.8601e-04) (hash(x)=6346459) +184 train 7.776855 (lr=3.8811e-04) (hash(x)=6504131) +185 train 7.749936 (lr=3.9021e-04) (hash(x)=5209234) +186 train 7.660500 (lr=3.9231e-04) (hash(x)=6163272) +187 train 7.670383 (lr=3.9441e-04) (hash(x)=5676768) +188 train 7.739820 (lr=3.9650e-04) (hash(x)=6090561) +189 train 7.867665 (lr=3.9860e-04) (hash(x)=5863092) +190 train 7.786218 (lr=4.0070e-04) (hash(x)=7201312) +191 train 7.877536 (lr=4.0280e-04) (hash(x)=7019489) +192 train 7.641703 (lr=4.0490e-04) (hash(x)=6225608) +193 train 7.706954 (lr=4.0699e-04) (hash(x)=5483019) +194 train 7.662026 (lr=4.0909e-04) (hash(x)=5903258) +195 train 7.709381 (lr=4.1119e-04) (hash(x)=5968716) +196 train 7.693431 (lr=4.1329e-04) (hash(x)=5778017) +197 train 7.405848 (lr=4.1538e-04) (hash(x)=7780194) +198 train 7.627909 (lr=4.1748e-04) (hash(x)=6140998) +199 train 7.615510 (lr=4.1958e-04) (hash(x)=3784321) +200 val loss 7.6411 +200 val perplexity 2082.1318 +200 train 7.637796 (lr=4.2168e-04) (hash(x)=5860821) +201 train 7.689400 (lr=4.2378e-04) (hash(x)=7774109) +202 train 7.851340 (lr=4.2587e-04) (hash(x)=7997664) +203 train 7.817283 (lr=4.2797e-04) (hash(x)=6576749) +204 train 7.736720 (lr=4.3007e-04) (hash(x)=7266655) +205 train 7.703222 (lr=4.3217e-04) (hash(x)=7072404) +206 train 7.609493 (lr=4.3427e-04) (hash(x)=6626459) +207 train 7.608912 (lr=4.3636e-04) (hash(x)=6556025) +208 train 7.640109 (lr=4.3846e-04) (hash(x)=5942129) +209 train 7.756197 (lr=4.4056e-04) (hash(x)=7325027) +210 train 7.761410 (lr=4.4266e-04) (hash(x)=7322467) +211 train 7.681025 (lr=4.4476e-04) (hash(x)=6373412) +212 train 7.465706 (lr=4.4685e-04) (hash(x)=7332255) +213 train 7.754479 (lr=4.4895e-04) (hash(x)=5262868) +214 train 7.449579 (lr=4.5105e-04) (hash(x)=5688247) +215 train 7.624244 (lr=4.5315e-04) (hash(x)=8055563) +216 train 7.650192 (lr=4.5524e-04) (hash(x)=5352405) +217 train 7.710214 (lr=4.5734e-04) (hash(x)=5932790) +218 train 7.673957 (lr=4.5944e-04) (hash(x)=6249312) +219 train 7.626753 (lr=4.6154e-04) (hash(x)=5680154) +220 train 7.718084 (lr=4.6364e-04) (hash(x)=8156280) +221 train 7.653222 (lr=4.6573e-04) (hash(x)=5914217) +222 train 7.498277 (lr=4.6783e-04) (hash(x)=7120215) +223 train 7.682629 (lr=4.6993e-04) (hash(x)=6424128) +224 train 7.449896 (lr=4.7203e-04) (hash(x)=4390027) +225 train 7.657551 (lr=4.7413e-04) (hash(x)=7804089) +226 train 7.770687 (lr=4.7622e-04) (hash(x)=7130267) +227 train 7.548355 (lr=4.7832e-04) (hash(x)=6490149) +228 train 7.596352 (lr=4.8042e-04) (hash(x)=9276378) +229 train 7.609941 (lr=4.8252e-04) (hash(x)=6283540) +230 train 7.591403 (lr=4.8462e-04) (hash(x)=5781680) +231 train 7.540724 (lr=4.8671e-04) (hash(x)=5728337) +232 train 7.542026 (lr=4.8881e-04) (hash(x)=6278202) +233 train 7.621364 (lr=4.9091e-04) (hash(x)=7400272) +234 train 7.602550 (lr=4.9301e-04) (hash(x)=5795128) +235 train 7.563025 (lr=4.9510e-04) (hash(x)=6473432) +236 train 7.574387 (lr=4.9720e-04) (hash(x)=5201502) +237 train 7.799979 (lr=4.9930e-04) (hash(x)=6922646) +238 train 7.517708 (lr=5.0140e-04) (hash(x)=5484641) +239 train 7.579128 (lr=5.0350e-04) (hash(x)=7277141) +240 train 7.600337 (lr=5.0559e-04) (hash(x)=5604614) +241 train 7.634101 (lr=5.0769e-04) (hash(x)=7443124) +242 train 7.652121 (lr=5.0979e-04) (hash(x)=5601968) +243 train 7.538076 (lr=5.1189e-04) (hash(x)=5632735) +244 train 7.540331 (lr=5.1399e-04) (hash(x)=5594810) +245 train 7.396225 (lr=5.1608e-04) (hash(x)=5881015) +246 train 7.552937 (lr=5.1818e-04) (hash(x)=6865361) +247 train 7.644498 (lr=5.2028e-04) (hash(x)=5809411) +248 train 7.618266 (lr=5.2238e-04) (hash(x)=6293025) +249 train 7.570415 (lr=5.2448e-04) (hash(x)=7232964) +250 val loss 7.5834 +250 val perplexity 1965.3892 +250 train 7.495591 (lr=5.2657e-04) (hash(x)=5646619) +251 train 7.631127 (lr=5.2867e-04) (hash(x)=6171829) +252 train 7.687405 (lr=5.3077e-04) (hash(x)=7787552) +253 train 7.646630 (lr=5.3287e-04) (hash(x)=5884456) +254 train 7.674005 (lr=5.3497e-04) (hash(x)=6752162) +255 train 7.574714 (lr=5.3706e-04) (hash(x)=5077031) +256 train 7.711064 (lr=5.3916e-04) (hash(x)=6883481) +257 train 7.622622 (lr=5.4126e-04) (hash(x)=6248895) +258 train 7.493264 (lr=5.4336e-04) (hash(x)=6636615) +259 train 7.672825 (lr=5.4545e-04) (hash(x)=6918004) +260 train 7.607893 (lr=5.4755e-04) (hash(x)=7302874) +261 train 7.707395 (lr=5.4965e-04) (hash(x)=6482466) +262 train 7.527684 (lr=5.5175e-04) (hash(x)=7298317) +263 train 7.560835 (lr=5.5385e-04) (hash(x)=6588573) +264 train 7.567956 (lr=5.5594e-04) (hash(x)=6229630) +265 train 7.636111 (lr=5.5804e-04) (hash(x)=6136939) +266 train 7.369267 (lr=5.6014e-04) (hash(x)=6394645) +267 train 7.615485 (lr=5.6224e-04) (hash(x)=7040157) +268 train 7.656740 (lr=5.6434e-04) (hash(x)=7041858) +269 train 7.558827 (lr=5.6643e-04) (hash(x)=6455595) +270 train 7.496607 (lr=5.6853e-04) (hash(x)=6480443) +271 train 7.673820 (lr=5.7063e-04) (hash(x)=4122983) +272 train 7.496593 (lr=5.7273e-04) (hash(x)=7672190) +273 train 7.520903 (lr=5.7483e-04) (hash(x)=4724052) +274 train 7.483509 (lr=5.7692e-04) (hash(x)=6654267) +275 train 7.469798 (lr=5.7902e-04) (hash(x)=6820797) +276 train 7.531802 (lr=5.8112e-04) (hash(x)=6458662) +277 train 7.938339 (lr=5.8322e-04) (hash(x)=7477594) +278 train 7.603208 (lr=5.8531e-04) (hash(x)=5876574) +279 train 7.331324 (lr=5.8741e-04) (hash(x)=6146305) +280 train 7.511984 (lr=5.8951e-04) (hash(x)=6162080) +281 train 7.460836 (lr=5.9161e-04) (hash(x)=6814831) +282 train 7.599224 (lr=5.9371e-04) (hash(x)=7138295) +283 train 7.366713 (lr=5.9580e-04) (hash(x)=5548298) +284 train 7.484172 (lr=5.9790e-04) (hash(x)=6265078) +285 train 7.851252 (lr=6.0000e-04) (hash(x)=7609416) +286 train 7.528177 (lr=6.0000e-04) (hash(x)=6909367) +287 train 7.651495 (lr=6.0000e-04) (hash(x)=7574342) +288 train 7.455995 (lr=5.9999e-04) (hash(x)=8859748) +289 train 7.411236 (lr=5.9998e-04) (hash(x)=5906937) +290 train 7.418136 (lr=5.9996e-04) (hash(x)=7243024) +291 train 7.566036 (lr=5.9993e-04) (hash(x)=8013471) +292 train 7.470599 (lr=5.9991e-04) (hash(x)=5659461) +293 train 7.515259 (lr=5.9987e-04) (hash(x)=6146213) +294 train 7.542570 (lr=5.9983e-04) (hash(x)=6602917) +295 train 7.468372 (lr=5.9979e-04) (hash(x)=6709902) +296 train 7.565743 (lr=5.9974e-04) (hash(x)=8154341) +297 train 7.703870 (lr=5.9968e-04) (hash(x)=6402571) +298 train 7.472234 (lr=5.9962e-04) (hash(x)=5605466) +299 train 7.432295 (lr=5.9956e-04) (hash(x)=7683614) +300 val loss 7.4926 +300 val perplexity 1794.7140 +300 train 7.523793 (lr=5.9949e-04) (hash(x)=5421572) +301 train 7.359306 (lr=5.9941e-04) (hash(x)=5453026) +302 train 7.431515 (lr=5.9933e-04) (hash(x)=6437746) +303 train 7.342433 (lr=5.9925e-04) (hash(x)=6260017) +304 train 7.438472 (lr=5.9915e-04) (hash(x)=6119053) +305 train 7.620222 (lr=5.9906e-04) (hash(x)=6591466) +306 train 7.545717 (lr=5.9896e-04) (hash(x)=5652701) +307 train 7.512481 (lr=5.9885e-04) (hash(x)=5501472) +308 train 7.680413 (lr=5.9874e-04) (hash(x)=6160695) +309 train 7.436362 (lr=5.9862e-04) (hash(x)=5871698) +310 train 7.424843 (lr=5.9850e-04) (hash(x)=7301184) +311 train 7.333471 (lr=5.9837e-04) (hash(x)=4282052) +312 train 7.556336 (lr=5.9824e-04) (hash(x)=5679330) +313 train 7.398046 (lr=5.9810e-04) (hash(x)=7824660) +314 train 7.446006 (lr=5.9795e-04) (hash(x)=4857318) +315 train 7.377851 (lr=5.9780e-04) (hash(x)=5954950) +316 train 7.458410 (lr=5.9765e-04) (hash(x)=5758178) +317 train 7.456526 (lr=5.9749e-04) (hash(x)=5484656) +318 train 7.470703 (lr=5.9733e-04) (hash(x)=6818913) +319 train 7.667947 (lr=5.9716e-04) (hash(x)=7031328) +320 train 7.512761 (lr=5.9698e-04) (hash(x)=6837621) +321 train 7.554557 (lr=5.9680e-04) (hash(x)=9157069) +322 train 7.796219 (lr=5.9662e-04) (hash(x)=6509536) +323 train 7.488502 (lr=5.9643e-04) (hash(x)=5996883) +324 train 7.753985 (lr=5.9623e-04) (hash(x)=6850868) +325 train 7.668226 (lr=5.9603e-04) (hash(x)=7645447) +326 train 7.686477 (lr=5.9583e-04) (hash(x)=6717515) +327 train 7.781077 (lr=5.9562e-04) (hash(x)=6336164) +328 train 7.544042 (lr=5.9540e-04) (hash(x)=6897445) +329 train 7.429827 (lr=5.9518e-04) (hash(x)=5224240) +330 train 7.564602 (lr=5.9496e-04) (hash(x)=6612945) +331 train 8.056437 (lr=5.9472e-04) (hash(x)=5447801) +332 train 7.565676 (lr=5.9449e-04) (hash(x)=7308579) +333 train 7.436541 (lr=5.9425e-04) (hash(x)=4155598) +334 train 7.475054 (lr=5.9400e-04) (hash(x)=6106773) +335 train 7.512260 (lr=5.9375e-04) (hash(x)=7482744) +336 train 7.581775 (lr=5.9349e-04) (hash(x)=6310687) +337 train 7.458077 (lr=5.9323e-04) (hash(x)=4733414) +338 train 7.566585 (lr=5.9296e-04) (hash(x)=6979734) +339 train 7.373516 (lr=5.9269e-04) (hash(x)=7806284) +340 train 7.402220 (lr=5.9241e-04) (hash(x)=5080536) +341 train 7.604598 (lr=5.9213e-04) (hash(x)=7236478) +342 train 7.536064 (lr=5.9185e-04) (hash(x)=6619318) +343 train 7.448080 (lr=5.9155e-04) (hash(x)=4656255) +344 train 7.377260 (lr=5.9126e-04) (hash(x)=5546888) +345 train 7.802300 (lr=5.9095e-04) (hash(x)=9298325) +346 train 7.515367 (lr=5.9065e-04) (hash(x)=5994232) +347 train 7.494215 (lr=5.9033e-04) (hash(x)=6287524) +348 train 7.615618 (lr=5.9002e-04) (hash(x)=6200049) +349 train 7.527794 (lr=5.8969e-04) (hash(x)=7895970) +350 val loss 7.4594 +350 val perplexity 1736.0244 +350 train 7.429392 (lr=5.8937e-04) (hash(x)=6051847) +351 train 7.592376 (lr=5.8903e-04) (hash(x)=8847992) +352 train 7.946909 (lr=5.8869e-04) (hash(x)=5123883) +353 train 7.561691 (lr=5.8835e-04) (hash(x)=6338998) +354 train 7.542570 (lr=5.8800e-04) (hash(x)=5765866) +355 train 7.865689 (lr=5.8765e-04) (hash(x)=7104011) +356 train 7.630899 (lr=5.8729e-04) (hash(x)=7438267) +357 train 7.375215 (lr=5.8693e-04) (hash(x)=5573214) +358 train 7.665130 (lr=5.8656e-04) (hash(x)=6897283) +359 train 7.451800 (lr=5.8619e-04) (hash(x)=6882897) +360 train 7.574414 (lr=5.8581e-04) (hash(x)=5343615) +361 train 7.487301 (lr=5.8543e-04) (hash(x)=5854242) +362 train 7.402685 (lr=5.8504e-04) (hash(x)=6317324) +363 train 7.335915 (lr=5.8465e-04) (hash(x)=6972494) +364 train 7.408969 (lr=5.8425e-04) (hash(x)=5661167) +365 train 7.416083 (lr=5.8385e-04) (hash(x)=6796805) +366 train 7.268819 (lr=5.8345e-04) (hash(x)=5817209) +367 train 7.324818 (lr=5.8303e-04) (hash(x)=6139120) +368 train 7.522725 (lr=5.8262e-04) (hash(x)=6121296) +369 train 7.476782 (lr=5.8219e-04) (hash(x)=6486796) +370 train 7.389194 (lr=5.8177e-04) (hash(x)=5514645) +371 train 7.312624 (lr=5.8134e-04) (hash(x)=5578797) +372 train 7.342657 (lr=5.8090e-04) (hash(x)=7651738) +373 train 7.538512 (lr=5.8046e-04) (hash(x)=6895326) +374 train 7.550953 (lr=5.8001e-04) (hash(x)=5490256) +375 train 7.416971 (lr=5.7956e-04) (hash(x)=7783160) +376 train 7.607244 (lr=5.7911e-04) (hash(x)=5608424) +377 train 7.397610 (lr=5.7864e-04) (hash(x)=4867625) +378 train 7.297838 (lr=5.7818e-04) (hash(x)=4655472) +379 train 7.379138 (lr=5.7771e-04) (hash(x)=6631123) +380 train 7.052860 (lr=5.7723e-04) (hash(x)=5751990) +381 train 7.331201 (lr=5.7675e-04) (hash(x)=6710965) +382 train 7.311111 (lr=5.7627e-04) (hash(x)=5293800) +383 train 7.328506 (lr=5.7578e-04) (hash(x)=6294657) +384 train 7.495664 (lr=5.7529e-04) (hash(x)=6999538) +385 train 7.480060 (lr=5.7479e-04) (hash(x)=5443606) +386 train 7.448761 (lr=5.7428e-04) (hash(x)=5650401) +387 train 7.472044 (lr=5.7377e-04) (hash(x)=7035770) +388 train 7.410122 (lr=5.7326e-04) (hash(x)=6678271) +389 train 7.598022 (lr=5.7274e-04) (hash(x)=4899541) +390 train 7.341848 (lr=5.7222e-04) (hash(x)=5359260) +391 train 7.343041 (lr=5.7169e-04) (hash(x)=6227120) +392 train 7.392641 (lr=5.7116e-04) (hash(x)=6643916) +393 train 7.459245 (lr=5.7063e-04) (hash(x)=5981648) +394 train 7.415752 (lr=5.7008e-04) (hash(x)=6467540) +395 train 7.354648 (lr=5.6954e-04) (hash(x)=5558993) +396 train 7.515326 (lr=5.6899e-04) (hash(x)=6698959) +397 train 7.322493 (lr=5.6843e-04) (hash(x)=7015671) +398 train 7.330193 (lr=5.6787e-04) (hash(x)=6800890) +399 train 7.495105 (lr=5.6731e-04) (hash(x)=5931234) +400 val loss 7.4136 +400 val perplexity 1658.3185 +400 train 7.479136 (lr=5.6674e-04) (hash(x)=3995070) +401 train 7.398735 (lr=5.6617e-04) (hash(x)=4582159) +402 train 7.471117 (lr=5.6559e-04) (hash(x)=7081906) +403 train 7.393870 (lr=5.6501e-04) (hash(x)=5029472) +404 train 7.417179 (lr=5.6442e-04) (hash(x)=3946232) +405 train 7.336188 (lr=5.6383e-04) (hash(x)=5434102) +406 train 8.071891 (lr=5.6323e-04) (hash(x)=5340646) +407 train 7.280314 (lr=5.6263e-04) (hash(x)=6810638) +408 train 7.517649 (lr=5.6202e-04) (hash(x)=6768026) +409 train 7.474656 (lr=5.6141e-04) (hash(x)=6521562) +410 train 7.450127 (lr=5.6080e-04) (hash(x)=4429434) +411 train 7.509519 (lr=5.6018e-04) (hash(x)=7226932) +412 train 7.286231 (lr=5.5956e-04) (hash(x)=5065932) +413 train 7.463832 (lr=5.5893e-04) (hash(x)=6957849) +414 train 7.462948 (lr=5.5830e-04) (hash(x)=6431457) +415 train 7.522455 (lr=5.5766e-04) (hash(x)=5334281) +416 train 7.576844 (lr=5.5702e-04) (hash(x)=5471747) +417 train 7.707797 (lr=5.5638e-04) (hash(x)=5887983) +418 train 7.593360 (lr=5.5573e-04) (hash(x)=5075909) +419 train 7.342703 (lr=5.5507e-04) (hash(x)=6393576) +420 train 7.474147 (lr=5.5441e-04) (hash(x)=6608979) +421 train 7.904588 (lr=5.5375e-04) (hash(x)=5057959) +422 train 7.842519 (lr=5.5308e-04) (hash(x)=6414858) +423 train 7.628152 (lr=5.5241e-04) (hash(x)=8595271) +424 train 7.500178 (lr=5.5174e-04) (hash(x)=6500949) +425 train 7.656741 (lr=5.5106e-04) (hash(x)=8395167) +426 train 7.767010 (lr=5.5037e-04) (hash(x)=6288420) +427 train 7.571026 (lr=5.4968e-04) (hash(x)=7634417) +428 train 7.449651 (lr=5.4899e-04) (hash(x)=6795561) +429 train 7.334975 (lr=5.4829e-04) (hash(x)=5257771) +430 train 7.493868 (lr=5.4759e-04) (hash(x)=7506860) +431 train 7.543115 (lr=5.4689e-04) (hash(x)=7674238) +432 train 7.662741 (lr=5.4618e-04) (hash(x)=5353794) +433 train 7.594309 (lr=5.4546e-04) (hash(x)=5300555) +434 train 7.246423 (lr=5.4475e-04) (hash(x)=5564419) +435 train 7.511977 (lr=5.4402e-04) (hash(x)=6066139) +436 train 7.475303 (lr=5.4330e-04) (hash(x)=6863709) +437 train 7.461981 (lr=5.4257e-04) (hash(x)=6688212) +438 train 7.626807 (lr=5.4183e-04) (hash(x)=7095090) +439 train 7.698229 (lr=5.4109e-04) (hash(x)=6642404) +440 train 7.448263 (lr=5.4035e-04) (hash(x)=6539227) +441 train 7.427066 (lr=5.3960e-04) (hash(x)=4961570) +442 train 7.367023 (lr=5.3885e-04) (hash(x)=6606391) +443 train 7.186488 (lr=5.3810e-04) (hash(x)=5105190) +444 train 7.730626 (lr=5.3734e-04) (hash(x)=5695997) +445 train 7.445870 (lr=5.3658e-04) (hash(x)=7155991) +446 train 7.427727 (lr=5.3581e-04) (hash(x)=7249727) +447 train 7.404298 (lr=5.3504e-04) (hash(x)=5132972) +448 train 7.391469 (lr=5.3426e-04) (hash(x)=5381802) +449 train 7.469279 (lr=5.3349e-04) (hash(x)=6269946) +450 val loss 7.4822 +450 val perplexity 1776.1138 +450 train 7.460820 (lr=5.3270e-04) (hash(x)=4976762) +451 train 7.517453 (lr=5.3192e-04) (hash(x)=5396133) +452 train 7.449825 (lr=5.3113e-04) (hash(x)=6173473) +453 train 7.431961 (lr=5.3033e-04) (hash(x)=6394083) +454 train 7.473815 (lr=5.2953e-04) (hash(x)=6436030) +455 train 7.350336 (lr=5.2873e-04) (hash(x)=5237804) +456 train 7.322403 (lr=5.2792e-04) (hash(x)=6540397) +457 train 7.580071 (lr=5.2711e-04) (hash(x)=5216638) +458 train 7.405390 (lr=5.2630e-04) (hash(x)=5750537) +459 train 7.397734 (lr=5.2548e-04) (hash(x)=6735565) +460 train 7.412652 (lr=5.2466e-04) (hash(x)=7297488) +461 train 7.626505 (lr=5.2384e-04) (hash(x)=5983575) +462 train 7.420442 (lr=5.2301e-04) (hash(x)=4808543) +463 train 7.533787 (lr=5.2217e-04) (hash(x)=5831619) +464 train 7.292300 (lr=5.2134e-04) (hash(x)=6280052) +465 train 7.314069 (lr=5.2050e-04) (hash(x)=9109083) +466 train 7.542974 (lr=5.1965e-04) (hash(x)=5848604) +467 train 7.506039 (lr=5.1881e-04) (hash(x)=6912967) +468 train 7.660066 (lr=5.1796e-04) (hash(x)=6615365) +469 train 7.718111 (lr=5.1710e-04) (hash(x)=5965674) +470 train 7.568694 (lr=5.1624e-04) (hash(x)=6879965) +471 train 7.546909 (lr=5.1538e-04) (hash(x)=5822533) +472 train 7.413808 (lr=5.1452e-04) (hash(x)=5794462) +473 train 7.482859 (lr=5.1365e-04) (hash(x)=5268216) +474 train 7.340450 (lr=5.1277e-04) (hash(x)=7058396) +475 train 7.426243 (lr=5.1190e-04) (hash(x)=6531900) +476 train 7.428068 (lr=5.1102e-04) (hash(x)=5878912) +477 train 7.256622 (lr=5.1013e-04) (hash(x)=5426499) +478 train 7.468186 (lr=5.0925e-04) (hash(x)=8107004) +479 train 8.161177 (lr=5.0836e-04) (hash(x)=7455372) +480 train 8.098068 (lr=5.0746e-04) (hash(x)=7727959) +481 train 8.030257 (lr=5.0657e-04) (hash(x)=8319119) +482 train 7.958362 (lr=5.0567e-04) (hash(x)=7581656) +483 train 8.024536 (lr=5.0476e-04) (hash(x)=7592128) +484 train 8.010198 (lr=5.0386e-04) (hash(x)=10506633) +485 train 7.968315 (lr=5.0295e-04) (hash(x)=8704170) +486 train 7.770382 (lr=5.0203e-04) (hash(x)=7461138) +487 train 7.645183 (lr=5.0111e-04) (hash(x)=7165037) +488 train 7.694169 (lr=5.0019e-04) (hash(x)=4976998) +489 train 7.427641 (lr=4.9927e-04) (hash(x)=7678000) +490 train 7.493781 (lr=4.9834e-04) (hash(x)=6299409) +491 train 7.453413 (lr=4.9741e-04) (hash(x)=7414788) +492 train 7.551577 (lr=4.9648e-04) (hash(x)=5063061) +493 train 7.460238 (lr=4.9554e-04) (hash(x)=7326216) +494 train 7.628795 (lr=4.9460e-04) (hash(x)=7492012) +495 train 7.583567 (lr=4.9366e-04) (hash(x)=5857162) +496 train 7.374400 (lr=4.9271e-04) (hash(x)=6169001) +497 train 9.269088 (lr=4.9176e-04) (hash(x)=14715669) +498 train 12.063933 (lr=4.9081e-04) (hash(x)=18256706) +499 train 11.927104 (lr=4.8985e-04) (hash(x)=16950560) +500 val loss 7.4951 +500 val perplexity 1799.1215 +500 train 8.214057 (lr=4.8889e-04) (hash(x)=6113563) +501 train 7.147960 (lr=4.8793e-04) (hash(x)=6159125) +502 train 7.538379 (lr=4.8697e-04) (hash(x)=5482303) +503 train 7.596037 (lr=4.8600e-04) (hash(x)=5908442) +504 train 7.495262 (lr=4.8503e-04) (hash(x)=4985045) +505 train 7.437412 (lr=4.8405e-04) (hash(x)=6668887) +506 train 7.479714 (lr=4.8308e-04) (hash(x)=6123910) +507 train 7.548012 (lr=4.8210e-04) (hash(x)=7662975) +508 train 7.509267 (lr=4.8111e-04) (hash(x)=7191898) +509 train 7.439939 (lr=4.8013e-04) (hash(x)=6669539) +510 train 7.491449 (lr=4.7914e-04) (hash(x)=6557481) +511 train 7.400560 (lr=4.7815e-04) (hash(x)=5015998) +512 train 7.446541 (lr=4.7715e-04) (hash(x)=4964540) +513 train 7.317691 (lr=4.7615e-04) (hash(x)=5458386) +514 train 7.688615 (lr=4.7515e-04) (hash(x)=6077616) +515 train 7.435133 (lr=4.7415e-04) (hash(x)=4849847) +516 train 7.495171 (lr=4.7315e-04) (hash(x)=5431422) +517 train 7.674491 (lr=4.7214e-04) (hash(x)=5125562) +518 train 7.600319 (lr=4.7113e-04) (hash(x)=5587715) +519 train 7.633126 (lr=4.7011e-04) (hash(x)=6012047) +520 train 7.495192 (lr=4.6909e-04) (hash(x)=5668436) +521 train 7.497051 (lr=4.6807e-04) (hash(x)=6079364) +522 train 7.626535 (lr=4.6705e-04) (hash(x)=5200504) +523 train 7.381415 (lr=4.6603e-04) (hash(x)=6030395) +524 train 7.610798 (lr=4.6500e-04) (hash(x)=6855319) +525 train 7.377956 (lr=4.6397e-04) (hash(x)=6781762) +526 train 7.539228 (lr=4.6294e-04) (hash(x)=6717939) +527 train 7.529874 (lr=4.6190e-04) (hash(x)=5238325) +528 train 7.418520 (lr=4.6086e-04) (hash(x)=5808069) +529 train 7.741337 (lr=4.5982e-04) (hash(x)=8611144) +530 train 7.438085 (lr=4.5878e-04) (hash(x)=6028738) +531 train 7.476452 (lr=4.5774e-04) (hash(x)=6901605) +532 train 7.418335 (lr=4.5669e-04) (hash(x)=6723307) +533 train 7.521075 (lr=4.5564e-04) (hash(x)=5499337) +534 train 7.457000 (lr=4.5458e-04) (hash(x)=6586372) +535 train 7.556586 (lr=4.5353e-04) (hash(x)=7134874) +536 train 7.483534 (lr=4.5247e-04) (hash(x)=8415623) +537 train 7.503858 (lr=4.5141e-04) (hash(x)=6149038) +538 train 7.538121 (lr=4.5035e-04) (hash(x)=6078325) +539 train 7.505559 (lr=4.4928e-04) (hash(x)=6609760) +540 train 7.413511 (lr=4.4822e-04) (hash(x)=6185253) +541 train 7.776970 (lr=4.4715e-04) (hash(x)=6652627) +542 train 7.591706 (lr=4.4608e-04) (hash(x)=7758536) +543 train 7.565064 (lr=4.4500e-04) (hash(x)=8618579) +544 train 7.525749 (lr=4.4393e-04) (hash(x)=6710226) +545 train 7.394250 (lr=4.4285e-04) (hash(x)=5896892) +546 train 7.430432 (lr=4.4177e-04) (hash(x)=6332995) +547 train 7.822806 (lr=4.4069e-04) (hash(x)=8945854) +548 train 7.401792 (lr=4.3960e-04) (hash(x)=4329129) +549 train 7.468691 (lr=4.3852e-04) (hash(x)=6775103) +550 val loss 7.4938 +550 val perplexity 1796.9258 +550 train 7.568115 (lr=4.3743e-04) (hash(x)=4465735) +551 train 7.444073 (lr=4.3634e-04) (hash(x)=6200024) +552 train 7.417078 (lr=4.3524e-04) (hash(x)=5520748) +553 train 7.436573 (lr=4.3415e-04) (hash(x)=5238139) +554 train 7.671274 (lr=4.3305e-04) (hash(x)=7639817) +555 train 7.431081 (lr=4.3195e-04) (hash(x)=5780948) +556 train 7.570434 (lr=4.3085e-04) (hash(x)=6733444) +557 train 7.528986 (lr=4.2975e-04) (hash(x)=6168407) +558 train 7.559849 (lr=4.2864e-04) (hash(x)=6680197) +559 train 7.481858 (lr=4.2754e-04) (hash(x)=3775881) +560 train 7.330757 (lr=4.2643e-04) (hash(x)=5784096) +561 train 7.739794 (lr=4.2532e-04) (hash(x)=6848709) +562 train 7.789821 (lr=4.2420e-04) (hash(x)=7449019) +563 train 7.867923 (lr=4.2309e-04) (hash(x)=6478113) +564 train 7.532221 (lr=4.2197e-04) (hash(x)=5925744) +565 train 7.593219 (lr=4.2086e-04) (hash(x)=6483914) +566 train 7.516080 (lr=4.1974e-04) (hash(x)=6010847) +567 train 7.572649 (lr=4.1861e-04) (hash(x)=5927795) +568 train 7.580252 (lr=4.1749e-04) (hash(x)=5896332) +569 train 7.528873 (lr=4.1637e-04) (hash(x)=8438033) +570 train 7.614348 (lr=4.1524e-04) (hash(x)=6081660) +571 train 7.548667 (lr=4.1411e-04) (hash(x)=5684788) +572 train 7.465087 (lr=4.1298e-04) (hash(x)=6272055) +573 train 7.417908 (lr=4.1185e-04) (hash(x)=5710182) +574 train 7.526451 (lr=4.1072e-04) (hash(x)=6219616) +575 train 7.505020 (lr=4.0958e-04) (hash(x)=6160063) +576 train 7.502904 (lr=4.0845e-04) (hash(x)=5710809) +577 train 7.282405 (lr=4.0731e-04) (hash(x)=5955100) +578 train 7.313626 (lr=4.0617e-04) (hash(x)=5356088) +579 train 7.388020 (lr=4.0503e-04) (hash(x)=6672309) +580 train 7.600929 (lr=4.0389e-04) (hash(x)=5841684) +581 train 7.898613 (lr=4.0275e-04) (hash(x)=9001564) +582 train 8.465384 (lr=4.0160e-04) (hash(x)=6897178) +583 train 7.718410 (lr=4.0045e-04) (hash(x)=5454654) +584 train 7.473066 (lr=3.9931e-04) (hash(x)=6391454) +585 train 7.474938 (lr=3.9816e-04) (hash(x)=5174062) +586 train 7.565986 (lr=3.9701e-04) (hash(x)=5197924) +587 train 7.628664 (lr=3.9586e-04) (hash(x)=6199203) +588 train 7.464124 (lr=3.9470e-04) (hash(x)=5786498) +589 train 7.567856 (lr=3.9355e-04) (hash(x)=8352747) +590 train 7.846512 (lr=3.9239e-04) (hash(x)=4829700) +591 train 7.404994 (lr=3.9124e-04) (hash(x)=4547106) +592 train 7.677233 (lr=3.9008e-04) (hash(x)=7686831) +593 train 7.548573 (lr=3.8892e-04) (hash(x)=6433099) +594 train 7.433736 (lr=3.8776e-04) (hash(x)=4826460) +595 train 7.505824 (lr=3.8660e-04) (hash(x)=6424428) +596 train 7.401475 (lr=3.8544e-04) (hash(x)=6073605) +597 train 7.697602 (lr=3.8428e-04) (hash(x)=5975712) +598 train 7.360698 (lr=3.8311e-04) (hash(x)=7030029) +599 train 7.625644 (lr=3.8195e-04) (hash(x)=5458532) +600 val loss 7.5493 +600 val perplexity 1899.3959 +600 train 7.471428 (lr=3.8078e-04) (hash(x)=7823919) +601 train 7.853218 (lr=3.7961e-04) (hash(x)=7002774) +602 train 7.693135 (lr=3.7844e-04) (hash(x)=7056399) +603 train 7.855587 (lr=3.7727e-04) (hash(x)=8206173) +604 train 7.676380 (lr=3.7610e-04) (hash(x)=8034846) +605 train 7.937305 (lr=3.7493e-04) (hash(x)=7784971) +606 train 8.153524 (lr=3.7376e-04) (hash(x)=7118076) +607 train 7.478840 (lr=3.7259e-04) (hash(x)=6001843) +608 train 7.592979 (lr=3.7142e-04) (hash(x)=5582437) +609 train 7.699918 (lr=3.7024e-04) (hash(x)=5698642) +610 train 7.606857 (lr=3.6907e-04) (hash(x)=6615301) +611 train 7.631514 (lr=3.6789e-04) (hash(x)=6600751) +612 train 7.572807 (lr=3.6671e-04) (hash(x)=6880955) +613 train 7.630366 (lr=3.6554e-04) (hash(x)=5804610) +614 train 7.558325 (lr=3.6436e-04) (hash(x)=6263347) +615 train 7.528210 (lr=3.6318e-04) (hash(x)=5162652) +616 train 7.550850 (lr=3.6200e-04) (hash(x)=6055710) +617 train 7.507485 (lr=3.6082e-04) (hash(x)=5297006) +618 train 7.506775 (lr=3.5964e-04) (hash(x)=5923648) +619 train 7.499279 (lr=3.5846e-04) (hash(x)=6728323) +620 train 7.490343 (lr=3.5728e-04) (hash(x)=6660239) +621 train 7.452674 (lr=3.5610e-04) (hash(x)=3964882) +622 train 7.496390 (lr=3.5491e-04) (hash(x)=5868942) +623 train 7.430064 (lr=3.5373e-04) (hash(x)=6735993) +624 train 7.739559 (lr=3.5255e-04) (hash(x)=5926190) +625 train 7.451614 (lr=3.5136e-04) (hash(x)=5150316) +626 train 7.466722 (lr=3.5018e-04) (hash(x)=7571467) +627 train 7.374788 (lr=3.4899e-04) (hash(x)=5220448) +628 train 7.397710 (lr=3.4781e-04) (hash(x)=6790397) +629 train 7.821467 (lr=3.4662e-04) (hash(x)=6971289) +630 train 7.743573 (lr=3.4544e-04) (hash(x)=7123359) +631 train 7.565454 (lr=3.4425e-04) (hash(x)=5012069) +632 train 7.510221 (lr=3.4306e-04) (hash(x)=6183574) +633 train 7.435110 (lr=3.4188e-04) (hash(x)=6576136) +634 train 7.471381 (lr=3.4069e-04) (hash(x)=6157346) +635 train 7.478382 (lr=3.3950e-04) (hash(x)=6077647) +636 train 7.685055 (lr=3.3831e-04) (hash(x)=8369488) +637 train 7.497798 (lr=3.3713e-04) (hash(x)=6032381) +638 train 7.463762 (lr=3.3594e-04) (hash(x)=5924756) +639 train 7.471825 (lr=3.3475e-04) (hash(x)=8410716) +640 train 7.457464 (lr=3.3356e-04) (hash(x)=5803440) +641 train 7.535853 (lr=3.3238e-04) (hash(x)=6212516) +642 train 7.608991 (lr=3.3119e-04) (hash(x)=7165945) +643 train 7.324841 (lr=3.3000e-04) (hash(x)=5298545) +644 train 7.548638 (lr=3.2881e-04) (hash(x)=6281739) +645 train 7.552476 (lr=3.2762e-04) (hash(x)=5779073) +646 train 7.452138 (lr=3.2644e-04) (hash(x)=5090107) +647 train 7.514206 (lr=3.2525e-04) (hash(x)=6340947) +648 train 7.276607 (lr=3.2406e-04) (hash(x)=4741418) +649 train 7.204868 (lr=3.2287e-04) (hash(x)=6530441) +650 val loss 7.5406 +650 val perplexity 1882.9160 +650 train 7.725106 (lr=3.2169e-04) (hash(x)=6396041) +651 train 7.444445 (lr=3.2050e-04) (hash(x)=7818007) +652 train 7.456826 (lr=3.1931e-04) (hash(x)=6478457) +653 train 7.526430 (lr=3.1812e-04) (hash(x)=6277435) +654 train 7.486071 (lr=3.1694e-04) (hash(x)=6042369) +655 train 7.471161 (lr=3.1575e-04) (hash(x)=6226320) +656 train 7.474314 (lr=3.1456e-04) (hash(x)=5826883) +657 train 7.560239 (lr=3.1338e-04) (hash(x)=5463751) +658 train 7.492961 (lr=3.1219e-04) (hash(x)=6433080) +659 train 7.351055 (lr=3.1101e-04) (hash(x)=6579329) +660 train 7.382396 (lr=3.0982e-04) (hash(x)=4724703) +661 train 7.708202 (lr=3.0864e-04) (hash(x)=6660540) +662 train 7.533688 (lr=3.0745e-04) (hash(x)=5918756) +663 train 7.471567 (lr=3.0627e-04) (hash(x)=6491272) +664 train 7.405888 (lr=3.0509e-04) (hash(x)=5452863) +665 train 7.549006 (lr=3.0390e-04) (hash(x)=6766947) +666 train 7.850081 (lr=3.0272e-04) (hash(x)=7459504) +667 train 7.566401 (lr=3.0154e-04) (hash(x)=3721218) +668 train 7.739560 (lr=3.0036e-04) (hash(x)=7929571) +669 train 7.459270 (lr=2.9918e-04) (hash(x)=5229898) +670 train 7.517999 (lr=2.9800e-04) (hash(x)=6083090) +671 train 7.369981 (lr=2.9682e-04) (hash(x)=6054428) +672 train 7.473878 (lr=2.9564e-04) (hash(x)=6072563) +673 train 7.579222 (lr=2.9446e-04) (hash(x)=6290464) +674 train 7.662116 (lr=2.9329e-04) (hash(x)=6314742) +675 train 7.359091 (lr=2.9211e-04) (hash(x)=6904498) +676 train 7.504623 (lr=2.9093e-04) (hash(x)=5378107) +677 train 7.612312 (lr=2.8976e-04) (hash(x)=7765805) +678 train 7.448923 (lr=2.8858e-04) (hash(x)=5871280) +679 train 7.623127 (lr=2.8741e-04) (hash(x)=6543764) +680 train 7.461518 (lr=2.8624e-04) (hash(x)=7369665) +681 train 7.547501 (lr=2.8507e-04) (hash(x)=7204955) +682 train 7.501801 (lr=2.8390e-04) (hash(x)=5856543) +683 train 7.369583 (lr=2.8273e-04) (hash(x)=4423711) +684 train 7.337687 (lr=2.8156e-04) (hash(x)=5818153) +685 train 7.445026 (lr=2.8039e-04) (hash(x)=5343477) +686 train 7.609451 (lr=2.7922e-04) (hash(x)=6581702) +687 train 7.459729 (lr=2.7805e-04) (hash(x)=6595856) +688 train 7.406947 (lr=2.7689e-04) (hash(x)=5325378) +689 train 7.317366 (lr=2.7572e-04) (hash(x)=7229015) +690 train 7.486290 (lr=2.7456e-04) (hash(x)=5918186) +691 train 7.365761 (lr=2.7340e-04) (hash(x)=5916034) +692 train 7.357935 (lr=2.7224e-04) (hash(x)=5280722) +693 train 7.757558 (lr=2.7108e-04) (hash(x)=6939521) +694 train 7.489736 (lr=2.6992e-04) (hash(x)=5172566) +695 train 7.352476 (lr=2.6876e-04) (hash(x)=5492185) +696 train 7.214737 (lr=2.6761e-04) (hash(x)=5779011) +697 train 7.479747 (lr=2.6645e-04) (hash(x)=6898006) +698 train 7.339122 (lr=2.6530e-04) (hash(x)=5779217) +699 train 7.197156 (lr=2.6414e-04) (hash(x)=5462008) +700 val loss 7.4713 +700 val perplexity 1756.8961 +700 train 7.317289 (lr=2.6299e-04) (hash(x)=6243843) +701 train 7.388223 (lr=2.6184e-04) (hash(x)=7821902) +702 train 7.454326 (lr=2.6069e-04) (hash(x)=5222501) +703 train 7.407744 (lr=2.5955e-04) (hash(x)=6608108) +704 train 7.520305 (lr=2.5840e-04) (hash(x)=7602879) +705 train 7.435827 (lr=2.5725e-04) (hash(x)=6295394) +706 train 7.408885 (lr=2.5611e-04) (hash(x)=6579907) +707 train 7.302642 (lr=2.5497e-04) (hash(x)=6803449) +708 train 7.379996 (lr=2.5383e-04) (hash(x)=5413733) +709 train 7.340014 (lr=2.5269e-04) (hash(x)=7444134) +710 train 7.485411 (lr=2.5155e-04) (hash(x)=7028652) +711 train 7.307853 (lr=2.5042e-04) (hash(x)=5361923) +712 train 7.405814 (lr=2.4928e-04) (hash(x)=5478293) +713 train 7.376436 (lr=2.4815e-04) (hash(x)=7803039) +714 train 7.559270 (lr=2.4702e-04) (hash(x)=6469017) +715 train 7.447619 (lr=2.4589e-04) (hash(x)=7042578) +716 train 7.499601 (lr=2.4476e-04) (hash(x)=6927957) +717 train 7.324241 (lr=2.4363e-04) (hash(x)=6647007) +718 train 7.294512 (lr=2.4251e-04) (hash(x)=6230888) +719 train 7.554673 (lr=2.4139e-04) (hash(x)=6303658) +720 train 7.585694 (lr=2.4026e-04) (hash(x)=6769880) +721 train 7.445073 (lr=2.3914e-04) (hash(x)=6158927) +722 train 7.424825 (lr=2.3803e-04) (hash(x)=5991631) +723 train 7.296274 (lr=2.3691e-04) (hash(x)=6419656) +724 train 7.286866 (lr=2.3580e-04) (hash(x)=7739209) +725 train 7.223708 (lr=2.3468e-04) (hash(x)=7891271) +726 train 7.556625 (lr=2.3357e-04) (hash(x)=7171433) +727 train 7.368251 (lr=2.3246e-04) (hash(x)=7099888) +728 train 7.377460 (lr=2.3136e-04) (hash(x)=6103730) +729 train 7.486798 (lr=2.3025e-04) (hash(x)=6352424) +730 train 7.377328 (lr=2.2915e-04) (hash(x)=4893671) +731 train 7.327184 (lr=2.2805e-04) (hash(x)=5863145) +732 train 7.432084 (lr=2.2695e-04) (hash(x)=5502233) +733 train 7.324784 (lr=2.2585e-04) (hash(x)=6844597) +734 train 7.365928 (lr=2.2476e-04) (hash(x)=6744526) +735 train 7.505476 (lr=2.2366e-04) (hash(x)=6009861) +736 train 7.378266 (lr=2.2257e-04) (hash(x)=6152358) +737 train 7.303636 (lr=2.2148e-04) (hash(x)=5374957) +738 train 7.327635 (lr=2.2040e-04) (hash(x)=6495309) +739 train 7.468936 (lr=2.1931e-04) (hash(x)=3923225) +740 train 7.243707 (lr=2.1823e-04) (hash(x)=6255243) +741 train 7.392305 (lr=2.1715e-04) (hash(x)=5848862) +742 train 7.421060 (lr=2.1607e-04) (hash(x)=4535000) +743 train 7.300793 (lr=2.1500e-04) (hash(x)=4440634) +744 train 7.288959 (lr=2.1392e-04) (hash(x)=5222077) +745 train 7.311811 (lr=2.1285e-04) (hash(x)=4788998) +746 train 7.317223 (lr=2.1178e-04) (hash(x)=6108350) +747 train 7.252658 (lr=2.1072e-04) (hash(x)=7378165) +748 train 7.323622 (lr=2.0965e-04) (hash(x)=5475646) +749 train 7.338755 (lr=2.0859e-04) (hash(x)=4771243) +750 val loss 7.4229 +750 val perplexity 1673.8523 +750 train 7.211879 (lr=2.0753e-04) (hash(x)=6668088) +751 train 7.428833 (lr=2.0647e-04) (hash(x)=5716089) +752 train 7.378295 (lr=2.0542e-04) (hash(x)=6991946) +753 train 7.280039 (lr=2.0436e-04) (hash(x)=7991009) +754 train 7.392335 (lr=2.0331e-04) (hash(x)=6037018) +755 train 7.352338 (lr=2.0226e-04) (hash(x)=5348607) +756 train 7.484348 (lr=2.0122e-04) (hash(x)=5190526) +757 train 7.377511 (lr=2.0018e-04) (hash(x)=6036146) +758 train 7.274209 (lr=1.9914e-04) (hash(x)=5329783) +759 train 7.366966 (lr=1.9810e-04) (hash(x)=6658718) +760 train 7.277110 (lr=1.9706e-04) (hash(x)=4820939) +761 train 7.268450 (lr=1.9603e-04) (hash(x)=6176253) +762 train 7.237620 (lr=1.9500e-04) (hash(x)=5316750) +763 train 7.328389 (lr=1.9397e-04) (hash(x)=4542895) +764 train 7.127876 (lr=1.9295e-04) (hash(x)=5395673) +765 train 7.220059 (lr=1.9193e-04) (hash(x)=5549073) +766 train 7.456569 (lr=1.9091e-04) (hash(x)=5233723) +767 train 7.505293 (lr=1.8989e-04) (hash(x)=5342783) +768 train 7.447536 (lr=1.8887e-04) (hash(x)=5552448) +769 train 7.584366 (lr=1.8786e-04) (hash(x)=6549546) +770 train 7.248025 (lr=1.8685e-04) (hash(x)=3816493) +771 train 7.294997 (lr=1.8585e-04) (hash(x)=6170599) +772 train 7.799537 (lr=1.8485e-04) (hash(x)=6708759) +773 train 7.397484 (lr=1.8385e-04) (hash(x)=8483134) +774 train 8.000689 (lr=1.8285e-04) (hash(x)=5583732) +775 train 7.382457 (lr=1.8185e-04) (hash(x)=4865036) +776 train 7.298882 (lr=1.8086e-04) (hash(x)=7234336) +777 train 7.311327 (lr=1.7987e-04) (hash(x)=4433890) +778 train 7.632164 (lr=1.7889e-04) (hash(x)=7484636) +779 train 8.123683 (lr=1.7790e-04) (hash(x)=6738597) +780 train 7.339438 (lr=1.7692e-04) (hash(x)=6752421) +781 train 7.543256 (lr=1.7595e-04) (hash(x)=5459620) +782 train 7.458041 (lr=1.7497e-04) (hash(x)=6718131) +783 train 7.426504 (lr=1.7400e-04) (hash(x)=4604074) +784 train 7.296329 (lr=1.7303e-04) (hash(x)=5946124) +785 train 7.549358 (lr=1.7207e-04) (hash(x)=8045501) +786 train 7.664804 (lr=1.7111e-04) (hash(x)=5712725) +787 train 7.388672 (lr=1.7015e-04) (hash(x)=6176464) +788 train 7.464062 (lr=1.6919e-04) (hash(x)=6276702) +789 train 7.289416 (lr=1.6824e-04) (hash(x)=6127317) +790 train 7.416360 (lr=1.6729e-04) (hash(x)=7221374) +791 train 7.384896 (lr=1.6634e-04) (hash(x)=5571462) +792 train 7.395666 (lr=1.6540e-04) (hash(x)=7518021) +793 train 7.380175 (lr=1.6446e-04) (hash(x)=6640755) +794 train 7.478694 (lr=1.6352e-04) (hash(x)=6870405) +795 train 7.470301 (lr=1.6259e-04) (hash(x)=6147295) +796 train 7.335927 (lr=1.6166e-04) (hash(x)=6782583) +797 train 7.459074 (lr=1.6073e-04) (hash(x)=6120461) +798 train 7.395648 (lr=1.5981e-04) (hash(x)=5893870) +799 train 7.333735 (lr=1.5889e-04) (hash(x)=5123928) +800 val loss 7.4147 +800 val perplexity 1660.1960 +800 train 7.402070 (lr=1.5797e-04) (hash(x)=7037251) +801 train 7.387918 (lr=1.5705e-04) (hash(x)=5428813) +802 train 7.322593 (lr=1.5614e-04) (hash(x)=5550387) +803 train 7.411188 (lr=1.5524e-04) (hash(x)=6448586) +804 train 7.553979 (lr=1.5433e-04) (hash(x)=5916934) +805 train 7.498193 (lr=1.5343e-04) (hash(x)=8116987) +806 train 7.477918 (lr=1.5254e-04) (hash(x)=6210899) +807 train 7.583663 (lr=1.5164e-04) (hash(x)=5974342) +808 train 7.566135 (lr=1.5075e-04) (hash(x)=7236199) +809 train 7.512315 (lr=1.4987e-04) (hash(x)=5261336) +810 train 7.330853 (lr=1.4898e-04) (hash(x)=6310720) +811 train 7.382512 (lr=1.4810e-04) (hash(x)=5307056) +812 train 7.215851 (lr=1.4723e-04) (hash(x)=7356633) +813 train 7.332372 (lr=1.4635e-04) (hash(x)=5865119) +814 train 7.244471 (lr=1.4548e-04) (hash(x)=5979205) +815 train 7.391685 (lr=1.4462e-04) (hash(x)=6672380) +816 train 7.384471 (lr=1.4376e-04) (hash(x)=5565030) +817 train 7.349057 (lr=1.4290e-04) (hash(x)=6886810) +818 train 7.405274 (lr=1.4204e-04) (hash(x)=5926478) +819 train 7.597179 (lr=1.4119e-04) (hash(x)=6564071) +820 train 7.251323 (lr=1.4035e-04) (hash(x)=5024280) +821 train 7.256396 (lr=1.3950e-04) (hash(x)=7705089) +822 train 7.226871 (lr=1.3866e-04) (hash(x)=4037371) +823 train 7.334517 (lr=1.3783e-04) (hash(x)=5773073) +824 train 7.342059 (lr=1.3699e-04) (hash(x)=7158139) +825 train 7.196819 (lr=1.3616e-04) (hash(x)=5905976) +826 train 7.609812 (lr=1.3534e-04) (hash(x)=13897369) +827 train 8.701560 (lr=1.3452e-04) (hash(x)=6936653) +828 train 7.387619 (lr=1.3370e-04) (hash(x)=6592246) +829 train 7.339836 (lr=1.3289e-04) (hash(x)=6592773) +830 train 7.399012 (lr=1.3208e-04) (hash(x)=5461178) +831 train 7.195902 (lr=1.3127e-04) (hash(x)=6796551) +832 train 7.389696 (lr=1.3047e-04) (hash(x)=4721691) +833 train 7.318141 (lr=1.2967e-04) (hash(x)=6151589) +834 train 7.450128 (lr=1.2887e-04) (hash(x)=7008995) +835 train 7.782890 (lr=1.2808e-04) (hash(x)=7045164) +836 train 7.372104 (lr=1.2730e-04) (hash(x)=6614221) +837 train 7.412194 (lr=1.2651e-04) (hash(x)=6650506) +838 train 7.237723 (lr=1.2574e-04) (hash(x)=6363762) +839 train 7.383145 (lr=1.2496e-04) (hash(x)=7839748) +840 train 7.292810 (lr=1.2419e-04) (hash(x)=5124077) +841 train 7.768057 (lr=1.2342e-04) (hash(x)=6028671) +842 train 7.241242 (lr=1.2266e-04) (hash(x)=5427175) +843 train 7.565908 (lr=1.2190e-04) (hash(x)=6118408) +844 train 7.361271 (lr=1.2115e-04) (hash(x)=6022552) +845 train 7.353770 (lr=1.2040e-04) (hash(x)=5757526) +846 train 7.802000 (lr=1.1965e-04) (hash(x)=6476549) +847 train 7.171439 (lr=1.1891e-04) (hash(x)=6030172) +848 train 7.514966 (lr=1.1817e-04) (hash(x)=5917229) +849 train 7.568004 (lr=1.1743e-04) (hash(x)=6719882) +850 val loss 7.4039 +850 val perplexity 1642.3744 +850 train 7.442924 (lr=1.1670e-04) (hash(x)=5441498) +851 train 7.333658 (lr=1.1598e-04) (hash(x)=5028050) +852 train 7.370717 (lr=1.1525e-04) (hash(x)=8487491) +853 train 7.358019 (lr=1.1454e-04) (hash(x)=5682910) +854 train 7.577865 (lr=1.1382e-04) (hash(x)=6781362) +855 train 7.375556 (lr=1.1311e-04) (hash(x)=5747891) +856 train 7.428603 (lr=1.1241e-04) (hash(x)=7627661) +857 train 7.081341 (lr=1.1171e-04) (hash(x)=5734208) +858 train 7.236390 (lr=1.1101e-04) (hash(x)=6162015) +859 train 7.457911 (lr=1.1032e-04) (hash(x)=7024381) +860 train 7.635249 (lr=1.0963e-04) (hash(x)=5198498) +861 train 7.619263 (lr=1.0894e-04) (hash(x)=7814361) +862 train 7.503750 (lr=1.0826e-04) (hash(x)=7394995) +863 train 7.395034 (lr=1.0759e-04) (hash(x)=5765893) +864 train 7.211984 (lr=1.0692e-04) (hash(x)=4990435) +865 train 7.329374 (lr=1.0625e-04) (hash(x)=5572048) +866 train 7.495348 (lr=1.0559e-04) (hash(x)=7093293) +867 train 7.391334 (lr=1.0493e-04) (hash(x)=5610058) +868 train 7.290190 (lr=1.0427e-04) (hash(x)=6771468) +869 train 7.310052 (lr=1.0362e-04) (hash(x)=4459483) +870 train 7.228568 (lr=1.0298e-04) (hash(x)=4926546) +871 train 7.333742 (lr=1.0234e-04) (hash(x)=6758411) +872 train 7.290088 (lr=1.0170e-04) (hash(x)=7394277) +873 train 7.405588 (lr=1.0107e-04) (hash(x)=6701381) +874 train 7.750064 (lr=1.0044e-04) (hash(x)=8120966) +875 train 7.281210 (lr=9.9818e-05) (hash(x)=5416400) +876 train 7.283932 (lr=9.9199e-05) (hash(x)=6292778) +877 train 7.217313 (lr=9.8585e-05) (hash(x)=5919569) +878 train 7.511626 (lr=9.7975e-05) (hash(x)=7561740) +879 train 7.280114 (lr=9.7370e-05) (hash(x)=5282870) +880 train 7.317101 (lr=9.6769e-05) (hash(x)=5473238) +881 train 7.197863 (lr=9.6173e-05) (hash(x)=8072181) +882 train 7.208914 (lr=9.5581e-05) (hash(x)=6757322) +883 train 7.180673 (lr=9.4994e-05) (hash(x)=7996770) +884 train 7.273538 (lr=9.4412e-05) (hash(x)=3181021) +885 train 7.303356 (lr=9.3833e-05) (hash(x)=5093519) +886 train 7.278176 (lr=9.3260e-05) (hash(x)=5391352) +887 train 7.325156 (lr=9.2691e-05) (hash(x)=6270917) +888 train 7.312292 (lr=9.2127e-05) (hash(x)=5818195) +889 train 7.084382 (lr=9.1567e-05) (hash(x)=5852780) +890 train 7.007315 (lr=9.1012e-05) (hash(x)=5777928) +891 train 7.194953 (lr=9.0461e-05) (hash(x)=5327728) +892 train 7.223559 (lr=8.9916e-05) (hash(x)=7651281) +893 train 7.429352 (lr=8.9374e-05) (hash(x)=6260765) +894 train 7.311416 (lr=8.8838e-05) (hash(x)=6265102) +895 train 7.495597 (lr=8.8306e-05) (hash(x)=6212894) +896 train 7.249778 (lr=8.7779e-05) (hash(x)=6901967) +897 train 7.316270 (lr=8.7256e-05) (hash(x)=6724010) +898 train 7.302013 (lr=8.6738e-05) (hash(x)=6299033) +899 train 7.474260 (lr=8.6225e-05) (hash(x)=6059934) +900 val loss 7.3957 +900 val perplexity 1629.0153 +900 train 7.194336 (lr=8.5717e-05) (hash(x)=6029696) +901 train 7.104962 (lr=8.5213e-05) (hash(x)=5587382) +902 train 7.312527 (lr=8.4714e-05) (hash(x)=5890076) +903 train 7.235409 (lr=8.4220e-05) (hash(x)=7274108) +904 train 7.326291 (lr=8.3731e-05) (hash(x)=7975528) +905 train 7.366099 (lr=8.3246e-05) (hash(x)=6085396) +906 train 7.249203 (lr=8.2766e-05) (hash(x)=6724496) +907 train 7.255675 (lr=8.2291e-05) (hash(x)=4784666) +908 train 7.259977 (lr=8.1821e-05) (hash(x)=7193845) +909 train 7.421794 (lr=8.1356e-05) (hash(x)=6288638) +910 train 7.384106 (lr=8.0895e-05) (hash(x)=5685285) +911 train 7.362555 (lr=8.0439e-05) (hash(x)=7714288) +912 train 7.453488 (lr=7.9988e-05) (hash(x)=5983679) +913 train 7.401822 (lr=7.9542e-05) (hash(x)=5534748) +914 train 7.340928 (lr=7.9101e-05) (hash(x)=6545471) +915 train 7.333602 (lr=7.8664e-05) (hash(x)=6361270) +916 train 7.334080 (lr=7.8232e-05) (hash(x)=6257744) +917 train 7.352935 (lr=7.7806e-05) (hash(x)=4682956) +918 train 7.233799 (lr=7.7384e-05) (hash(x)=4521756) +919 train 7.387115 (lr=7.6967e-05) (hash(x)=7568935) +920 train 7.287231 (lr=7.6555e-05) (hash(x)=7969353) +921 train 7.478317 (lr=7.6148e-05) (hash(x)=7973311) +922 train 7.173110 (lr=7.5746e-05) (hash(x)=4843937) +923 train 7.320529 (lr=7.5348e-05) (hash(x)=6987352) +924 train 7.427464 (lr=7.4956e-05) (hash(x)=7179418) +925 train 7.106161 (lr=7.4568e-05) (hash(x)=5413904) +926 train 7.474583 (lr=7.4186e-05) (hash(x)=6028105) +927 train 7.423166 (lr=7.3808e-05) (hash(x)=6732924) +928 train 7.311118 (lr=7.3436e-05) (hash(x)=4547651) +929 train 7.466083 (lr=7.3068e-05) (hash(x)=6219754) +930 train 7.251711 (lr=7.2706e-05) (hash(x)=7465186) +931 train 7.369419 (lr=7.2348e-05) (hash(x)=6839070) +932 train 7.277572 (lr=7.1995e-05) (hash(x)=5390324) +933 train 7.233884 (lr=7.1648e-05) (hash(x)=6090120) +934 train 7.833404 (lr=7.1305e-05) (hash(x)=7123181) +935 train 7.529774 (lr=7.0967e-05) (hash(x)=7115176) +936 train 7.508936 (lr=7.0635e-05) (hash(x)=7016990) +937 train 7.307872 (lr=7.0307e-05) (hash(x)=4989299) +938 train 7.327625 (lr=6.9984e-05) (hash(x)=6783311) +939 train 7.299093 (lr=6.9667e-05) (hash(x)=7497590) +940 train 7.517374 (lr=6.9354e-05) (hash(x)=6767514) +941 train 7.276549 (lr=6.9047e-05) (hash(x)=3977557) +942 train 7.399262 (lr=6.8744e-05) (hash(x)=4806492) +943 train 7.315210 (lr=6.8447e-05) (hash(x)=5524165) +944 train 7.356539 (lr=6.8155e-05) (hash(x)=4930752) +945 train 7.337016 (lr=6.7868e-05) (hash(x)=5124936) +946 train 7.218724 (lr=6.7585e-05) (hash(x)=6877351) +947 train 7.500359 (lr=6.7308e-05) (hash(x)=5522119) +948 train 7.319206 (lr=6.7036e-05) (hash(x)=6183512) +949 train 7.230593 (lr=6.6769e-05) (hash(x)=5030865) +950 val loss 7.3867 +950 val perplexity 1614.3286 +950 train 7.328748 (lr=6.6508e-05) (hash(x)=6619812) +951 train 7.326028 (lr=6.6251e-05) (hash(x)=6411783) +952 train 7.324862 (lr=6.5999e-05) (hash(x)=6748982) +953 train 7.226121 (lr=6.5753e-05) (hash(x)=6581937) +954 train 7.339303 (lr=6.5511e-05) (hash(x)=7881022) +955 train 7.294113 (lr=6.5275e-05) (hash(x)=5116910) +956 train 7.093679 (lr=6.5044e-05) (hash(x)=4880833) +957 train 7.157098 (lr=6.4818e-05) (hash(x)=7353459) +958 train 7.197947 (lr=6.4597e-05) (hash(x)=4951302) +959 train 7.129109 (lr=6.4382e-05) (hash(x)=6344535) +960 train 7.733262 (lr=6.4171e-05) (hash(x)=7411763) +961 train 7.306331 (lr=6.3966e-05) (hash(x)=5840169) +962 train 7.393124 (lr=6.3765e-05) (hash(x)=5784788) +963 train 7.212029 (lr=6.3570e-05) (hash(x)=6754290) +964 train 7.480842 (lr=6.3380e-05) (hash(x)=6369963) +965 train 7.557301 (lr=6.3195e-05) (hash(x)=6484573) +966 train 7.139091 (lr=6.3016e-05) (hash(x)=6516338) +967 train 7.194467 (lr=6.2841e-05) (hash(x)=5260125) +968 train 7.308279 (lr=6.2672e-05) (hash(x)=5781624) +969 train 7.106126 (lr=6.2508e-05) (hash(x)=4881179) +970 train 7.224420 (lr=6.2349e-05) (hash(x)=6707821) +971 train 7.369723 (lr=6.2195e-05) (hash(x)=5001634) +972 train 7.237186 (lr=6.2046e-05) (hash(x)=4402949) +973 train 7.255580 (lr=6.1903e-05) (hash(x)=7424810) +974 train 7.137177 (lr=6.1765e-05) (hash(x)=4814803) +975 train 7.053448 (lr=6.1632e-05) (hash(x)=5176431) +976 train 7.244096 (lr=6.1504e-05) (hash(x)=5769393) +977 train 7.190416 (lr=6.1381e-05) (hash(x)=5421624) +978 train 7.404060 (lr=6.1264e-05) (hash(x)=5999773) +979 train 7.137156 (lr=6.1152e-05) (hash(x)=5674439) +980 train 7.222005 (lr=6.1045e-05) (hash(x)=6345351) +981 train 7.152803 (lr=6.0943e-05) (hash(x)=5819157) +982 train 7.368664 (lr=6.0846e-05) (hash(x)=11159355) +983 train 7.343806 (lr=6.0755e-05) (hash(x)=6506856) +984 train 7.247784 (lr=6.0669e-05) (hash(x)=6331023) +985 train 7.153956 (lr=6.0588e-05) (hash(x)=6119124) +986 train 7.362333 (lr=6.0512e-05) (hash(x)=8142528) +987 train 7.506615 (lr=6.0442e-05) (hash(x)=6241669) +988 train 7.159579 (lr=6.0376e-05) (hash(x)=3852991) +989 train 6.913616 (lr=6.0316e-05) (hash(x)=4992756) +990 train 7.596752 (lr=6.0261e-05) (hash(x)=7097145) +991 train 7.384545 (lr=6.0212e-05) (hash(x)=7277927) +992 train 7.451182 (lr=6.0167e-05) (hash(x)=5661400) +993 train 7.378108 (lr=6.0128e-05) (hash(x)=6622097) +994 train 7.501946 (lr=6.0094e-05) (hash(x)=5016804) +995 train 7.562570 (lr=6.0065e-05) (hash(x)=7026582) +996 train 7.363502 (lr=6.0042e-05) (hash(x)=5639136) +997 train 7.515571 (lr=6.0024e-05) (hash(x)=5840987) +998 train 7.150072 (lr=6.0010e-05) (hash(x)=5265410) +999 val loss 7.3822 +999 val perplexity 1607.0883 +999 train 7.134945 (lr=6.0003e-05) (hash(x)=4351074)