diff --git "a/lr1e-4_total_batch_size10240_seq_len128/log2.txt" "b/lr1e-4_total_batch_size10240_seq_len128/log2.txt" --- "a/lr1e-4_total_batch_size10240_seq_len128/log2.txt" +++ "b/lr1e-4_total_batch_size10240_seq_len128/log2.txt" @@ -1,1043 +1,5203 @@ -max_steps: 1000 -0 val loss 11.6870 -0 val perplexity 119016.5000 -0 train 11.691129 (lr=3.4965e-07) (hash(x)=6605789) -1 train 11.715714 (lr=6.9930e-07) (hash(x)=5113283) -2 train 11.677877 (lr=1.0490e-06) (hash(x)=7007748) -3 train 11.696216 (lr=1.3986e-06) (hash(x)=5534142) -4 train 11.698164 (lr=1.7483e-06) (hash(x)=5974274) -5 train 11.693561 (lr=2.0979e-06) (hash(x)=6763231) -6 train 11.663198 (lr=2.4476e-06) (hash(x)=6706513) -7 train 11.692604 (lr=2.7972e-06) (hash(x)=6328012) -8 train 11.669147 (lr=3.1469e-06) (hash(x)=6183012) -9 train 11.655550 (lr=3.4965e-06) (hash(x)=7052161) -10 train 11.631498 (lr=3.8462e-06) (hash(x)=6586466) -11 train 11.661675 (lr=4.1958e-06) (hash(x)=5556098) -12 train 11.645960 (lr=4.5455e-06) (hash(x)=8155572) -13 train 11.602326 (lr=4.8951e-06) (hash(x)=4696943) -14 train 11.583433 (lr=5.2448e-06) (hash(x)=7649389) -15 train 11.568135 (lr=5.5944e-06) (hash(x)=6219138) -16 train 11.537117 (lr=5.9441e-06) (hash(x)=7075794) -17 train 11.528027 (lr=6.2937e-06) (hash(x)=6049878) -18 train 11.538563 (lr=6.6434e-06) (hash(x)=6385927) -19 train 11.504963 (lr=6.9930e-06) (hash(x)=5491972) -20 train 11.490391 (lr=7.3427e-06) (hash(x)=6061420) -21 train 11.492226 (lr=7.6923e-06) (hash(x)=8075458) -22 train 11.383057 (lr=8.0420e-06) (hash(x)=7238769) -23 train 11.447841 (lr=8.3916e-06) (hash(x)=5917741) -24 train 11.400802 (lr=8.7413e-06) (hash(x)=5430605) -25 train 11.395272 (lr=9.0909e-06) (hash(x)=5750403) -26 train 11.354577 (lr=9.4406e-06) (hash(x)=4792640) -27 train 11.341745 (lr=9.7902e-06) (hash(x)=6112458) -28 train 11.292657 (lr=1.0140e-05) (hash(x)=5801122) -29 train 11.317315 (lr=1.0490e-05) (hash(x)=5806490) -30 train 11.257146 (lr=1.0839e-05) (hash(x)=5754140) -31 train 11.199593 (lr=1.1189e-05) (hash(x)=6568379) -32 train 11.133384 (lr=1.1538e-05) (hash(x)=7134932) -33 train 11.164309 (lr=1.1888e-05) (hash(x)=7212403) -34 train 11.064849 (lr=1.2238e-05) (hash(x)=7720703) -35 train 11.096609 (lr=1.2587e-05) (hash(x)=7386082) -36 train 11.024403 (lr=1.2937e-05) (hash(x)=6848513) -37 train 11.035874 (lr=1.3287e-05) (hash(x)=6359743) -38 train 10.946769 (lr=1.3636e-05) (hash(x)=7536538) -39 train 10.977413 (lr=1.3986e-05) (hash(x)=6151674) -40 train 10.942835 (lr=1.4336e-05) (hash(x)=6317099) -41 train 10.886848 (lr=1.4685e-05) (hash(x)=7168704) -42 train 10.885317 (lr=1.5035e-05) (hash(x)=6736092) -43 train 10.812740 (lr=1.5385e-05) (hash(x)=7859060) -44 train 10.821023 (lr=1.5734e-05) (hash(x)=6958223) -45 train 10.686498 (lr=1.6084e-05) (hash(x)=6976239) -46 train 10.730842 (lr=1.6434e-05) (hash(x)=6956845) -47 train 10.738949 (lr=1.6783e-05) (hash(x)=6391506) -48 train 10.788889 (lr=1.7133e-05) (hash(x)=6113701) -49 train 10.591890 (lr=1.7483e-05) (hash(x)=5245999) -50 val loss 10.6346 -50 val perplexity 41549.5352 -50 train 10.623287 (lr=1.7832e-05) (hash(x)=5774189) -51 train 10.636392 (lr=1.8182e-05) (hash(x)=5985675) -52 train 10.594037 (lr=1.8531e-05) (hash(x)=6451776) -53 train 10.461292 (lr=1.8881e-05) (hash(x)=4355733) -54 train 10.536674 (lr=1.9231e-05) (hash(x)=6669188) -55 train 10.767937 (lr=1.9580e-05) (hash(x)=6984772) -56 train 10.482365 (lr=1.9930e-05) (hash(x)=7440580) -57 train 10.540380 (lr=2.0280e-05) (hash(x)=6244096) -58 train 10.531529 (lr=2.0629e-05) (hash(x)=8381560) -59 train 10.482718 (lr=2.0979e-05) (hash(x)=6603717) -60 train 10.406415 (lr=2.1329e-05) (hash(x)=6437516) -61 train 10.411435 (lr=2.1678e-05) (hash(x)=5669522) -62 train 10.355264 (lr=2.2028e-05) (hash(x)=5505889) -63 train 10.414718 (lr=2.2378e-05) (hash(x)=6190579) -64 train 10.417758 (lr=2.2727e-05) (hash(x)=5153196) -65 train 10.457509 (lr=2.3077e-05) (hash(x)=4912983) -66 train 10.406000 (lr=2.3427e-05) (hash(x)=5109125) -67 train 10.235314 (lr=2.3776e-05) (hash(x)=7276303) -68 train 10.400863 (lr=2.4126e-05) (hash(x)=6645716) -69 train 10.332122 (lr=2.4476e-05) (hash(x)=5479947) -70 train 10.451086 (lr=2.4825e-05) (hash(x)=7850360) -71 train 10.455929 (lr=2.5175e-05) (hash(x)=6630378) -72 train 10.349250 (lr=2.5524e-05) (hash(x)=6295358) -73 train 10.428650 (lr=2.5874e-05) (hash(x)=8097010) -74 train 10.360823 (lr=2.6224e-05) (hash(x)=3958188) -75 train 10.521447 (lr=2.6573e-05) (hash(x)=9989744) -76 train 10.334774 (lr=2.6923e-05) (hash(x)=6343832) -77 train 10.311204 (lr=2.7273e-05) (hash(x)=6694932) -78 train 10.278445 (lr=2.7622e-05) (hash(x)=6429137) -79 train 10.220717 (lr=2.7972e-05) (hash(x)=6317894) -80 train 10.144623 (lr=2.8322e-05) (hash(x)=5165595) -81 train 10.203988 (lr=2.8671e-05) (hash(x)=5046327) -82 train 10.299314 (lr=2.9021e-05) (hash(x)=7060363) -83 train 10.193643 (lr=2.9371e-05) (hash(x)=7947703) -84 train 10.129883 (lr=2.9720e-05) (hash(x)=5971240) -85 train 10.101086 (lr=3.0070e-05) (hash(x)=5916068) -86 train 10.165997 (lr=3.0420e-05) (hash(x)=7426277) -87 train 10.254584 (lr=3.0769e-05) (hash(x)=5777498) -88 train 10.221705 (lr=3.1119e-05) (hash(x)=6403331) -89 train 10.059228 (lr=3.1469e-05) (hash(x)=5753092) -90 train 10.120261 (lr=3.1818e-05) (hash(x)=5981486) -91 train 10.138000 (lr=3.2168e-05) (hash(x)=7723226) -92 train 10.086612 (lr=3.2517e-05) (hash(x)=6069558) -93 train 10.141511 (lr=3.2867e-05) (hash(x)=7007016) -94 train 10.032905 (lr=3.3217e-05) (hash(x)=5027958) -95 train 10.056123 (lr=3.3566e-05) (hash(x)=6491229) -96 train 10.060586 (lr=3.3916e-05) (hash(x)=7036653) -97 train 10.112430 (lr=3.4266e-05) (hash(x)=6390752) -98 train 10.217685 (lr=3.4615e-05) (hash(x)=7758167) -99 train 10.176164 (lr=3.4965e-05) (hash(x)=6019389) -100 val loss 10.0864 -100 val perplexity 24014.5977 -100 train 10.158809 (lr=3.5315e-05) (hash(x)=6503191) -101 train 9.981990 (lr=3.5664e-05) (hash(x)=7662067) -102 train 10.049532 (lr=3.6014e-05) (hash(x)=7901992) -103 train 10.092311 (lr=3.6364e-05) (hash(x)=4648609) -104 train 10.026969 (lr=3.6713e-05) (hash(x)=5897288) -105 train 9.998008 (lr=3.7063e-05) (hash(x)=4725966) -106 train 9.951184 (lr=3.7413e-05) (hash(x)=6243442) -107 train 10.000803 (lr=3.7762e-05) (hash(x)=5558355) -108 train 10.049534 (lr=3.8112e-05) (hash(x)=5400407) -109 train 9.979938 (lr=3.8462e-05) (hash(x)=6524933) -110 train 9.982258 (lr=3.8811e-05) (hash(x)=5889724) -111 train 9.947940 (lr=3.9161e-05) (hash(x)=6369326) -112 train 9.881700 (lr=3.9510e-05) (hash(x)=5911906) -113 train 9.994719 (lr=3.9860e-05) (hash(x)=6022625) -114 train 9.846291 (lr=4.0210e-05) (hash(x)=6584810) -115 train 9.940397 (lr=4.0559e-05) (hash(x)=4906853) -116 train 9.738394 (lr=4.0909e-05) (hash(x)=4564564) -117 train 9.710005 (lr=4.1259e-05) (hash(x)=5589269) -118 train 9.845630 (lr=4.1608e-05) (hash(x)=6969180) -119 train 9.838554 (lr=4.1958e-05) (hash(x)=6437376) -120 train 9.881484 (lr=4.2308e-05) (hash(x)=7116258) -121 train 9.859009 (lr=4.2657e-05) (hash(x)=7304892) -122 train 9.838655 (lr=4.3007e-05) (hash(x)=7366721) -123 train 9.825720 (lr=4.3357e-05) (hash(x)=7084093) -124 train 9.906609 (lr=4.3706e-05) (hash(x)=7197652) -125 train 9.792642 (lr=4.4056e-05) (hash(x)=5908178) -126 train 9.634016 (lr=4.4406e-05) (hash(x)=6349974) -127 train 9.669449 (lr=4.4755e-05) (hash(x)=7048804) -128 train 9.718451 (lr=4.5105e-05) (hash(x)=7909039) -129 train 9.742558 (lr=4.5455e-05) (hash(x)=6085549) -130 train 9.775120 (lr=4.5804e-05) (hash(x)=7463181) -131 train 9.685642 (lr=4.6154e-05) (hash(x)=5752594) -132 train 9.536407 (lr=4.6503e-05) (hash(x)=6114601) -133 train 9.566474 (lr=4.6853e-05) (hash(x)=7662769) -134 train 9.543540 (lr=4.7203e-05) (hash(x)=7485666) -135 train 9.284313 (lr=4.7552e-05) (hash(x)=6393520) -136 train 9.599241 (lr=4.7902e-05) (hash(x)=5586291) -137 train 9.706452 (lr=4.8252e-05) (hash(x)=5942867) -138 train 9.675098 (lr=4.8601e-05) (hash(x)=7574027) -139 train 9.608974 (lr=4.8951e-05) (hash(x)=6793550) -140 train 9.516984 (lr=4.9301e-05) (hash(x)=6264789) -141 train 9.483897 (lr=4.9650e-05) (hash(x)=7105976) -142 train 9.519382 (lr=5.0000e-05) (hash(x)=7244279) -143 train 9.530899 (lr=5.0350e-05) (hash(x)=6581348) -144 train 9.495308 (lr=5.0699e-05) (hash(x)=6543825) -145 train 9.433113 (lr=5.1049e-05) (hash(x)=5555598) -146 train 9.428387 (lr=5.1399e-05) (hash(x)=7254232) -147 train 9.366930 (lr=5.1748e-05) (hash(x)=6235837) -148 train 9.337235 (lr=5.2098e-05) (hash(x)=4738550) -149 train 9.329519 (lr=5.2448e-05) (hash(x)=5591770) -150 val loss 9.3583 -150 val perplexity 11594.8623 -150 train 9.720510 (lr=5.2797e-05) (hash(x)=8012491) -151 train 9.331465 (lr=5.3147e-05) (hash(x)=7083021) -152 train 9.370584 (lr=5.3497e-05) (hash(x)=6456022) -153 train 9.336122 (lr=5.3846e-05) (hash(x)=7281348) -154 train 9.382425 (lr=5.4196e-05) (hash(x)=7824794) -155 train 9.377480 (lr=5.4545e-05) (hash(x)=6155821) -156 train 9.306238 (lr=5.4895e-05) (hash(x)=7807564) -157 train 9.142947 (lr=5.5245e-05) (hash(x)=5736241) -158 train 9.229507 (lr=5.5594e-05) (hash(x)=5688415) -159 train 9.050955 (lr=5.5944e-05) (hash(x)=5657123) -160 train 9.043358 (lr=5.6294e-05) (hash(x)=6102985) -161 train 9.007455 (lr=5.6643e-05) (hash(x)=6452095) -162 train 9.028298 (lr=5.6993e-05) (hash(x)=5848921) -163 train 9.049395 (lr=5.7343e-05) (hash(x)=5312267) -164 train 9.039939 (lr=5.7692e-05) (hash(x)=5025297) -165 train 8.954381 (lr=5.8042e-05) (hash(x)=5434493) -166 train 9.139805 (lr=5.8392e-05) (hash(x)=5197474) -167 train 9.037271 (lr=5.8741e-05) (hash(x)=6830813) -168 train 9.008745 (lr=5.9091e-05) (hash(x)=5242548) -169 train 8.934137 (lr=5.9441e-05) (hash(x)=4752771) -170 train 8.994386 (lr=5.9790e-05) (hash(x)=6691249) -171 train 8.956799 (lr=6.0140e-05) (hash(x)=6424933) -172 train 8.924302 (lr=6.0490e-05) (hash(x)=6960120) -173 train 8.824750 (lr=6.0839e-05) (hash(x)=5786517) -174 train 8.833849 (lr=6.1189e-05) (hash(x)=7229689) -175 train 8.956733 (lr=6.1538e-05) (hash(x)=6680023) -176 train 8.773468 (lr=6.1888e-05) (hash(x)=7688393) -177 train 8.780998 (lr=6.2238e-05) (hash(x)=6474729) -178 train 8.859513 (lr=6.2587e-05) (hash(x)=5946650) -179 train 8.776073 (lr=6.2937e-05) (hash(x)=7523279) -180 train 8.668302 (lr=6.3287e-05) (hash(x)=5531605) -181 train 8.576374 (lr=6.3636e-05) (hash(x)=5508768) -182 train 8.736878 (lr=6.3986e-05) (hash(x)=6415982) -183 train 8.701837 (lr=6.4336e-05) (hash(x)=6635925) -184 train 8.620385 (lr=6.4685e-05) (hash(x)=5923706) -185 train 8.682731 (lr=6.5035e-05) (hash(x)=6663801) -186 train 8.523819 (lr=6.5385e-05) (hash(x)=6113540) -187 train 8.680603 (lr=6.5734e-05) (hash(x)=5869441) -188 train 8.679300 (lr=6.6084e-05) (hash(x)=6913454) -189 train 8.524346 (lr=6.6434e-05) (hash(x)=6698878) -190 train 8.540435 (lr=6.6783e-05) (hash(x)=6094899) -191 train 8.540534 (lr=6.7133e-05) (hash(x)=6349004) -192 train 8.539870 (lr=6.7483e-05) (hash(x)=6045933) -193 train 8.500272 (lr=6.7832e-05) (hash(x)=4986137) -194 train 8.281454 (lr=6.8182e-05) (hash(x)=4798229) -195 train 8.319677 (lr=6.8531e-05) (hash(x)=6008454) -196 train 8.370437 (lr=6.8881e-05) (hash(x)=5938362) -197 train 8.305453 (lr=6.9231e-05) (hash(x)=6550770) -198 train 8.384578 (lr=6.9580e-05) (hash(x)=7055344) -199 train 8.513483 (lr=6.9930e-05) (hash(x)=7682741) -200 val loss 8.4100 -200 val perplexity 4491.9609 -200 train 8.341786 (lr=7.0280e-05) (hash(x)=7372095) -201 train 8.598861 (lr=7.0629e-05) (hash(x)=7892158) -202 train 8.341990 (lr=7.0979e-05) (hash(x)=5929740) -203 train 8.357166 (lr=7.1329e-05) (hash(x)=7794028) -204 train 8.464108 (lr=7.1678e-05) (hash(x)=6839923) -205 train 8.203156 (lr=7.2028e-05) (hash(x)=7093523) -206 train 8.295508 (lr=7.2378e-05) (hash(x)=5341312) -207 train 8.347928 (lr=7.2727e-05) (hash(x)=6166062) -208 train 8.284388 (lr=7.3077e-05) (hash(x)=5992164) -209 train 8.226460 (lr=7.3427e-05) (hash(x)=6645781) -210 train 8.294956 (lr=7.3776e-05) (hash(x)=6207724) -211 train 8.174348 (lr=7.4126e-05) (hash(x)=4811192) -212 train 8.161320 (lr=7.4476e-05) (hash(x)=6906335) -213 train 8.119017 (lr=7.4825e-05) (hash(x)=5970866) -214 train 8.136651 (lr=7.5175e-05) (hash(x)=5238015) -215 train 8.193901 (lr=7.5524e-05) (hash(x)=7822680) -216 train 8.030585 (lr=7.5874e-05) (hash(x)=5478019) -217 train 8.130445 (lr=7.6224e-05) (hash(x)=6317317) -218 train 8.152289 (lr=7.6573e-05) (hash(x)=5832344) -219 train 8.153970 (lr=7.6923e-05) (hash(x)=6431409) -220 train 8.155324 (lr=7.7273e-05) (hash(x)=5900130) -221 train 8.180564 (lr=7.7622e-05) (hash(x)=6653337) -222 train 8.067355 (lr=7.7972e-05) (hash(x)=6696784) -223 train 8.116126 (lr=7.8322e-05) (hash(x)=5323032) -224 train 7.992850 (lr=7.8671e-05) (hash(x)=5372100) -225 train 8.009519 (lr=7.9021e-05) (hash(x)=5125339) -226 train 7.958435 (lr=7.9371e-05) (hash(x)=5664463) -227 train 7.962347 (lr=7.9720e-05) (hash(x)=7363286) -228 train 8.321622 (lr=8.0070e-05) (hash(x)=7444468) -229 train 8.161204 (lr=8.0420e-05) (hash(x)=7670050) -230 train 8.074509 (lr=8.0769e-05) (hash(x)=8189420) -231 train 7.987268 (lr=8.1119e-05) (hash(x)=5616075) -232 train 8.002240 (lr=8.1469e-05) (hash(x)=6360924) -233 train 8.146235 (lr=8.1818e-05) (hash(x)=6593764) -234 train 8.280091 (lr=8.2168e-05) (hash(x)=6764377) -235 train 7.952452 (lr=8.2517e-05) (hash(x)=5672608) -236 train 7.871394 (lr=8.2867e-05) (hash(x)=6985256) -237 train 8.116099 (lr=8.3217e-05) (hash(x)=6828653) -238 train 7.915079 (lr=8.3566e-05) (hash(x)=5199845) -239 train 8.002543 (lr=8.3916e-05) (hash(x)=6839867) -240 train 8.115566 (lr=8.4266e-05) (hash(x)=6928712) -241 train 7.993395 (lr=8.4615e-05) (hash(x)=8426992) -242 train 7.981725 (lr=8.4965e-05) (hash(x)=5330355) -243 train 7.560278 (lr=8.5315e-05) (hash(x)=4916928) -244 train 7.947277 (lr=8.5664e-05) (hash(x)=7287928) -245 train 7.976170 (lr=8.6014e-05) (hash(x)=6484050) -246 train 8.020281 (lr=8.6364e-05) (hash(x)=5062850) -247 train 8.033268 (lr=8.6713e-05) (hash(x)=8353379) -248 train 7.921080 (lr=8.7063e-05) (hash(x)=6805358) -249 train 7.926918 (lr=8.7413e-05) (hash(x)=6552510) -250 val loss 7.9394 -250 val perplexity 2805.7080 -250 train 7.947418 (lr=8.7762e-05) (hash(x)=5105545) -251 train 7.907321 (lr=8.8112e-05) (hash(x)=4838871) -252 train 8.009884 (lr=8.8462e-05) (hash(x)=5945286) -253 train 7.340507 (lr=8.8811e-05) (hash(x)=3021697) -254 train 7.757444 (lr=8.9161e-05) (hash(x)=6443070) -255 train 7.844752 (lr=8.9510e-05) (hash(x)=6795665) -256 train 7.989934 (lr=8.9860e-05) (hash(x)=7683068) -257 train 7.620282 (lr=9.0210e-05) (hash(x)=5486935) -258 train 7.923187 (lr=9.0559e-05) (hash(x)=6115232) -259 train 8.029565 (lr=9.0909e-05) (hash(x)=6678038) -260 train 7.989561 (lr=9.1259e-05) (hash(x)=5747629) -261 train 7.993327 (lr=9.1608e-05) (hash(x)=6657714) -262 train 7.854912 (lr=9.1958e-05) (hash(x)=6190642) -263 train 7.960157 (lr=9.2308e-05) (hash(x)=6112215) -264 train 7.854783 (lr=9.2657e-05) (hash(x)=7314989) -265 train 7.983354 (lr=9.3007e-05) (hash(x)=8353143) -266 train 7.972321 (lr=9.3357e-05) (hash(x)=5912570) -267 train 7.889248 (lr=9.3706e-05) (hash(x)=5915361) -268 train 7.711596 (lr=9.4056e-05) (hash(x)=6369494) -269 train 7.941582 (lr=9.4406e-05) (hash(x)=6254885) -270 train 7.836363 (lr=9.4755e-05) (hash(x)=5425120) -271 train 7.861965 (lr=9.5105e-05) (hash(x)=5771588) -272 train 7.842351 (lr=9.5455e-05) (hash(x)=6763967) -273 train 7.791145 (lr=9.5804e-05) (hash(x)=5561507) -274 train 7.744189 (lr=9.6154e-05) (hash(x)=7081151) -275 train 7.823861 (lr=9.6503e-05) (hash(x)=5688829) -276 train 7.779854 (lr=9.6853e-05) (hash(x)=7821554) -277 train 7.712911 (lr=9.7203e-05) (hash(x)=5371951) -278 train 7.826582 (lr=9.7552e-05) (hash(x)=8120149) -279 train 7.947105 (lr=9.7902e-05) (hash(x)=5443305) -280 train 7.755939 (lr=9.8252e-05) (hash(x)=7066030) -281 train 8.032635 (lr=9.8601e-05) (hash(x)=5016757) -282 train 7.887743 (lr=9.8951e-05) (hash(x)=6296163) -283 train 7.889939 (lr=9.9301e-05) (hash(x)=6901933) -284 train 7.784420 (lr=9.9650e-05) (hash(x)=8056633) -285 train 7.900005 (lr=1.0000e-04) (hash(x)=6019085) -286 train 7.718867 (lr=1.0000e-04) (hash(x)=7003893) -287 train 7.687271 (lr=1.0000e-04) (hash(x)=4294425) -288 train 7.707568 (lr=9.9998e-05) (hash(x)=6568540) -289 train 7.890723 (lr=9.9996e-05) (hash(x)=6095229) -290 train 7.826421 (lr=9.9993e-05) (hash(x)=5512150) -291 train 7.442386 (lr=9.9989e-05) (hash(x)=4363941) -292 train 7.733924 (lr=9.9984e-05) (hash(x)=6457783) -293 train 7.695461 (lr=9.9979e-05) (hash(x)=4693798) -294 train 8.200798 (lr=9.9972e-05) (hash(x)=8759806) -295 train 8.214126 (lr=9.9965e-05) (hash(x)=5486335) -296 train 7.879014 (lr=9.9956e-05) (hash(x)=6964993) -297 train 8.163002 (lr=9.9947e-05) (hash(x)=7907450) -298 train 7.910578 (lr=9.9937e-05) (hash(x)=5236642) -299 train 7.843867 (lr=9.9926e-05) (hash(x)=7295165) -300 val loss 7.7771 -300 val perplexity 2385.2905 -300 train 7.780232 (lr=9.9915e-05) (hash(x)=4913602) -301 train 7.839532 (lr=9.9902e-05) (hash(x)=6814026) -302 train 7.930420 (lr=9.9889e-05) (hash(x)=7042051) -303 train 7.842582 (lr=9.9874e-05) (hash(x)=6267424) -304 train 7.889661 (lr=9.9859e-05) (hash(x)=5614727) -305 train 7.856449 (lr=9.9843e-05) (hash(x)=8086437) -306 train 7.962467 (lr=9.9826e-05) (hash(x)=5900143) -307 train 7.881742 (lr=9.9808e-05) (hash(x)=5270452) -308 train 7.833651 (lr=9.9789e-05) (hash(x)=8617707) -309 train 7.694805 (lr=9.9770e-05) (hash(x)=6420820) -310 train 7.576705 (lr=9.9749e-05) (hash(x)=6215930) -311 train 7.764153 (lr=9.9728e-05) (hash(x)=6305297) -312 train 7.990970 (lr=9.9706e-05) (hash(x)=4026682) -313 train 7.688000 (lr=9.9683e-05) (hash(x)=7889849) -314 train 7.930256 (lr=9.9659e-05) (hash(x)=6141721) -315 train 8.413348 (lr=9.9634e-05) (hash(x)=6040077) -316 train 8.392202 (lr=9.9609e-05) (hash(x)=6155449) -317 train 7.945762 (lr=9.9582e-05) (hash(x)=5652497) -318 train 7.841300 (lr=9.9555e-05) (hash(x)=6961314) -319 train 7.693284 (lr=9.9526e-05) (hash(x)=7130251) -320 train 7.557432 (lr=9.9497e-05) (hash(x)=5927461) -321 train 7.720663 (lr=9.9467e-05) (hash(x)=6610177) -322 train 7.783356 (lr=9.9437e-05) (hash(x)=7277580) -323 train 7.602861 (lr=9.9405e-05) (hash(x)=6508350) -324 train 7.889494 (lr=9.9372e-05) (hash(x)=6536034) -325 train 7.795445 (lr=9.9339e-05) (hash(x)=6994983) -326 train 7.807154 (lr=9.9305e-05) (hash(x)=8700721) -327 train 7.756165 (lr=9.9270e-05) (hash(x)=5859576) -328 train 7.351646 (lr=9.9234e-05) (hash(x)=5264962) -329 train 7.362898 (lr=9.9197e-05) (hash(x)=5487065) -330 train 7.498593 (lr=9.9159e-05) (hash(x)=5731624) -331 train 7.631650 (lr=9.9121e-05) (hash(x)=4892065) -332 train 7.528642 (lr=9.9081e-05) (hash(x)=5489496) -333 train 7.415709 (lr=9.9041e-05) (hash(x)=4933674) -334 train 7.677978 (lr=9.9000e-05) (hash(x)=7021003) -335 train 7.832438 (lr=9.8958e-05) (hash(x)=7317289) -336 train 7.859572 (lr=9.8915e-05) (hash(x)=7869305) -337 train 7.820935 (lr=9.8872e-05) (hash(x)=6811522) -338 train 7.731375 (lr=9.8827e-05) (hash(x)=6601423) -339 train 7.629858 (lr=9.8782e-05) (hash(x)=5510218) -340 train 7.958024 (lr=9.8736e-05) (hash(x)=7180298) -341 train 7.718833 (lr=9.8689e-05) (hash(x)=7304235) -342 train 7.887617 (lr=9.8641e-05) (hash(x)=8111920) -343 train 8.112843 (lr=9.8592e-05) (hash(x)=6752265) -344 train 7.617948 (lr=9.8543e-05) (hash(x)=6788720) -345 train 7.728952 (lr=9.8492e-05) (hash(x)=5994476) -346 train 7.594692 (lr=9.8441e-05) (hash(x)=5862533) -347 train 7.700786 (lr=9.8389e-05) (hash(x)=6530867) -348 train 7.701354 (lr=9.8336e-05) (hash(x)=5914734) -349 train 7.800994 (lr=9.8282e-05) (hash(x)=5746260) -350 val loss 7.7044 -350 val perplexity 2217.9963 -350 train 7.708432 (lr=9.8228e-05) (hash(x)=6856097) -351 train 7.698062 (lr=9.8172e-05) (hash(x)=5790078) -352 train 7.829632 (lr=9.8116e-05) (hash(x)=5805002) -353 train 7.626110 (lr=9.8059e-05) (hash(x)=6430135) -354 train 7.624830 (lr=9.8001e-05) (hash(x)=6156715) -355 train 7.945642 (lr=9.7942e-05) (hash(x)=7614023) -356 train 7.858819 (lr=9.7882e-05) (hash(x)=4861744) -357 train 7.688467 (lr=9.7822e-05) (hash(x)=5244861) -358 train 7.739106 (lr=9.7761e-05) (hash(x)=7163697) -359 train 7.775827 (lr=9.7699e-05) (hash(x)=5245146) -360 train 7.632038 (lr=9.7636e-05) (hash(x)=6153866) -361 train 7.681840 (lr=9.7572e-05) (hash(x)=6415565) -362 train 7.951396 (lr=9.7507e-05) (hash(x)=7835853) -363 train 7.465362 (lr=9.7442e-05) (hash(x)=5786972) -364 train 7.806993 (lr=9.7376e-05) (hash(x)=6733560) -365 train 7.683011 (lr=9.7309e-05) (hash(x)=6131703) -366 train 7.541628 (lr=9.7241e-05) (hash(x)=6001331) -367 train 7.989435 (lr=9.7172e-05) (hash(x)=6346459) -368 train 7.824390 (lr=9.7103e-05) (hash(x)=8943770) -369 train 7.774294 (lr=9.7032e-05) (hash(x)=6504131) -370 train 7.724070 (lr=9.6961e-05) (hash(x)=5869339) -371 train 7.809279 (lr=9.6889e-05) (hash(x)=5209234) -372 train 7.660731 (lr=9.6817e-05) (hash(x)=7678937) -373 train 7.710608 (lr=9.6743e-05) (hash(x)=6163272) -374 train 7.712218 (lr=9.6669e-05) (hash(x)=5774172) -375 train 7.669598 (lr=9.6593e-05) (hash(x)=5676768) -376 train 7.349015 (lr=9.6518e-05) (hash(x)=6443895) -377 train 8.201034 (lr=9.6441e-05) (hash(x)=6090561) -378 train 7.812503 (lr=9.6363e-05) (hash(x)=7788628) -379 train 7.969537 (lr=9.6285e-05) (hash(x)=5863092) -380 train 7.729538 (lr=9.6206e-05) (hash(x)=7141354) -381 train 7.901978 (lr=9.6126e-05) (hash(x)=7201312) -382 train 7.867665 (lr=9.6045e-05) (hash(x)=6414278) -383 train 7.927705 (lr=9.5963e-05) (hash(x)=7019489) -384 train 7.662621 (lr=9.5881e-05) (hash(x)=7914626) -385 train 7.661434 (lr=9.5798e-05) (hash(x)=6225608) -386 train 7.760068 (lr=9.5714e-05) (hash(x)=5998078) -387 train 7.716781 (lr=9.5629e-05) (hash(x)=5483019) -388 train 7.565473 (lr=9.5544e-05) (hash(x)=5911642) -389 train 7.813452 (lr=9.5457e-05) (hash(x)=5903258) -390 train 7.816289 (lr=9.5370e-05) (hash(x)=5632006) -391 train 7.662690 (lr=9.5282e-05) (hash(x)=5968716) -392 train 7.743196 (lr=9.5194e-05) (hash(x)=6401968) -393 train 7.696720 (lr=9.5104e-05) (hash(x)=5778017) -394 train 7.284863 (lr=9.5014e-05) (hash(x)=5772567) -395 train 7.642454 (lr=9.4923e-05) (hash(x)=7780194) -396 train 7.714479 (lr=9.4831e-05) (hash(x)=6424771) -397 train 7.598411 (lr=9.4739e-05) (hash(x)=6140998) -398 train 7.581070 (lr=9.4646e-05) (hash(x)=7859566) -399 train 7.713297 (lr=9.4551e-05) (hash(x)=3784321) -400 val loss 7.6699 -400 val perplexity 2142.7986 -400 train 7.599418 (lr=9.4457e-05) (hash(x)=5557891) -401 train 7.730908 (lr=9.4361e-05) (hash(x)=5860821) -402 train 7.726912 (lr=9.4265e-05) (hash(x)=5674826) -403 train 7.704773 (lr=9.4168e-05) (hash(x)=7774109) -404 train 7.735427 (lr=9.4070e-05) (hash(x)=5466449) -405 train 8.021085 (lr=9.3971e-05) (hash(x)=7997664) -406 train 7.918145 (lr=9.3872e-05) (hash(x)=7006517) -407 train 7.796578 (lr=9.3772e-05) (hash(x)=6576749) -408 train 7.672090 (lr=9.3671e-05) (hash(x)=6896198) -409 train 7.881176 (lr=9.3569e-05) (hash(x)=7266655) -410 train 7.674552 (lr=9.3467e-05) (hash(x)=5696696) -411 train 7.788144 (lr=9.3364e-05) (hash(x)=7072404) -412 train 7.625633 (lr=9.3260e-05) (hash(x)=6590657) -413 train 7.678952 (lr=9.3155e-05) (hash(x)=6626459) -414 train 7.733379 (lr=9.3050e-05) (hash(x)=5644977) -415 train 7.630622 (lr=9.2944e-05) (hash(x)=6556025) -416 train 7.834709 (lr=9.2837e-05) (hash(x)=6407492) -417 train 7.597487 (lr=9.2729e-05) (hash(x)=5942129) -418 train 7.691179 (lr=9.2621e-05) (hash(x)=6012163) -419 train 7.934721 (lr=9.2512e-05) (hash(x)=7325027) -420 train 7.861867 (lr=9.2402e-05) (hash(x)=4425520) -421 train 7.736204 (lr=9.2292e-05) (hash(x)=7322467) -422 train 7.683742 (lr=9.2181e-05) (hash(x)=7482800) -423 train 7.769143 (lr=9.2069e-05) (hash(x)=6373412) -424 train 7.429379 (lr=9.1956e-05) (hash(x)=6981426) -425 train 7.612888 (lr=9.1843e-05) (hash(x)=7332255) -426 train 7.804729 (lr=9.1729e-05) (hash(x)=5930894) -427 train 7.813303 (lr=9.1614e-05) (hash(x)=5262868) -428 train 7.553454 (lr=9.1499e-05) (hash(x)=5585769) -429 train 7.464406 (lr=9.1382e-05) (hash(x)=5688247) -430 train 7.767093 (lr=9.1266e-05) (hash(x)=7462079) -431 train 7.604372 (lr=9.1148e-05) (hash(x)=8055563) -432 train 7.691264 (lr=9.1030e-05) (hash(x)=6221701) -433 train 7.702159 (lr=9.0911e-05) (hash(x)=5352405) -434 train 7.754059 (lr=9.0791e-05) (hash(x)=6730666) -435 train 7.766275 (lr=9.0671e-05) (hash(x)=5932790) -436 train 7.800768 (lr=9.0550e-05) (hash(x)=6223114) -437 train 7.628172 (lr=9.0428e-05) (hash(x)=6249312) -438 train 7.776098 (lr=9.0306e-05) (hash(x)=7242827) -439 train 7.543546 (lr=9.0182e-05) (hash(x)=5680154) -440 train 7.795954 (lr=9.0059e-05) (hash(x)=6332332) -441 train 7.731644 (lr=8.9934e-05) (hash(x)=8156280) -442 train 7.718644 (lr=8.9809e-05) (hash(x)=6659781) -443 train 7.692819 (lr=8.9683e-05) (hash(x)=5914217) -444 train 7.604506 (lr=8.9557e-05) (hash(x)=6714110) -445 train 7.530135 (lr=8.9430e-05) (hash(x)=7120215) -446 train 7.770674 (lr=8.9302e-05) (hash(x)=6593413) -447 train 7.710507 (lr=8.9173e-05) (hash(x)=6424128) -448 train 7.525712 (lr=8.9044e-05) (hash(x)=5903043) -449 train 7.437259 (lr=8.8914e-05) (hash(x)=4390027) -450 val loss 7.6538 -450 val perplexity 2108.5488 -450 train 7.666108 (lr=8.8784e-05) (hash(x)=6945760) -451 train 7.721063 (lr=8.8653e-05) (hash(x)=7804089) -452 train 7.779444 (lr=8.8521e-05) (hash(x)=6273417) -453 train 7.831733 (lr=8.8388e-05) (hash(x)=7130267) -454 train 7.636298 (lr=8.8255e-05) (hash(x)=6140697) -455 train 7.566982 (lr=8.8122e-05) (hash(x)=6490149) -456 train 7.453558 (lr=8.7987e-05) (hash(x)=4847733) -457 train 7.814668 (lr=8.7852e-05) (hash(x)=9276378) -458 train 7.584894 (lr=8.7717e-05) (hash(x)=7082053) -459 train 7.739535 (lr=8.7580e-05) (hash(x)=6283540) -460 train 7.581912 (lr=8.7444e-05) (hash(x)=5200956) -461 train 7.716771 (lr=8.7306e-05) (hash(x)=5781680) -462 train 7.701544 (lr=8.7168e-05) (hash(x)=8652907) -463 train 7.488564 (lr=8.7029e-05) (hash(x)=5728337) -464 train 7.597054 (lr=8.6890e-05) (hash(x)=5832401) -465 train 7.557499 (lr=8.6750e-05) (hash(x)=6278202) -466 train 7.686906 (lr=8.6609e-05) (hash(x)=7403868) -467 train 7.689198 (lr=8.6468e-05) (hash(x)=7400272) -468 train 7.656137 (lr=8.6326e-05) (hash(x)=5943413) -469 train 7.662551 (lr=8.6184e-05) (hash(x)=5795128) -470 train 7.689536 (lr=8.6041e-05) (hash(x)=5519980) -471 train 7.564383 (lr=8.5897e-05) (hash(x)=6473432) -472 train 7.585644 (lr=8.5753e-05) (hash(x)=5484669) -473 train 7.686556 (lr=8.5608e-05) (hash(x)=5201502) -474 train 7.767343 (lr=8.5462e-05) (hash(x)=7227057) -475 train 7.912324 (lr=8.5316e-05) (hash(x)=6922646) -476 train 7.503634 (lr=8.5170e-05) (hash(x)=6056673) -477 train 7.645999 (lr=8.5022e-05) (hash(x)=5484641) -478 train 7.756403 (lr=8.4875e-05) (hash(x)=7100865) -479 train 7.513305 (lr=8.4726e-05) (hash(x)=7277141) -480 train 7.594075 (lr=8.4577e-05) (hash(x)=6407603) -481 train 7.696346 (lr=8.4428e-05) (hash(x)=5604614) -482 train 7.704046 (lr=8.4278e-05) (hash(x)=6200612) -483 train 7.708209 (lr=8.4127e-05) (hash(x)=7443124) -484 train 7.666949 (lr=8.3976e-05) (hash(x)=6728764) -485 train 7.768128 (lr=8.3824e-05) (hash(x)=5601968) -486 train 7.527875 (lr=8.3672e-05) (hash(x)=6877761) -487 train 7.716736 (lr=8.3519e-05) (hash(x)=5632735) -488 train 7.713551 (lr=8.3366e-05) (hash(x)=5658845) -489 train 7.498044 (lr=8.3212e-05) (hash(x)=5594810) -490 train 7.268214 (lr=8.3057e-05) (hash(x)=4738523) -491 train 7.632048 (lr=8.2902e-05) (hash(x)=5881015) -492 train 7.617334 (lr=8.2746e-05) (hash(x)=5263325) -493 train 7.590922 (lr=8.2590e-05) (hash(x)=6865361) -494 train 7.765965 (lr=8.2434e-05) (hash(x)=5644619) -495 train 7.622214 (lr=8.2276e-05) (hash(x)=5809411) -496 train 7.667578 (lr=8.2119e-05) (hash(x)=7044374) -497 train 7.711046 (lr=8.1960e-05) (hash(x)=6293025) -498 train 7.657429 (lr=8.1801e-05) (hash(x)=5189023) -499 train 7.577607 (lr=8.1642e-05) (hash(x)=7232964) -500 val loss 7.6342 -500 val perplexity 2067.7461 -500 train 7.604221 (lr=8.1482e-05) (hash(x)=5806257) -501 train 7.511958 (lr=8.1322e-05) (hash(x)=5646619) -502 train 7.674515 (lr=8.1161e-05) (hash(x)=6966594) -503 train 7.697623 (lr=8.1000e-05) (hash(x)=6171829) -504 train 7.621675 (lr=8.0838e-05) (hash(x)=5945953) -505 train 7.853555 (lr=8.0676e-05) (hash(x)=7787552) -506 train 7.767939 (lr=8.0513e-05) (hash(x)=7184332) -507 train 7.610711 (lr=8.0349e-05) (hash(x)=5884456) -508 train 7.731466 (lr=8.0186e-05) (hash(x)=6443281) -509 train 7.711513 (lr=8.0021e-05) (hash(x)=6752162) -510 train 7.697983 (lr=7.9856e-05) (hash(x)=7140204) -511 train 7.533455 (lr=7.9691e-05) (hash(x)=5077031) -512 train 7.783298 (lr=7.9525e-05) (hash(x)=6490444) -513 train 7.817858 (lr=7.9359e-05) (hash(x)=6883481) -514 train 7.665957 (lr=7.9192e-05) (hash(x)=7381497) -515 train 7.700274 (lr=7.9025e-05) (hash(x)=6248895) -516 train 7.593194 (lr=7.8858e-05) (hash(x)=6655640) -517 train 7.509380 (lr=7.8689e-05) (hash(x)=6636615) -518 train 7.836347 (lr=7.8521e-05) (hash(x)=5452148) -519 train 7.655565 (lr=7.8352e-05) (hash(x)=6918004) -520 train 7.647577 (lr=7.8182e-05) (hash(x)=6547295) -521 train 7.682449 (lr=7.8012e-05) (hash(x)=7302874) -522 train 7.843414 (lr=7.7842e-05) (hash(x)=5637695) -523 train 7.696862 (lr=7.7671e-05) (hash(x)=6482466) -524 train 7.644479 (lr=7.7500e-05) (hash(x)=7612126) -525 train 7.585289 (lr=7.7328e-05) (hash(x)=7298317) -526 train 7.735364 (lr=7.7156e-05) (hash(x)=5635777) -527 train 7.586355 (lr=7.6984e-05) (hash(x)=6588573) -528 train 7.776093 (lr=7.6811e-05) (hash(x)=6634173) -529 train 7.548323 (lr=7.6637e-05) (hash(x)=6229630) -530 train 7.830211 (lr=7.6463e-05) (hash(x)=6867600) -531 train 7.612793 (lr=7.6289e-05) (hash(x)=6136939) -532 train 7.463357 (lr=7.6115e-05) (hash(x)=6014704) -533 train 7.484867 (lr=7.5940e-05) (hash(x)=6394645) -534 train 7.821832 (lr=7.5764e-05) (hash(x)=6548145) -535 train 7.612110 (lr=7.5588e-05) (hash(x)=7040157) -536 train 7.786055 (lr=7.5412e-05) (hash(x)=5642718) -537 train 7.720269 (lr=7.5235e-05) (hash(x)=7041858) -538 train 7.673180 (lr=7.5058e-05) (hash(x)=6392891) -539 train 7.687346 (lr=7.4881e-05) (hash(x)=6455595) -540 train 7.651456 (lr=7.4703e-05) (hash(x)=6245990) -541 train 7.542789 (lr=7.4525e-05) (hash(x)=6480443) -542 train 7.700452 (lr=7.4346e-05) (hash(x)=7680751) -543 train 7.809138 (lr=7.4167e-05) (hash(x)=4122983) -544 train 7.525611 (lr=7.3988e-05) (hash(x)=5996900) -545 train 7.663051 (lr=7.3808e-05) (hash(x)=7672190) -546 train 7.552675 (lr=7.3628e-05) (hash(x)=8149488) -547 train 7.692812 (lr=7.3448e-05) (hash(x)=4724052) -548 train 7.614067 (lr=7.3267e-05) (hash(x)=6812761) -549 train 7.547799 (lr=7.3086e-05) (hash(x)=6654267) -550 val loss 7.5978 -550 val perplexity 1993.7491 -550 train 7.581007 (lr=7.2904e-05) (hash(x)=6756431) -551 train 7.569304 (lr=7.2723e-05) (hash(x)=6820797) -552 train 7.670911 (lr=7.2540e-05) (hash(x)=5645711) -553 train 7.620242 (lr=7.2358e-05) (hash(x)=6458662) -554 train 7.634208 (lr=7.2175e-05) (hash(x)=5300771) -555 train 8.420155 (lr=7.1992e-05) (hash(x)=7477594) -556 train 7.725153 (lr=7.1808e-05) (hash(x)=5157748) -557 train 7.665180 (lr=7.1624e-05) (hash(x)=5876574) -558 train 7.438022 (lr=7.1440e-05) (hash(x)=6821258) -559 train 7.416778 (lr=7.1256e-05) (hash(x)=6146305) -560 train 7.691299 (lr=7.1071e-05) (hash(x)=5278517) -561 train 7.515166 (lr=7.0886e-05) (hash(x)=6162080) -562 train 7.483430 (lr=7.0701e-05) (hash(x)=5908198) -563 train 7.627465 (lr=7.0515e-05) (hash(x)=6814831) -564 train 7.675510 (lr=7.0329e-05) (hash(x)=5632357) -565 train 7.706075 (lr=7.0143e-05) (hash(x)=7138295) -566 train 7.324525 (lr=6.9956e-05) (hash(x)=4678562) -567 train 7.589485 (lr=6.9769e-05) (hash(x)=5548298) -568 train 7.452751 (lr=6.9582e-05) (hash(x)=6495991) -569 train 7.659283 (lr=6.9394e-05) (hash(x)=6265078) -570 train 7.857799 (lr=6.9207e-05) (hash(x)=5746797) -571 train 8.023754 (lr=6.9019e-05) (hash(x)=7609416) -572 train 7.759391 (lr=6.8830e-05) (hash(x)=5593869) -573 train 7.514686 (lr=6.8642e-05) (hash(x)=6909367) -574 train 7.552631 (lr=6.8453e-05) (hash(x)=4756034) -575 train 7.905088 (lr=6.8264e-05) (hash(x)=7574342) -576 train 7.347488 (lr=6.8075e-05) (hash(x)=4502769) -577 train 7.770018 (lr=6.7885e-05) (hash(x)=8859748) -578 train 7.527095 (lr=6.7695e-05) (hash(x)=5683686) -579 train 7.508165 (lr=6.7505e-05) (hash(x)=5906937) -580 train 7.638266 (lr=6.7315e-05) (hash(x)=6051136) -581 train 7.415813 (lr=6.7124e-05) (hash(x)=7243024) -582 train 7.450380 (lr=6.6933e-05) (hash(x)=5382761) -583 train 7.858344 (lr=6.6742e-05) (hash(x)=8013471) -584 train 7.496560 (lr=6.6551e-05) (hash(x)=5165270) -585 train 7.624969 (lr=6.6360e-05) (hash(x)=5659461) -586 train 7.658638 (lr=6.6168e-05) (hash(x)=5767800) -587 train 7.519105 (lr=6.5976e-05) (hash(x)=6146213) -588 train 7.859895 (lr=6.5784e-05) (hash(x)=7238407) -589 train 7.418145 (lr=6.5592e-05) (hash(x)=6602917) -590 train 7.626936 (lr=6.5399e-05) (hash(x)=6287715) -591 train 7.515945 (lr=6.5206e-05) (hash(x)=6709902) -592 train 7.636279 (lr=6.5013e-05) (hash(x)=6902255) -593 train 7.716199 (lr=6.4820e-05) (hash(x)=8154341) -594 train 7.952908 (lr=6.4627e-05) (hash(x)=5220688) -595 train 7.713269 (lr=6.4433e-05) (hash(x)=6402571) -596 train 7.512260 (lr=6.4240e-05) (hash(x)=5895167) -597 train 7.653013 (lr=6.4046e-05) (hash(x)=5605466) -598 train 7.576892 (lr=6.3852e-05) (hash(x)=6404902) -599 train 7.510896 (lr=6.3658e-05) (hash(x)=7683614) -600 val loss 7.5828 -600 val perplexity 1964.1759 -600 train 7.673580 (lr=6.3463e-05) (hash(x)=6103542) -601 train 7.578035 (lr=6.3269e-05) (hash(x)=5421572) -602 train 7.477685 (lr=6.3074e-05) (hash(x)=5808144) -603 train 7.465957 (lr=6.2879e-05) (hash(x)=5453026) -604 train 7.486405 (lr=6.2684e-05) (hash(x)=6337335) -605 train 7.598549 (lr=6.2489e-05) (hash(x)=6437746) -606 train 7.574255 (lr=6.2294e-05) (hash(x)=8782554) -607 train 7.327761 (lr=6.2098e-05) (hash(x)=6260017) -608 train 7.508539 (lr=6.1903e-05) (hash(x)=6917394) -609 train 7.602421 (lr=6.1707e-05) (hash(x)=6119053) -610 train 7.702817 (lr=6.1511e-05) (hash(x)=6089308) -611 train 7.738514 (lr=6.1315e-05) (hash(x)=6591466) -612 train 7.662880 (lr=6.1119e-05) (hash(x)=5858271) -613 train 7.549045 (lr=6.0923e-05) (hash(x)=5652701) -614 train 7.612792 (lr=6.0726e-05) (hash(x)=7058229) -615 train 7.602983 (lr=6.0530e-05) (hash(x)=5501472) -616 train 7.712741 (lr=6.0333e-05) (hash(x)=6232515) -617 train 7.902630 (lr=6.0137e-05) (hash(x)=6160695) -618 train 7.610404 (lr=5.9940e-05) (hash(x)=6020418) -619 train 7.458741 (lr=5.9743e-05) (hash(x)=5871698) -620 train 7.486407 (lr=5.9546e-05) (hash(x)=6796897) -621 train 7.544331 (lr=5.9349e-05) (hash(x)=7301184) -622 train 7.507976 (lr=5.9152e-05) (hash(x)=5748484) -623 train 7.388951 (lr=5.8955e-05) (hash(x)=4282052) -624 train 7.545971 (lr=5.8758e-05) (hash(x)=4758217) -625 train 7.757703 (lr=5.8560e-05) (hash(x)=5679330) -626 train 7.435371 (lr=5.8363e-05) (hash(x)=6726349) -627 train 7.598531 (lr=5.8165e-05) (hash(x)=7824660) -628 train 7.476168 (lr=5.7968e-05) (hash(x)=6255315) -629 train 7.613735 (lr=5.7770e-05) (hash(x)=4857318) -630 train 7.581805 (lr=5.7573e-05) (hash(x)=6974405) -631 train 7.376272 (lr=5.7375e-05) (hash(x)=5954950) -632 train 7.628785 (lr=5.7177e-05) (hash(x)=5981982) -633 train 7.492799 (lr=5.6979e-05) (hash(x)=5758178) -634 train 7.725732 (lr=5.6782e-05) (hash(x)=7816503) -635 train 7.436110 (lr=5.6584e-05) (hash(x)=5484656) -636 train 7.560784 (lr=5.6386e-05) (hash(x)=5513418) -637 train 7.618986 (lr=5.6188e-05) (hash(x)=6818913) -638 train 7.848207 (lr=5.5990e-05) (hash(x)=7444913) -639 train 7.693310 (lr=5.5792e-05) (hash(x)=7031328) -640 train 7.546820 (lr=5.5594e-05) (hash(x)=5202673) -641 train 7.702653 (lr=5.5396e-05) (hash(x)=6837621) -642 train 7.436080 (lr=5.5198e-05) (hash(x)=6590985) -643 train 7.834605 (lr=5.5000e-05) (hash(x)=9157069) -644 train 8.068957 (lr=5.4802e-05) (hash(x)=5123556) -645 train 7.667952 (lr=5.4604e-05) (hash(x)=6509536) -646 train 7.817702 (lr=5.4406e-05) (hash(x)=6252013) -647 train 7.330516 (lr=5.4208e-05) (hash(x)=5996883) -648 train 7.532339 (lr=5.4010e-05) (hash(x)=5942379) -649 train 8.084683 (lr=5.3812e-05) (hash(x)=6850868) -650 val loss 7.5635 -650 val perplexity 1926.4976 -650 train 7.701354 (lr=5.3614e-05) (hash(x)=8017172) -651 train 7.821044 (lr=5.3416e-05) (hash(x)=7645447) -652 train 7.689682 (lr=5.3218e-05) (hash(x)=8751332) -653 train 7.828826 (lr=5.3021e-05) (hash(x)=6717515) -654 train 7.952513 (lr=5.2823e-05) (hash(x)=6521028) -655 train 7.809446 (lr=5.2625e-05) (hash(x)=6336164) -656 train 7.586422 (lr=5.2427e-05) (hash(x)=6289337) -657 train 7.615901 (lr=5.2230e-05) (hash(x)=6897445) -658 train 7.732130 (lr=5.2032e-05) (hash(x)=7037289) -659 train 7.288346 (lr=5.1835e-05) (hash(x)=5224240) -660 train 7.626452 (lr=5.1637e-05) (hash(x)=6834715) -661 train 7.698432 (lr=5.1440e-05) (hash(x)=6612945) -662 train 8.323870 (lr=5.1242e-05) (hash(x)=8320588) -663 train 7.959212 (lr=5.1045e-05) (hash(x)=5447801) -664 train 7.603154 (lr=5.0848e-05) (hash(x)=6656376) -665 train 7.720012 (lr=5.0651e-05) (hash(x)=7308579) -666 train 7.732092 (lr=5.0454e-05) (hash(x)=5344256) -667 train 7.317959 (lr=5.0257e-05) (hash(x)=4155598) -668 train 7.536976 (lr=5.0060e-05) (hash(x)=5177976) -669 train 7.522072 (lr=4.9863e-05) (hash(x)=6106773) -670 train 7.505962 (lr=4.9667e-05) (hash(x)=8334761) -671 train 7.661094 (lr=4.9470e-05) (hash(x)=7482744) -672 train 7.945910 (lr=4.9274e-05) (hash(x)=6435528) -673 train 7.354980 (lr=4.9077e-05) (hash(x)=6310687) -674 train 7.367802 (lr=4.8881e-05) (hash(x)=6917344) -675 train 7.678216 (lr=4.8685e-05) (hash(x)=4733414) -676 train 7.439636 (lr=4.8489e-05) (hash(x)=5146340) -677 train 7.894372 (lr=4.8293e-05) (hash(x)=6979734) -678 train 7.399564 (lr=4.8097e-05) (hash(x)=5847143) -679 train 7.486138 (lr=4.7902e-05) (hash(x)=7806284) -680 train 7.366781 (lr=4.7706e-05) (hash(x)=6367699) -681 train 7.547650 (lr=4.7511e-05) (hash(x)=5080536) -682 train 7.731310 (lr=4.7316e-05) (hash(x)=7218763) -683 train 7.627647 (lr=4.7121e-05) (hash(x)=7236478) -684 train 7.586207 (lr=4.6926e-05) (hash(x)=5497206) -685 train 7.659680 (lr=4.6731e-05) (hash(x)=6619318) -686 train 7.595905 (lr=4.6537e-05) (hash(x)=5916845) -687 train 7.429915 (lr=4.6342e-05) (hash(x)=4656255) -688 train 7.439491 (lr=4.6148e-05) (hash(x)=5788889) -689 train 7.471800 (lr=4.5954e-05) (hash(x)=5546888) -690 train 7.644482 (lr=4.5760e-05) (hash(x)=8072073) -691 train 8.184129 (lr=4.5567e-05) (hash(x)=9298325) -692 train 7.674432 (lr=4.5373e-05) (hash(x)=5553198) -693 train 7.539440 (lr=4.5180e-05) (hash(x)=5994232) -694 train 7.578222 (lr=4.4987e-05) (hash(x)=7133014) -695 train 7.602300 (lr=4.4794e-05) (hash(x)=6287524) -696 train 7.478854 (lr=4.4601e-05) (hash(x)=4968095) -697 train 7.919140 (lr=4.4408e-05) (hash(x)=6200049) -698 train 7.578990 (lr=4.4216e-05) (hash(x)=6569299) -699 train 7.655171 (lr=4.4024e-05) (hash(x)=7895970) -700 val loss 7.5421 -700 val perplexity 1885.8561 -700 train 7.649476 (lr=4.3832e-05) (hash(x)=5286600) -701 train 7.434981 (lr=4.3640e-05) (hash(x)=6051847) -702 train 7.474664 (lr=4.3449e-05) (hash(x)=5156899) -703 train 7.943992 (lr=4.3258e-05) (hash(x)=8847992) -704 train 7.987175 (lr=4.3067e-05) (hash(x)=5343653) -705 train 8.064356 (lr=4.2876e-05) (hash(x)=5123883) -706 train 7.697535 (lr=4.2685e-05) (hash(x)=6462379) -707 train 7.573382 (lr=4.2495e-05) (hash(x)=6338998) -708 train 7.735487 (lr=4.2305e-05) (hash(x)=5803128) -709 train 7.505132 (lr=4.2115e-05) (hash(x)=5765866) -710 train 8.120043 (lr=4.1925e-05) (hash(x)=7297901) -711 train 7.863288 (lr=4.1736e-05) (hash(x)=7104011) -712 train 7.469209 (lr=4.1547e-05) (hash(x)=6511383) -713 train 7.996648 (lr=4.1358e-05) (hash(x)=7438267) -714 train 7.453244 (lr=4.1170e-05) (hash(x)=5600336) -715 train 7.452913 (lr=4.0981e-05) (hash(x)=5573214) -716 train 7.562665 (lr=4.0793e-05) (hash(x)=5751679) -717 train 7.951883 (lr=4.0606e-05) (hash(x)=6897283) -718 train 7.560116 (lr=4.0418e-05) (hash(x)=6011576) -719 train 7.497442 (lr=4.0231e-05) (hash(x)=6882897) -720 train 7.610111 (lr=4.0044e-05) (hash(x)=7223798) -721 train 7.707412 (lr=3.9857e-05) (hash(x)=5343615) -722 train 7.608165 (lr=3.9671e-05) (hash(x)=5500678) -723 train 7.487851 (lr=3.9485e-05) (hash(x)=5854242) -724 train 7.547425 (lr=3.9299e-05) (hash(x)=6087004) -725 train 7.376379 (lr=3.9114e-05) (hash(x)=6317324) -726 train 7.385437 (lr=3.8929e-05) (hash(x)=5502743) -727 train 7.432744 (lr=3.8744e-05) (hash(x)=6972494) -728 train 7.649336 (lr=3.8560e-05) (hash(x)=5138900) -729 train 7.351365 (lr=3.8376e-05) (hash(x)=5661167) -730 train 7.393908 (lr=3.8192e-05) (hash(x)=5204562) -731 train 7.593745 (lr=3.8008e-05) (hash(x)=6796805) -732 train 7.319299 (lr=3.7825e-05) (hash(x)=4915685) -733 train 7.356728 (lr=3.7642e-05) (hash(x)=5817209) -734 train 7.510828 (lr=3.7460e-05) (hash(x)=5270999) -735 train 7.280176 (lr=3.7277e-05) (hash(x)=6139120) -736 train 7.549130 (lr=3.7096e-05) (hash(x)=6348780) -737 train 7.591702 (lr=3.6914e-05) (hash(x)=6121296) -738 train 7.489943 (lr=3.6733e-05) (hash(x)=5527309) -739 train 7.595429 (lr=3.6552e-05) (hash(x)=6486796) -740 train 7.565967 (lr=3.6372e-05) (hash(x)=5859868) -741 train 7.372787 (lr=3.6192e-05) (hash(x)=5514645) -742 train 7.541854 (lr=3.6012e-05) (hash(x)=5740298) -743 train 7.251213 (lr=3.5833e-05) (hash(x)=5578797) -744 train 7.407275 (lr=3.5654e-05) (hash(x)=3634442) -745 train 7.400749 (lr=3.5475e-05) (hash(x)=7651738) -746 train 7.615992 (lr=3.5297e-05) (hash(x)=7118416) -747 train 7.662997 (lr=3.5119e-05) (hash(x)=6895326) -748 train 7.671333 (lr=3.4942e-05) (hash(x)=8607990) -749 train 7.560277 (lr=3.4765e-05) (hash(x)=5490256) -750 val loss 7.5285 -750 val perplexity 1860.3459 -750 train 7.499443 (lr=3.4588e-05) (hash(x)=6918464) -751 train 7.474308 (lr=3.4412e-05) (hash(x)=7783160) -752 train 7.494863 (lr=3.4236e-05) (hash(x)=4910007) -753 train 7.902472 (lr=3.4060e-05) (hash(x)=5608424) -754 train 7.686212 (lr=3.3885e-05) (hash(x)=5176743) -755 train 7.244814 (lr=3.3711e-05) (hash(x)=4867625) -756 train 7.361460 (lr=3.3537e-05) (hash(x)=4859474) -757 train 7.342831 (lr=3.3363e-05) (hash(x)=4655472) -758 train 7.362894 (lr=3.3189e-05) (hash(x)=4985126) -759 train 7.486481 (lr=3.3016e-05) (hash(x)=6631123) -760 train 7.258254 (lr=3.2844e-05) (hash(x)=3652957) -761 train 6.904194 (lr=3.2672e-05) (hash(x)=5751990) -762 train 7.301682 (lr=3.2500e-05) (hash(x)=6798916) -763 train 7.527537 (lr=3.2329e-05) (hash(x)=6710965) -764 train 7.436090 (lr=3.2158e-05) (hash(x)=5490166) -765 train 7.301960 (lr=3.1988e-05) (hash(x)=5293800) -766 train 7.307724 (lr=3.1818e-05) (hash(x)=5884835) -767 train 7.490651 (lr=3.1648e-05) (hash(x)=6294657) -768 train 7.662206 (lr=3.1479e-05) (hash(x)=7085154) -769 train 7.454737 (lr=3.1311e-05) (hash(x)=6999538) -770 train 7.626788 (lr=3.1142e-05) (hash(x)=5244581) -771 train 7.457083 (lr=3.0975e-05) (hash(x)=5443606) -772 train 7.585644 (lr=3.0808e-05) (hash(x)=7028408) -773 train 7.454031 (lr=3.0641e-05) (hash(x)=5650401) -774 train 7.538034 (lr=3.0475e-05) (hash(x)=6770125) -775 train 7.506220 (lr=3.0309e-05) (hash(x)=7035770) -776 train 7.360514 (lr=3.0144e-05) (hash(x)=6405982) -777 train 7.576938 (lr=2.9979e-05) (hash(x)=6678271) -778 train 7.474920 (lr=2.9814e-05) (hash(x)=6088760) -779 train 7.878087 (lr=2.9651e-05) (hash(x)=4899541) -780 train 7.381652 (lr=2.9487e-05) (hash(x)=5154342) -781 train 7.450532 (lr=2.9324e-05) (hash(x)=5359260) -782 train 7.276431 (lr=2.9162e-05) (hash(x)=5513509) -783 train 7.547409 (lr=2.9000e-05) (hash(x)=6227120) -784 train 7.462834 (lr=2.8839e-05) (hash(x)=5165184) -785 train 7.525308 (lr=2.8678e-05) (hash(x)=6643916) -786 train 7.538626 (lr=2.8518e-05) (hash(x)=7048323) -787 train 7.549625 (lr=2.8358e-05) (hash(x)=5981648) -788 train 7.409541 (lr=2.8199e-05) (hash(x)=4827872) -789 train 7.600919 (lr=2.8040e-05) (hash(x)=6467540) -790 train 7.468550 (lr=2.7881e-05) (hash(x)=6542722) -791 train 7.412214 (lr=2.7724e-05) (hash(x)=5558993) -792 train 7.625873 (lr=2.7566e-05) (hash(x)=5310679) -793 train 7.614507 (lr=2.7410e-05) (hash(x)=6698959) -794 train 7.320004 (lr=2.7254e-05) (hash(x)=6858783) -795 train 7.536436 (lr=2.7098e-05) (hash(x)=7015671) -796 train 7.450267 (lr=2.6943e-05) (hash(x)=4483663) -797 train 7.415480 (lr=2.6788e-05) (hash(x)=6800890) -798 train 7.439596 (lr=2.6634e-05) (hash(x)=6730827) -799 train 7.770207 (lr=2.6481e-05) (hash(x)=5931234) -800 val loss 7.5067 -800 val perplexity 1820.1267 -800 train 7.566363 (lr=2.6328e-05) (hash(x)=4866660) -801 train 7.511165 (lr=2.6176e-05) (hash(x)=3995070) -802 train 7.588165 (lr=2.6024e-05) (hash(x)=4488617) -803 train 7.374712 (lr=2.5873e-05) (hash(x)=4582159) -804 train 7.550923 (lr=2.5722e-05) (hash(x)=5164570) -805 train 7.630752 (lr=2.5572e-05) (hash(x)=7081906) -806 train 7.414999 (lr=2.5423e-05) (hash(x)=5480570) -807 train 7.515975 (lr=2.5274e-05) (hash(x)=5029472) -808 train 7.503846 (lr=2.5125e-05) (hash(x)=8207798) -809 train 7.397047 (lr=2.4978e-05) (hash(x)=3946232) -810 train 7.329582 (lr=2.4830e-05) (hash(x)=5652175) -811 train 7.418349 (lr=2.4684e-05) (hash(x)=5434102) -812 train 8.598052 (lr=2.4538e-05) (hash(x)=6558885) -813 train 7.662760 (lr=2.4392e-05) (hash(x)=5340646) -814 train 7.212672 (lr=2.4247e-05) (hash(x)=6403613) -815 train 7.261681 (lr=2.4103e-05) (hash(x)=6810638) -816 train 7.191861 (lr=2.3959e-05) (hash(x)=4382313) -817 train 7.828535 (lr=2.3816e-05) (hash(x)=6768026) -818 train 7.484043 (lr=2.3674e-05) (hash(x)=6423059) -819 train 7.539890 (lr=2.3532e-05) (hash(x)=6521562) -820 train 7.492550 (lr=2.3391e-05) (hash(x)=5653405) -821 train 7.506424 (lr=2.3250e-05) (hash(x)=4429434) -822 train 7.619540 (lr=2.3110e-05) (hash(x)=6885745) -823 train 7.512046 (lr=2.2971e-05) (hash(x)=7226932) -824 train 7.276736 (lr=2.2832e-05) (hash(x)=5371082) -825 train 7.385677 (lr=2.2694e-05) (hash(x)=5065932) -826 train 7.425768 (lr=2.2556e-05) (hash(x)=5384078) -827 train 7.552860 (lr=2.2420e-05) (hash(x)=6957849) -828 train 7.653790 (lr=2.2283e-05) (hash(x)=6049310) -829 train 7.328592 (lr=2.2148e-05) (hash(x)=6431457) -830 train 7.667130 (lr=2.2013e-05) (hash(x)=6479516) -831 train 7.457409 (lr=2.1878e-05) (hash(x)=5334281) -832 train 7.389798 (lr=2.1745e-05) (hash(x)=6811166) -833 train 7.769713 (lr=2.1612e-05) (hash(x)=5471747) -834 train 7.652188 (lr=2.1479e-05) (hash(x)=6733641) -835 train 7.665160 (lr=2.1347e-05) (hash(x)=5887983) -836 train 7.673751 (lr=2.1216e-05) (hash(x)=5366857) -837 train 7.466955 (lr=2.1086e-05) (hash(x)=5075909) -838 train 7.351113 (lr=2.0956e-05) (hash(x)=4961569) -839 train 7.391370 (lr=2.0827e-05) (hash(x)=6393576) -840 train 7.511384 (lr=2.0698e-05) (hash(x)=5520210) -841 train 7.461373 (lr=2.0570e-05) (hash(x)=6608979) -842 train 7.790101 (lr=2.0443e-05) (hash(x)=6223763) -843 train 7.976683 (lr=2.0317e-05) (hash(x)=5057959) -844 train 7.811944 (lr=2.0191e-05) (hash(x)=8268189) -845 train 7.900192 (lr=2.0066e-05) (hash(x)=6414858) -846 train 7.415768 (lr=1.9941e-05) (hash(x)=6468918) -847 train 7.793662 (lr=1.9818e-05) (hash(x)=8595271) -848 train 7.463602 (lr=1.9694e-05) (hash(x)=5833443) -849 train 7.461945 (lr=1.9572e-05) (hash(x)=6500949) -850 val loss 7.4960 -850 val perplexity 1800.8192 -850 train 7.441362 (lr=1.9450e-05) (hash(x)=5866207) -851 train 7.809490 (lr=1.9329e-05) (hash(x)=8395167) -852 train 7.822474 (lr=1.9209e-05) (hash(x)=8155803) -853 train 7.702494 (lr=1.9089e-05) (hash(x)=6288420) -854 train 7.661083 (lr=1.8970e-05) (hash(x)=6770885) -855 train 7.479127 (lr=1.8852e-05) (hash(x)=7634417) -856 train 7.401660 (lr=1.8734e-05) (hash(x)=6102598) -857 train 7.487947 (lr=1.8618e-05) (hash(x)=6795561) -858 train 7.428987 (lr=1.8501e-05) (hash(x)=6178545) -859 train 7.279370 (lr=1.8386e-05) (hash(x)=5257771) -860 train 7.226755 (lr=1.8271e-05) (hash(x)=5794385) -861 train 7.770595 (lr=1.8157e-05) (hash(x)=7506860) -862 train 7.579564 (lr=1.8044e-05) (hash(x)=4617636) -863 train 7.545092 (lr=1.7931e-05) (hash(x)=7674238) -864 train 8.023362 (lr=1.7819e-05) (hash(x)=7502317) -865 train 7.372228 (lr=1.7708e-05) (hash(x)=5353794) -866 train 7.906255 (lr=1.7598e-05) (hash(x)=8474964) -867 train 7.324858 (lr=1.7488e-05) (hash(x)=5300555) -868 train 7.202689 (lr=1.7379e-05) (hash(x)=6638039) -869 train 7.376221 (lr=1.7271e-05) (hash(x)=5564419) -870 train 7.725939 (lr=1.7163e-05) (hash(x)=6466311) -871 train 7.428892 (lr=1.7056e-05) (hash(x)=6066139) -872 train 7.577918 (lr=1.6950e-05) (hash(x)=6790356) -873 train 7.466569 (lr=1.6845e-05) (hash(x)=6863709) -874 train 7.622839 (lr=1.6740e-05) (hash(x)=6872703) -875 train 7.422786 (lr=1.6636e-05) (hash(x)=6688212) -876 train 7.627353 (lr=1.6533e-05) (hash(x)=4838260) -877 train 7.753117 (lr=1.6431e-05) (hash(x)=7095090) -878 train 7.931962 (lr=1.6329e-05) (hash(x)=6775236) -879 train 7.579637 (lr=1.6228e-05) (hash(x)=6642404) -880 train 7.413118 (lr=1.6128e-05) (hash(x)=6365570) -881 train 7.552148 (lr=1.6029e-05) (hash(x)=6539227) -882 train 7.508293 (lr=1.5930e-05) (hash(x)=5854007) -883 train 7.453975 (lr=1.5832e-05) (hash(x)=4961570) -884 train 7.250690 (lr=1.5735e-05) (hash(x)=3961674) -885 train 7.567011 (lr=1.5639e-05) (hash(x)=6606391) -886 train 7.019990 (lr=1.5543e-05) (hash(x)=6179396) -887 train 7.426561 (lr=1.5449e-05) (hash(x)=5105190) -888 train 7.890964 (lr=1.5354e-05) (hash(x)=5970936) -889 train 7.700416 (lr=1.5261e-05) (hash(x)=5695997) -890 train 7.427362 (lr=1.5169e-05) (hash(x)=6171397) -891 train 7.587002 (lr=1.5077e-05) (hash(x)=7155991) -892 train 7.333276 (lr=1.4986e-05) (hash(x)=6739404) -893 train 7.643411 (lr=1.4896e-05) (hash(x)=7249727) -894 train 7.569254 (lr=1.4806e-05) (hash(x)=6782303) -895 train 7.370490 (lr=1.4718e-05) (hash(x)=5132972) -896 train 7.566735 (lr=1.4630e-05) (hash(x)=5962092) -897 train 7.343990 (lr=1.4543e-05) (hash(x)=5381802) -898 train 7.379108 (lr=1.4456e-05) (hash(x)=6546040) -899 train 7.614974 (lr=1.4371e-05) (hash(x)=6269946) -900 val loss 7.4845 -900 val perplexity 1780.1853 -900 train 7.518080 (lr=1.4286e-05) (hash(x)=5427088) -901 train 7.408569 (lr=1.4202e-05) (hash(x)=4976762) -902 train 7.536988 (lr=1.4119e-05) (hash(x)=5758632) -903 train 7.545311 (lr=1.4037e-05) (hash(x)=5396133) -904 train 7.586462 (lr=1.3955e-05) (hash(x)=6805706) -905 train 7.417842 (lr=1.3874e-05) (hash(x)=6173473) -906 train 7.614098 (lr=1.3794e-05) (hash(x)=6565677) -907 train 7.362490 (lr=1.3715e-05) (hash(x)=6394083) -908 train 7.521427 (lr=1.3637e-05) (hash(x)=6445589) -909 train 7.541846 (lr=1.3559e-05) (hash(x)=6436030) -910 train 7.422109 (lr=1.3482e-05) (hash(x)=7220327) -911 train 7.407835 (lr=1.3407e-05) (hash(x)=5237804) -912 train 7.362480 (lr=1.3331e-05) (hash(x)=4906982) -913 train 7.412511 (lr=1.3257e-05) (hash(x)=6540397) -914 train 7.627008 (lr=1.3183e-05) (hash(x)=5799609) -915 train 7.672608 (lr=1.3111e-05) (hash(x)=5216638) -916 train 7.242054 (lr=1.3039e-05) (hash(x)=5646696) -917 train 7.679734 (lr=1.2968e-05) (hash(x)=5750537) -918 train 7.431813 (lr=1.2897e-05) (hash(x)=6625042) -919 train 7.462953 (lr=1.2828e-05) (hash(x)=6735565) -920 train 7.414454 (lr=1.2759e-05) (hash(x)=6600526) -921 train 7.516166 (lr=1.2691e-05) (hash(x)=7297488) -922 train 7.594961 (lr=1.2624e-05) (hash(x)=8039568) -923 train 7.804259 (lr=1.2558e-05) (hash(x)=5983575) -924 train 7.511978 (lr=1.2493e-05) (hash(x)=5322135) -925 train 7.457790 (lr=1.2428e-05) (hash(x)=4808543) -926 train 7.530905 (lr=1.2364e-05) (hash(x)=6387352) -927 train 7.608785 (lr=1.2301e-05) (hash(x)=5831619) -928 train 7.357819 (lr=1.2239e-05) (hash(x)=5418207) -929 train 7.342892 (lr=1.2178e-05) (hash(x)=6280052) -930 train 7.435105 (lr=1.2118e-05) (hash(x)=5668790) -931 train 7.335024 (lr=1.2058e-05) (hash(x)=9109083) -932 train 8.112984 (lr=1.1999e-05) (hash(x)=7957194) -933 train 7.182177 (lr=1.1941e-05) (hash(x)=5848604) -934 train 7.443889 (lr=1.1884e-05) (hash(x)=6466898) -935 train 7.651526 (lr=1.1828e-05) (hash(x)=6912967) -936 train 7.759449 (lr=1.1772e-05) (hash(x)=6802045) -937 train 7.676170 (lr=1.1718e-05) (hash(x)=6615365) -938 train 7.849210 (lr=1.1664e-05) (hash(x)=5956271) -939 train 7.719796 (lr=1.1611e-05) (hash(x)=5965674) -940 train 7.558442 (lr=1.1559e-05) (hash(x)=5925388) -941 train 7.711016 (lr=1.1508e-05) (hash(x)=6879965) -942 train 7.847147 (lr=1.1457e-05) (hash(x)=6850068) -943 train 7.360738 (lr=1.1408e-05) (hash(x)=5822533) -944 train 7.387764 (lr=1.1359e-05) (hash(x)=5175909) -945 train 7.514094 (lr=1.1311e-05) (hash(x)=5794462) -946 train 7.446325 (lr=1.1264e-05) (hash(x)=5451297) -947 train 7.654750 (lr=1.1218e-05) (hash(x)=5268216) -948 train 7.382711 (lr=1.1173e-05) (hash(x)=5828351) -949 train 7.319025 (lr=1.1128e-05) (hash(x)=7058396) -950 val loss 7.4760 -950 val perplexity 1765.1952 -950 train 7.331544 (lr=1.1085e-05) (hash(x)=6202824) -951 train 7.615052 (lr=1.1042e-05) (hash(x)=6531900) -952 train 7.483186 (lr=1.1000e-05) (hash(x)=6989972) -953 train 7.487875 (lr=1.0959e-05) (hash(x)=5878912) -954 train 7.285697 (lr=1.0919e-05) (hash(x)=7862929) -955 train 7.305834 (lr=1.0879e-05) (hash(x)=5426499) -956 train 7.307633 (lr=1.0841e-05) (hash(x)=5926459) -957 train 7.739917 (lr=1.0803e-05) (hash(x)=8107004) -958 train 8.225524 (lr=1.0766e-05) (hash(x)=8057219) -959 train 8.225957 (lr=1.0730e-05) (hash(x)=7455372) -960 train 8.154076 (lr=1.0695e-05) (hash(x)=7083241) -961 train 8.191495 (lr=1.0661e-05) (hash(x)=7727959) -962 train 8.145690 (lr=1.0628e-05) (hash(x)=8069628) -963 train 8.165591 (lr=1.0595e-05) (hash(x)=8319119) -964 train 8.110381 (lr=1.0563e-05) (hash(x)=8080739) -965 train 8.121663 (lr=1.0533e-05) (hash(x)=7581656) -966 train 8.160464 (lr=1.0503e-05) (hash(x)=7644116) -967 train 8.227348 (lr=1.0474e-05) (hash(x)=7592128) -968 train 8.112431 (lr=1.0445e-05) (hash(x)=7555224) -969 train 8.325616 (lr=1.0418e-05) (hash(x)=10506633) -970 train 8.113401 (lr=1.0391e-05) (hash(x)=7171723) -971 train 8.276295 (lr=1.0366e-05) (hash(x)=8704170) -972 train 8.171270 (lr=1.0341e-05) (hash(x)=6236578) -973 train 7.578439 (lr=1.0317e-05) (hash(x)=7461138) -974 train 7.582643 (lr=1.0294e-05) (hash(x)=6802094) -975 train 7.687768 (lr=1.0272e-05) (hash(x)=7165037) -976 train 7.962582 (lr=1.0251e-05) (hash(x)=7619348) -977 train 7.602947 (lr=1.0230e-05) (hash(x)=4976998) -978 train 7.525236 (lr=1.0211e-05) (hash(x)=7270148) -979 train 7.372386 (lr=1.0192e-05) (hash(x)=7678000) -980 train 7.524564 (lr=1.0174e-05) (hash(x)=5853099) -981 train 7.466434 (lr=1.0157e-05) (hash(x)=6299409) -982 train 7.458116 (lr=1.0141e-05) (hash(x)=5422994) -983 train 7.372293 (lr=1.0126e-05) (hash(x)=7414788) -984 train 7.663271 (lr=1.0111e-05) (hash(x)=5094219) -985 train 7.358177 (lr=1.0098e-05) (hash(x)=5063061) -986 train 7.395866 (lr=1.0085e-05) (hash(x)=5964965) -987 train 7.520918 (lr=1.0074e-05) (hash(x)=7326216) -988 train 7.642244 (lr=1.0063e-05) (hash(x)=7677783) -989 train 7.547838 (lr=1.0053e-05) (hash(x)=7492012) -990 train 7.513676 (lr=1.0044e-05) (hash(x)=5898822) -991 train 7.609740 (lr=1.0035e-05) (hash(x)=5857162) -992 train 7.313636 (lr=1.0028e-05) (hash(x)=5675101) -993 train 7.396257 (lr=1.0021e-05) (hash(x)=6169001) -994 train 7.530569 (lr=1.0016e-05) (hash(x)=6691027) -995 train 10.939221 (lr=1.0011e-05) (hash(x)=14715669) -996 train 12.059456 (lr=1.0007e-05) (hash(x)=14724033) -997 train 12.056811 (lr=1.0004e-05) (hash(x)=18256706) -998 train 12.625253 (lr=1.0002e-05) (hash(x)=16949966) -999 val loss 7.4720 -999 val perplexity 1758.0585 -999 train 11.496600 (lr=1.0000e-05) (hash(x)=16950560) +max_steps: 5000 +0 val loss 11.6964 +0 val perplexity 120134.1641 +0 train 11.690742 (lr=6.9930e-08) (hash(x)=26375038) +1 train 11.729673 (lr=1.3986e-07) (hash(x)=27234506) +2 train 11.684299 (lr=2.0979e-07) (hash(x)=23702020) +3 train 11.704971 (lr=2.7972e-07) (hash(x)=20782690) +4 train 11.697201 (lr=3.4965e-07) (hash(x)=23094976) +5 train 11.721626 (lr=4.1958e-07) (hash(x)=26532095) +6 train 11.667393 (lr=4.8951e-07) (hash(x)=27151649) +7 train 11.713636 (lr=5.5944e-07) (hash(x)=23890908) +8 train 11.696812 (lr=6.2937e-07) (hash(x)=25588236) +9 train 11.683083 (lr=6.9930e-07) (hash(x)=24011372) +10 train 11.679422 (lr=7.6923e-07) (hash(x)=28375581) +11 train 11.696705 (lr=8.3916e-07) (hash(x)=24611628) +12 train 11.712009 (lr=9.0909e-07) (hash(x)=30298407) +13 train 11.676620 (lr=9.7902e-07) (hash(x)=19245352) +14 train 11.669795 (lr=1.0490e-06) (hash(x)=28936608) +15 train 11.671635 (lr=1.1189e-06) (hash(x)=25767553) +16 train 11.664365 (lr=1.1888e-06) (hash(x)=31093473) +17 train 11.670269 (lr=1.2587e-06) (hash(x)=24809873) +18 train 11.676332 (lr=1.3287e-06) (hash(x)=27852919) +19 train 11.649427 (lr=1.3986e-06) (hash(x)=22512166) +20 train 11.685263 (lr=1.4685e-06) (hash(x)=27620338) +21 train 11.684132 (lr=1.5385e-06) (hash(x)=28092148) +22 train 11.638237 (lr=1.6084e-06) (hash(x)=27938767) +23 train 11.667180 (lr=1.6783e-06) (hash(x)=24732833) +24 train 11.638054 (lr=1.7483e-06) (hash(x)=23200230) +25 train 11.651146 (lr=1.8182e-06) (hash(x)=22694718) +26 train 11.641487 (lr=1.8881e-06) (hash(x)=23125151) +27 train 11.628527 (lr=1.9580e-06) (hash(x)=25129410) +28 train 11.633565 (lr=2.0280e-06) (hash(x)=23059154) +29 train 11.606318 (lr=2.0979e-06) (hash(x)=27858570) +30 train 11.604024 (lr=2.1678e-06) (hash(x)=22402617) +31 train 11.612592 (lr=2.2378e-06) (hash(x)=26582391) +32 train 11.571957 (lr=2.3077e-06) (hash(x)=26075451) +33 train 11.587166 (lr=2.3776e-06) (hash(x)=27279806) +34 train 11.550721 (lr=2.4476e-06) (hash(x)=26188136) +35 train 11.565956 (lr=2.5175e-06) (hash(x)=26472336) +36 train 11.576809 (lr=2.5874e-06) (hash(x)=26376212) +37 train 11.540867 (lr=2.6573e-06) (hash(x)=28301589) +38 train 11.536943 (lr=2.7273e-06) (hash(x)=28035221) +39 train 11.541970 (lr=2.7972e-06) (hash(x)=27654289) +40 train 11.543651 (lr=2.8671e-06) (hash(x)=21560904) +41 train 11.509266 (lr=2.9371e-06) (hash(x)=24995715) +42 train 11.563976 (lr=3.0070e-06) (hash(x)=23792508) +43 train 11.530199 (lr=3.0769e-06) (hash(x)=26559876) +44 train 11.503267 (lr=3.1469e-06) (hash(x)=25758852) +45 train 11.480848 (lr=3.2168e-06) (hash(x)=28364895) +46 train 11.494434 (lr=3.2867e-06) (hash(x)=25269299) +47 train 11.496878 (lr=3.3566e-06) (hash(x)=21770329) +48 train 11.481480 (lr=3.4266e-06) (hash(x)=24785397) +49 train 11.432987 (lr=3.4965e-06) (hash(x)=24628606) +50 val loss 11.4349 +50 val perplexity 92490.3203 +50 train 11.439604 (lr=3.5664e-06) (hash(x)=23181910) +51 train 11.426868 (lr=3.6364e-06) (hash(x)=22723459) +52 train 11.430687 (lr=3.7063e-06) (hash(x)=25506632) +53 train 11.360913 (lr=3.7762e-06) (hash(x)=22897919) +54 train 11.377836 (lr=3.8462e-06) (hash(x)=26546719) +55 train 11.442345 (lr=3.9161e-06) (hash(x)=30338342) +56 train 11.372355 (lr=3.9860e-06) (hash(x)=29175888) +57 train 11.374412 (lr=4.0559e-06) (hash(x)=27063280) +58 train 11.368296 (lr=4.1259e-06) (hash(x)=32915097) +59 train 11.343601 (lr=4.1958e-06) (hash(x)=25678059) +60 train 11.314718 (lr=4.2657e-06) (hash(x)=20083773) +61 train 11.279016 (lr=4.3357e-06) (hash(x)=21853028) +62 train 11.304262 (lr=4.4056e-06) (hash(x)=21808483) +63 train 11.308235 (lr=4.4755e-06) (hash(x)=26109335) +64 train 11.295149 (lr=4.5455e-06) (hash(x)=24916754) +65 train 11.284315 (lr=4.6154e-06) (hash(x)=25334848) +66 train 11.260025 (lr=4.6853e-06) (hash(x)=24917705) +67 train 11.158278 (lr=4.7552e-06) (hash(x)=25044885) +68 train 11.195553 (lr=4.8252e-06) (hash(x)=28747022) +69 train 11.232515 (lr=4.8951e-06) (hash(x)=23678349) +70 train 11.247366 (lr=4.9650e-06) (hash(x)=28529813) +71 train 11.229904 (lr=5.0350e-06) (hash(x)=28870690) +72 train 11.185102 (lr=5.1049e-06) (hash(x)=25044834) +73 train 11.192621 (lr=5.1748e-06) (hash(x)=32982615) +74 train 11.178533 (lr=5.2448e-06) (hash(x)=20970960) +75 train 11.230579 (lr=5.3147e-06) (hash(x)=35279941) +76 train 11.129540 (lr=5.3846e-06) (hash(x)=25529472) +77 train 11.089846 (lr=5.4545e-06) (hash(x)=26400041) +78 train 11.093430 (lr=5.5245e-06) (hash(x)=24656138) +79 train 11.050531 (lr=5.5944e-06) (hash(x)=25015923) +80 train 10.981668 (lr=5.6643e-06) (hash(x)=22924885) +81 train 10.994120 (lr=5.7343e-06) (hash(x)=24853586) +82 train 11.036135 (lr=5.8042e-06) (hash(x)=27004780) +83 train 10.980446 (lr=5.8741e-06) (hash(x)=26740855) +84 train 10.918530 (lr=5.9441e-06) (hash(x)=23950114) +85 train 10.898762 (lr=6.0140e-06) (hash(x)=24584116) +86 train 10.908869 (lr=6.0839e-06) (hash(x)=25718516) +87 train 10.948042 (lr=6.1538e-06) (hash(x)=22262151) +88 train 10.928476 (lr=6.2238e-06) (hash(x)=23025303) +89 train 10.859241 (lr=6.2937e-06) (hash(x)=26627860) +90 train 10.879793 (lr=6.3636e-06) (hash(x)=23700532) +91 train 10.853809 (lr=6.4336e-06) (hash(x)=26621834) +92 train 10.810335 (lr=6.5035e-06) (hash(x)=21821465) +93 train 10.834971 (lr=6.5734e-06) (hash(x)=26930630) +94 train 10.770636 (lr=6.6434e-06) (hash(x)=19557946) +95 train 10.779814 (lr=6.7133e-06) (hash(x)=23234741) +96 train 10.757848 (lr=6.7832e-06) (hash(x)=26713563) +97 train 10.766600 (lr=6.8531e-06) (hash(x)=28102443) +98 train 10.875882 (lr=6.9231e-06) (hash(x)=31689122) +99 train 10.827652 (lr=6.9930e-06) (hash(x)=25470563) +100 val loss 10.7356 +100 val perplexity 45963.2148 +100 train 10.811583 (lr=7.0629e-06) (hash(x)=23757479) +101 train 10.643835 (lr=7.1329e-06) (hash(x)=28282861) +102 train 10.722900 (lr=7.2028e-06) (hash(x)=26731964) +103 train 10.752064 (lr=7.2727e-06) (hash(x)=21799102) +104 train 10.701377 (lr=7.3427e-06) (hash(x)=24672077) +105 train 10.644577 (lr=7.4126e-06) (hash(x)=23471769) +106 train 10.632232 (lr=7.4825e-06) (hash(x)=24058931) +107 train 10.635239 (lr=7.5524e-06) (hash(x)=23275479) +108 train 10.707773 (lr=7.6224e-06) (hash(x)=24364396) +109 train 10.650689 (lr=7.6923e-06) (hash(x)=24473581) +110 train 10.621929 (lr=7.7622e-06) (hash(x)=23774644) +111 train 10.620817 (lr=7.8322e-06) (hash(x)=22091862) +112 train 10.536441 (lr=7.9021e-06) (hash(x)=25482303) +113 train 10.656721 (lr=7.9720e-06) (hash(x)=26018202) +114 train 10.527460 (lr=8.0420e-06) (hash(x)=24560096) +115 train 10.601419 (lr=8.1119e-06) (hash(x)=17430373) +116 train 10.434622 (lr=8.1818e-06) (hash(x)=20098681) +117 train 10.390629 (lr=8.2517e-06) (hash(x)=24078083) +118 train 10.525700 (lr=8.3217e-06) (hash(x)=26595592) +119 train 10.521581 (lr=8.3916e-06) (hash(x)=22954861) +120 train 10.546805 (lr=8.4615e-06) (hash(x)=29294271) +121 train 10.550329 (lr=8.5315e-06) (hash(x)=28695016) +122 train 10.527302 (lr=8.6014e-06) (hash(x)=27100115) +123 train 10.516151 (lr=8.6713e-06) (hash(x)=26671799) +124 train 10.579380 (lr=8.7413e-06) (hash(x)=28137394) +125 train 10.515220 (lr=8.8112e-06) (hash(x)=23166092) +126 train 10.376602 (lr=8.8811e-06) (hash(x)=25885986) +127 train 10.406994 (lr=8.9510e-06) (hash(x)=26924723) +128 train 10.450733 (lr=9.0210e-06) (hash(x)=26140590) +129 train 10.484803 (lr=9.0909e-06) (hash(x)=25138659) +130 train 10.513576 (lr=9.1608e-06) (hash(x)=27224685) +131 train 10.433712 (lr=9.2308e-06) (hash(x)=23557495) +132 train 10.324814 (lr=9.3007e-06) (hash(x)=23928957) +133 train 10.364628 (lr=9.3706e-06) (hash(x)=25288123) +134 train 10.359480 (lr=9.4406e-06) (hash(x)=23246294) +135 train 10.099140 (lr=9.5105e-06) (hash(x)=27804380) +136 train 10.429182 (lr=9.5804e-06) (hash(x)=23089140) +137 train 10.512815 (lr=9.6503e-06) (hash(x)=26993263) +138 train 10.508226 (lr=9.7203e-06) (hash(x)=27397203) +139 train 10.452492 (lr=9.7902e-06) (hash(x)=26654908) +140 train 10.389021 (lr=9.8601e-06) (hash(x)=21965022) +141 train 10.361942 (lr=9.9301e-06) (hash(x)=27347722) +142 train 10.415810 (lr=1.0000e-05) (hash(x)=28314127) +143 train 10.462876 (lr=1.0070e-05) (hash(x)=23627518) +144 train 10.441091 (lr=1.0140e-05) (hash(x)=25024764) +145 train 10.375940 (lr=1.0210e-05) (hash(x)=21768671) +146 train 10.364031 (lr=1.0280e-05) (hash(x)=25076667) +147 train 10.348312 (lr=1.0350e-05) (hash(x)=21889990) +148 train 10.325742 (lr=1.0420e-05) (hash(x)=20932794) +149 train 10.334614 (lr=1.0490e-05) (hash(x)=23665838) +150 val loss 10.3648 +150 val perplexity 31722.6484 +150 train 10.641626 (lr=1.0559e-05) (hash(x)=30223582) +151 train 10.404593 (lr=1.0629e-05) (hash(x)=22528001) +152 train 10.396338 (lr=1.0699e-05) (hash(x)=25181641) +153 train 10.389452 (lr=1.0769e-05) (hash(x)=22487328) +154 train 10.432519 (lr=1.0839e-05) (hash(x)=26544630) +155 train 10.422050 (lr=1.0909e-05) (hash(x)=29248942) +156 train 10.412046 (lr=1.0979e-05) (hash(x)=25052066) +157 train 10.255971 (lr=1.1049e-05) (hash(x)=23543273) +158 train 10.386531 (lr=1.1119e-05) (hash(x)=27451288) +159 train 10.247346 (lr=1.1189e-05) (hash(x)=25533417) +160 train 10.241920 (lr=1.1259e-05) (hash(x)=24432899) +161 train 10.159497 (lr=1.1329e-05) (hash(x)=25552036) +162 train 10.236443 (lr=1.1399e-05) (hash(x)=28149782) +163 train 10.326161 (lr=1.1469e-05) (hash(x)=20612533) +164 train 10.358227 (lr=1.1538e-05) (hash(x)=19774173) +165 train 10.304837 (lr=1.1608e-05) (hash(x)=20216795) +166 train 10.404428 (lr=1.1678e-05) (hash(x)=25896435) +167 train 10.336811 (lr=1.1748e-05) (hash(x)=24677740) +168 train 10.343723 (lr=1.1818e-05) (hash(x)=21835643) +169 train 10.290783 (lr=1.1888e-05) (hash(x)=16722715) +170 train 10.322159 (lr=1.1958e-05) (hash(x)=26303975) +171 train 10.324040 (lr=1.2028e-05) (hash(x)=25347203) +172 train 10.313398 (lr=1.2098e-05) (hash(x)=25973417) +173 train 10.237167 (lr=1.2168e-05) (hash(x)=24272489) +174 train 10.252502 (lr=1.2238e-05) (hash(x)=29260846) +175 train 10.324348 (lr=1.2308e-05) (hash(x)=28922363) +176 train 10.184172 (lr=1.2378e-05) (hash(x)=26322572) +177 train 10.241709 (lr=1.2448e-05) (hash(x)=25510798) +178 train 10.309429 (lr=1.2517e-05) (hash(x)=24138948) +179 train 10.271446 (lr=1.2587e-05) (hash(x)=25631397) +180 train 10.193684 (lr=1.2657e-05) (hash(x)=24001903) +181 train 10.158322 (lr=1.2727e-05) (hash(x)=21333676) +182 train 10.199251 (lr=1.2797e-05) (hash(x)=30770484) +183 train 10.239061 (lr=1.2867e-05) (hash(x)=26237983) +184 train 10.209682 (lr=1.2937e-05) (hash(x)=26205744) +185 train 10.298344 (lr=1.3007e-05) (hash(x)=25976502) +186 train 10.161404 (lr=1.3077e-05) (hash(x)=24080636) +187 train 10.317057 (lr=1.3147e-05) (hash(x)=24742645) +188 train 10.300900 (lr=1.3217e-05) (hash(x)=28677257) +189 train 10.172282 (lr=1.3287e-05) (hash(x)=27086333) +190 train 10.181519 (lr=1.3357e-05) (hash(x)=27855233) +191 train 10.302767 (lr=1.3427e-05) (hash(x)=26157660) +192 train 10.253893 (lr=1.3497e-05) (hash(x)=25046062) +193 train 10.226677 (lr=1.3566e-05) (hash(x)=23616370) +194 train 10.064716 (lr=1.3636e-05) (hash(x)=24302232) +195 train 10.081670 (lr=1.3706e-05) (hash(x)=22582169) +196 train 10.128762 (lr=1.3776e-05) (hash(x)=22773833) +197 train 10.111918 (lr=1.3846e-05) (hash(x)=26233189) +198 train 10.182570 (lr=1.3916e-05) (hash(x)=26431507) +199 train 10.262657 (lr=1.3986e-05) (hash(x)=26431960) +200 val loss 10.2010 +200 val perplexity 26930.0820 +200 train 10.144894 (lr=1.4056e-05) (hash(x)=25112360) +201 train 10.361131 (lr=1.4126e-05) (hash(x)=30707498) +202 train 10.169018 (lr=1.4196e-05) (hash(x)=22586447) +203 train 10.239132 (lr=1.4266e-05) (hash(x)=25716176) +204 train 10.271934 (lr=1.4336e-05) (hash(x)=25118971) +205 train 10.161192 (lr=1.4406e-05) (hash(x)=26256420) +206 train 10.205061 (lr=1.4476e-05) (hash(x)=22633318) +207 train 10.167380 (lr=1.4545e-05) (hash(x)=28019788) +208 train 10.104158 (lr=1.4615e-05) (hash(x)=27396089) +209 train 10.136521 (lr=1.4685e-05) (hash(x)=23510110) +210 train 10.199759 (lr=1.4755e-05) (hash(x)=23646926) +211 train 10.179728 (lr=1.4825e-05) (hash(x)=20382963) +212 train 10.127595 (lr=1.4895e-05) (hash(x)=24304768) +213 train 10.052370 (lr=1.4965e-05) (hash(x)=25339466) +214 train 10.141193 (lr=1.5035e-05) (hash(x)=22088696) +215 train 10.191642 (lr=1.5105e-05) (hash(x)=24489647) +216 train 9.994972 (lr=1.5175e-05) (hash(x)=22940357) +217 train 10.160796 (lr=1.5245e-05) (hash(x)=22927699) +218 train 10.064096 (lr=1.5315e-05) (hash(x)=27631132) +219 train 10.135612 (lr=1.5385e-05) (hash(x)=25128502) +220 train 10.124343 (lr=1.5455e-05) (hash(x)=23576982) +221 train 10.124802 (lr=1.5524e-05) (hash(x)=25808969) +222 train 10.095691 (lr=1.5594e-05) (hash(x)=23429962) +223 train 10.095449 (lr=1.5664e-05) (hash(x)=25231390) +224 train 10.033884 (lr=1.5734e-05) (hash(x)=25395441) +225 train 10.089479 (lr=1.5804e-05) (hash(x)=21154388) +226 train 10.092579 (lr=1.5874e-05) (hash(x)=24278611) +227 train 10.069687 (lr=1.5944e-05) (hash(x)=22708977) +228 train 10.140999 (lr=1.6014e-05) (hash(x)=28228490) +229 train 10.095218 (lr=1.6084e-05) (hash(x)=27258353) +230 train 10.082066 (lr=1.6154e-05) (hash(x)=23252199) +231 train 10.018395 (lr=1.6224e-05) (hash(x)=24364920) +232 train 10.079066 (lr=1.6294e-05) (hash(x)=23283905) +233 train 10.090525 (lr=1.6364e-05) (hash(x)=27243972) +234 train 10.246466 (lr=1.6434e-05) (hash(x)=28113043) +235 train 10.004034 (lr=1.6503e-05) (hash(x)=24932925) +236 train 10.094431 (lr=1.6573e-05) (hash(x)=19001259) +237 train 10.060642 (lr=1.6643e-05) (hash(x)=26371091) +238 train 10.002590 (lr=1.6713e-05) (hash(x)=24258817) +239 train 10.029902 (lr=1.6783e-05) (hash(x)=26913684) +240 train 10.127560 (lr=1.6853e-05) (hash(x)=27753043) +241 train 9.980370 (lr=1.6923e-05) (hash(x)=29239611) +242 train 10.037615 (lr=1.6993e-05) (hash(x)=22984557) +243 train 9.873613 (lr=1.7063e-05) (hash(x)=18017792) +244 train 10.063791 (lr=1.7133e-05) (hash(x)=23374526) +245 train 9.994743 (lr=1.7203e-05) (hash(x)=27574089) +246 train 10.008470 (lr=1.7273e-05) (hash(x)=26154906) +247 train 10.065066 (lr=1.7343e-05) (hash(x)=28613882) +248 train 9.985352 (lr=1.7413e-05) (hash(x)=25272182) +249 train 9.948185 (lr=1.7483e-05) (hash(x)=26981914) +250 val loss 9.9817 +250 val perplexity 21625.9727 +250 train 9.990757 (lr=1.7552e-05) (hash(x)=24232348) +251 train 10.010859 (lr=1.7622e-05) (hash(x)=22652243) +252 train 10.038023 (lr=1.7692e-05) (hash(x)=25411991) +253 train 9.756573 (lr=1.7762e-05) (hash(x)=15446025) +254 train 9.875750 (lr=1.7832e-05) (hash(x)=27846176) +255 train 9.900261 (lr=1.7902e-05) (hash(x)=27194521) +256 train 9.937436 (lr=1.7972e-05) (hash(x)=29430001) +257 train 9.753612 (lr=1.8042e-05) (hash(x)=25264518) +258 train 9.950717 (lr=1.8112e-05) (hash(x)=25568956) +259 train 10.013736 (lr=1.8182e-05) (hash(x)=24936836) +260 train 9.942068 (lr=1.8252e-05) (hash(x)=27452099) +261 train 9.971541 (lr=1.8322e-05) (hash(x)=28197282) +262 train 9.919928 (lr=1.8392e-05) (hash(x)=22931889) +263 train 9.981867 (lr=1.8462e-05) (hash(x)=24765578) +264 train 9.845216 (lr=1.8531e-05) (hash(x)=25078649) +265 train 9.942845 (lr=1.8601e-05) (hash(x)=27448185) +266 train 9.992942 (lr=1.8671e-05) (hash(x)=24804856) +267 train 9.830757 (lr=1.8741e-05) (hash(x)=23107416) +268 train 9.634457 (lr=1.8811e-05) (hash(x)=24960796) +269 train 9.916851 (lr=1.8881e-05) (hash(x)=26755138) +270 train 9.861683 (lr=1.8951e-05) (hash(x)=24542526) +271 train 9.902065 (lr=1.9021e-05) (hash(x)=29314255) +272 train 9.745187 (lr=1.9091e-05) (hash(x)=27347755) +273 train 9.839918 (lr=1.9161e-05) (hash(x)=22112669) +274 train 9.812531 (lr=1.9231e-05) (hash(x)=25161929) +275 train 9.856415 (lr=1.9301e-05) (hash(x)=24013079) +276 train 9.832156 (lr=1.9371e-05) (hash(x)=26768629) +277 train 9.645758 (lr=1.9441e-05) (hash(x)=22537194) +278 train 9.637988 (lr=1.9510e-05) (hash(x)=24974360) +279 train 9.871611 (lr=1.9580e-05) (hash(x)=25322001) +280 train 9.854668 (lr=1.9650e-05) (hash(x)=20562247) +281 train 9.938965 (lr=1.9720e-05) (hash(x)=27028126) +282 train 9.845312 (lr=1.9790e-05) (hash(x)=25666355) +283 train 9.814117 (lr=1.9860e-05) (hash(x)=26690440) +284 train 9.770067 (lr=1.9930e-05) (hash(x)=27348418) +285 train 9.743496 (lr=2.0000e-05) (hash(x)=26967331) +286 train 9.787535 (lr=2.0070e-05) (hash(x)=24765121) +287 train 9.819496 (lr=2.0140e-05) (hash(x)=22598512) +288 train 9.811995 (lr=2.0210e-05) (hash(x)=23725598) +289 train 9.771534 (lr=2.0280e-05) (hash(x)=24697985) +290 train 9.717348 (lr=2.0350e-05) (hash(x)=25201962) +291 train 9.568714 (lr=2.0420e-05) (hash(x)=18473911) +292 train 9.742908 (lr=2.0490e-05) (hash(x)=25982840) +293 train 9.760418 (lr=2.0559e-05) (hash(x)=23172124) +294 train 9.879694 (lr=2.0629e-05) (hash(x)=34646114) +295 train 9.764612 (lr=2.0699e-05) (hash(x)=22322442) +296 train 9.641899 (lr=2.0769e-05) (hash(x)=26211794) +297 train 9.748532 (lr=2.0839e-05) (hash(x)=29659121) +298 train 9.700926 (lr=2.0909e-05) (hash(x)=23538306) +299 train 9.710512 (lr=2.0979e-05) (hash(x)=26324153) +300 val loss 9.7010 +300 val perplexity 16333.1729 +300 train 9.661652 (lr=2.1049e-05) (hash(x)=24910403) +301 train 9.723969 (lr=2.1119e-05) (hash(x)=26939970) +302 train 9.671789 (lr=2.1189e-05) (hash(x)=27515446) +303 train 9.767620 (lr=2.1259e-05) (hash(x)=23446058) +304 train 9.757229 (lr=2.1329e-05) (hash(x)=25308253) +305 train 9.679197 (lr=2.1399e-05) (hash(x)=29981801) +306 train 9.633627 (lr=2.1469e-05) (hash(x)=23470413) +307 train 9.649160 (lr=2.1538e-05) (hash(x)=24843741) +308 train 9.686563 (lr=2.1608e-05) (hash(x)=27176996) +309 train 9.651074 (lr=2.1678e-05) (hash(x)=22855363) +310 train 9.520674 (lr=2.1748e-05) (hash(x)=22960957) +311 train 9.721649 (lr=2.1818e-05) (hash(x)=23197102) +312 train 9.669054 (lr=2.1888e-05) (hash(x)=26132276) +313 train 9.566977 (lr=2.1958e-05) (hash(x)=25704919) +314 train 9.662512 (lr=2.2028e-05) (hash(x)=22280814) +315 train 9.867509 (lr=2.2098e-05) (hash(x)=23054940) +316 train 9.797565 (lr=2.2168e-05) (hash(x)=24712416) +317 train 9.713720 (lr=2.2238e-05) (hash(x)=24909904) +318 train 9.626366 (lr=2.2308e-05) (hash(x)=24321591) +319 train 9.296043 (lr=2.2378e-05) (hash(x)=27140757) +320 train 9.420919 (lr=2.2448e-05) (hash(x)=26563770) +321 train 9.479474 (lr=2.2517e-05) (hash(x)=25993110) +322 train 9.462049 (lr=2.2587e-05) (hash(x)=28520222) +323 train 9.464747 (lr=2.2657e-05) (hash(x)=25149419) +324 train 9.589695 (lr=2.2727e-05) (hash(x)=26112813) +325 train 9.570065 (lr=2.2797e-05) (hash(x)=27623643) +326 train 9.545168 (lr=2.2867e-05) (hash(x)=29199854) +327 train 9.584236 (lr=2.2937e-05) (hash(x)=24727764) +328 train 9.252939 (lr=2.3007e-05) (hash(x)=22667179) +329 train 9.282925 (lr=2.3077e-05) (hash(x)=23155773) +330 train 9.477123 (lr=2.3147e-05) (hash(x)=23453788) +331 train 9.495989 (lr=2.3217e-05) (hash(x)=21935931) +332 train 9.431241 (lr=2.3287e-05) (hash(x)=24481079) +333 train 9.393909 (lr=2.3357e-05) (hash(x)=20054917) +334 train 9.487060 (lr=2.3427e-05) (hash(x)=25907741) +335 train 9.511618 (lr=2.3497e-05) (hash(x)=27606073) +336 train 9.569716 (lr=2.3566e-05) (hash(x)=25202001) +337 train 9.491137 (lr=2.3636e-05) (hash(x)=26534487) +338 train 9.536945 (lr=2.3706e-05) (hash(x)=24095850) +339 train 9.299612 (lr=2.3776e-05) (hash(x)=22450341) +340 train 9.552876 (lr=2.3846e-05) (hash(x)=27993763) +341 train 9.388597 (lr=2.3916e-05) (hash(x)=25013073) +342 train 9.408981 (lr=2.3986e-05) (hash(x)=30934371) +343 train 9.546349 (lr=2.4056e-05) (hash(x)=25945859) +344 train 9.365334 (lr=2.4126e-05) (hash(x)=25218689) +345 train 9.402443 (lr=2.4196e-05) (hash(x)=24418091) +346 train 9.394996 (lr=2.4266e-05) (hash(x)=24615466) +347 train 9.364246 (lr=2.4336e-05) (hash(x)=21613707) +348 train 9.334831 (lr=2.4406e-05) (hash(x)=24348175) +349 train 9.386295 (lr=2.4476e-05) (hash(x)=26386157) +350 val loss 9.3709 +350 val perplexity 11741.9600 +350 train 9.413349 (lr=2.4545e-05) (hash(x)=25771047) +351 train 9.348189 (lr=2.4615e-05) (hash(x)=24396519) +352 train 9.467689 (lr=2.4685e-05) (hash(x)=25142399) +353 train 9.196591 (lr=2.4755e-05) (hash(x)=23265507) +354 train 9.321170 (lr=2.4825e-05) (hash(x)=22514858) +355 train 9.397852 (lr=2.4895e-05) (hash(x)=29138828) +356 train 9.418425 (lr=2.4965e-05) (hash(x)=20531210) +357 train 9.260423 (lr=2.5035e-05) (hash(x)=24265353) +358 train 9.344686 (lr=2.5105e-05) (hash(x)=24999726) +359 train 9.356032 (lr=2.5175e-05) (hash(x)=24685515) +360 train 9.244402 (lr=2.5245e-05) (hash(x)=25071701) +361 train 9.311719 (lr=2.5315e-05) (hash(x)=24876269) +362 train 9.422531 (lr=2.5385e-05) (hash(x)=31733180) +363 train 9.122704 (lr=2.5455e-05) (hash(x)=22825749) +364 train 9.308639 (lr=2.5524e-05) (hash(x)=26393943) +365 train 9.252937 (lr=2.5594e-05) (hash(x)=21239652) +366 train 9.121815 (lr=2.5664e-05) (hash(x)=24943881) +367 train 9.287088 (lr=2.5734e-05) (hash(x)=28767869) +368 train 9.234972 (lr=2.5804e-05) (hash(x)=29341482) +369 train 9.194169 (lr=2.5874e-05) (hash(x)=25614301) +370 train 9.274575 (lr=2.5944e-05) (hash(x)=26030058) +371 train 9.224163 (lr=2.6014e-05) (hash(x)=21159060) +372 train 9.162056 (lr=2.6084e-05) (hash(x)=24629937) +373 train 9.172271 (lr=2.6154e-05) (hash(x)=26751788) +374 train 9.168272 (lr=2.6224e-05) (hash(x)=26012353) +375 train 9.099259 (lr=2.6294e-05) (hash(x)=25045397) +376 train 8.992895 (lr=2.6364e-05) (hash(x)=23751143) +377 train 9.478315 (lr=2.6434e-05) (hash(x)=29989709) +378 train 9.230366 (lr=2.6503e-05) (hash(x)=31017246) +379 train 9.303522 (lr=2.6573e-05) (hash(x)=25560928) +380 train 9.196114 (lr=2.6643e-05) (hash(x)=27352253) +381 train 9.276297 (lr=2.6713e-05) (hash(x)=26062687) +382 train 9.170877 (lr=2.6783e-05) (hash(x)=27614522) +383 train 9.139617 (lr=2.6853e-05) (hash(x)=28959222) +384 train 9.060068 (lr=2.6923e-05) (hash(x)=25122598) +385 train 9.021961 (lr=2.6993e-05) (hash(x)=25434884) +386 train 9.066758 (lr=2.7063e-05) (hash(x)=27824438) +387 train 9.197889 (lr=2.7133e-05) (hash(x)=21248405) +388 train 9.059446 (lr=2.7203e-05) (hash(x)=26482588) +389 train 9.130011 (lr=2.7273e-05) (hash(x)=25044192) +390 train 9.111866 (lr=2.7343e-05) (hash(x)=28645524) +391 train 9.082142 (lr=2.7413e-05) (hash(x)=25830182) +392 train 9.085911 (lr=2.7483e-05) (hash(x)=25585137) +393 train 9.028769 (lr=2.7552e-05) (hash(x)=26621419) +394 train 8.862897 (lr=2.7622e-05) (hash(x)=22165286) +395 train 9.046309 (lr=2.7692e-05) (hash(x)=25173113) +396 train 9.045418 (lr=2.7762e-05) (hash(x)=27267091) +397 train 9.045079 (lr=2.7832e-05) (hash(x)=24400133) +398 train 8.941266 (lr=2.7902e-05) (hash(x)=23103223) +399 train 9.041512 (lr=2.7972e-05) (hash(x)=23486277) +400 val loss 9.0011 +400 val perplexity 8112.1226 +400 train 8.918294 (lr=2.8042e-05) (hash(x)=23421286) +401 train 9.034676 (lr=2.8112e-05) (hash(x)=25978130) +402 train 9.015829 (lr=2.8182e-05) (hash(x)=25769432) +403 train 8.999851 (lr=2.8252e-05) (hash(x)=28916006) +404 train 9.037079 (lr=2.8322e-05) (hash(x)=24226056) +405 train 9.133806 (lr=2.8392e-05) (hash(x)=33195100) +406 train 9.086657 (lr=2.8462e-05) (hash(x)=27730410) +407 train 8.978981 (lr=2.8531e-05) (hash(x)=25556929) +408 train 8.957786 (lr=2.8601e-05) (hash(x)=25991247) +409 train 9.007450 (lr=2.8671e-05) (hash(x)=29536986) +410 train 8.982000 (lr=2.8741e-05) (hash(x)=26125216) +411 train 8.944823 (lr=2.8811e-05) (hash(x)=29648798) +412 train 8.970469 (lr=2.8881e-05) (hash(x)=23195388) +413 train 8.918907 (lr=2.8951e-05) (hash(x)=23124767) +414 train 8.916449 (lr=2.9021e-05) (hash(x)=25713275) +415 train 8.653189 (lr=2.9091e-05) (hash(x)=24976217) +416 train 8.889861 (lr=2.9161e-05) (hash(x)=27500801) +417 train 8.842020 (lr=2.9231e-05) (hash(x)=23632825) +418 train 8.917753 (lr=2.9301e-05) (hash(x)=24456276) +419 train 9.032506 (lr=2.9371e-05) (hash(x)=31019606) +420 train 9.000190 (lr=2.9441e-05) (hash(x)=25027904) +421 train 8.905977 (lr=2.9510e-05) (hash(x)=28236580) +422 train 8.809811 (lr=2.9580e-05) (hash(x)=25386473) +423 train 8.937870 (lr=2.9650e-05) (hash(x)=28269421) +424 train 8.675201 (lr=2.9720e-05) (hash(x)=24308447) +425 train 8.828802 (lr=2.9790e-05) (hash(x)=25563279) +426 train 8.839563 (lr=2.9860e-05) (hash(x)=26152637) +427 train 8.831087 (lr=2.9930e-05) (hash(x)=24865358) +428 train 8.755907 (lr=3.0000e-05) (hash(x)=22230964) +429 train 8.734436 (lr=3.0070e-05) (hash(x)=22155546) +430 train 8.828810 (lr=3.0140e-05) (hash(x)=29142319) +431 train 8.515303 (lr=3.0210e-05) (hash(x)=26984272) +432 train 8.775410 (lr=3.0280e-05) (hash(x)=27077032) +433 train 8.742796 (lr=3.0350e-05) (hash(x)=23193673) +434 train 8.798432 (lr=3.0420e-05) (hash(x)=27112558) +435 train 8.795906 (lr=3.0490e-05) (hash(x)=24544116) +436 train 8.789482 (lr=3.0559e-05) (hash(x)=25890184) +437 train 8.749880 (lr=3.0629e-05) (hash(x)=24547533) +438 train 8.821388 (lr=3.0699e-05) (hash(x)=27467688) +439 train 8.640163 (lr=3.0769e-05) (hash(x)=22059850) +440 train 8.824439 (lr=3.0839e-05) (hash(x)=23893130) +441 train 8.757427 (lr=3.0909e-05) (hash(x)=25994573) +442 train 8.742758 (lr=3.0979e-05) (hash(x)=26577783) +443 train 8.741581 (lr=3.1049e-05) (hash(x)=23926632) +444 train 8.739922 (lr=3.1119e-05) (hash(x)=23574207) +445 train 8.579082 (lr=3.1189e-05) (hash(x)=27111369) +446 train 8.718896 (lr=3.1259e-05) (hash(x)=23979820) +447 train 8.738392 (lr=3.1329e-05) (hash(x)=27025333) +448 train 8.652737 (lr=3.1399e-05) (hash(x)=22846386) +449 train 8.652788 (lr=3.1469e-05) (hash(x)=16908068) +450 val loss 8.6769 +450 val perplexity 5866.0073 +450 train 8.672997 (lr=3.1538e-05) (hash(x)=25664727) +451 train 8.669798 (lr=3.1608e-05) (hash(x)=29120407) +452 train 8.804841 (lr=3.1678e-05) (hash(x)=25564213) +453 train 8.865331 (lr=3.1748e-05) (hash(x)=27092710) +454 train 8.733643 (lr=3.1818e-05) (hash(x)=28533197) +455 train 8.610714 (lr=3.1888e-05) (hash(x)=23827393) +456 train 8.487192 (lr=3.1958e-05) (hash(x)=24154233) +457 train 8.625460 (lr=3.2028e-05) (hash(x)=32812727) +458 train 8.656540 (lr=3.2098e-05) (hash(x)=26305435) +459 train 8.699203 (lr=3.2168e-05) (hash(x)=27230027) +460 train 8.575463 (lr=3.2238e-05) (hash(x)=23532437) +461 train 8.686043 (lr=3.2308e-05) (hash(x)=25703381) +462 train 8.602468 (lr=3.2378e-05) (hash(x)=26961429) +463 train 8.567656 (lr=3.2448e-05) (hash(x)=24968260) +464 train 8.620388 (lr=3.2517e-05) (hash(x)=24854265) +465 train 8.590502 (lr=3.2587e-05) (hash(x)=25676468) +466 train 8.656578 (lr=3.2657e-05) (hash(x)=25503865) +467 train 8.589008 (lr=3.2727e-05) (hash(x)=27544803) +468 train 8.589678 (lr=3.2797e-05) (hash(x)=24658683) +469 train 8.634713 (lr=3.2867e-05) (hash(x)=24331407) +470 train 8.605266 (lr=3.2937e-05) (hash(x)=21892556) +471 train 8.544264 (lr=3.3007e-05) (hash(x)=26540663) +472 train 8.496643 (lr=3.3077e-05) (hash(x)=26819462) +473 train 8.628642 (lr=3.3147e-05) (hash(x)=25532657) +474 train 8.620456 (lr=3.3217e-05) (hash(x)=26515570) +475 train 8.689799 (lr=3.3287e-05) (hash(x)=25856625) +476 train 8.488948 (lr=3.3357e-05) (hash(x)=25260471) +477 train 8.524252 (lr=3.3427e-05) (hash(x)=23437426) +478 train 8.664003 (lr=3.3497e-05) (hash(x)=25961833) +479 train 8.462437 (lr=3.3566e-05) (hash(x)=23164356) +480 train 8.475103 (lr=3.3636e-05) (hash(x)=25052665) +481 train 8.567804 (lr=3.3706e-05) (hash(x)=25957896) +482 train 8.541885 (lr=3.3776e-05) (hash(x)=24723263) +483 train 8.567241 (lr=3.3846e-05) (hash(x)=25646282) +484 train 8.520219 (lr=3.3916e-05) (hash(x)=25851993) +485 train 8.590618 (lr=3.3986e-05) (hash(x)=21513584) +486 train 8.425169 (lr=3.4056e-05) (hash(x)=26017176) +487 train 8.546069 (lr=3.4126e-05) (hash(x)=23843233) +488 train 8.509894 (lr=3.4196e-05) (hash(x)=21476847) +489 train 8.405796 (lr=3.4266e-05) (hash(x)=23226697) +490 train 8.223912 (lr=3.4336e-05) (hash(x)=19772969) +491 train 8.387327 (lr=3.4406e-05) (hash(x)=24506028) +492 train 8.388490 (lr=3.4476e-05) (hash(x)=21077417) +493 train 8.460022 (lr=3.4545e-05) (hash(x)=26024321) +494 train 8.548983 (lr=3.4615e-05) (hash(x)=27786174) +495 train 8.479696 (lr=3.4685e-05) (hash(x)=22781277) +496 train 8.478997 (lr=3.4755e-05) (hash(x)=24459895) +497 train 8.522593 (lr=3.4825e-05) (hash(x)=24451843) +498 train 8.486242 (lr=3.4895e-05) (hash(x)=21116390) +499 train 8.469432 (lr=3.4965e-05) (hash(x)=24948650) +500 val loss 8.4454 +500 val perplexity 4653.4448 +500 train 8.412222 (lr=3.5035e-05) (hash(x)=25617781) +501 train 8.422417 (lr=3.5105e-05) (hash(x)=25559534) +502 train 8.473438 (lr=3.5175e-05) (hash(x)=25546274) +503 train 8.392671 (lr=3.5245e-05) (hash(x)=26373991) +504 train 8.401636 (lr=3.5315e-05) (hash(x)=26410662) +505 train 8.537443 (lr=3.5385e-05) (hash(x)=27756673) +506 train 8.555323 (lr=3.5455e-05) (hash(x)=23661686) +507 train 8.387391 (lr=3.5524e-05) (hash(x)=23402396) +508 train 8.481287 (lr=3.5594e-05) (hash(x)=26547918) +509 train 8.381535 (lr=3.5664e-05) (hash(x)=28250354) +510 train 8.474730 (lr=3.5734e-05) (hash(x)=25598861) +511 train 8.390716 (lr=3.5804e-05) (hash(x)=21562133) +512 train 8.573660 (lr=3.5874e-05) (hash(x)=25312391) +513 train 8.461157 (lr=3.5944e-05) (hash(x)=27253861) +514 train 8.421654 (lr=3.6014e-05) (hash(x)=26795921) +515 train 8.427609 (lr=3.6084e-05) (hash(x)=25009210) +516 train 8.357092 (lr=3.6154e-05) (hash(x)=26254538) +517 train 8.228937 (lr=3.6224e-05) (hash(x)=23052577) +518 train 8.480295 (lr=3.6294e-05) (hash(x)=23667224) +519 train 8.295721 (lr=3.6364e-05) (hash(x)=27161811) +520 train 8.274876 (lr=3.6434e-05) (hash(x)=26313522) +521 train 8.330503 (lr=3.6503e-05) (hash(x)=27302459) +522 train 8.453587 (lr=3.6573e-05) (hash(x)=26837963) +523 train 8.363329 (lr=3.6643e-05) (hash(x)=29515100) +524 train 8.270988 (lr=3.6713e-05) (hash(x)=26674478) +525 train 8.292062 (lr=3.6783e-05) (hash(x)=25318001) +526 train 8.404912 (lr=3.6853e-05) (hash(x)=25174043) +527 train 8.242570 (lr=3.6923e-05) (hash(x)=25305929) +528 train 8.423829 (lr=3.6993e-05) (hash(x)=26175477) +529 train 8.205457 (lr=3.7063e-05) (hash(x)=24339043) +530 train 8.472940 (lr=3.7133e-05) (hash(x)=25412772) +531 train 8.272922 (lr=3.7203e-05) (hash(x)=26808543) +532 train 8.239235 (lr=3.7273e-05) (hash(x)=24738650) +533 train 8.238927 (lr=3.7343e-05) (hash(x)=25763991) +534 train 8.406149 (lr=3.7413e-05) (hash(x)=28182190) +535 train 8.260846 (lr=3.7483e-05) (hash(x)=25669509) +536 train 8.382465 (lr=3.7552e-05) (hash(x)=25616522) +537 train 8.362928 (lr=3.7622e-05) (hash(x)=27676869) +538 train 8.293081 (lr=3.7692e-05) (hash(x)=26316170) +539 train 8.228192 (lr=3.7762e-05) (hash(x)=28435805) +540 train 8.276140 (lr=3.7832e-05) (hash(x)=26869022) +541 train 8.172129 (lr=3.7902e-05) (hash(x)=23455211) +542 train 8.400764 (lr=3.7972e-05) (hash(x)=29321187) +543 train 8.394329 (lr=3.8042e-05) (hash(x)=26482758) +544 train 8.178461 (lr=3.8112e-05) (hash(x)=26046639) +545 train 8.230627 (lr=3.8182e-05) (hash(x)=27068280) +546 train 8.188328 (lr=3.8252e-05) (hash(x)=26782091) +547 train 8.325580 (lr=3.8322e-05) (hash(x)=24929929) +548 train 8.275822 (lr=3.8392e-05) (hash(x)=25950541) +549 train 8.236288 (lr=3.8462e-05) (hash(x)=25373676) +550 val loss 8.2401 +550 val perplexity 3789.8538 +550 train 8.279553 (lr=3.8531e-05) (hash(x)=27283187) +551 train 8.226327 (lr=3.8601e-05) (hash(x)=25043037) +552 train 8.321621 (lr=3.8671e-05) (hash(x)=27027534) +553 train 8.252300 (lr=3.8741e-05) (hash(x)=27906976) +554 train 8.225452 (lr=3.8811e-05) (hash(x)=23889709) +555 train 8.779345 (lr=3.8881e-05) (hash(x)=29151257) +556 train 8.349623 (lr=3.8951e-05) (hash(x)=21307974) +557 train 8.302156 (lr=3.9021e-05) (hash(x)=26405613) +558 train 8.135519 (lr=3.9091e-05) (hash(x)=24233887) +559 train 8.103419 (lr=3.9161e-05) (hash(x)=26400365) +560 train 8.283518 (lr=3.9231e-05) (hash(x)=22293114) +561 train 8.139302 (lr=3.9301e-05) (hash(x)=23971905) +562 train 8.113969 (lr=3.9371e-05) (hash(x)=20076502) +563 train 8.190751 (lr=3.9441e-05) (hash(x)=24098812) +564 train 8.305332 (lr=3.9510e-05) (hash(x)=27610410) +565 train 8.262882 (lr=3.9580e-05) (hash(x)=29402976) +566 train 8.065121 (lr=3.9650e-05) (hash(x)=19032564) +567 train 8.208203 (lr=3.9720e-05) (hash(x)=20967666) +568 train 8.116385 (lr=3.9790e-05) (hash(x)=22666342) +569 train 8.259691 (lr=3.9860e-05) (hash(x)=24287610) +570 train 8.326998 (lr=3.9930e-05) (hash(x)=28637634) +571 train 8.503241 (lr=4.0000e-05) (hash(x)=28667963) +572 train 8.300302 (lr=4.0070e-05) (hash(x)=23621685) +573 train 8.115033 (lr=4.0140e-05) (hash(x)=25974316) +574 train 8.140406 (lr=4.0210e-05) (hash(x)=24487710) +575 train 8.422989 (lr=4.0280e-05) (hash(x)=27083417) +576 train 8.023375 (lr=4.0350e-05) (hash(x)=22850633) +577 train 8.288055 (lr=4.0420e-05) (hash(x)=28605205) +578 train 8.132451 (lr=4.0490e-05) (hash(x)=24786468) +579 train 8.151125 (lr=4.0559e-05) (hash(x)=23649001) +580 train 8.213137 (lr=4.0629e-05) (hash(x)=26473994) +581 train 8.038525 (lr=4.0699e-05) (hash(x)=25921700) +582 train 8.038196 (lr=4.0769e-05) (hash(x)=24117626) +583 train 8.338470 (lr=4.0839e-05) (hash(x)=31338300) +584 train 8.048629 (lr=4.0909e-05) (hash(x)=21337692) +585 train 8.178109 (lr=4.0979e-05) (hash(x)=23862328) +586 train 8.226645 (lr=4.1049e-05) (hash(x)=24380098) +587 train 8.092865 (lr=4.1119e-05) (hash(x)=30603174) +588 train 8.325654 (lr=4.1189e-05) (hash(x)=30882548) +589 train 8.034408 (lr=4.1259e-05) (hash(x)=23603806) +590 train 8.162816 (lr=4.1329e-05) (hash(x)=24382442) +591 train 8.069885 (lr=4.1399e-05) (hash(x)=24830965) +592 train 8.192265 (lr=4.1469e-05) (hash(x)=25547480) +593 train 8.222952 (lr=4.1538e-05) (hash(x)=32488729) +594 train 8.338691 (lr=4.1608e-05) (hash(x)=31331643) +595 train 8.182062 (lr=4.1678e-05) (hash(x)=27269893) +596 train 8.101644 (lr=4.1748e-05) (hash(x)=23278725) +597 train 8.146628 (lr=4.1818e-05) (hash(x)=25215077) +598 train 8.109501 (lr=4.1888e-05) (hash(x)=22442404) +599 train 8.066055 (lr=4.1958e-05) (hash(x)=24825041) +600 val loss 8.1086 +600 val perplexity 3322.8296 +600 train 8.185061 (lr=4.2028e-05) (hash(x)=25590276) +601 train 8.127841 (lr=4.2098e-05) (hash(x)=25893804) +602 train 8.009729 (lr=4.2168e-05) (hash(x)=22222468) +603 train 8.042007 (lr=4.2238e-05) (hash(x)=22724871) +604 train 8.043649 (lr=4.2308e-05) (hash(x)=25140744) +605 train 8.070316 (lr=4.2378e-05) (hash(x)=27317554) +606 train 8.062438 (lr=4.2448e-05) (hash(x)=26692343) +607 train 7.965703 (lr=4.2517e-05) (hash(x)=24683717) +608 train 8.008658 (lr=4.2587e-05) (hash(x)=26849303) +609 train 8.067092 (lr=4.2657e-05) (hash(x)=21584083) +610 train 8.172340 (lr=4.2727e-05) (hash(x)=26059939) +611 train 8.200708 (lr=4.2797e-05) (hash(x)=26190337) +612 train 8.108775 (lr=4.2867e-05) (hash(x)=23663918) +613 train 8.135217 (lr=4.2937e-05) (hash(x)=22249019) +614 train 8.105878 (lr=4.3007e-05) (hash(x)=25779849) +615 train 8.068590 (lr=4.3077e-05) (hash(x)=23086289) +616 train 8.179958 (lr=4.3147e-05) (hash(x)=27523941) +617 train 8.348303 (lr=4.3217e-05) (hash(x)=28047044) +618 train 8.102356 (lr=4.3287e-05) (hash(x)=25125498) +619 train 7.951319 (lr=4.3357e-05) (hash(x)=23593875) +620 train 8.025940 (lr=4.3427e-05) (hash(x)=25117733) +621 train 8.000637 (lr=4.3497e-05) (hash(x)=26059735) +622 train 8.024593 (lr=4.3566e-05) (hash(x)=23028679) +623 train 7.936064 (lr=4.3636e-05) (hash(x)=22414190) +624 train 8.055202 (lr=4.3706e-05) (hash(x)=22223137) +625 train 8.167895 (lr=4.3776e-05) (hash(x)=24204591) +626 train 7.957342 (lr=4.3846e-05) (hash(x)=22922475) +627 train 8.084461 (lr=4.3916e-05) (hash(x)=26758114) +628 train 7.990994 (lr=4.3986e-05) (hash(x)=25358064) +629 train 8.108311 (lr=4.4056e-05) (hash(x)=20084233) +630 train 8.072581 (lr=4.4126e-05) (hash(x)=26395104) +631 train 7.872966 (lr=4.4196e-05) (hash(x)=21563184) +632 train 8.077248 (lr=4.4266e-05) (hash(x)=25207694) +633 train 7.942939 (lr=4.4336e-05) (hash(x)=23861489) +634 train 8.129162 (lr=4.4406e-05) (hash(x)=23471007) +635 train 7.953823 (lr=4.4476e-05) (hash(x)=19218470) +636 train 8.046698 (lr=4.4545e-05) (hash(x)=22944035) +637 train 8.031645 (lr=4.4615e-05) (hash(x)=28469562) +638 train 8.172002 (lr=4.4685e-05) (hash(x)=26452814) +639 train 8.117779 (lr=4.4755e-05) (hash(x)=25588469) +640 train 8.018270 (lr=4.4825e-05) (hash(x)=24788298) +641 train 8.063878 (lr=4.4895e-05) (hash(x)=25236367) +642 train 7.920441 (lr=4.4965e-05) (hash(x)=23069067) +643 train 8.189961 (lr=4.5035e-05) (hash(x)=30433767) +644 train 8.358845 (lr=4.5105e-05) (hash(x)=29268881) +645 train 8.080614 (lr=4.5175e-05) (hash(x)=26302626) +646 train 8.172912 (lr=4.5245e-05) (hash(x)=24749682) +647 train 7.804380 (lr=4.5315e-05) (hash(x)=17851621) +648 train 7.961715 (lr=4.5385e-05) (hash(x)=25620741) +649 train 8.348459 (lr=4.5455e-05) (hash(x)=27028191) +650 val loss 8.0054 +650 val perplexity 2997.1436 +650 train 8.066511 (lr=4.5524e-05) (hash(x)=27590299) +651 train 8.183214 (lr=4.5594e-05) (hash(x)=25183690) +652 train 8.109227 (lr=4.5664e-05) (hash(x)=31114252) +653 train 8.193423 (lr=4.5734e-05) (hash(x)=26182243) +654 train 8.261454 (lr=4.5804e-05) (hash(x)=30419908) +655 train 8.205196 (lr=4.5874e-05) (hash(x)=27040642) +656 train 8.015928 (lr=4.5944e-05) (hash(x)=26240761) +657 train 7.993984 (lr=4.6014e-05) (hash(x)=24489607) +658 train 8.148478 (lr=4.6084e-05) (hash(x)=25012872) +659 train 7.795298 (lr=4.6154e-05) (hash(x)=22183303) +660 train 8.022511 (lr=4.6224e-05) (hash(x)=27682633) +661 train 8.089152 (lr=4.6294e-05) (hash(x)=28844646) +662 train 8.526134 (lr=4.6364e-05) (hash(x)=31082070) +663 train 8.292898 (lr=4.6434e-05) (hash(x)=27537063) +664 train 8.004047 (lr=4.6503e-05) (hash(x)=26125988) +665 train 8.101000 (lr=4.6573e-05) (hash(x)=25446686) +666 train 8.136047 (lr=4.6643e-05) (hash(x)=19819857) +667 train 7.800828 (lr=4.6713e-05) (hash(x)=19492832) +668 train 7.922976 (lr=4.6783e-05) (hash(x)=23741214) +669 train 7.979284 (lr=4.6853e-05) (hash(x)=25484958) +670 train 7.963727 (lr=4.6923e-05) (hash(x)=25525370) +671 train 8.044321 (lr=4.6993e-05) (hash(x)=25951629) +672 train 8.233843 (lr=4.7063e-05) (hash(x)=28557663) +673 train 7.814538 (lr=4.7133e-05) (hash(x)=23462798) +674 train 7.801642 (lr=4.7203e-05) (hash(x)=27320280) +675 train 8.060727 (lr=4.7273e-05) (hash(x)=22408682) +676 train 7.888561 (lr=4.7343e-05) (hash(x)=22230799) +677 train 8.259338 (lr=4.7413e-05) (hash(x)=31317970) +678 train 7.925068 (lr=4.7483e-05) (hash(x)=24020983) +679 train 7.901785 (lr=4.7552e-05) (hash(x)=27633457) +680 train 7.820998 (lr=4.7622e-05) (hash(x)=23766987) +681 train 7.982926 (lr=4.7692e-05) (hash(x)=23729283) +682 train 8.117132 (lr=4.7762e-05) (hash(x)=25975834) +683 train 8.018628 (lr=4.7832e-05) (hash(x)=27635080) +684 train 7.998369 (lr=4.7902e-05) (hash(x)=27181156) +685 train 7.994286 (lr=4.7972e-05) (hash(x)=25918780) +686 train 8.061900 (lr=4.8042e-05) (hash(x)=22370417) +687 train 7.867872 (lr=4.8112e-05) (hash(x)=22287596) +688 train 7.867644 (lr=4.8182e-05) (hash(x)=21584419) +689 train 7.900035 (lr=4.8252e-05) (hash(x)=22694623) +690 train 8.025595 (lr=4.8322e-05) (hash(x)=30820846) +691 train 8.390560 (lr=4.8392e-05) (hash(x)=35895440) +692 train 8.035145 (lr=4.8462e-05) (hash(x)=27058657) +693 train 7.957857 (lr=4.8531e-05) (hash(x)=24298886) +694 train 7.949383 (lr=4.8601e-05) (hash(x)=27303061) +695 train 7.979492 (lr=4.8671e-05) (hash(x)=25888847) +696 train 7.844123 (lr=4.8741e-05) (hash(x)=21267641) +697 train 8.191000 (lr=4.8811e-05) (hash(x)=30860646) +698 train 7.944805 (lr=4.8881e-05) (hash(x)=26881837) +699 train 8.020011 (lr=4.8951e-05) (hash(x)=26518800) +700 val loss 7.9185 +700 val perplexity 2747.7786 +700 train 8.036907 (lr=4.9021e-05) (hash(x)=25863277) +701 train 7.813935 (lr=4.9091e-05) (hash(x)=25385523) +702 train 7.877307 (lr=4.9161e-05) (hash(x)=23362519) +703 train 8.242008 (lr=4.9231e-05) (hash(x)=37519283) +704 train 8.262175 (lr=4.9301e-05) (hash(x)=23392584) +705 train 8.336795 (lr=4.9371e-05) (hash(x)=20564397) +706 train 8.027091 (lr=4.9441e-05) (hash(x)=27065499) +707 train 7.925479 (lr=4.9510e-05) (hash(x)=25141945) +708 train 8.038802 (lr=4.9580e-05) (hash(x)=25466598) +709 train 7.892987 (lr=4.9650e-05) (hash(x)=22717866) +710 train 8.462174 (lr=4.9720e-05) (hash(x)=29648992) +711 train 8.159887 (lr=4.9790e-05) (hash(x)=28527939) +712 train 7.871010 (lr=4.9860e-05) (hash(x)=25134784) +713 train 8.252941 (lr=4.9930e-05) (hash(x)=32757059) +714 train 7.872623 (lr=5.0000e-05) (hash(x)=24145729) +715 train 7.836281 (lr=5.0070e-05) (hash(x)=21942471) +716 train 7.931807 (lr=5.0140e-05) (hash(x)=25325444) +717 train 8.295347 (lr=5.0210e-05) (hash(x)=24247339) +718 train 7.948881 (lr=5.0280e-05) (hash(x)=24142989) +719 train 7.863824 (lr=5.0350e-05) (hash(x)=24955630) +720 train 7.941189 (lr=5.0420e-05) (hash(x)=25491335) +721 train 8.040634 (lr=5.0490e-05) (hash(x)=21368780) +722 train 7.960185 (lr=5.0559e-05) (hash(x)=27146278) +723 train 7.837763 (lr=5.0629e-05) (hash(x)=25541230) +724 train 7.864661 (lr=5.0699e-05) (hash(x)=25375355) +725 train 7.780392 (lr=5.0769e-05) (hash(x)=23098806) +726 train 7.823208 (lr=5.0839e-05) (hash(x)=22061174) +727 train 7.816224 (lr=5.0909e-05) (hash(x)=23501481) +728 train 7.970102 (lr=5.0979e-05) (hash(x)=24656430) +729 train 7.732312 (lr=5.1049e-05) (hash(x)=23802681) +730 train 7.810917 (lr=5.1119e-05) (hash(x)=23496118) +731 train 7.936036 (lr=5.1189e-05) (hash(x)=22754988) +732 train 7.726565 (lr=5.1259e-05) (hash(x)=21461650) +733 train 7.795265 (lr=5.1329e-05) (hash(x)=22183009) +734 train 7.840655 (lr=5.1399e-05) (hash(x)=22300616) +735 train 7.640139 (lr=5.1469e-05) (hash(x)=23475070) +736 train 7.862689 (lr=5.1538e-05) (hash(x)=24508407) +737 train 7.858733 (lr=5.1608e-05) (hash(x)=23359061) +738 train 7.836387 (lr=5.1678e-05) (hash(x)=22588667) +739 train 7.926486 (lr=5.1748e-05) (hash(x)=23609959) +740 train 7.909669 (lr=5.1818e-05) (hash(x)=25394852) +741 train 7.754148 (lr=5.1888e-05) (hash(x)=22408449) +742 train 7.893541 (lr=5.1958e-05) (hash(x)=26947398) +743 train 7.659472 (lr=5.2028e-05) (hash(x)=23441847) +744 train 7.750387 (lr=5.2098e-05) (hash(x)=23101350) +745 train 7.744606 (lr=5.2168e-05) (hash(x)=23676365) +746 train 7.943790 (lr=5.2238e-05) (hash(x)=26488811) +747 train 7.938446 (lr=5.2308e-05) (hash(x)=23096292) +748 train 7.969716 (lr=5.2378e-05) (hash(x)=24512380) +749 train 7.899137 (lr=5.2448e-05) (hash(x)=27706294) +750 val loss 7.8497 +750 val perplexity 2564.9304 +750 train 7.854964 (lr=5.2517e-05) (hash(x)=21892472) +751 train 7.815755 (lr=5.2587e-05) (hash(x)=26171093) +752 train 7.839805 (lr=5.2657e-05) (hash(x)=23191101) +753 train 8.156120 (lr=5.2727e-05) (hash(x)=34946941) +754 train 7.980219 (lr=5.2797e-05) (hash(x)=25569942) +755 train 7.597536 (lr=5.2867e-05) (hash(x)=20060838) +756 train 7.701924 (lr=5.2937e-05) (hash(x)=24581020) +757 train 7.701828 (lr=5.3007e-05) (hash(x)=21591702) +758 train 7.763254 (lr=5.3077e-05) (hash(x)=21870012) +759 train 7.832306 (lr=5.3147e-05) (hash(x)=25451055) +760 train 7.618488 (lr=5.3217e-05) (hash(x)=18989695) +761 train 7.330967 (lr=5.3287e-05) (hash(x)=18691455) +762 train 7.698718 (lr=5.3357e-05) (hash(x)=22406503) +763 train 7.857756 (lr=5.3427e-05) (hash(x)=24934792) +764 train 7.758128 (lr=5.3497e-05) (hash(x)=24249677) +765 train 7.655087 (lr=5.3566e-05) (hash(x)=23864361) +766 train 7.679482 (lr=5.3636e-05) (hash(x)=21549554) +767 train 7.830834 (lr=5.3706e-05) (hash(x)=25367597) +768 train 7.948168 (lr=5.3776e-05) (hash(x)=24409290) +769 train 7.760854 (lr=5.3846e-05) (hash(x)=27016702) +770 train 7.911597 (lr=5.3916e-05) (hash(x)=25520453) +771 train 7.757201 (lr=5.3986e-05) (hash(x)=25022148) +772 train 7.886436 (lr=5.4056e-05) (hash(x)=25010319) +773 train 7.782702 (lr=5.4126e-05) (hash(x)=24459012) +774 train 7.819573 (lr=5.4196e-05) (hash(x)=26528670) +775 train 7.823457 (lr=5.4266e-05) (hash(x)=25431365) +776 train 7.685737 (lr=5.4336e-05) (hash(x)=24229522) +777 train 7.833734 (lr=5.4406e-05) (hash(x)=25958785) +778 train 7.776005 (lr=5.4476e-05) (hash(x)=22882640) +779 train 8.133474 (lr=5.4545e-05) (hash(x)=29307788) +780 train 7.695004 (lr=5.4615e-05) (hash(x)=23167825) +781 train 7.737351 (lr=5.4685e-05) (hash(x)=24965435) +782 train 7.630119 (lr=5.4755e-05) (hash(x)=23772949) +783 train 7.852965 (lr=5.4825e-05) (hash(x)=25651929) +784 train 7.754521 (lr=5.4895e-05) (hash(x)=23146724) +785 train 7.794220 (lr=5.4965e-05) (hash(x)=28451031) +786 train 7.808039 (lr=5.5035e-05) (hash(x)=23796771) +787 train 7.830116 (lr=5.5105e-05) (hash(x)=26312387) +788 train 7.746166 (lr=5.5175e-05) (hash(x)=21257377) +789 train 7.874257 (lr=5.5245e-05) (hash(x)=25326650) +790 train 7.749450 (lr=5.5315e-05) (hash(x)=24605603) +791 train 7.718937 (lr=5.5385e-05) (hash(x)=23804913) +792 train 7.917698 (lr=5.5455e-05) (hash(x)=24322926) +793 train 7.925773 (lr=5.5524e-05) (hash(x)=25537529) +794 train 7.669663 (lr=5.5594e-05) (hash(x)=25707197) +795 train 7.842839 (lr=5.5664e-05) (hash(x)=26115519) +796 train 7.762859 (lr=5.5734e-05) (hash(x)=24850654) +797 train 7.699524 (lr=5.5804e-05) (hash(x)=25494804) +798 train 7.734128 (lr=5.5874e-05) (hash(x)=21972022) +799 train 7.960864 (lr=5.5944e-05) (hash(x)=23210747) +800 val loss 7.7838 +800 val perplexity 2401.2698 +800 train 7.770511 (lr=5.6014e-05) (hash(x)=17064773) +801 train 7.776778 (lr=5.6084e-05) (hash(x)=15717069) +802 train 7.821982 (lr=5.6154e-05) (hash(x)=16189636) +803 train 7.593920 (lr=5.6224e-05) (hash(x)=18463712) +804 train 7.717484 (lr=5.6294e-05) (hash(x)=19970072) +805 train 7.775805 (lr=5.6364e-05) (hash(x)=20705573) +806 train 7.754278 (lr=5.6434e-05) (hash(x)=22913147) +807 train 7.812070 (lr=5.6503e-05) (hash(x)=23245699) +808 train 7.783280 (lr=5.6573e-05) (hash(x)=27121904) +809 train 7.718926 (lr=5.6643e-05) (hash(x)=23444521) +810 train 7.692472 (lr=5.6713e-05) (hash(x)=20917937) +811 train 7.703287 (lr=5.6783e-05) (hash(x)=21770300) +812 train 8.722979 (lr=5.6853e-05) (hash(x)=24642519) +813 train 7.920707 (lr=5.6923e-05) (hash(x)=23334569) +814 train 7.579972 (lr=5.6993e-05) (hash(x)=21796200) +815 train 7.606483 (lr=5.7063e-05) (hash(x)=25387532) +816 train 7.516168 (lr=5.7133e-05) (hash(x)=22203733) +817 train 8.065192 (lr=5.7203e-05) (hash(x)=29466743) +818 train 7.787288 (lr=5.7273e-05) (hash(x)=21756102) +819 train 7.826082 (lr=5.7343e-05) (hash(x)=27718703) +820 train 7.795719 (lr=5.7413e-05) (hash(x)=22978681) +821 train 7.828092 (lr=5.7483e-05) (hash(x)=17631973) +822 train 7.883764 (lr=5.7552e-05) (hash(x)=27947891) +823 train 7.783240 (lr=5.7622e-05) (hash(x)=27661052) +824 train 7.563356 (lr=5.7692e-05) (hash(x)=23061452) +825 train 7.670251 (lr=5.7762e-05) (hash(x)=22244096) +826 train 7.709648 (lr=5.7832e-05) (hash(x)=25389713) +827 train 7.796686 (lr=5.7902e-05) (hash(x)=26538928) +828 train 7.839804 (lr=5.7972e-05) (hash(x)=25685569) +829 train 7.609000 (lr=5.8042e-05) (hash(x)=26256802) +830 train 7.896957 (lr=5.8112e-05) (hash(x)=24412323) +831 train 7.791864 (lr=5.8182e-05) (hash(x)=21772654) +832 train 7.647842 (lr=5.8252e-05) (hash(x)=25456825) +833 train 7.953285 (lr=5.8322e-05) (hash(x)=25026277) +834 train 7.901797 (lr=5.8392e-05) (hash(x)=26855439) +835 train 7.917826 (lr=5.8462e-05) (hash(x)=26263254) +836 train 7.939088 (lr=5.8531e-05) (hash(x)=21917396) +837 train 7.754387 (lr=5.8601e-05) (hash(x)=24726314) +838 train 7.627221 (lr=5.8671e-05) (hash(x)=24375100) +839 train 7.659298 (lr=5.8741e-05) (hash(x)=23552356) +840 train 7.784454 (lr=5.8811e-05) (hash(x)=25343112) +841 train 7.729139 (lr=5.8881e-05) (hash(x)=26699819) +842 train 8.013735 (lr=5.8951e-05) (hash(x)=25218858) +843 train 8.164486 (lr=5.9021e-05) (hash(x)=22707141) +844 train 8.023645 (lr=5.9091e-05) (hash(x)=29168269) +845 train 8.121172 (lr=5.9161e-05) (hash(x)=25676149) +846 train 7.675354 (lr=5.9231e-05) (hash(x)=24324401) +847 train 7.981902 (lr=5.9301e-05) (hash(x)=34234481) +848 train 7.733874 (lr=5.9371e-05) (hash(x)=24511386) +849 train 7.723206 (lr=5.9441e-05) (hash(x)=25401624) +850 val loss 7.7488 +850 val perplexity 2318.8794 +850 train 7.712522 (lr=5.9510e-05) (hash(x)=22340685) +851 train 8.017552 (lr=5.9580e-05) (hash(x)=35008670) +852 train 8.016077 (lr=5.9650e-05) (hash(x)=29662286) +853 train 7.881158 (lr=5.9720e-05) (hash(x)=25682280) +854 train 7.911352 (lr=5.9790e-05) (hash(x)=27686498) +855 train 7.741438 (lr=5.9860e-05) (hash(x)=25891543) +856 train 7.654632 (lr=5.9930e-05) (hash(x)=22538881) +857 train 7.761053 (lr=6.0000e-05) (hash(x)=25962407) +858 train 7.709263 (lr=6.0070e-05) (hash(x)=24819073) +859 train 7.582533 (lr=6.0140e-05) (hash(x)=21971224) +860 train 7.565965 (lr=6.0210e-05) (hash(x)=20951317) +861 train 7.943989 (lr=6.0280e-05) (hash(x)=30838142) +862 train 7.779339 (lr=6.0350e-05) (hash(x)=23102419) +863 train 7.808508 (lr=6.0420e-05) (hash(x)=27312186) +864 train 8.170492 (lr=6.0490e-05) (hash(x)=30920030) +865 train 7.619479 (lr=6.0559e-05) (hash(x)=23657081) +866 train 8.064472 (lr=6.0629e-05) (hash(x)=35351214) +867 train 7.623046 (lr=6.0699e-05) (hash(x)=22163749) +868 train 7.471849 (lr=6.0769e-05) (hash(x)=24629160) +869 train 7.593278 (lr=6.0839e-05) (hash(x)=24829818) +870 train 7.901993 (lr=6.0909e-05) (hash(x)=25424550) +871 train 7.682379 (lr=6.0979e-05) (hash(x)=25942888) +872 train 7.799688 (lr=6.1049e-05) (hash(x)=26418501) +873 train 7.685640 (lr=6.1119e-05) (hash(x)=23785671) +874 train 7.847627 (lr=6.1189e-05) (hash(x)=25097859) +875 train 7.686390 (lr=6.1259e-05) (hash(x)=25493916) +876 train 7.853680 (lr=6.1329e-05) (hash(x)=19819210) +877 train 7.967946 (lr=6.1399e-05) (hash(x)=28618702) +878 train 8.102901 (lr=6.1469e-05) (hash(x)=29707907) +879 train 7.802185 (lr=6.1538e-05) (hash(x)=24289951) +880 train 7.665711 (lr=6.1608e-05) (hash(x)=25147026) +881 train 7.765967 (lr=6.1678e-05) (hash(x)=26331486) +882 train 7.747631 (lr=6.1748e-05) (hash(x)=25885126) +883 train 7.683144 (lr=6.1818e-05) (hash(x)=23648671) +884 train 7.527898 (lr=6.1888e-05) (hash(x)=20252079) +885 train 7.786923 (lr=6.1958e-05) (hash(x)=27292797) +886 train 7.330560 (lr=6.2028e-05) (hash(x)=18317379) +887 train 7.658503 (lr=6.2098e-05) (hash(x)=24992055) +888 train 8.088664 (lr=6.2168e-05) (hash(x)=24734221) +889 train 7.907431 (lr=6.2238e-05) (hash(x)=24398330) +890 train 7.672947 (lr=6.2308e-05) (hash(x)=23573984) +891 train 7.782568 (lr=6.2378e-05) (hash(x)=26005549) +892 train 7.570706 (lr=6.2448e-05) (hash(x)=22583878) +893 train 7.848307 (lr=6.2517e-05) (hash(x)=30259737) +894 train 7.784857 (lr=6.2587e-05) (hash(x)=25196470) +895 train 7.592758 (lr=6.2657e-05) (hash(x)=21046554) +896 train 7.783712 (lr=6.2727e-05) (hash(x)=25454371) +897 train 7.598475 (lr=6.2797e-05) (hash(x)=18773877) +898 train 7.624607 (lr=6.2867e-05) (hash(x)=24645168) +899 train 7.809205 (lr=6.2937e-05) (hash(x)=26321539) +900 val loss 7.7073 +900 val perplexity 2224.5898 +900 train 7.734323 (lr=6.3007e-05) (hash(x)=25722713) +901 train 7.645831 (lr=6.3077e-05) (hash(x)=22850804) +902 train 7.738389 (lr=6.3147e-05) (hash(x)=22503524) +903 train 7.760847 (lr=6.3217e-05) (hash(x)=27807872) +904 train 7.771271 (lr=6.3287e-05) (hash(x)=25845590) +905 train 7.668800 (lr=6.3357e-05) (hash(x)=25545137) +906 train 7.831692 (lr=6.3427e-05) (hash(x)=25471231) +907 train 7.617954 (lr=6.3497e-05) (hash(x)=21555364) +908 train 7.735058 (lr=6.3566e-05) (hash(x)=24474988) +909 train 7.773468 (lr=6.3636e-05) (hash(x)=27243798) +910 train 7.667670 (lr=6.3706e-05) (hash(x)=24419085) +911 train 7.633158 (lr=6.3776e-05) (hash(x)=26325324) +912 train 7.588046 (lr=6.3846e-05) (hash(x)=24822111) +913 train 7.653014 (lr=6.3916e-05) (hash(x)=26228728) +914 train 7.835828 (lr=6.3986e-05) (hash(x)=24707042) +915 train 7.863822 (lr=6.4056e-05) (hash(x)=24956294) +916 train 7.500225 (lr=6.4126e-05) (hash(x)=23424737) +917 train 7.881249 (lr=6.4196e-05) (hash(x)=25592289) +918 train 7.639921 (lr=6.4266e-05) (hash(x)=26826109) +919 train 7.686322 (lr=6.4336e-05) (hash(x)=24429389) +920 train 7.660558 (lr=6.4406e-05) (hash(x)=24747421) +921 train 7.726251 (lr=6.4476e-05) (hash(x)=28733708) +922 train 7.775621 (lr=6.4545e-05) (hash(x)=29704803) +923 train 7.958072 (lr=6.4615e-05) (hash(x)=27929846) +924 train 7.716961 (lr=6.4685e-05) (hash(x)=18961171) +925 train 7.689630 (lr=6.4755e-05) (hash(x)=22417476) +926 train 7.726560 (lr=6.4825e-05) (hash(x)=26364120) +927 train 7.835356 (lr=6.4895e-05) (hash(x)=25282897) +928 train 7.616839 (lr=6.4965e-05) (hash(x)=22082503) +929 train 7.556375 (lr=6.5035e-05) (hash(x)=22278062) +930 train 7.638580 (lr=6.5105e-05) (hash(x)=24271468) +931 train 7.561144 (lr=6.5175e-05) (hash(x)=26802508) +932 train 8.205858 (lr=6.5245e-05) (hash(x)=33468379) +933 train 7.448827 (lr=6.5315e-05) (hash(x)=22094832) +934 train 7.644368 (lr=6.5385e-05) (hash(x)=26759850) +935 train 7.844305 (lr=6.5455e-05) (hash(x)=28390416) +936 train 7.951525 (lr=6.5524e-05) (hash(x)=22727956) +937 train 7.856586 (lr=6.5594e-05) (hash(x)=26379331) +938 train 7.992636 (lr=6.5664e-05) (hash(x)=25048158) +939 train 7.859441 (lr=6.5734e-05) (hash(x)=26292451) +940 train 7.716919 (lr=6.5804e-05) (hash(x)=23336031) +941 train 7.931314 (lr=6.5874e-05) (hash(x)=26301866) +942 train 8.060879 (lr=6.5944e-05) (hash(x)=26687040) +943 train 7.632695 (lr=6.6014e-05) (hash(x)=22915344) +944 train 7.640776 (lr=6.6084e-05) (hash(x)=19831900) +945 train 7.761407 (lr=6.6154e-05) (hash(x)=25448318) +946 train 7.723511 (lr=6.6224e-05) (hash(x)=24993116) +947 train 7.857544 (lr=6.6294e-05) (hash(x)=24744383) +948 train 7.630731 (lr=6.6364e-05) (hash(x)=23731849) +949 train 7.542306 (lr=6.6434e-05) (hash(x)=22835201) +950 val loss 7.7032 +950 val perplexity 2215.3350 +950 train 7.574839 (lr=6.6503e-05) (hash(x)=24652361) +951 train 7.802203 (lr=6.6573e-05) (hash(x)=26284678) +952 train 7.724604 (lr=6.6643e-05) (hash(x)=27522881) +953 train 7.698142 (lr=6.6713e-05) (hash(x)=24745936) +954 train 7.525305 (lr=6.6783e-05) (hash(x)=21973969) +955 train 7.538445 (lr=6.6853e-05) (hash(x)=21654269) +956 train 7.545004 (lr=6.6923e-05) (hash(x)=21708739) +957 train 7.914093 (lr=6.6993e-05) (hash(x)=32387999) +958 train 8.381014 (lr=6.7063e-05) (hash(x)=32662682) +959 train 8.380362 (lr=6.7133e-05) (hash(x)=29466268) +960 train 8.306012 (lr=6.7203e-05) (hash(x)=28372973) +961 train 8.328291 (lr=6.7273e-05) (hash(x)=30736727) +962 train 8.275635 (lr=6.7343e-05) (hash(x)=29935562) +963 train 8.282721 (lr=6.7413e-05) (hash(x)=32616762) +964 train 8.244914 (lr=6.7483e-05) (hash(x)=32861403) +965 train 8.256063 (lr=6.7552e-05) (hash(x)=29358578) +966 train 8.281553 (lr=6.7622e-05) (hash(x)=31218966) +967 train 8.339453 (lr=6.7692e-05) (hash(x)=32201138) +968 train 8.266185 (lr=6.7762e-05) (hash(x)=30545133) +969 train 8.420273 (lr=6.7832e-05) (hash(x)=30041621) +970 train 8.231956 (lr=6.7902e-05) (hash(x)=30371023) +971 train 8.370215 (lr=6.7972e-05) (hash(x)=33683468) +972 train 8.279076 (lr=6.8042e-05) (hash(x)=29809830) +973 train 7.862167 (lr=6.8112e-05) (hash(x)=26837755) +974 train 7.833266 (lr=6.8182e-05) (hash(x)=26084089) +975 train 7.920377 (lr=6.8252e-05) (hash(x)=27498125) +976 train 8.146332 (lr=6.8322e-05) (hash(x)=34478395) +977 train 7.845847 (lr=6.8392e-05) (hash(x)=22372507) +978 train 7.739328 (lr=6.8462e-05) (hash(x)=25638879) +979 train 7.583118 (lr=6.8531e-05) (hash(x)=25164318) +980 train 7.721622 (lr=6.8601e-05) (hash(x)=27271900) +981 train 7.655042 (lr=6.8671e-05) (hash(x)=26562947) +982 train 7.672786 (lr=6.8741e-05) (hash(x)=24917192) +983 train 7.612528 (lr=6.8811e-05) (hash(x)=25690221) +984 train 7.802032 (lr=6.8881e-05) (hash(x)=24807841) +985 train 7.577646 (lr=6.8951e-05) (hash(x)=21947305) +986 train 7.592240 (lr=6.9021e-05) (hash(x)=22195089) +987 train 7.735232 (lr=6.9091e-05) (hash(x)=29031550) +988 train 7.837220 (lr=6.9161e-05) (hash(x)=29395823) +989 train 7.750573 (lr=6.9231e-05) (hash(x)=26551589) +990 train 7.721276 (lr=6.9301e-05) (hash(x)=23689487) +991 train 7.785607 (lr=6.9371e-05) (hash(x)=24094093) +992 train 7.521352 (lr=6.9441e-05) (hash(x)=24106453) +993 train 7.596789 (lr=6.9510e-05) (hash(x)=23639076) +994 train 7.721914 (lr=6.9580e-05) (hash(x)=25107314) +995 train 11.202837 (lr=6.9650e-05) (hash(x)=61455960) +996 train 12.284594 (lr=6.9720e-05) (hash(x)=63899424) +997 train 12.154388 (lr=6.9790e-05) (hash(x)=65636572) +998 train 12.471895 (lr=6.9860e-05) (hash(x)=71578682) +999 train 11.232031 (lr=6.9930e-05) (hash(x)=61104710) +1000 val loss 8.4247 +1000 val perplexity 4558.4673 +1000 train 9.472786 (lr=7.0000e-05) (hash(x)=23633693) +1001 train 8.612818 (lr=7.0070e-05) (hash(x)=24123821) +1002 train 8.003271 (lr=7.0140e-05) (hash(x)=19919984) +1003 train 7.820059 (lr=7.0210e-05) (hash(x)=20881126) +1004 train 8.052729 (lr=7.0280e-05) (hash(x)=27528050) +1005 train 7.958755 (lr=7.0350e-05) (hash(x)=23209969) +1006 train 7.933469 (lr=7.0420e-05) (hash(x)=28426467) +1007 train 7.884211 (lr=7.0490e-05) (hash(x)=26920243) +1008 train 7.721591 (lr=7.0559e-05) (hash(x)=25730699) +1009 train 7.732027 (lr=7.0629e-05) (hash(x)=26127756) +1010 train 7.565155 (lr=7.0699e-05) (hash(x)=26479346) +1011 train 7.704203 (lr=7.0769e-05) (hash(x)=21970343) +1012 train 7.797496 (lr=7.0839e-05) (hash(x)=24874094) +1013 train 7.580085 (lr=7.0909e-05) (hash(x)=24097897) +1014 train 7.737963 (lr=7.0979e-05) (hash(x)=26692093) +1015 train 7.784689 (lr=7.1049e-05) (hash(x)=31676352) +1016 train 7.678354 (lr=7.1119e-05) (hash(x)=26245173) +1017 train 7.752584 (lr=7.1189e-05) (hash(x)=23908053) +1018 train 7.601165 (lr=7.1259e-05) (hash(x)=24102198) +1019 train 7.720528 (lr=7.1329e-05) (hash(x)=25600562) +1020 train 7.734791 (lr=7.1399e-05) (hash(x)=24776954) +1021 train 7.665772 (lr=7.1469e-05) (hash(x)=23549168) +1022 train 7.619096 (lr=7.1538e-05) (hash(x)=26663184) +1023 train 7.628364 (lr=7.1608e-05) (hash(x)=22022924) +1024 train 7.761885 (lr=7.1678e-05) (hash(x)=24899178) +1025 train 7.595404 (lr=7.1748e-05) (hash(x)=23294980) +1026 train 7.474295 (lr=7.1818e-05) (hash(x)=21004461) +1027 train 7.626145 (lr=7.1888e-05) (hash(x)=22777085) +1028 train 7.814086 (lr=7.1958e-05) (hash(x)=28395880) +1029 train 7.874478 (lr=7.2028e-05) (hash(x)=26271115) +1030 train 7.771196 (lr=7.2098e-05) (hash(x)=26398325) +1031 train 7.513265 (lr=7.2168e-05) (hash(x)=21727744) +1032 train 7.726946 (lr=7.2238e-05) (hash(x)=27108132) +1033 train 7.637813 (lr=7.2308e-05) (hash(x)=22729318) +1034 train 7.841986 (lr=7.2378e-05) (hash(x)=32820084) +1035 train 7.852847 (lr=7.2448e-05) (hash(x)=20701998) +1036 train 7.735947 (lr=7.2517e-05) (hash(x)=24157446) +1037 train 7.807796 (lr=7.2587e-05) (hash(x)=27928398) +1038 train 7.990336 (lr=7.2657e-05) (hash(x)=34991795) +1039 train 7.643632 (lr=7.2727e-05) (hash(x)=20863982) +1040 train 7.884308 (lr=7.2797e-05) (hash(x)=25813615) +1041 train 7.480982 (lr=7.2867e-05) (hash(x)=22827054) +1042 train 7.621788 (lr=7.2937e-05) (hash(x)=25756087) +1043 train 7.794863 (lr=7.3007e-05) (hash(x)=25084926) +1044 train 7.754869 (lr=7.3077e-05) (hash(x)=27843638) +1045 train 7.880102 (lr=7.3147e-05) (hash(x)=25540961) +1046 train 7.575626 (lr=7.3217e-05) (hash(x)=23996956) +1047 train 7.544485 (lr=7.3287e-05) (hash(x)=24412897) +1048 train 7.813444 (lr=7.3357e-05) (hash(x)=29525589) +1049 train 7.753715 (lr=7.3427e-05) (hash(x)=26269869) +1050 val loss 7.6626 +1050 val perplexity 2127.2498 +1050 train 7.614739 (lr=7.3497e-05) (hash(x)=26039611) +1051 train 7.552280 (lr=7.3566e-05) (hash(x)=25434913) +1052 train 7.728369 (lr=7.3636e-05) (hash(x)=26016998) +1053 train 7.742670 (lr=7.3706e-05) (hash(x)=25157653) +1054 train 7.723457 (lr=7.3776e-05) (hash(x)=22630574) +1055 train 7.746039 (lr=7.3846e-05) (hash(x)=26302544) +1056 train 7.713966 (lr=7.3916e-05) (hash(x)=27566393) +1057 train 7.533880 (lr=7.3986e-05) (hash(x)=22010703) +1058 train 7.748668 (lr=7.4056e-05) (hash(x)=26105026) +1059 train 8.064484 (lr=7.4126e-05) (hash(x)=34976197) +1060 train 7.621855 (lr=7.4196e-05) (hash(x)=24368234) +1061 train 7.650968 (lr=7.4266e-05) (hash(x)=28248301) +1062 train 7.707164 (lr=7.4336e-05) (hash(x)=26416200) +1063 train 7.615647 (lr=7.4406e-05) (hash(x)=23870805) +1064 train 7.659346 (lr=7.4476e-05) (hash(x)=25795021) +1065 train 7.607928 (lr=7.4545e-05) (hash(x)=24457252) +1066 train 7.605429 (lr=7.4615e-05) (hash(x)=23503725) +1067 train 7.822903 (lr=7.4685e-05) (hash(x)=25041103) +1068 train 7.545115 (lr=7.4755e-05) (hash(x)=23037755) +1069 train 7.719743 (lr=7.4825e-05) (hash(x)=25998487) +1070 train 7.717736 (lr=7.4895e-05) (hash(x)=27705382) +1071 train 7.779119 (lr=7.4965e-05) (hash(x)=26041745) +1072 train 7.597377 (lr=7.5035e-05) (hash(x)=24353905) +1073 train 7.707011 (lr=7.5105e-05) (hash(x)=27249810) +1074 train 7.717605 (lr=7.5175e-05) (hash(x)=23831457) +1075 train 7.624205 (lr=7.5245e-05) (hash(x)=24068619) +1076 train 7.717894 (lr=7.5315e-05) (hash(x)=26680905) +1077 train 7.734821 (lr=7.5385e-05) (hash(x)=26359528) +1078 train 7.799270 (lr=7.5455e-05) (hash(x)=28347177) +1079 train 7.570065 (lr=7.5524e-05) (hash(x)=25441262) +1080 train 7.589034 (lr=7.5594e-05) (hash(x)=27888093) +1081 train 7.591039 (lr=7.5664e-05) (hash(x)=24413659) +1082 train 8.245132 (lr=7.5734e-05) (hash(x)=21159323) +1083 train 7.756675 (lr=7.5804e-05) (hash(x)=29181867) +1084 train 7.591029 (lr=7.5874e-05) (hash(x)=26469077) +1085 train 7.927440 (lr=7.5944e-05) (hash(x)=31551575) +1086 train 7.525966 (lr=7.6014e-05) (hash(x)=20896465) +1087 train 7.950403 (lr=7.6084e-05) (hash(x)=27093757) +1088 train 7.724756 (lr=7.6154e-05) (hash(x)=26443521) +1089 train 7.717033 (lr=7.6224e-05) (hash(x)=23624298) +1090 train 7.641092 (lr=7.6294e-05) (hash(x)=23016570) +1091 train 7.513060 (lr=7.6364e-05) (hash(x)=25150275) +1092 train 7.479303 (lr=7.6434e-05) (hash(x)=25876062) +1093 train 7.706901 (lr=7.6503e-05) (hash(x)=26239886) +1094 train 7.743121 (lr=7.6573e-05) (hash(x)=31024703) +1095 train 8.214703 (lr=7.6643e-05) (hash(x)=33457102) +1096 train 7.582587 (lr=7.6713e-05) (hash(x)=21989055) +1097 train 7.530350 (lr=7.6783e-05) (hash(x)=17499738) +1098 train 7.559421 (lr=7.6853e-05) (hash(x)=24195578) +1099 train 7.663941 (lr=7.6923e-05) (hash(x)=25755322) +1100 val loss 7.6337 +1100 val perplexity 2066.7505 +1100 train 7.762851 (lr=7.6993e-05) (hash(x)=26164625) +1101 train 7.658978 (lr=7.7063e-05) (hash(x)=23722795) +1102 train 7.647648 (lr=7.7133e-05) (hash(x)=23415339) +1103 train 7.544001 (lr=7.7203e-05) (hash(x)=23630794) +1104 train 7.603762 (lr=7.7273e-05) (hash(x)=25632158) +1105 train 7.536705 (lr=7.7343e-05) (hash(x)=23374168) +1106 train 7.571363 (lr=7.7413e-05) (hash(x)=23461285) +1107 train 7.537827 (lr=7.7483e-05) (hash(x)=25167987) +1108 train 7.994206 (lr=7.7552e-05) (hash(x)=31038116) +1109 train 7.693314 (lr=7.7622e-05) (hash(x)=30941010) +1110 train 7.636553 (lr=7.7692e-05) (hash(x)=22703293) +1111 train 7.533093 (lr=7.7762e-05) (hash(x)=24043224) +1112 train 7.538077 (lr=7.7832e-05) (hash(x)=26445994) +1113 train 7.883333 (lr=7.7902e-05) (hash(x)=29736627) +1114 train 7.637062 (lr=7.7972e-05) (hash(x)=24357840) +1115 train 7.676501 (lr=7.8042e-05) (hash(x)=24665411) +1116 train 7.595584 (lr=7.8112e-05) (hash(x)=25670741) +1117 train 7.747812 (lr=7.8182e-05) (hash(x)=27916043) +1118 train 7.694551 (lr=7.8252e-05) (hash(x)=27357379) +1119 train 7.522816 (lr=7.8322e-05) (hash(x)=17321657) +1120 train 7.350107 (lr=7.8392e-05) (hash(x)=17550988) +1121 train 7.539732 (lr=7.8462e-05) (hash(x)=23829833) +1122 train 7.819866 (lr=7.8531e-05) (hash(x)=24673611) +1123 train 7.884974 (lr=7.8601e-05) (hash(x)=27932591) +1124 train 7.885263 (lr=7.8671e-05) (hash(x)=26067367) +1125 train 8.032339 (lr=7.8741e-05) (hash(x)=28206079) +1126 train 8.326914 (lr=7.8811e-05) (hash(x)=27977422) +1127 train 7.764920 (lr=7.8881e-05) (hash(x)=29447954) +1128 train 7.631481 (lr=7.8951e-05) (hash(x)=24976337) +1129 train 7.720675 (lr=7.9021e-05) (hash(x)=25935364) +1130 train 7.778496 (lr=7.9091e-05) (hash(x)=26887303) +1131 train 7.624779 (lr=7.9161e-05) (hash(x)=24621816) +1132 train 7.470135 (lr=7.9231e-05) (hash(x)=22648602) +1133 train 7.736202 (lr=7.9301e-05) (hash(x)=24070405) +1134 train 7.708135 (lr=7.9371e-05) (hash(x)=27547292) +1135 train 7.683176 (lr=7.9441e-05) (hash(x)=24682294) +1136 train 7.803642 (lr=7.9510e-05) (hash(x)=22172182) +1137 train 7.571101 (lr=7.9580e-05) (hash(x)=24050209) +1138 train 7.553336 (lr=7.9650e-05) (hash(x)=23644616) +1139 train 7.703356 (lr=7.9720e-05) (hash(x)=28057095) +1140 train 7.861696 (lr=7.9790e-05) (hash(x)=22252427) +1141 train 7.630095 (lr=7.9860e-05) (hash(x)=22523232) +1142 train 7.755652 (lr=7.9930e-05) (hash(x)=25025388) +1143 train 7.542160 (lr=8.0000e-05) (hash(x)=24547536) +1144 train 7.401844 (lr=8.0070e-05) (hash(x)=23874051) +1145 train 7.645428 (lr=8.0140e-05) (hash(x)=24978712) +1146 train 7.565364 (lr=8.0210e-05) (hash(x)=24298295) +1147 train 7.423193 (lr=8.0280e-05) (hash(x)=18987545) +1148 train 7.509076 (lr=8.0350e-05) (hash(x)=23903200) +1149 train 7.717458 (lr=8.0420e-05) (hash(x)=24092784) +1150 val loss 7.6257 +1150 val perplexity 2050.2815 +1150 train 7.595740 (lr=8.0490e-05) (hash(x)=24253964) +1151 train 7.596369 (lr=8.0559e-05) (hash(x)=26745063) +1152 train 7.589180 (lr=8.0629e-05) (hash(x)=26680082) +1153 train 7.613564 (lr=8.0699e-05) (hash(x)=22539112) +1154 train 7.376297 (lr=8.0769e-05) (hash(x)=21431267) +1155 train 7.387516 (lr=8.0839e-05) (hash(x)=21447406) +1156 train 7.382043 (lr=8.0909e-05) (hash(x)=20849089) +1157 train 7.371043 (lr=8.0979e-05) (hash(x)=21082139) +1158 train 7.337510 (lr=8.1049e-05) (hash(x)=19506447) +1159 train 7.475731 (lr=8.1119e-05) (hash(x)=24650655) +1160 train 7.560464 (lr=8.1189e-05) (hash(x)=26355512) +1161 train 7.698305 (lr=8.1259e-05) (hash(x)=22130721) +1162 train 7.709718 (lr=8.1329e-05) (hash(x)=26444359) +1163 train 8.287425 (lr=8.1399e-05) (hash(x)=26519976) +1164 train 9.267206 (lr=8.1469e-05) (hash(x)=30877729) +1165 train 7.869868 (lr=8.1538e-05) (hash(x)=25582440) +1166 train 7.946219 (lr=8.1608e-05) (hash(x)=25200284) +1167 train 7.629475 (lr=8.1678e-05) (hash(x)=20106514) +1168 train 7.515164 (lr=8.1748e-05) (hash(x)=23362041) +1169 train 7.640463 (lr=8.1818e-05) (hash(x)=25695510) +1170 train 7.527120 (lr=8.1888e-05) (hash(x)=21573008) +1171 train 7.695655 (lr=8.1958e-05) (hash(x)=20117808) +1172 train 7.642686 (lr=8.2028e-05) (hash(x)=19909192) +1173 train 7.701697 (lr=8.2098e-05) (hash(x)=24501900) +1174 train 7.604679 (lr=8.2168e-05) (hash(x)=25606665) +1175 train 7.693360 (lr=8.2238e-05) (hash(x)=25510334) +1176 train 7.543305 (lr=8.2308e-05) (hash(x)=24656801) +1177 train 7.394588 (lr=8.2378e-05) (hash(x)=22099158) +1178 train 7.529623 (lr=8.2448e-05) (hash(x)=28351614) +1179 train 7.672336 (lr=8.2517e-05) (hash(x)=25749120) +1180 train 8.092078 (lr=8.2587e-05) (hash(x)=29645018) +1181 train 7.737216 (lr=8.2657e-05) (hash(x)=21720691) +1182 train 7.408164 (lr=8.2727e-05) (hash(x)=21597124) +1183 train 7.433386 (lr=8.2797e-05) (hash(x)=24357241) +1184 train 7.567146 (lr=8.2867e-05) (hash(x)=25136495) +1185 train 7.904792 (lr=8.2937e-05) (hash(x)=28911272) +1186 train 7.588778 (lr=8.3007e-05) (hash(x)=25225894) +1187 train 7.601860 (lr=8.3077e-05) (hash(x)=25584945) +1188 train 7.485358 (lr=8.3147e-05) (hash(x)=23521916) +1189 train 7.453722 (lr=8.3217e-05) (hash(x)=21847287) +1190 train 7.628751 (lr=8.3287e-05) (hash(x)=24069020) +1191 train 7.475108 (lr=8.3357e-05) (hash(x)=25198897) +1192 train 7.405738 (lr=8.3427e-05) (hash(x)=20122390) +1193 train 7.474917 (lr=8.3497e-05) (hash(x)=22436833) +1194 train 7.799654 (lr=8.3566e-05) (hash(x)=27691436) +1195 train 7.683770 (lr=8.3636e-05) (hash(x)=23475891) +1196 train 7.258730 (lr=8.3706e-05) (hash(x)=21469159) +1197 train 7.518313 (lr=8.3776e-05) (hash(x)=25083992) +1198 train 7.703190 (lr=8.3846e-05) (hash(x)=20441653) +1199 train 7.652310 (lr=8.3916e-05) (hash(x)=23644804) +1200 val loss 7.5955 +1200 val perplexity 1989.2706 +1200 train 7.366088 (lr=8.3986e-05) (hash(x)=20820913) +1201 train 7.695944 (lr=8.4056e-05) (hash(x)=31377168) +1202 train 8.233430 (lr=8.4126e-05) (hash(x)=34450341) +1203 train 7.648051 (lr=8.4196e-05) (hash(x)=25629584) +1204 train 7.484830 (lr=8.4266e-05) (hash(x)=21975628) +1205 train 8.057867 (lr=8.4336e-05) (hash(x)=29285135) +1206 train 7.896777 (lr=8.4406e-05) (hash(x)=29628864) +1207 train 8.004512 (lr=8.4476e-05) (hash(x)=29797280) +1208 train 7.646217 (lr=8.4545e-05) (hash(x)=28346842) +1209 train 7.986383 (lr=8.4615e-05) (hash(x)=33122326) +1210 train 8.047846 (lr=8.4685e-05) (hash(x)=31250981) +1211 train 8.112430 (lr=8.4755e-05) (hash(x)=30026394) +1212 train 8.202509 (lr=8.4825e-05) (hash(x)=24850684) +1213 train 8.344097 (lr=8.4895e-05) (hash(x)=34353164) +1214 train 7.597443 (lr=8.4965e-05) (hash(x)=24528186) +1215 train 7.541463 (lr=8.5035e-05) (hash(x)=26594177) +1216 train 7.690637 (lr=8.5105e-05) (hash(x)=21331715) +1217 train 7.664901 (lr=8.5175e-05) (hash(x)=25554738) +1218 train 7.803477 (lr=8.5245e-05) (hash(x)=26872344) +1219 train 7.676409 (lr=8.5315e-05) (hash(x)=23766256) +1220 train 7.643133 (lr=8.5385e-05) (hash(x)=22992618) +1221 train 7.575906 (lr=8.5455e-05) (hash(x)=26853444) +1222 train 7.570038 (lr=8.5524e-05) (hash(x)=24705456) +1223 train 7.668883 (lr=8.5594e-05) (hash(x)=24250150) +1224 train 7.554720 (lr=8.5664e-05) (hash(x)=27579257) +1225 train 7.506592 (lr=8.5734e-05) (hash(x)=26289588) +1226 train 7.491398 (lr=8.5804e-05) (hash(x)=23437197) +1227 train 7.657785 (lr=8.5874e-05) (hash(x)=26108817) +1228 train 7.545231 (lr=8.5944e-05) (hash(x)=24583191) +1229 train 7.473876 (lr=8.6014e-05) (hash(x)=23814987) +1230 train 7.630222 (lr=8.6084e-05) (hash(x)=25692442) +1231 train 7.355692 (lr=8.6154e-05) (hash(x)=18582688) +1232 train 7.600048 (lr=8.6224e-05) (hash(x)=26565489) +1233 train 7.449580 (lr=8.6294e-05) (hash(x)=25558792) +1234 train 7.529239 (lr=8.6364e-05) (hash(x)=26263661) +1235 train 7.451271 (lr=8.6434e-05) (hash(x)=23272705) +1236 train 7.597793 (lr=8.6503e-05) (hash(x)=26802369) +1237 train 7.392287 (lr=8.6573e-05) (hash(x)=24709241) +1238 train 7.490476 (lr=8.6643e-05) (hash(x)=25201108) +1239 train 7.547723 (lr=8.6713e-05) (hash(x)=24793412) +1240 train 7.513850 (lr=8.6783e-05) (hash(x)=25177251) +1241 train 7.546576 (lr=8.6853e-05) (hash(x)=27256707) +1242 train 7.656355 (lr=8.6923e-05) (hash(x)=21641481) +1243 train 7.343059 (lr=8.6993e-05) (hash(x)=19280989) +1244 train 7.586158 (lr=8.7063e-05) (hash(x)=26651546) +1245 train 7.515871 (lr=8.7133e-05) (hash(x)=26508642) +1246 train 7.520619 (lr=8.7203e-05) (hash(x)=23916886) +1247 train 7.426212 (lr=8.7273e-05) (hash(x)=22751150) +1248 train 8.017270 (lr=8.7343e-05) (hash(x)=25372010) +1249 train 7.501399 (lr=8.7413e-05) (hash(x)=23880160) +1250 val loss 7.5893 +1250 val perplexity 1976.9869 +1250 train 7.486858 (lr=8.7483e-05) (hash(x)=24932950) +1251 train 7.478702 (lr=8.7552e-05) (hash(x)=23537942) +1252 train 7.417412 (lr=8.7622e-05) (hash(x)=21296580) +1253 train 7.604478 (lr=8.7692e-05) (hash(x)=26975313) +1254 train 7.570574 (lr=8.7762e-05) (hash(x)=24302204) +1255 train 7.244933 (lr=8.7832e-05) (hash(x)=23748375) +1256 train 7.361880 (lr=8.7902e-05) (hash(x)=22026776) +1257 train 7.454879 (lr=8.7972e-05) (hash(x)=25541754) +1258 train 7.881379 (lr=8.8042e-05) (hash(x)=27900386) +1259 train 7.833080 (lr=8.8112e-05) (hash(x)=27413825) +1260 train 7.863955 (lr=8.8182e-05) (hash(x)=27223027) +1261 train 7.767997 (lr=8.8252e-05) (hash(x)=27075951) +1262 train 7.738355 (lr=8.8322e-05) (hash(x)=28100582) +1263 train 7.568452 (lr=8.8392e-05) (hash(x)=21682445) +1264 train 7.697572 (lr=8.8462e-05) (hash(x)=29616079) +1265 train 7.536709 (lr=8.8531e-05) (hash(x)=23361504) +1266 train 7.543163 (lr=8.8601e-05) (hash(x)=24035993) +1267 train 7.511050 (lr=8.8671e-05) (hash(x)=22040184) +1268 train 7.580498 (lr=8.8741e-05) (hash(x)=27383080) +1269 train 7.492147 (lr=8.8811e-05) (hash(x)=23727731) +1270 train 7.449208 (lr=8.8881e-05) (hash(x)=23794649) +1271 train 7.602777 (lr=8.8951e-05) (hash(x)=24463229) +1272 train 7.533130 (lr=8.9021e-05) (hash(x)=18891545) +1273 train 7.940315 (lr=8.9091e-05) (hash(x)=32663792) +1274 train 7.582107 (lr=8.9161e-05) (hash(x)=26702407) +1275 train 7.502939 (lr=8.9231e-05) (hash(x)=24091954) +1276 train 7.461659 (lr=8.9301e-05) (hash(x)=23686239) +1277 train 7.472889 (lr=8.9371e-05) (hash(x)=23599013) +1278 train 7.474139 (lr=8.9441e-05) (hash(x)=21634218) +1279 train 7.555054 (lr=8.9510e-05) (hash(x)=26670219) +1280 train 7.510905 (lr=8.9580e-05) (hash(x)=23547908) +1281 train 7.437636 (lr=8.9650e-05) (hash(x)=24380893) +1282 train 7.498180 (lr=8.9720e-05) (hash(x)=26967512) +1283 train 7.673553 (lr=8.9790e-05) (hash(x)=25558986) +1284 train 7.672535 (lr=8.9860e-05) (hash(x)=26048135) +1285 train 7.624613 (lr=8.9930e-05) (hash(x)=25729492) +1286 train 7.332527 (lr=9.0000e-05) (hash(x)=24563606) +1287 train 7.435977 (lr=9.0070e-05) (hash(x)=19218943) +1288 train 7.609940 (lr=9.0140e-05) (hash(x)=24133609) +1289 train 7.609484 (lr=9.0210e-05) (hash(x)=23952206) +1290 train 7.452322 (lr=9.0280e-05) (hash(x)=25365277) +1291 train 7.690536 (lr=9.0350e-05) (hash(x)=24551402) +1292 train 7.488435 (lr=9.0420e-05) (hash(x)=24966478) +1293 train 7.446942 (lr=9.0490e-05) (hash(x)=24007642) +1294 train 7.524124 (lr=9.0559e-05) (hash(x)=25204207) +1295 train 7.519188 (lr=9.0629e-05) (hash(x)=25229281) +1296 train 7.399285 (lr=9.0699e-05) (hash(x)=22435944) +1297 train 7.168812 (lr=9.0769e-05) (hash(x)=18214283) +1298 train 7.148273 (lr=9.0839e-05) (hash(x)=20609675) +1299 train 7.258496 (lr=9.0909e-05) (hash(x)=21251127) +1300 val loss 7.5560 +1300 val perplexity 1912.1937 +1300 train 7.885284 (lr=9.0979e-05) (hash(x)=32279160) +1301 train 7.598333 (lr=9.1049e-05) (hash(x)=25097619) +1302 train 7.232656 (lr=9.1119e-05) (hash(x)=22212821) +1303 train 7.587262 (lr=9.1189e-05) (hash(x)=25800857) +1304 train 7.338756 (lr=9.1259e-05) (hash(x)=20921910) +1305 train 7.464915 (lr=9.1329e-05) (hash(x)=22918428) +1306 train 7.460819 (lr=9.1399e-05) (hash(x)=24345816) +1307 train 7.497732 (lr=9.1469e-05) (hash(x)=25836189) +1308 train 7.523141 (lr=9.1538e-05) (hash(x)=21697866) +1309 train 7.387325 (lr=9.1608e-05) (hash(x)=24504567) +1310 train 7.471786 (lr=9.1678e-05) (hash(x)=23135849) +1311 train 7.507771 (lr=9.1748e-05) (hash(x)=25999255) +1312 train 7.333906 (lr=9.1818e-05) (hash(x)=21137520) +1313 train 7.641959 (lr=9.1888e-05) (hash(x)=27308968) +1314 train 7.509576 (lr=9.1958e-05) (hash(x)=25924731) +1315 train 7.611019 (lr=9.2028e-05) (hash(x)=20149394) +1316 train 7.590129 (lr=9.2098e-05) (hash(x)=23830286) +1317 train 7.434699 (lr=9.2168e-05) (hash(x)=24498556) +1318 train 7.484328 (lr=9.2238e-05) (hash(x)=25484922) +1319 train 7.245873 (lr=9.2308e-05) (hash(x)=21999338) +1320 train 7.412132 (lr=9.2378e-05) (hash(x)=24064168) +1321 train 7.375965 (lr=9.2448e-05) (hash(x)=23280568) +1322 train 7.590809 (lr=9.2517e-05) (hash(x)=30082352) +1323 train 7.832500 (lr=9.2587e-05) (hash(x)=27611302) +1324 train 7.790861 (lr=9.2657e-05) (hash(x)=22356183) +1325 train 7.286273 (lr=9.2727e-05) (hash(x)=23982308) +1326 train 7.519036 (lr=9.2797e-05) (hash(x)=22973788) +1327 train 7.441322 (lr=9.2867e-05) (hash(x)=22778356) +1328 train 7.441372 (lr=9.2937e-05) (hash(x)=23542930) +1329 train 7.398313 (lr=9.3007e-05) (hash(x)=23467046) +1330 train 7.758675 (lr=9.3077e-05) (hash(x)=29719902) +1331 train 7.399838 (lr=9.3147e-05) (hash(x)=24195959) +1332 train 7.615891 (lr=9.3217e-05) (hash(x)=27168434) +1333 train 8.210028 (lr=9.3287e-05) (hash(x)=32710438) +1334 train 7.659922 (lr=9.3357e-05) (hash(x)=26951664) +1335 train 7.591544 (lr=9.3427e-05) (hash(x)=19127465) +1336 train 7.532085 (lr=9.3497e-05) (hash(x)=25673955) +1337 train 8.011366 (lr=9.3566e-05) (hash(x)=28962580) +1338 train 7.535180 (lr=9.3636e-05) (hash(x)=25238916) +1339 train 7.482898 (lr=9.3706e-05) (hash(x)=22426274) +1340 train 7.499753 (lr=9.3776e-05) (hash(x)=24668644) +1341 train 7.571642 (lr=9.3846e-05) (hash(x)=25606512) +1342 train 7.427933 (lr=9.3916e-05) (hash(x)=21290254) +1343 train 7.330886 (lr=9.3986e-05) (hash(x)=23785205) +1344 train 7.548747 (lr=9.4056e-05) (hash(x)=27083886) +1345 train 7.453203 (lr=9.4126e-05) (hash(x)=24779414) +1346 train 7.427132 (lr=9.4196e-05) (hash(x)=26907868) +1347 train 7.844227 (lr=9.4266e-05) (hash(x)=28505676) +1348 train 7.521901 (lr=9.4336e-05) (hash(x)=29804750) +1349 train 7.868101 (lr=9.4406e-05) (hash(x)=29156288) +1350 val loss 7.5570 +1350 val perplexity 1914.1160 +1350 train 7.414815 (lr=9.4476e-05) (hash(x)=21173795) +1351 train 7.417531 (lr=9.4545e-05) (hash(x)=27706477) +1352 train 7.570890 (lr=9.4615e-05) (hash(x)=23548492) +1353 train 7.458796 (lr=9.4685e-05) (hash(x)=23711800) +1354 train 7.695048 (lr=9.4755e-05) (hash(x)=23327642) +1355 train 7.548305 (lr=9.4825e-05) (hash(x)=28684175) +1356 train 7.413138 (lr=9.4895e-05) (hash(x)=21795980) +1357 train 7.525594 (lr=9.4965e-05) (hash(x)=25225466) +1358 train 7.658358 (lr=9.5035e-05) (hash(x)=24703036) +1359 train 7.594193 (lr=9.5105e-05) (hash(x)=28003600) +1360 train 7.252942 (lr=9.5175e-05) (hash(x)=24189246) +1361 train 7.688775 (lr=9.5245e-05) (hash(x)=27989890) +1362 train 7.587118 (lr=9.5315e-05) (hash(x)=24781792) +1363 train 7.568344 (lr=9.5385e-05) (hash(x)=27586845) +1364 train 7.623876 (lr=9.5455e-05) (hash(x)=26808464) +1365 train 7.443477 (lr=9.5524e-05) (hash(x)=22373927) +1366 train 7.436440 (lr=9.5594e-05) (hash(x)=25304441) +1367 train 7.364119 (lr=9.5664e-05) (hash(x)=21176405) +1368 train 7.392836 (lr=9.5734e-05) (hash(x)=23825332) +1369 train 7.370207 (lr=9.5804e-05) (hash(x)=23806052) +1370 train 7.409436 (lr=9.5874e-05) (hash(x)=25548695) +1371 train 7.523041 (lr=9.5944e-05) (hash(x)=25888433) +1372 train 7.294376 (lr=9.6014e-05) (hash(x)=22543301) +1373 train 7.976552 (lr=9.6084e-05) (hash(x)=27797727) +1374 train 7.571479 (lr=9.6154e-05) (hash(x)=25278538) +1375 train 7.440951 (lr=9.6224e-05) (hash(x)=27916982) +1376 train 7.425605 (lr=9.6294e-05) (hash(x)=25227141) +1377 train 7.493653 (lr=9.6364e-05) (hash(x)=24621793) +1378 train 7.397834 (lr=9.6434e-05) (hash(x)=24899679) +1379 train 7.341742 (lr=9.6503e-05) (hash(x)=24334708) +1380 train 7.720314 (lr=9.6573e-05) (hash(x)=30389813) +1381 train 7.339100 (lr=9.6643e-05) (hash(x)=24419143) +1382 train 7.493204 (lr=9.6713e-05) (hash(x)=24181393) +1383 train 7.288530 (lr=9.6783e-05) (hash(x)=25617709) +1384 train 7.409696 (lr=9.6853e-05) (hash(x)=21656802) +1385 train 7.390273 (lr=9.6923e-05) (hash(x)=24556034) +1386 train 7.377645 (lr=9.6993e-05) (hash(x)=26761579) +1387 train 8.185066 (lr=9.7063e-05) (hash(x)=25152362) +1388 train 7.538588 (lr=9.7133e-05) (hash(x)=25427935) +1389 train 7.547432 (lr=9.7203e-05) (hash(x)=24326376) +1390 train 7.469341 (lr=9.7273e-05) (hash(x)=24003710) +1391 train 7.384148 (lr=9.7343e-05) (hash(x)=24276512) +1392 train 7.198904 (lr=9.7413e-05) (hash(x)=20031488) +1393 train 7.293443 (lr=9.7483e-05) (hash(x)=24344695) +1394 train 7.386106 (lr=9.7552e-05) (hash(x)=23710755) +1395 train 7.701113 (lr=9.7622e-05) (hash(x)=26776133) +1396 train 7.402884 (lr=9.7692e-05) (hash(x)=25440959) +1397 train 7.365735 (lr=9.7762e-05) (hash(x)=21847282) +1398 train 7.366163 (lr=9.7832e-05) (hash(x)=21199921) +1399 train 7.163581 (lr=9.7902e-05) (hash(x)=20254159) +1400 val loss 7.5331 +1400 val perplexity 1868.9126 +1400 train 7.317706 (lr=9.7972e-05) (hash(x)=24908033) +1401 train 7.418893 (lr=9.8042e-05) (hash(x)=25044762) +1402 train 7.271022 (lr=9.8112e-05) (hash(x)=22169363) +1403 train 7.620084 (lr=9.8182e-05) (hash(x)=27873855) +1404 train 7.601319 (lr=9.8252e-05) (hash(x)=27001634) +1405 train 7.382909 (lr=9.8322e-05) (hash(x)=22575615) +1406 train 7.438025 (lr=9.8392e-05) (hash(x)=24765155) +1407 train 7.509867 (lr=9.8462e-05) (hash(x)=25113614) +1408 train 7.525302 (lr=9.8531e-05) (hash(x)=25140622) +1409 train 7.695685 (lr=9.8601e-05) (hash(x)=28062905) +1410 train 7.481446 (lr=9.8671e-05) (hash(x)=24957184) +1411 train 7.533860 (lr=9.8741e-05) (hash(x)=26192886) +1412 train 7.458551 (lr=9.8811e-05) (hash(x)=24721193) +1413 train 7.476591 (lr=9.8881e-05) (hash(x)=25770338) +1414 train 7.502641 (lr=9.8951e-05) (hash(x)=25060684) +1415 train 7.246803 (lr=9.9021e-05) (hash(x)=24614912) +1416 train 7.113982 (lr=9.9091e-05) (hash(x)=21111215) +1417 train 7.758385 (lr=9.9161e-05) (hash(x)=26934071) +1418 train 7.437169 (lr=9.9231e-05) (hash(x)=25706447) +1419 train 7.343808 (lr=9.9301e-05) (hash(x)=25397093) +1420 train 7.738785 (lr=9.9371e-05) (hash(x)=25383069) +1421 train 7.330417 (lr=9.9441e-05) (hash(x)=25925963) +1422 train 7.337879 (lr=9.9510e-05) (hash(x)=21881216) +1423 train 7.355138 (lr=9.9580e-05) (hash(x)=19811802) +1424 train 7.440930 (lr=9.9650e-05) (hash(x)=25034966) +1425 train 7.447386 (lr=9.9720e-05) (hash(x)=23248423) +1426 train 7.367733 (lr=9.9790e-05) (hash(x)=23804418) +1427 train 7.461974 (lr=9.9860e-05) (hash(x)=25579655) +1428 train 7.663218 (lr=9.9930e-05) (hash(x)=26468479) +1429 train 7.563042 (lr=1.0000e-04) (hash(x)=25537603) +1430 train 7.476362 (lr=1.0000e-04) (hash(x)=26504374) +1431 train 7.564078 (lr=1.0000e-04) (hash(x)=26096514) +1432 train 7.545293 (lr=1.0000e-04) (hash(x)=26058348) +1433 train 7.561090 (lr=1.0000e-04) (hash(x)=24132888) +1434 train 7.308126 (lr=1.0000e-04) (hash(x)=25387506) +1435 train 7.438611 (lr=1.0000e-04) (hash(x)=22589633) +1436 train 7.415310 (lr=9.9999e-05) (hash(x)=25511322) +1437 train 7.260956 (lr=9.9999e-05) (hash(x)=27781566) +1438 train 7.532374 (lr=9.9999e-05) (hash(x)=30018637) +1439 train 7.664757 (lr=9.9999e-05) (hash(x)=26757147) +1440 train 7.607132 (lr=9.9998e-05) (hash(x)=24795024) +1441 train 7.711818 (lr=9.9998e-05) (hash(x)=26649864) +1442 train 7.523731 (lr=9.9997e-05) (hash(x)=27568311) +1443 train 7.511839 (lr=9.9997e-05) (hash(x)=24963730) +1444 train 7.618978 (lr=9.9997e-05) (hash(x)=29447356) +1445 train 7.341539 (lr=9.9996e-05) (hash(x)=25249959) +1446 train 7.355313 (lr=9.9996e-05) (hash(x)=26333258) +1447 train 7.367557 (lr=9.9995e-05) (hash(x)=27703124) +1448 train 7.294246 (lr=9.9994e-05) (hash(x)=25252411) +1449 train 7.391268 (lr=9.9994e-05) (hash(x)=26459082) +1450 val loss 7.5155 +1450 val perplexity 1836.3538 +1450 train 7.235490 (lr=9.9993e-05) (hash(x)=19803884) +1451 train 7.326766 (lr=9.9992e-05) (hash(x)=24781713) +1452 train 7.670054 (lr=9.9992e-05) (hash(x)=29006906) +1453 train 7.588187 (lr=9.9991e-05) (hash(x)=26597693) +1454 train 7.419542 (lr=9.9990e-05) (hash(x)=24943747) +1455 train 7.405328 (lr=9.9989e-05) (hash(x)=24720476) +1456 train 7.322629 (lr=9.9988e-05) (hash(x)=23567535) +1457 train 7.526951 (lr=9.9987e-05) (hash(x)=23691295) +1458 train 7.637229 (lr=9.9986e-05) (hash(x)=23237812) +1459 train 7.468192 (lr=9.9985e-05) (hash(x)=23481301) +1460 train 7.454119 (lr=9.9984e-05) (hash(x)=23327755) +1461 train 7.466215 (lr=9.9983e-05) (hash(x)=23295676) +1462 train 7.403832 (lr=9.9982e-05) (hash(x)=26067788) +1463 train 7.398067 (lr=9.9981e-05) (hash(x)=25641033) +1464 train 7.558288 (lr=9.9980e-05) (hash(x)=27803515) +1465 train 7.376995 (lr=9.9979e-05) (hash(x)=22441379) +1466 train 7.307631 (lr=9.9977e-05) (hash(x)=24595257) +1467 train 7.446287 (lr=9.9976e-05) (hash(x)=27369437) +1468 train 7.356915 (lr=9.9975e-05) (hash(x)=25923735) +1469 train 7.448806 (lr=9.9974e-05) (hash(x)=24482272) +1470 train 7.480825 (lr=9.9972e-05) (hash(x)=26425020) +1471 train 7.645417 (lr=9.9971e-05) (hash(x)=24760900) +1472 train 7.367362 (lr=9.9969e-05) (hash(x)=22886951) +1473 train 7.518153 (lr=9.9968e-05) (hash(x)=23919156) +1474 train 7.545133 (lr=9.9966e-05) (hash(x)=30440878) +1475 train 7.180781 (lr=9.9965e-05) (hash(x)=21692546) +1476 train 7.372679 (lr=9.9963e-05) (hash(x)=26663597) +1477 train 7.396731 (lr=9.9962e-05) (hash(x)=27692087) +1478 train 7.691922 (lr=9.9960e-05) (hash(x)=29534673) +1479 train 7.288136 (lr=9.9958e-05) (hash(x)=22720391) +1480 train 7.190732 (lr=9.9956e-05) (hash(x)=22853822) +1481 train 7.412436 (lr=9.9955e-05) (hash(x)=26146560) +1482 train 7.593454 (lr=9.9953e-05) (hash(x)=23001150) +1483 train 7.295288 (lr=9.9951e-05) (hash(x)=24376979) +1484 train 7.389977 (lr=9.9949e-05) (hash(x)=25315495) +1485 train 7.496093 (lr=9.9947e-05) (hash(x)=22917712) +1486 train 7.454414 (lr=9.9945e-05) (hash(x)=19890855) +1487 train 7.214548 (lr=9.9943e-05) (hash(x)=22244509) +1488 train 7.234057 (lr=9.9941e-05) (hash(x)=23465789) +1489 train 7.463542 (lr=9.9939e-05) (hash(x)=25243385) +1490 train 7.511735 (lr=9.9937e-05) (hash(x)=24615492) +1491 train 7.198986 (lr=9.9935e-05) (hash(x)=21831960) +1492 train 7.254110 (lr=9.9933e-05) (hash(x)=24308188) +1493 train 7.441544 (lr=9.9931e-05) (hash(x)=24842373) +1494 train 7.226114 (lr=9.9929e-05) (hash(x)=22951616) +1495 train 7.332515 (lr=9.9926e-05) (hash(x)=24921535) +1496 train 7.314641 (lr=9.9924e-05) (hash(x)=20716218) +1497 train 7.393805 (lr=9.9922e-05) (hash(x)=24344615) +1498 train 7.228824 (lr=9.9919e-05) (hash(x)=23859426) +1499 train 7.514691 (lr=9.9917e-05) (hash(x)=25381251) +1500 val loss 7.4842 +1500 val perplexity 1779.7780 +1500 train 7.311614 (lr=9.9915e-05) (hash(x)=24220410) +1501 train 7.221865 (lr=9.9912e-05) (hash(x)=22887303) +1502 train 7.394298 (lr=9.9910e-05) (hash(x)=22098530) +1503 train 7.534080 (lr=9.9907e-05) (hash(x)=25687352) +1504 train 7.325706 (lr=9.9905e-05) (hash(x)=26021124) +1505 train 7.513484 (lr=9.9902e-05) (hash(x)=27791412) +1506 train 7.358431 (lr=9.9899e-05) (hash(x)=25521889) +1507 train 7.295915 (lr=9.9897e-05) (hash(x)=25221654) +1508 train 7.492613 (lr=9.9894e-05) (hash(x)=24200150) +1509 train 7.390336 (lr=9.9891e-05) (hash(x)=23243731) +1510 train 7.303466 (lr=9.9889e-05) (hash(x)=23876902) +1511 train 7.476170 (lr=9.9886e-05) (hash(x)=24469863) +1512 train 7.791180 (lr=9.9883e-05) (hash(x)=20515778) +1513 train 7.308487 (lr=9.9880e-05) (hash(x)=22484936) +1514 train 7.386967 (lr=9.9877e-05) (hash(x)=26835174) +1515 train 7.439347 (lr=9.9874e-05) (hash(x)=25291413) +1516 train 7.374057 (lr=9.9871e-05) (hash(x)=28880142) +1517 train 7.248724 (lr=9.9868e-05) (hash(x)=23952225) +1518 train 7.366570 (lr=9.9865e-05) (hash(x)=23260323) +1519 train 7.440413 (lr=9.9862e-05) (hash(x)=25744274) +1520 train 7.449396 (lr=9.9859e-05) (hash(x)=25079786) +1521 train 7.161427 (lr=9.9856e-05) (hash(x)=22616739) +1522 train 7.333557 (lr=9.9853e-05) (hash(x)=22293489) +1523 train 7.301899 (lr=9.9849e-05) (hash(x)=24246963) +1524 train 7.457717 (lr=9.9846e-05) (hash(x)=22372895) +1525 train 7.092032 (lr=9.9843e-05) (hash(x)=19407094) +1526 train 7.458304 (lr=9.9840e-05) (hash(x)=24719318) +1527 train 7.263319 (lr=9.9836e-05) (hash(x)=19724058) +1528 train 7.061886 (lr=9.9833e-05) (hash(x)=12468292) +1529 train 7.278847 (lr=9.9829e-05) (hash(x)=18836491) +1530 train 7.200818 (lr=9.9826e-05) (hash(x)=22814208) +1531 train 7.244574 (lr=9.9822e-05) (hash(x)=20705649) +1532 train 7.940587 (lr=9.9819e-05) (hash(x)=25972430) +1533 train 7.132591 (lr=9.9815e-05) (hash(x)=21325875) +1534 train 7.566437 (lr=9.9812e-05) (hash(x)=27282337) +1535 train 7.573521 (lr=9.9808e-05) (hash(x)=24938685) +1536 train 7.660104 (lr=9.9804e-05) (hash(x)=23506879) +1537 train 7.402927 (lr=9.9801e-05) (hash(x)=25152403) +1538 train 7.720656 (lr=9.9797e-05) (hash(x)=23966181) +1539 train 7.626350 (lr=9.9793e-05) (hash(x)=21707000) +1540 train 7.394008 (lr=9.9789e-05) (hash(x)=24270631) +1541 train 7.222487 (lr=9.9785e-05) (hash(x)=17952018) +1542 train 7.280303 (lr=9.9782e-05) (hash(x)=26946100) +1543 train 7.371419 (lr=9.9778e-05) (hash(x)=24948980) +1544 train 8.060042 (lr=9.9774e-05) (hash(x)=28330877) +1545 train 7.539120 (lr=9.9770e-05) (hash(x)=28012110) +1546 train 7.450794 (lr=9.9766e-05) (hash(x)=26225786) +1547 train 7.388028 (lr=9.9762e-05) (hash(x)=30773958) +1548 train 7.915082 (lr=9.9758e-05) (hash(x)=28201086) +1549 train 8.020592 (lr=9.9753e-05) (hash(x)=29481068) +1550 val loss 7.5283 +1550 val perplexity 1859.9973 +1550 train 7.382030 (lr=9.9749e-05) (hash(x)=24153602) +1551 train 7.579778 (lr=9.9745e-05) (hash(x)=26769046) +1552 train 7.469395 (lr=9.9741e-05) (hash(x)=27693052) +1553 train 7.271231 (lr=9.9737e-05) (hash(x)=26755048) +1554 train 7.374105 (lr=9.9732e-05) (hash(x)=21009792) +1555 train 7.368590 (lr=9.9728e-05) (hash(x)=18849656) +1556 train 7.602861 (lr=9.9724e-05) (hash(x)=25652491) +1557 train 7.700473 (lr=9.9719e-05) (hash(x)=25449800) +1558 train 8.256560 (lr=9.9715e-05) (hash(x)=29878248) +1559 train 8.081706 (lr=9.9710e-05) (hash(x)=24624950) +1560 train 7.299951 (lr=9.9706e-05) (hash(x)=26581679) +1561 train 7.445235 (lr=9.9701e-05) (hash(x)=26174069) +1562 train 7.548648 (lr=9.9697e-05) (hash(x)=20919061) +1563 train 7.659553 (lr=9.9692e-05) (hash(x)=27299605) +1564 train 7.414015 (lr=9.9687e-05) (hash(x)=23601883) +1565 train 7.564922 (lr=9.9683e-05) (hash(x)=24777273) +1566 train 7.438924 (lr=9.9678e-05) (hash(x)=28913150) +1567 train 7.493407 (lr=9.9673e-05) (hash(x)=24113445) +1568 train 7.360313 (lr=9.9669e-05) (hash(x)=26581432) +1569 train 7.271824 (lr=9.9664e-05) (hash(x)=23970384) +1570 train 7.408319 (lr=9.9659e-05) (hash(x)=26883445) +1571 train 7.769937 (lr=9.9654e-05) (hash(x)=32644465) +1572 train 7.512198 (lr=9.9649e-05) (hash(x)=23814853) +1573 train 7.911865 (lr=9.9644e-05) (hash(x)=29951548) +1574 train 7.510064 (lr=9.9639e-05) (hash(x)=23727657) +1575 train 7.324990 (lr=9.9634e-05) (hash(x)=25829219) +1576 train 7.588346 (lr=9.9629e-05) (hash(x)=28173447) +1577 train 7.402145 (lr=9.9624e-05) (hash(x)=20556094) +1578 train 7.240214 (lr=9.9619e-05) (hash(x)=22525971) +1579 train 7.360007 (lr=9.9614e-05) (hash(x)=25194550) +1580 train 7.430946 (lr=9.9609e-05) (hash(x)=23848640) +1581 train 7.424844 (lr=9.9603e-05) (hash(x)=28482186) +1582 train 7.381205 (lr=9.9598e-05) (hash(x)=22540954) +1583 train 7.362060 (lr=9.9593e-05) (hash(x)=25941804) +1584 train 7.481303 (lr=9.9587e-05) (hash(x)=25631269) +1585 train 7.328176 (lr=9.9582e-05) (hash(x)=27049208) +1586 train 7.435650 (lr=9.9577e-05) (hash(x)=25712617) +1587 train 7.373771 (lr=9.9571e-05) (hash(x)=24075727) +1588 train 7.392353 (lr=9.9566e-05) (hash(x)=25786577) +1589 train 7.505011 (lr=9.9560e-05) (hash(x)=25082806) +1590 train 7.402897 (lr=9.9555e-05) (hash(x)=24080140) +1591 train 7.547280 (lr=9.9549e-05) (hash(x)=23104539) +1592 train 7.328940 (lr=9.9544e-05) (hash(x)=27972420) +1593 train 7.368831 (lr=9.9538e-05) (hash(x)=25351113) +1594 train 7.514454 (lr=9.9532e-05) (hash(x)=30149312) +1595 train 7.413947 (lr=9.9526e-05) (hash(x)=23018983) +1596 train 7.454513 (lr=9.9521e-05) (hash(x)=27798543) +1597 train 7.326111 (lr=9.9515e-05) (hash(x)=25302106) +1598 train 7.363241 (lr=9.9509e-05) (hash(x)=25399101) +1599 train 7.251191 (lr=9.9503e-05) (hash(x)=24422929) +1600 val loss 7.4221 +1600 val perplexity 1672.5607 +1600 train 7.287776 (lr=9.9497e-05) (hash(x)=23278576) +1601 train 7.481318 (lr=9.9491e-05) (hash(x)=29052117) +1602 train 7.479832 (lr=9.9486e-05) (hash(x)=25885977) +1603 train 7.301751 (lr=9.9480e-05) (hash(x)=23389696) +1604 train 7.292248 (lr=9.9474e-05) (hash(x)=23703987) +1605 train 7.353173 (lr=9.9467e-05) (hash(x)=23962503) +1606 train 7.337381 (lr=9.9461e-05) (hash(x)=25841931) +1607 train 7.450215 (lr=9.9455e-05) (hash(x)=29102969) +1608 train 7.519799 (lr=9.9449e-05) (hash(x)=28825867) +1609 train 7.564044 (lr=9.9443e-05) (hash(x)=24948166) +1610 train 7.498827 (lr=9.9437e-05) (hash(x)=27236198) +1611 train 7.474813 (lr=9.9430e-05) (hash(x)=28359859) +1612 train 7.470394 (lr=9.9424e-05) (hash(x)=27159867) +1613 train 7.518963 (lr=9.9418e-05) (hash(x)=22360298) +1614 train 7.627283 (lr=9.9411e-05) (hash(x)=26575886) +1615 train 7.540566 (lr=9.9405e-05) (hash(x)=24630955) +1616 train 7.726451 (lr=9.9399e-05) (hash(x)=28444407) +1617 train 7.446440 (lr=9.9392e-05) (hash(x)=26897402) +1618 train 7.616696 (lr=9.9386e-05) (hash(x)=27268677) +1619 train 7.446427 (lr=9.9379e-05) (hash(x)=22969113) +1620 train 7.374983 (lr=9.9372e-05) (hash(x)=21671079) +1621 train 7.338471 (lr=9.9366e-05) (hash(x)=25205781) +1622 train 7.236441 (lr=9.9359e-05) (hash(x)=23335929) +1623 train 7.470990 (lr=9.9353e-05) (hash(x)=27004415) +1624 train 7.202888 (lr=9.9346e-05) (hash(x)=25797941) +1625 train 7.211089 (lr=9.9339e-05) (hash(x)=22974875) +1626 train 7.381548 (lr=9.9332e-05) (hash(x)=25584910) +1627 train 7.257045 (lr=9.9325e-05) (hash(x)=22265063) +1628 train 7.127713 (lr=9.9319e-05) (hash(x)=23073191) +1629 train 7.292079 (lr=9.9312e-05) (hash(x)=23312114) +1630 train 7.336228 (lr=9.9305e-05) (hash(x)=25514824) +1631 train 7.421240 (lr=9.9298e-05) (hash(x)=26905990) +1632 train 7.223070 (lr=9.9291e-05) (hash(x)=21149081) +1633 train 7.536239 (lr=9.9284e-05) (hash(x)=27089280) +1634 train 7.328103 (lr=9.9277e-05) (hash(x)=25061229) +1635 train 7.392396 (lr=9.9270e-05) (hash(x)=24047679) +1636 train 7.413720 (lr=9.9263e-05) (hash(x)=25315110) +1637 train 7.381714 (lr=9.9255e-05) (hash(x)=25034684) +1638 train 7.634637 (lr=9.9248e-05) (hash(x)=28661487) +1639 train 7.542935 (lr=9.9241e-05) (hash(x)=26905582) +1640 train 7.459647 (lr=9.9234e-05) (hash(x)=23949017) +1641 train 7.046926 (lr=9.9226e-05) (hash(x)=21406950) +1642 train 7.096318 (lr=9.9219e-05) (hash(x)=21440152) +1643 train 7.365184 (lr=9.9212e-05) (hash(x)=29018970) +1644 train 7.267271 (lr=9.9204e-05) (hash(x)=19190537) +1645 train 7.141161 (lr=9.9197e-05) (hash(x)=20853530) +1646 train 7.159623 (lr=9.9190e-05) (hash(x)=23786853) +1647 train 7.454542 (lr=9.9182e-05) (hash(x)=24503315) +1648 train 7.389595 (lr=9.9174e-05) (hash(x)=27067328) +1649 train 7.226103 (lr=9.9167e-05) (hash(x)=23080074) +1650 val loss 7.4041 +1650 val perplexity 1642.7823 +1650 train 7.143694 (lr=9.9159e-05) (hash(x)=24105430) +1651 train 7.241171 (lr=9.9152e-05) (hash(x)=22607537) +1652 train 7.535196 (lr=9.9144e-05) (hash(x)=26063650) +1653 train 7.814738 (lr=9.9136e-05) (hash(x)=32179773) +1654 train 10.239361 (lr=9.9129e-05) (hash(x)=37724427) +1655 train 7.709096 (lr=9.9121e-05) (hash(x)=26690225) +1656 train 7.430074 (lr=9.9113e-05) (hash(x)=23702010) +1657 train 7.451614 (lr=9.9105e-05) (hash(x)=22109609) +1658 train 7.419639 (lr=9.9097e-05) (hash(x)=24503786) +1659 train 7.407598 (lr=9.9089e-05) (hash(x)=24226255) +1660 train 7.668100 (lr=9.9081e-05) (hash(x)=24752754) +1661 train 7.220428 (lr=9.9073e-05) (hash(x)=23013573) +1662 train 7.088125 (lr=9.9065e-05) (hash(x)=22700287) +1663 train 7.318540 (lr=9.9057e-05) (hash(x)=23622702) +1664 train 7.514171 (lr=9.9049e-05) (hash(x)=25435452) +1665 train 7.212566 (lr=9.9041e-05) (hash(x)=21517429) +1666 train 7.281267 (lr=9.9033e-05) (hash(x)=23374788) +1667 train 7.310277 (lr=9.9025e-05) (hash(x)=23910425) +1668 train 7.635488 (lr=9.9017e-05) (hash(x)=26737440) +1669 train 7.249165 (lr=9.9008e-05) (hash(x)=24407484) +1670 train 7.858779 (lr=9.9000e-05) (hash(x)=29038937) +1671 train 7.677667 (lr=9.8992e-05) (hash(x)=27213318) +1672 train 7.352350 (lr=9.8983e-05) (hash(x)=20332324) +1673 train 7.359306 (lr=9.8975e-05) (hash(x)=25524191) +1674 train 7.373899 (lr=9.8967e-05) (hash(x)=25614848) +1675 train 7.394015 (lr=9.8958e-05) (hash(x)=26701577) +1676 train 7.213274 (lr=9.8950e-05) (hash(x)=24461007) +1677 train 7.204272 (lr=9.8941e-05) (hash(x)=22091266) +1678 train 7.313425 (lr=9.8933e-05) (hash(x)=24500423) +1679 train 7.419544 (lr=9.8924e-05) (hash(x)=26216794) +1680 train 7.233513 (lr=9.8915e-05) (hash(x)=23143515) +1681 train 7.309047 (lr=9.8907e-05) (hash(x)=20817340) +1682 train 7.562005 (lr=9.8898e-05) (hash(x)=28151597) +1683 train 7.962824 (lr=9.8889e-05) (hash(x)=27579623) +1684 train 7.218034 (lr=9.8881e-05) (hash(x)=22166810) +1685 train 7.220432 (lr=9.8872e-05) (hash(x)=21532187) +1686 train 7.435511 (lr=9.8863e-05) (hash(x)=26911513) +1687 train 7.635793 (lr=9.8854e-05) (hash(x)=26086198) +1688 train 7.312875 (lr=9.8845e-05) (hash(x)=21817762) +1689 train 7.337799 (lr=9.8836e-05) (hash(x)=23911729) +1690 train 7.368070 (lr=9.8827e-05) (hash(x)=27955492) +1691 train 7.278624 (lr=9.8818e-05) (hash(x)=24863441) +1692 train 7.694122 (lr=9.8809e-05) (hash(x)=29174796) +1693 train 7.865982 (lr=9.8800e-05) (hash(x)=28856978) +1694 train 7.169960 (lr=9.8791e-05) (hash(x)=23431801) +1695 train 7.119473 (lr=9.8782e-05) (hash(x)=25236385) +1696 train 7.530560 (lr=9.8773e-05) (hash(x)=25713464) +1697 train 7.512036 (lr=9.8764e-05) (hash(x)=24278687) +1698 train 7.480480 (lr=9.8754e-05) (hash(x)=24513692) +1699 train 7.580567 (lr=9.8745e-05) (hash(x)=25330803) +1700 val loss 7.3973 +1700 val perplexity 1631.5861 +1700 train 7.592285 (lr=9.8736e-05) (hash(x)=26811522) +1701 train 7.259317 (lr=9.8726e-05) (hash(x)=21568545) +1702 train 7.276999 (lr=9.8717e-05) (hash(x)=27927608) +1703 train 7.342946 (lr=9.8708e-05) (hash(x)=22508532) +1704 train 7.477404 (lr=9.8698e-05) (hash(x)=23675869) +1705 train 7.246003 (lr=9.8689e-05) (hash(x)=24850662) +1706 train 7.322763 (lr=9.8679e-05) (hash(x)=24193434) +1707 train 7.369679 (lr=9.8670e-05) (hash(x)=21799261) +1708 train 7.450527 (lr=9.8660e-05) (hash(x)=26719309) +1709 train 7.612217 (lr=9.8651e-05) (hash(x)=24884891) +1710 train 7.387614 (lr=9.8641e-05) (hash(x)=26021405) +1711 train 7.338677 (lr=9.8631e-05) (hash(x)=26311168) +1712 train 7.257866 (lr=9.8621e-05) (hash(x)=23553179) +1713 train 7.539264 (lr=9.8612e-05) (hash(x)=27549895) +1714 train 7.069518 (lr=9.8602e-05) (hash(x)=21647642) +1715 train 7.011032 (lr=9.8592e-05) (hash(x)=20977430) +1716 train 7.099972 (lr=9.8582e-05) (hash(x)=23494380) +1717 train 7.320655 (lr=9.8572e-05) (hash(x)=23448855) +1718 train 7.382704 (lr=9.8563e-05) (hash(x)=21760032) +1719 train 7.438737 (lr=9.8553e-05) (hash(x)=26941617) +1720 train 7.645667 (lr=9.8543e-05) (hash(x)=27464193) +1721 train 7.550028 (lr=9.8533e-05) (hash(x)=26953192) +1722 train 7.362865 (lr=9.8523e-05) (hash(x)=24044587) +1723 train 7.858563 (lr=9.8512e-05) (hash(x)=30008957) +1724 train 7.480038 (lr=9.8502e-05) (hash(x)=19733965) +1725 train 7.550636 (lr=9.8492e-05) (hash(x)=27069893) +1726 train 7.331937 (lr=9.8482e-05) (hash(x)=22707406) +1727 train 7.407537 (lr=9.8472e-05) (hash(x)=27125962) +1728 train 7.152408 (lr=9.8462e-05) (hash(x)=23545652) +1729 train 7.182814 (lr=9.8451e-05) (hash(x)=23341415) +1730 train 7.277776 (lr=9.8441e-05) (hash(x)=22214769) +1731 train 7.331421 (lr=9.8431e-05) (hash(x)=25888358) +1732 train 7.260983 (lr=9.8420e-05) (hash(x)=24918697) +1733 train 7.666363 (lr=9.8410e-05) (hash(x)=26761645) +1734 train 7.308486 (lr=9.8399e-05) (hash(x)=23553754) +1735 train 7.325930 (lr=9.8389e-05) (hash(x)=21725719) +1736 train 7.324437 (lr=9.8378e-05) (hash(x)=26175307) +1737 train 7.170317 (lr=9.8368e-05) (hash(x)=25746493) +1738 train 7.367854 (lr=9.8357e-05) (hash(x)=22937341) +1739 train 7.231575 (lr=9.8347e-05) (hash(x)=21669704) +1740 train 7.189955 (lr=9.8336e-05) (hash(x)=22763387) +1741 train 7.162240 (lr=9.8325e-05) (hash(x)=21167493) +1742 train 7.255677 (lr=9.8315e-05) (hash(x)=26175023) +1743 train 7.293180 (lr=9.8304e-05) (hash(x)=23166993) +1744 train 7.227577 (lr=9.8293e-05) (hash(x)=21824285) +1745 train 7.276775 (lr=9.8282e-05) (hash(x)=23947208) +1746 train 7.356342 (lr=9.8271e-05) (hash(x)=25103214) +1747 train 7.366635 (lr=9.8260e-05) (hash(x)=26235974) +1748 train 7.835104 (lr=9.8249e-05) (hash(x)=28282027) +1749 train 7.703368 (lr=9.8239e-05) (hash(x)=29822604) +1750 val loss 7.3928 +1750 val perplexity 1624.2188 +1750 train 7.345817 (lr=9.8228e-05) (hash(x)=25249294) +1751 train 7.171763 (lr=9.8217e-05) (hash(x)=25426430) +1752 train 7.225114 (lr=9.8205e-05) (hash(x)=25602639) +1753 train 7.280386 (lr=9.8194e-05) (hash(x)=26043735) +1754 train 7.234641 (lr=9.8183e-05) (hash(x)=20936107) +1755 train 7.162649 (lr=9.8172e-05) (hash(x)=22966314) +1756 train 7.401006 (lr=9.8161e-05) (hash(x)=24656635) +1757 train 7.526269 (lr=9.8150e-05) (hash(x)=27944619) +1758 train 7.187976 (lr=9.8138e-05) (hash(x)=20844620) +1759 train 7.233392 (lr=9.8127e-05) (hash(x)=23448505) +1760 train 7.288948 (lr=9.8116e-05) (hash(x)=23963103) +1761 train 7.234059 (lr=9.8104e-05) (hash(x)=24205942) +1762 train 7.002928 (lr=9.8093e-05) (hash(x)=21631366) +1763 train 7.302637 (lr=9.8082e-05) (hash(x)=26330693) +1764 train 7.120103 (lr=9.8070e-05) (hash(x)=27345885) +1765 train 7.177544 (lr=9.8059e-05) (hash(x)=24844466) +1766 train 6.889908 (lr=9.8047e-05) (hash(x)=23229414) +1767 train 7.337018 (lr=9.8036e-05) (hash(x)=29550596) +1768 train 7.173767 (lr=9.8024e-05) (hash(x)=25843852) +1769 train 7.193208 (lr=9.8012e-05) (hash(x)=20506540) +1770 train 7.202241 (lr=9.8001e-05) (hash(x)=26395519) +1771 train 7.249317 (lr=9.7989e-05) (hash(x)=22124892) +1772 train 7.198262 (lr=9.7977e-05) (hash(x)=24316212) +1773 train 7.242023 (lr=9.7966e-05) (hash(x)=24867036) +1774 train 7.259637 (lr=9.7954e-05) (hash(x)=21576408) +1775 train 7.267866 (lr=9.7942e-05) (hash(x)=25607640) +1776 train 7.257660 (lr=9.7930e-05) (hash(x)=23454533) +1777 train 7.226772 (lr=9.7918e-05) (hash(x)=26176930) +1778 train 7.038716 (lr=9.7906e-05) (hash(x)=21821757) +1779 train 7.014724 (lr=9.7894e-05) (hash(x)=23795894) +1780 train 6.930408 (lr=9.7882e-05) (hash(x)=21510825) +1781 train 6.890146 (lr=9.7870e-05) (hash(x)=23756298) +1782 train 7.031230 (lr=9.7858e-05) (hash(x)=23262803) +1783 train 7.239412 (lr=9.7846e-05) (hash(x)=24165449) +1784 train 7.302028 (lr=9.7834e-05) (hash(x)=26532839) +1785 train 7.088664 (lr=9.7822e-05) (hash(x)=26643739) +1786 train 7.420814 (lr=9.7810e-05) (hash(x)=25810624) +1787 train 7.371139 (lr=9.7798e-05) (hash(x)=24697756) +1788 train 7.359740 (lr=9.7785e-05) (hash(x)=25793633) +1789 train 7.160846 (lr=9.7773e-05) (hash(x)=24431101) +1790 train 7.297590 (lr=9.7761e-05) (hash(x)=26286249) +1791 train 7.621495 (lr=9.7748e-05) (hash(x)=27218899) +1792 train 7.248130 (lr=9.7736e-05) (hash(x)=23659934) +1793 train 7.168838 (lr=9.7724e-05) (hash(x)=29462219) +1794 train 7.328394 (lr=9.7711e-05) (hash(x)=27168432) +1795 train 7.181676 (lr=9.7699e-05) (hash(x)=24748522) +1796 train 7.218784 (lr=9.7686e-05) (hash(x)=25539383) +1797 train 7.287920 (lr=9.7674e-05) (hash(x)=24843486) +1798 train 7.412295 (lr=9.7661e-05) (hash(x)=23873745) +1799 train 7.414619 (lr=9.7648e-05) (hash(x)=24965317) +1800 val loss 7.3483 +1800 val perplexity 1553.5325 +1800 train 6.970724 (lr=9.7636e-05) (hash(x)=23632877) +1801 train 7.251170 (lr=9.7623e-05) (hash(x)=26584754) +1802 train 6.950528 (lr=9.7610e-05) (hash(x)=20573248) +1803 train 7.102076 (lr=9.7598e-05) (hash(x)=22031210) +1804 train 7.201640 (lr=9.7585e-05) (hash(x)=22650144) +1805 train 7.244164 (lr=9.7572e-05) (hash(x)=24860582) +1806 train 7.039287 (lr=9.7559e-05) (hash(x)=23447130) +1807 train 7.293318 (lr=9.7546e-05) (hash(x)=25877990) +1808 train 7.245119 (lr=9.7533e-05) (hash(x)=24103543) +1809 train 7.307687 (lr=9.7520e-05) (hash(x)=24970646) +1810 train 7.341035 (lr=9.7507e-05) (hash(x)=25313591) +1811 train 7.244379 (lr=9.7494e-05) (hash(x)=24382381) +1812 train 7.258189 (lr=9.7481e-05) (hash(x)=25074871) +1813 train 7.119140 (lr=9.7468e-05) (hash(x)=25221746) +1814 train 7.233863 (lr=9.7455e-05) (hash(x)=25221431) +1815 train 7.106010 (lr=9.7442e-05) (hash(x)=24551999) +1816 train 7.158515 (lr=9.7429e-05) (hash(x)=22792380) +1817 train 7.208440 (lr=9.7416e-05) (hash(x)=28151378) +1818 train 7.341017 (lr=9.7402e-05) (hash(x)=27251870) +1819 train 7.328075 (lr=9.7389e-05) (hash(x)=25765516) +1820 train 7.345172 (lr=9.7376e-05) (hash(x)=23927187) +1821 train 7.273489 (lr=9.7362e-05) (hash(x)=25630696) +1822 train 7.167173 (lr=9.7349e-05) (hash(x)=28781600) +1823 train 7.419993 (lr=9.7336e-05) (hash(x)=25204247) +1824 train 7.541038 (lr=9.7322e-05) (hash(x)=26193103) +1825 train 7.204704 (lr=9.7309e-05) (hash(x)=26326447) +1826 train 7.311120 (lr=9.7295e-05) (hash(x)=26373461) +1827 train 7.322927 (lr=9.7282e-05) (hash(x)=26321813) +1828 train 7.361773 (lr=9.7268e-05) (hash(x)=24583976) +1829 train 7.127104 (lr=9.7254e-05) (hash(x)=25400396) +1830 train 7.179623 (lr=9.7241e-05) (hash(x)=27231042) +1831 train 7.338269 (lr=9.7227e-05) (hash(x)=25528323) +1832 train 7.182677 (lr=9.7213e-05) (hash(x)=22463800) +1833 train 7.304600 (lr=9.7200e-05) (hash(x)=24035353) +1834 train 7.146853 (lr=9.7186e-05) (hash(x)=22995856) +1835 train 7.374264 (lr=9.7172e-05) (hash(x)=25114729) +1836 train 7.326754 (lr=9.7158e-05) (hash(x)=26674420) +1837 train 6.948297 (lr=9.7144e-05) (hash(x)=21634962) +1838 train 7.165094 (lr=9.7131e-05) (hash(x)=24781824) +1839 train 7.427129 (lr=9.7117e-05) (hash(x)=31341964) +1840 train 7.223626 (lr=9.7103e-05) (hash(x)=19486640) +1841 train 7.180750 (lr=9.7089e-05) (hash(x)=29172813) +1842 train 7.604894 (lr=9.7075e-05) (hash(x)=27377840) +1843 train 7.201966 (lr=9.7061e-05) (hash(x)=26326024) +1844 train 7.063977 (lr=9.7046e-05) (hash(x)=20963675) +1845 train 7.053664 (lr=9.7032e-05) (hash(x)=20140071) +1846 train 7.078391 (lr=9.7018e-05) (hash(x)=23848422) +1847 train 7.384731 (lr=9.7004e-05) (hash(x)=27273311) +1848 train 7.264118 (lr=9.6990e-05) (hash(x)=22010794) +1849 train 7.419294 (lr=9.6976e-05) (hash(x)=31276487) +1850 val loss 7.3252 +1850 val perplexity 1518.0819 +1850 train 7.165572 (lr=9.6961e-05) (hash(x)=21985431) +1851 train 6.822181 (lr=9.6947e-05) (hash(x)=17819313) +1852 train 7.370856 (lr=9.6933e-05) (hash(x)=27260043) +1853 train 7.443851 (lr=9.6918e-05) (hash(x)=25843618) +1854 train 7.431958 (lr=9.6904e-05) (hash(x)=24960960) +1855 train 7.292136 (lr=9.6889e-05) (hash(x)=23769243) +1856 train 7.238998 (lr=9.6875e-05) (hash(x)=22817285) +1857 train 7.211569 (lr=9.6860e-05) (hash(x)=28731298) +1858 train 7.514425 (lr=9.6846e-05) (hash(x)=28825233) +1859 train 7.248247 (lr=9.6831e-05) (hash(x)=23788738) +1860 train 6.890818 (lr=9.6817e-05) (hash(x)=24755102) +1861 train 7.392569 (lr=9.6802e-05) (hash(x)=26599031) +1862 train 7.366458 (lr=9.6787e-05) (hash(x)=27434751) +1863 train 7.196137 (lr=9.6773e-05) (hash(x)=24818744) +1864 train 7.213861 (lr=9.6758e-05) (hash(x)=24987021) +1865 train 7.099616 (lr=9.6743e-05) (hash(x)=23053871) +1866 train 7.108008 (lr=9.6728e-05) (hash(x)=23718117) +1867 train 7.175818 (lr=9.6713e-05) (hash(x)=23472795) +1868 train 7.575418 (lr=9.6699e-05) (hash(x)=25243911) +1869 train 8.051172 (lr=9.6684e-05) (hash(x)=29748225) +1870 train 7.355525 (lr=9.6669e-05) (hash(x)=25619065) +1871 train 7.527741 (lr=9.6654e-05) (hash(x)=24991832) +1872 train 7.195253 (lr=9.6639e-05) (hash(x)=24651902) +1873 train 7.706679 (lr=9.6624e-05) (hash(x)=23681545) +1874 train 7.204695 (lr=9.6609e-05) (hash(x)=24932453) +1875 train 7.316906 (lr=9.6593e-05) (hash(x)=22424066) +1876 train 7.195979 (lr=9.6578e-05) (hash(x)=22113561) +1877 train 7.245013 (lr=9.6563e-05) (hash(x)=25262748) +1878 train 7.153259 (lr=9.6548e-05) (hash(x)=24681189) +1879 train 7.227355 (lr=9.6533e-05) (hash(x)=26474878) +1880 train 7.616941 (lr=9.6518e-05) (hash(x)=23832522) +1881 train 7.227070 (lr=9.6502e-05) (hash(x)=23930593) +1882 train 7.144713 (lr=9.6487e-05) (hash(x)=26865287) +1883 train 7.216772 (lr=9.6472e-05) (hash(x)=22704349) +1884 train 7.338061 (lr=9.6456e-05) (hash(x)=24935936) +1885 train 7.277011 (lr=9.6441e-05) (hash(x)=24801048) +1886 train 7.149734 (lr=9.6425e-05) (hash(x)=21166466) +1887 train 7.274783 (lr=9.6410e-05) (hash(x)=22293673) +1888 train 7.241298 (lr=9.6394e-05) (hash(x)=22370207) +1889 train 7.300678 (lr=9.6379e-05) (hash(x)=23311934) +1890 train 7.295542 (lr=9.6363e-05) (hash(x)=27132838) +1891 train 7.195889 (lr=9.6348e-05) (hash(x)=21785487) +1892 train 7.218863 (lr=9.6332e-05) (hash(x)=24806937) +1893 train 7.006706 (lr=9.6316e-05) (hash(x)=22981456) +1894 train 7.429258 (lr=9.6301e-05) (hash(x)=25867804) +1895 train 7.405840 (lr=9.6285e-05) (hash(x)=25251063) +1896 train 7.303057 (lr=9.6269e-05) (hash(x)=23819311) +1897 train 7.103238 (lr=9.6253e-05) (hash(x)=25796422) +1898 train 7.078795 (lr=9.6237e-05) (hash(x)=26120920) +1899 train 7.201476 (lr=9.6222e-05) (hash(x)=22722211) +1900 val loss 7.3085 +1900 val perplexity 1492.9814 +1900 train 7.136043 (lr=9.6206e-05) (hash(x)=24463866) +1901 train 7.287417 (lr=9.6190e-05) (hash(x)=24296755) +1902 train 7.369901 (lr=9.6174e-05) (hash(x)=26781262) +1903 train 7.097830 (lr=9.6158e-05) (hash(x)=24522269) +1904 train 7.192180 (lr=9.6142e-05) (hash(x)=24751946) +1905 train 7.218887 (lr=9.6126e-05) (hash(x)=25617184) +1906 train 7.012014 (lr=9.6110e-05) (hash(x)=22663402) +1907 train 7.220747 (lr=9.6093e-05) (hash(x)=23329475) +1908 train 7.124641 (lr=9.6077e-05) (hash(x)=22846270) +1909 train 7.347455 (lr=9.6061e-05) (hash(x)=30652062) +1910 train 7.177596 (lr=9.6045e-05) (hash(x)=26698904) +1911 train 7.186817 (lr=9.6029e-05) (hash(x)=24735165) +1912 train 6.939990 (lr=9.6012e-05) (hash(x)=23518594) +1913 train 7.018638 (lr=9.5996e-05) (hash(x)=23795686) +1914 train 6.805422 (lr=9.5980e-05) (hash(x)=19483392) +1915 train 7.216592 (lr=9.5963e-05) (hash(x)=27002892) +1916 train 7.190067 (lr=9.5947e-05) (hash(x)=26221916) +1917 train 6.982413 (lr=9.5930e-05) (hash(x)=21189101) +1918 train 7.051405 (lr=9.5914e-05) (hash(x)=25497439) +1919 train 6.939776 (lr=9.5897e-05) (hash(x)=23499349) +1920 train 8.032999 (lr=9.5881e-05) (hash(x)=26809295) +1921 train 7.259333 (lr=9.5864e-05) (hash(x)=26807896) +1922 train 7.263076 (lr=9.5848e-05) (hash(x)=25031330) +1923 train 7.114807 (lr=9.5831e-05) (hash(x)=22461589) +1924 train 7.262884 (lr=9.5814e-05) (hash(x)=24239512) +1925 train 7.379514 (lr=9.5798e-05) (hash(x)=26904123) +1926 train 6.946167 (lr=9.5781e-05) (hash(x)=21618533) +1927 train 7.268385 (lr=9.5764e-05) (hash(x)=26415040) +1928 train 7.486770 (lr=9.5748e-05) (hash(x)=22824767) +1929 train 7.244182 (lr=9.5731e-05) (hash(x)=24463181) +1930 train 7.246091 (lr=9.5714e-05) (hash(x)=26582384) +1931 train 7.676883 (lr=9.5697e-05) (hash(x)=26349465) +1932 train 7.142157 (lr=9.5680e-05) (hash(x)=23464639) +1933 train 6.920792 (lr=9.5663e-05) (hash(x)=21205988) +1934 train 6.937340 (lr=9.5646e-05) (hash(x)=24868938) +1935 train 7.188695 (lr=9.5629e-05) (hash(x)=21596677) +1936 train 7.290926 (lr=9.5612e-05) (hash(x)=26410272) +1937 train 7.091798 (lr=9.5595e-05) (hash(x)=23575666) +1938 train 6.794514 (lr=9.5578e-05) (hash(x)=16319719) +1939 train 7.143141 (lr=9.5561e-05) (hash(x)=24117012) +1940 train 7.130752 (lr=9.5544e-05) (hash(x)=23186527) +1941 train 7.095547 (lr=9.5526e-05) (hash(x)=26013014) +1942 train 7.338082 (lr=9.5509e-05) (hash(x)=23897834) +1943 train 7.153188 (lr=9.5492e-05) (hash(x)=24105761) +1944 train 7.192713 (lr=9.5475e-05) (hash(x)=21821937) +1945 train 7.077095 (lr=9.5457e-05) (hash(x)=20369133) +1946 train 7.011197 (lr=9.5440e-05) (hash(x)=22104086) +1947 train 7.263379 (lr=9.5423e-05) (hash(x)=25725049) +1948 train 7.051726 (lr=9.5405e-05) (hash(x)=18021467) +1949 train 7.037070 (lr=9.5388e-05) (hash(x)=19808118) +1950 val loss 7.2922 +1950 val perplexity 1468.8385 +1950 train 6.970918 (lr=9.5370e-05) (hash(x)=22434663) +1951 train 6.900764 (lr=9.5353e-05) (hash(x)=22892776) +1952 train 7.118377 (lr=9.5335e-05) (hash(x)=23704875) +1953 train 7.122384 (lr=9.5318e-05) (hash(x)=23736780) +1954 train 6.935417 (lr=9.5300e-05) (hash(x)=20091559) +1955 train 7.157124 (lr=9.5282e-05) (hash(x)=21630383) +1956 train 7.257133 (lr=9.5265e-05) (hash(x)=25355505) +1957 train 7.306198 (lr=9.5247e-05) (hash(x)=25397467) +1958 train 7.064427 (lr=9.5229e-05) (hash(x)=19036533) +1959 train 6.991222 (lr=9.5211e-05) (hash(x)=24727094) +1960 train 7.045060 (lr=9.5194e-05) (hash(x)=24424680) +1961 train 7.150455 (lr=9.5176e-05) (hash(x)=23951182) +1962 train 7.015788 (lr=9.5158e-05) (hash(x)=23533768) +1963 train 7.058959 (lr=9.5140e-05) (hash(x)=22835000) +1964 train 7.153439 (lr=9.5122e-05) (hash(x)=25171508) +1965 train 7.279812 (lr=9.5104e-05) (hash(x)=28767849) +1966 train 7.184834 (lr=9.5086e-05) (hash(x)=22723124) +1967 train 7.242813 (lr=9.5068e-05) (hash(x)=22839049) +1968 train 7.175381 (lr=9.5050e-05) (hash(x)=25945975) +1969 train 7.060854 (lr=9.5032e-05) (hash(x)=19930900) +1970 train 7.070868 (lr=9.5014e-05) (hash(x)=24592992) +1971 train 6.991776 (lr=9.4996e-05) (hash(x)=20654136) +1972 train 6.991898 (lr=9.4978e-05) (hash(x)=21441361) +1973 train 7.457299 (lr=9.4960e-05) (hash(x)=28495621) +1974 train 7.403140 (lr=9.4941e-05) (hash(x)=26750193) +1975 train 7.415208 (lr=9.4923e-05) (hash(x)=26776000) +1976 train 7.088292 (lr=9.4905e-05) (hash(x)=23441845) +1977 train 6.970830 (lr=9.4886e-05) (hash(x)=21584429) +1978 train 6.547841 (lr=9.4868e-05) (hash(x)=17946180) +1979 train 7.045558 (lr=9.4850e-05) (hash(x)=22560658) +1980 train 7.371272 (lr=9.4831e-05) (hash(x)=20438213) +1981 train 7.669319 (lr=9.4813e-05) (hash(x)=25276565) +1982 train 7.102459 (lr=9.4794e-05) (hash(x)=22850475) +1983 train 7.436436 (lr=9.4776e-05) (hash(x)=25995933) +1984 train 7.389175 (lr=9.4757e-05) (hash(x)=25066892) +1985 train 7.362242 (lr=9.4739e-05) (hash(x)=24163910) +1986 train 7.221053 (lr=9.4720e-05) (hash(x)=24323444) +1987 train 7.339356 (lr=9.4702e-05) (hash(x)=24635394) +1988 train 7.668762 (lr=9.4683e-05) (hash(x)=26710509) +1989 train 7.125534 (lr=9.4664e-05) (hash(x)=22556381) +1990 train 7.160947 (lr=9.4646e-05) (hash(x)=22268078) +1991 train 7.759778 (lr=9.4627e-05) (hash(x)=27537228) +1992 train 7.181250 (lr=9.4608e-05) (hash(x)=27006663) +1993 train 7.268692 (lr=9.4589e-05) (hash(x)=20883633) +1994 train 7.188983 (lr=9.4570e-05) (hash(x)=26775925) +1995 train 7.526641 (lr=9.4551e-05) (hash(x)=26496730) +1996 train 7.115787 (lr=9.4533e-05) (hash(x)=24887111) +1997 train 6.884457 (lr=9.4514e-05) (hash(x)=20342150) +1998 train 7.064125 (lr=9.4495e-05) (hash(x)=22731641) +1999 train 6.971921 (lr=9.4476e-05) (hash(x)=16533310) +2000 val loss 7.2780 +2000 val perplexity 1448.0287 +2000 train 7.148100 (lr=9.4457e-05) (hash(x)=24644301) +2001 train 7.046682 (lr=9.4438e-05) (hash(x)=24315862) +2002 train 7.204987 (lr=9.4419e-05) (hash(x)=24752796) +2003 train 7.209108 (lr=9.4399e-05) (hash(x)=24881176) +2004 train 7.293158 (lr=9.4380e-05) (hash(x)=27741054) +2005 train 7.520477 (lr=9.4361e-05) (hash(x)=23649686) +2006 train 7.359474 (lr=9.4342e-05) (hash(x)=29529498) +2007 train 7.232280 (lr=9.4323e-05) (hash(x)=25593613) +2008 train 7.066123 (lr=9.4303e-05) (hash(x)=21345346) +2009 train 7.107430 (lr=9.4284e-05) (hash(x)=23669244) +2010 train 7.010219 (lr=9.4265e-05) (hash(x)=22855256) +2011 train 7.312590 (lr=9.4245e-05) (hash(x)=22886646) +2012 train 7.144370 (lr=9.4226e-05) (hash(x)=25487028) +2013 train 7.848289 (lr=9.4207e-05) (hash(x)=30728540) +2014 train 7.242494 (lr=9.4187e-05) (hash(x)=22118783) +2015 train 7.206468 (lr=9.4168e-05) (hash(x)=21407676) +2016 train 7.029349 (lr=9.4148e-05) (hash(x)=24723788) +2017 train 7.239491 (lr=9.4129e-05) (hash(x)=26326164) +2018 train 7.454367 (lr=9.4109e-05) (hash(x)=30112933) +2019 train 7.225760 (lr=9.4089e-05) (hash(x)=21720304) +2020 train 7.490263 (lr=9.4070e-05) (hash(x)=25284552) +2021 train 7.369512 (lr=9.4050e-05) (hash(x)=23773870) +2022 train 7.415082 (lr=9.4030e-05) (hash(x)=34984911) +2023 train 7.285997 (lr=9.4011e-05) (hash(x)=27263416) +2024 train 7.103468 (lr=9.3991e-05) (hash(x)=24492055) +2025 train 7.156397 (lr=9.3971e-05) (hash(x)=25274710) +2026 train 7.112131 (lr=9.3951e-05) (hash(x)=25477340) +2027 train 7.169338 (lr=9.3931e-05) (hash(x)=25840801) +2028 train 7.386981 (lr=9.3912e-05) (hash(x)=26952458) +2029 train 6.825614 (lr=9.3892e-05) (hash(x)=20984129) +2030 train 7.132804 (lr=9.3872e-05) (hash(x)=24285302) +2031 train 7.833268 (lr=9.3852e-05) (hash(x)=31424568) +2032 train 7.580590 (lr=9.3832e-05) (hash(x)=27277376) +2033 train 7.160239 (lr=9.3812e-05) (hash(x)=25149712) +2034 train 7.038154 (lr=9.3792e-05) (hash(x)=25265136) +2035 train 7.355221 (lr=9.3772e-05) (hash(x)=23403065) +2036 train 7.132530 (lr=9.3752e-05) (hash(x)=23904844) +2037 train 7.029676 (lr=9.3731e-05) (hash(x)=23531744) +2038 train 7.132586 (lr=9.3711e-05) (hash(x)=22417529) +2039 train 7.077770 (lr=9.3691e-05) (hash(x)=22656033) +2040 train 7.200769 (lr=9.3671e-05) (hash(x)=25699377) +2041 train 7.039766 (lr=9.3650e-05) (hash(x)=18950799) +2042 train 7.400538 (lr=9.3630e-05) (hash(x)=34054446) +2043 train 7.310053 (lr=9.3610e-05) (hash(x)=26869295) +2044 train 7.416465 (lr=9.3590e-05) (hash(x)=29784110) +2045 train 8.091649 (lr=9.3569e-05) (hash(x)=34472685) +2046 train 7.301112 (lr=9.3549e-05) (hash(x)=22366381) +2047 train 7.311587 (lr=9.3528e-05) (hash(x)=25504151) +2048 train 7.731419 (lr=9.3508e-05) (hash(x)=25871651) +2049 train 7.086028 (lr=9.3487e-05) (hash(x)=22559978) +2050 val loss 7.3290 +2050 val perplexity 1523.8956 +2050 train 7.394568 (lr=9.3467e-05) (hash(x)=25440399) +2051 train 7.120614 (lr=9.3446e-05) (hash(x)=25781518) +2052 train 7.130786 (lr=9.3426e-05) (hash(x)=22440094) +2053 train 7.291516 (lr=9.3405e-05) (hash(x)=26966012) +2054 train 7.275395 (lr=9.3384e-05) (hash(x)=24110656) +2055 train 7.264227 (lr=9.3364e-05) (hash(x)=26432850) +2056 train 7.059054 (lr=9.3343e-05) (hash(x)=22740017) +2057 train 7.175583 (lr=9.3322e-05) (hash(x)=24725583) +2058 train 7.167371 (lr=9.3301e-05) (hash(x)=18529900) +2059 train 7.000956 (lr=9.3281e-05) (hash(x)=20155894) +2060 train 6.611125 (lr=9.3260e-05) (hash(x)=18905183) +2061 train 7.293555 (lr=9.3239e-05) (hash(x)=25247868) +2062 train 7.112638 (lr=9.3218e-05) (hash(x)=22929754) +2063 train 6.963861 (lr=9.3197e-05) (hash(x)=22270169) +2064 train 7.111455 (lr=9.3176e-05) (hash(x)=23821210) +2065 train 7.156551 (lr=9.3155e-05) (hash(x)=25240141) +2066 train 7.105727 (lr=9.3134e-05) (hash(x)=22909944) +2067 train 7.192635 (lr=9.3113e-05) (hash(x)=22108461) +2068 train 7.087464 (lr=9.3092e-05) (hash(x)=24701302) +2069 train 7.304290 (lr=9.3071e-05) (hash(x)=27896130) +2070 train 7.319510 (lr=9.3050e-05) (hash(x)=27158651) +2071 train 7.174183 (lr=9.3029e-05) (hash(x)=24802848) +2072 train 7.326513 (lr=9.3007e-05) (hash(x)=26473900) +2073 train 7.450054 (lr=9.2986e-05) (hash(x)=30188532) +2074 train 7.088758 (lr=9.2965e-05) (hash(x)=22409016) +2075 train 7.459661 (lr=9.2944e-05) (hash(x)=25086604) +2076 train 7.225906 (lr=9.2922e-05) (hash(x)=25014232) +2077 train 7.459264 (lr=9.2901e-05) (hash(x)=24031473) +2078 train 7.278912 (lr=9.2880e-05) (hash(x)=26069721) +2079 train 7.433795 (lr=9.2858e-05) (hash(x)=26983186) +2080 train 7.165554 (lr=9.2837e-05) (hash(x)=28155702) +2081 train 7.098516 (lr=9.2815e-05) (hash(x)=26492636) +2082 train 7.328995 (lr=9.2794e-05) (hash(x)=27079573) +2083 train 7.177680 (lr=9.2772e-05) (hash(x)=27208507) +2084 train 7.396510 (lr=9.2751e-05) (hash(x)=29641677) +2085 train 7.294146 (lr=9.2729e-05) (hash(x)=25227725) +2086 train 7.398872 (lr=9.2708e-05) (hash(x)=25581973) +2087 train 7.392982 (lr=9.2686e-05) (hash(x)=23862845) +2088 train 7.132029 (lr=9.2665e-05) (hash(x)=23111123) +2089 train 7.065019 (lr=9.2643e-05) (hash(x)=25148490) +2090 train 7.346734 (lr=9.2621e-05) (hash(x)=24779698) +2091 train 7.172282 (lr=9.2599e-05) (hash(x)=22664494) +2092 train 7.168010 (lr=9.2578e-05) (hash(x)=24707078) +2093 train 6.914624 (lr=9.2556e-05) (hash(x)=22219856) +2094 train 7.317601 (lr=9.2534e-05) (hash(x)=23398766) +2095 train 7.214768 (lr=9.2512e-05) (hash(x)=24092927) +2096 train 7.238378 (lr=9.2490e-05) (hash(x)=24676155) +2097 train 7.116160 (lr=9.2468e-05) (hash(x)=21999890) +2098 train 7.106331 (lr=9.2446e-05) (hash(x)=25120814) +2099 train 7.064565 (lr=9.2424e-05) (hash(x)=27213812) +2100 val loss 7.2563 +2100 val perplexity 1416.9600 +2100 train 6.953700 (lr=9.2402e-05) (hash(x)=23882161) +2101 train 7.222656 (lr=9.2380e-05) (hash(x)=27649723) +2102 train 7.191672 (lr=9.2358e-05) (hash(x)=23128552) +2103 train 7.081375 (lr=9.2336e-05) (hash(x)=23929955) +2104 train 6.945186 (lr=9.2314e-05) (hash(x)=21875178) +2105 train 7.239697 (lr=9.2292e-05) (hash(x)=25538503) +2106 train 7.248791 (lr=9.2270e-05) (hash(x)=22306665) +2107 train 7.002789 (lr=9.2248e-05) (hash(x)=23025790) +2108 train 7.155434 (lr=9.2225e-05) (hash(x)=27470230) +2109 train 7.002051 (lr=9.2203e-05) (hash(x)=21550313) +2110 train 7.048165 (lr=9.2181e-05) (hash(x)=25260787) +2111 train 7.003783 (lr=9.2158e-05) (hash(x)=20452272) +2112 train 7.016943 (lr=9.2136e-05) (hash(x)=19589460) +2113 train 7.475428 (lr=9.2114e-05) (hash(x)=27585442) +2114 train 7.312020 (lr=9.2091e-05) (hash(x)=24549919) +2115 train 7.340837 (lr=9.2069e-05) (hash(x)=26473464) +2116 train 7.446521 (lr=9.2046e-05) (hash(x)=29611296) +2117 train 7.223472 (lr=9.2024e-05) (hash(x)=26368203) +2118 train 7.192672 (lr=9.2001e-05) (hash(x)=26135379) +2119 train 7.123147 (lr=9.1979e-05) (hash(x)=28276603) +2120 train 7.088725 (lr=9.1956e-05) (hash(x)=22625589) +2121 train 7.245918 (lr=9.1934e-05) (hash(x)=25836838) +2122 train 7.085538 (lr=9.1911e-05) (hash(x)=22759365) +2123 train 6.873524 (lr=9.1888e-05) (hash(x)=21480367) +2124 train 7.440223 (lr=9.1866e-05) (hash(x)=29830546) +2125 train 7.290309 (lr=9.1843e-05) (hash(x)=25605672) +2126 train 6.924626 (lr=9.1820e-05) (hash(x)=22626883) +2127 train 7.326275 (lr=9.1797e-05) (hash(x)=24658642) +2128 train 7.317315 (lr=9.1775e-05) (hash(x)=22750846) +2129 train 7.113461 (lr=9.1752e-05) (hash(x)=22487960) +2130 train 7.098503 (lr=9.1729e-05) (hash(x)=21090180) +2131 train 7.227156 (lr=9.1706e-05) (hash(x)=26854801) +2132 train 7.109219 (lr=9.1683e-05) (hash(x)=23368704) +2133 train 7.198833 (lr=9.1660e-05) (hash(x)=25025039) +2134 train 7.144818 (lr=9.1637e-05) (hash(x)=27439380) +2135 train 6.817899 (lr=9.1614e-05) (hash(x)=17862226) +2136 train 7.063377 (lr=9.1591e-05) (hash(x)=21392062) +2137 train 7.241637 (lr=9.1568e-05) (hash(x)=26682036) +2138 train 7.067527 (lr=9.1545e-05) (hash(x)=22118984) +2139 train 7.257476 (lr=9.1522e-05) (hash(x)=28519182) +2140 train 7.148211 (lr=9.1499e-05) (hash(x)=24463139) +2141 train 7.178864 (lr=9.1475e-05) (hash(x)=29181174) +2142 train 7.169497 (lr=9.1452e-05) (hash(x)=29026537) +2143 train 7.073792 (lr=9.1429e-05) (hash(x)=25193694) +2144 train 7.146874 (lr=9.1406e-05) (hash(x)=24875410) +2145 train 7.274511 (lr=9.1382e-05) (hash(x)=26273661) +2146 train 7.108959 (lr=9.1359e-05) (hash(x)=23300732) +2147 train 7.224659 (lr=9.1336e-05) (hash(x)=25642620) +2148 train 7.193500 (lr=9.1312e-05) (hash(x)=25485335) +2149 train 7.194096 (lr=9.1289e-05) (hash(x)=28917143) +2150 val loss 7.2551 +2150 val perplexity 1415.2874 +2150 train 7.419412 (lr=9.1266e-05) (hash(x)=25989151) +2151 train 7.152993 (lr=9.1242e-05) (hash(x)=25765909) +2152 train 7.164569 (lr=9.1219e-05) (hash(x)=24438198) +2153 train 6.902313 (lr=9.1195e-05) (hash(x)=20160896) +2154 train 7.083345 (lr=9.1172e-05) (hash(x)=22073751) +2155 train 6.970531 (lr=9.1148e-05) (hash(x)=20750531) +2156 train 7.121061 (lr=9.1124e-05) (hash(x)=27324521) +2157 train 7.151261 (lr=9.1101e-05) (hash(x)=25741958) +2158 train 7.134140 (lr=9.1077e-05) (hash(x)=25387302) +2159 train 7.144238 (lr=9.1053e-05) (hash(x)=24917098) +2160 train 7.074222 (lr=9.1030e-05) (hash(x)=23518293) +2161 train 7.018031 (lr=9.1006e-05) (hash(x)=25659505) +2162 train 7.172649 (lr=9.0982e-05) (hash(x)=25082178) +2163 train 7.034001 (lr=9.0958e-05) (hash(x)=24499766) +2164 train 7.125664 (lr=9.0935e-05) (hash(x)=23225420) +2165 train 7.062906 (lr=9.0911e-05) (hash(x)=24634979) +2166 train 7.119267 (lr=9.0887e-05) (hash(x)=22559939) +2167 train 7.143933 (lr=9.0863e-05) (hash(x)=25067358) +2168 train 7.013611 (lr=9.0839e-05) (hash(x)=23820385) +2169 train 7.597623 (lr=9.0815e-05) (hash(x)=27138750) +2170 train 7.266209 (lr=9.0791e-05) (hash(x)=24602807) +2171 train 7.055374 (lr=9.0767e-05) (hash(x)=27479796) +2172 train 7.037490 (lr=9.0743e-05) (hash(x)=19728452) +2173 train 7.154751 (lr=9.0719e-05) (hash(x)=28225954) +2174 train 7.212083 (lr=9.0695e-05) (hash(x)=25654586) +2175 train 7.157375 (lr=9.0671e-05) (hash(x)=23136080) +2176 train 7.161063 (lr=9.0647e-05) (hash(x)=25461947) +2177 train 7.014380 (lr=9.0622e-05) (hash(x)=21441985) +2178 train 7.286016 (lr=9.0598e-05) (hash(x)=26245238) +2179 train 7.350746 (lr=9.0574e-05) (hash(x)=29810074) +2180 train 6.991862 (lr=9.0550e-05) (hash(x)=25229360) +2181 train 7.163533 (lr=9.0525e-05) (hash(x)=23222125) +2182 train 7.058771 (lr=9.0501e-05) (hash(x)=26995240) +2183 train 7.121121 (lr=9.0477e-05) (hash(x)=24765539) +2184 train 7.058107 (lr=9.0452e-05) (hash(x)=22559142) +2185 train 7.083519 (lr=9.0428e-05) (hash(x)=25938817) +2186 train 7.301921 (lr=9.0404e-05) (hash(x)=27866714) +2187 train 7.050080 (lr=9.0379e-05) (hash(x)=22216309) +2188 train 6.898821 (lr=9.0355e-05) (hash(x)=18784350) +2189 train 7.123665 (lr=9.0330e-05) (hash(x)=25647489) +2190 train 7.170573 (lr=9.0306e-05) (hash(x)=26539114) +2191 train 7.071209 (lr=9.0281e-05) (hash(x)=20613861) +2192 train 7.045082 (lr=9.0256e-05) (hash(x)=24893163) +2193 train 6.795004 (lr=9.0232e-05) (hash(x)=19580191) +2194 train 7.128013 (lr=9.0207e-05) (hash(x)=26433063) +2195 train 7.127837 (lr=9.0182e-05) (hash(x)=23462447) +2196 train 7.216418 (lr=9.0158e-05) (hash(x)=24109010) +2197 train 6.984376 (lr=9.0133e-05) (hash(x)=22230006) +2198 train 7.218201 (lr=9.0108e-05) (hash(x)=24112426) +2199 train 7.025233 (lr=9.0083e-05) (hash(x)=26739455) +2200 val loss 7.2357 +2200 val perplexity 1388.1594 +2200 train 7.017619 (lr=9.0059e-05) (hash(x)=26748712) +2201 train 7.250913 (lr=9.0034e-05) (hash(x)=26898808) +2202 train 7.139349 (lr=9.0009e-05) (hash(x)=25397145) +2203 train 7.194944 (lr=8.9984e-05) (hash(x)=23222996) +2204 train 7.272393 (lr=8.9959e-05) (hash(x)=27669038) +2205 train 7.168494 (lr=8.9934e-05) (hash(x)=25018789) +2206 train 7.205299 (lr=8.9909e-05) (hash(x)=22942904) +2207 train 7.155470 (lr=8.9884e-05) (hash(x)=26489285) +2208 train 6.572287 (lr=8.9859e-05) (hash(x)=23908505) +2209 train 7.181752 (lr=8.9834e-05) (hash(x)=27522868) +2210 train 6.957999 (lr=8.9809e-05) (hash(x)=24565522) +2211 train 7.178684 (lr=8.9784e-05) (hash(x)=25185942) +2212 train 7.161716 (lr=8.9759e-05) (hash(x)=26750372) +2213 train 7.423657 (lr=8.9734e-05) (hash(x)=28037060) +2214 train 7.457808 (lr=8.9708e-05) (hash(x)=28728766) +2215 train 7.258516 (lr=8.9683e-05) (hash(x)=27476158) +2216 train 7.047688 (lr=8.9658e-05) (hash(x)=23201299) +2217 train 6.987378 (lr=8.9633e-05) (hash(x)=23217512) +2218 train 7.236465 (lr=8.9607e-05) (hash(x)=23502072) +2219 train 7.140153 (lr=8.9582e-05) (hash(x)=23653175) +2220 train 6.960011 (lr=8.9557e-05) (hash(x)=22201854) +2221 train 7.128927 (lr=8.9531e-05) (hash(x)=25475122) +2222 train 7.131220 (lr=8.9506e-05) (hash(x)=26883852) +2223 train 6.989554 (lr=8.9480e-05) (hash(x)=22405076) +2224 train 7.166963 (lr=8.9455e-05) (hash(x)=25162594) +2225 train 7.193085 (lr=8.9430e-05) (hash(x)=26748800) +2226 train 7.009062 (lr=8.9404e-05) (hash(x)=25886430) +2227 train 6.955441 (lr=8.9378e-05) (hash(x)=25673545) +2228 train 7.245210 (lr=8.9353e-05) (hash(x)=21676076) +2229 train 7.084928 (lr=8.9327e-05) (hash(x)=22771197) +2230 train 7.313556 (lr=8.9302e-05) (hash(x)=24996433) +2231 train 7.151129 (lr=8.9276e-05) (hash(x)=22675428) +2232 train 7.223389 (lr=8.9250e-05) (hash(x)=22469290) +2233 train 7.446609 (lr=8.9225e-05) (hash(x)=26305388) +2234 train 7.271768 (lr=8.9199e-05) (hash(x)=23953315) +2235 train 7.301943 (lr=8.9173e-05) (hash(x)=28168456) +2236 train 7.047378 (lr=8.9147e-05) (hash(x)=24619336) +2237 train 7.545498 (lr=8.9122e-05) (hash(x)=31673254) +2238 train 7.603037 (lr=8.9096e-05) (hash(x)=29412572) +2239 train 7.477994 (lr=8.9070e-05) (hash(x)=26072586) +2240 train 7.181405 (lr=8.9044e-05) (hash(x)=21131363) +2241 train 7.462235 (lr=8.9018e-05) (hash(x)=32249577) +2242 train 7.051695 (lr=8.8992e-05) (hash(x)=24970539) +2243 train 7.078161 (lr=8.8966e-05) (hash(x)=24974331) +2244 train 7.160312 (lr=8.8940e-05) (hash(x)=11320385) +2245 train 6.936208 (lr=8.8914e-05) (hash(x)=10404694) +2246 train 6.919870 (lr=8.8888e-05) (hash(x)=11843609) +2247 train 6.962290 (lr=8.8862e-05) (hash(x)=21951984) +2248 train 7.815838 (lr=8.8836e-05) (hash(x)=21000228) +2249 train 7.367131 (lr=8.8810e-05) (hash(x)=24659058) +2250 val loss 7.2975 +2250 val perplexity 1476.6462 +2250 train 7.378282 (lr=8.8784e-05) (hash(x)=26232596) +2251 train 7.188343 (lr=8.8758e-05) (hash(x)=25403751) +2252 train 7.101426 (lr=8.8731e-05) (hash(x)=26560941) +2253 train 7.197962 (lr=8.8705e-05) (hash(x)=24405748) +2254 train 7.102700 (lr=8.8679e-05) (hash(x)=26358820) +2255 train 7.152487 (lr=8.8653e-05) (hash(x)=26396012) +2256 train 6.995312 (lr=8.8626e-05) (hash(x)=23855025) +2257 train 6.928733 (lr=8.8600e-05) (hash(x)=22779251) +2258 train 7.175754 (lr=8.8574e-05) (hash(x)=19886228) +2259 train 7.361477 (lr=8.8547e-05) (hash(x)=24827190) +2260 train 7.613189 (lr=8.8521e-05) (hash(x)=29752556) +2261 train 7.306498 (lr=8.8494e-05) (hash(x)=22209714) +2262 train 7.057004 (lr=8.8468e-05) (hash(x)=27808158) +2263 train 7.132353 (lr=8.8442e-05) (hash(x)=24847458) +2264 train 7.591259 (lr=8.8415e-05) (hash(x)=29745551) +2265 train 6.953553 (lr=8.8388e-05) (hash(x)=20720911) +2266 train 7.222254 (lr=8.8362e-05) (hash(x)=23780724) +2267 train 7.112658 (lr=8.8335e-05) (hash(x)=22159088) +2268 train 7.031919 (lr=8.8309e-05) (hash(x)=22813612) +2269 train 7.239792 (lr=8.8282e-05) (hash(x)=25737179) +2270 train 7.250763 (lr=8.8255e-05) (hash(x)=25071988) +2271 train 7.045659 (lr=8.8229e-05) (hash(x)=22140034) +2272 train 7.177892 (lr=8.8202e-05) (hash(x)=24099725) +2273 train 6.853949 (lr=8.8175e-05) (hash(x)=18992693) +2274 train 7.818101 (lr=8.8148e-05) (hash(x)=30389969) +2275 train 6.926614 (lr=8.8122e-05) (hash(x)=19044797) +2276 train 7.257210 (lr=8.8095e-05) (hash(x)=22780968) +2277 train 6.981992 (lr=8.8068e-05) (hash(x)=21374811) +2278 train 7.114090 (lr=8.8041e-05) (hash(x)=25691882) +2279 train 7.011484 (lr=8.8014e-05) (hash(x)=23932794) +2280 train 7.258696 (lr=8.7987e-05) (hash(x)=23417051) +2281 train 7.185396 (lr=8.7960e-05) (hash(x)=25428813) +2282 train 7.305794 (lr=8.7933e-05) (hash(x)=23015212) +2283 train 7.003106 (lr=8.7906e-05) (hash(x)=25256890) +2284 train 7.154047 (lr=8.7879e-05) (hash(x)=30167922) +2285 train 7.186675 (lr=8.7852e-05) (hash(x)=26752941) +2286 train 7.491380 (lr=8.7825e-05) (hash(x)=28508785) +2287 train 7.149128 (lr=8.7798e-05) (hash(x)=24161711) +2288 train 7.193504 (lr=8.7771e-05) (hash(x)=28248933) +2289 train 7.373833 (lr=8.7744e-05) (hash(x)=24589015) +2290 train 7.156122 (lr=8.7717e-05) (hash(x)=25131316) +2291 train 6.992803 (lr=8.7690e-05) (hash(x)=22036817) +2292 train 7.335229 (lr=8.7662e-05) (hash(x)=24828340) +2293 train 6.740054 (lr=8.7635e-05) (hash(x)=20733289) +2294 train 6.726393 (lr=8.7608e-05) (hash(x)=22148688) +2295 train 7.176270 (lr=8.7580e-05) (hash(x)=26663208) +2296 train 7.008668 (lr=8.7553e-05) (hash(x)=23608185) +2297 train 7.091567 (lr=8.7526e-05) (hash(x)=25409759) +2298 train 7.143756 (lr=8.7498e-05) (hash(x)=21782039) +2299 train 7.077689 (lr=8.7471e-05) (hash(x)=24072213) +2300 val loss 7.2238 +2300 val perplexity 1371.6506 +2300 train 7.036140 (lr=8.7444e-05) (hash(x)=23315415) +2301 train 7.035826 (lr=8.7416e-05) (hash(x)=24921200) +2302 train 7.146208 (lr=8.7389e-05) (hash(x)=22920960) +2303 train 7.059677 (lr=8.7361e-05) (hash(x)=22766044) +2304 train 7.172366 (lr=8.7334e-05) (hash(x)=24922621) +2305 train 7.331564 (lr=8.7306e-05) (hash(x)=32920298) +2306 train 7.005126 (lr=8.7278e-05) (hash(x)=22863054) +2307 train 7.209292 (lr=8.7251e-05) (hash(x)=27871153) +2308 train 7.176827 (lr=8.7223e-05) (hash(x)=24659561) +2309 train 7.109816 (lr=8.7196e-05) (hash(x)=22731460) +2310 train 7.084714 (lr=8.7168e-05) (hash(x)=26033948) +2311 train 7.288232 (lr=8.7140e-05) (hash(x)=24037280) +2312 train 7.813595 (lr=8.7112e-05) (hash(x)=26799867) +2313 train 7.133893 (lr=8.7085e-05) (hash(x)=23277695) +2314 train 7.180473 (lr=8.7057e-05) (hash(x)=26103104) +2315 train 7.231706 (lr=8.7029e-05) (hash(x)=24121850) +2316 train 7.152775 (lr=8.7001e-05) (hash(x)=22379412) +2317 train 7.225286 (lr=8.6973e-05) (hash(x)=22966977) +2318 train 7.001986 (lr=8.6946e-05) (hash(x)=23827429) +2319 train 7.132519 (lr=8.6918e-05) (hash(x)=24380031) +2320 train 7.160141 (lr=8.6890e-05) (hash(x)=24442902) +2321 train 6.956658 (lr=8.6862e-05) (hash(x)=26957303) +2322 train 7.126579 (lr=8.6834e-05) (hash(x)=27224706) +2323 train 7.087074 (lr=8.6806e-05) (hash(x)=23055215) +2324 train 7.604670 (lr=8.6778e-05) (hash(x)=13982941) +2325 train 7.327302 (lr=8.6750e-05) (hash(x)=22929154) +2326 train 7.177508 (lr=8.6722e-05) (hash(x)=24877951) +2327 train 7.124750 (lr=8.6694e-05) (hash(x)=25329724) +2328 train 6.861837 (lr=8.6665e-05) (hash(x)=20923083) +2329 train 7.041522 (lr=8.6637e-05) (hash(x)=24370475) +2330 train 7.331034 (lr=8.6609e-05) (hash(x)=26142119) +2331 train 7.024751 (lr=8.6581e-05) (hash(x)=25662408) +2332 train 7.118132 (lr=8.6553e-05) (hash(x)=23987677) +2333 train 7.369138 (lr=8.6524e-05) (hash(x)=25991817) +2334 train 7.010127 (lr=8.6496e-05) (hash(x)=22187158) +2335 train 7.205704 (lr=8.6468e-05) (hash(x)=26346814) +2336 train 7.352675 (lr=8.6440e-05) (hash(x)=24322101) +2337 train 7.237844 (lr=8.6411e-05) (hash(x)=24505725) +2338 train 7.316008 (lr=8.6383e-05) (hash(x)=28062311) +2339 train 7.144035 (lr=8.6354e-05) (hash(x)=25283256) +2340 train 6.961891 (lr=8.6326e-05) (hash(x)=22716214) +2341 train 7.038128 (lr=8.6298e-05) (hash(x)=22979072) +2342 train 7.150391 (lr=8.6269e-05) (hash(x)=24857737) +2343 train 7.162824 (lr=8.6241e-05) (hash(x)=24021771) +2344 train 7.009937 (lr=8.6212e-05) (hash(x)=22850411) +2345 train 7.086606 (lr=8.6184e-05) (hash(x)=22956381) +2346 train 7.254263 (lr=8.6155e-05) (hash(x)=25596844) +2347 train 6.969711 (lr=8.6126e-05) (hash(x)=23576840) +2348 train 6.991265 (lr=8.6098e-05) (hash(x)=26431349) +2349 train 7.190804 (lr=8.6069e-05) (hash(x)=23243097) +2350 val loss 7.2086 +2350 val perplexity 1350.9951 +2350 train 7.342319 (lr=8.6041e-05) (hash(x)=30678293) +2351 train 7.501760 (lr=8.6012e-05) (hash(x)=26414858) +2352 train 7.024163 (lr=8.5983e-05) (hash(x)=21627762) +2353 train 6.920759 (lr=8.5954e-05) (hash(x)=23570951) +2354 train 7.193116 (lr=8.5926e-05) (hash(x)=25933754) +2355 train 6.903283 (lr=8.5897e-05) (hash(x)=20099261) +2356 train 7.044055 (lr=8.5868e-05) (hash(x)=25332115) +2357 train 6.940165 (lr=8.5839e-05) (hash(x)=23786549) +2358 train 7.031952 (lr=8.5810e-05) (hash(x)=25967754) +2359 train 7.021428 (lr=8.5782e-05) (hash(x)=22453718) +2360 train 7.083239 (lr=8.5753e-05) (hash(x)=25284885) +2361 train 6.964334 (lr=8.5724e-05) (hash(x)=19448608) +2362 train 7.026145 (lr=8.5695e-05) (hash(x)=23203503) +2363 train 6.766137 (lr=8.5666e-05) (hash(x)=22529445) +2364 train 7.109032 (lr=8.5637e-05) (hash(x)=25661132) +2365 train 7.137140 (lr=8.5608e-05) (hash(x)=22575521) +2366 train 6.911235 (lr=8.5579e-05) (hash(x)=18637357) +2367 train 7.072423 (lr=8.5550e-05) (hash(x)=24484543) +2368 train 6.916863 (lr=8.5521e-05) (hash(x)=21544758) +2369 train 6.939881 (lr=8.5491e-05) (hash(x)=24893614) +2370 train 7.049599 (lr=8.5462e-05) (hash(x)=22233356) +2371 train 6.940243 (lr=8.5433e-05) (hash(x)=24043998) +2372 train 7.252905 (lr=8.5404e-05) (hash(x)=23858358) +2373 train 7.212115 (lr=8.5375e-05) (hash(x)=24813708) +2374 train 6.974916 (lr=8.5346e-05) (hash(x)=21850656) +2375 train 6.982075 (lr=8.5316e-05) (hash(x)=24301906) +2376 train 6.992090 (lr=8.5287e-05) (hash(x)=25649256) +2377 train 7.041935 (lr=8.5258e-05) (hash(x)=26332892) +2378 train 7.028403 (lr=8.5228e-05) (hash(x)=23146858) +2379 train 7.194633 (lr=8.5199e-05) (hash(x)=26328881) +2380 train 7.016867 (lr=8.5170e-05) (hash(x)=22122308) +2381 train 7.226580 (lr=8.5140e-05) (hash(x)=26841776) +2382 train 7.098599 (lr=8.5111e-05) (hash(x)=24912822) +2383 train 7.049932 (lr=8.5081e-05) (hash(x)=23101508) +2384 train 7.080884 (lr=8.5052e-05) (hash(x)=22798964) +2385 train 7.058749 (lr=8.5022e-05) (hash(x)=24946464) +2386 train 7.053917 (lr=8.4993e-05) (hash(x)=23173476) +2387 train 7.135082 (lr=8.4963e-05) (hash(x)=23527176) +2388 train 7.068689 (lr=8.4934e-05) (hash(x)=24451067) +2389 train 7.720510 (lr=8.4904e-05) (hash(x)=31163350) +2390 train 8.082992 (lr=8.4875e-05) (hash(x)=34939183) +2391 train 7.313557 (lr=8.4845e-05) (hash(x)=22705673) +2392 train 6.997387 (lr=8.4815e-05) (hash(x)=26079097) +2393 train 7.350912 (lr=8.4786e-05) (hash(x)=24705721) +2394 train 7.105896 (lr=8.4756e-05) (hash(x)=22550579) +2395 train 7.252586 (lr=8.4726e-05) (hash(x)=28664796) +2396 train 7.544774 (lr=8.4697e-05) (hash(x)=23862341) +2397 train 6.893294 (lr=8.4667e-05) (hash(x)=22659441) +2398 train 7.518376 (lr=8.4637e-05) (hash(x)=25822591) +2399 train 7.105990 (lr=8.4607e-05) (hash(x)=27102890) +2400 val loss 7.1955 +2400 val perplexity 1333.4441 +2400 train 7.250424 (lr=8.4577e-05) (hash(x)=25755963) +2401 train 7.400907 (lr=8.4548e-05) (hash(x)=26660930) +2402 train 7.426416 (lr=8.4518e-05) (hash(x)=24622741) +2403 train 7.388743 (lr=8.4488e-05) (hash(x)=26787259) +2404 train 7.619257 (lr=8.4458e-05) (hash(x)=37061654) +2405 train 7.416804 (lr=8.4428e-05) (hash(x)=26097180) +2406 train 7.369135 (lr=8.4398e-05) (hash(x)=23258030) +2407 train 7.197751 (lr=8.4368e-05) (hash(x)=23396088) +2408 train 7.122250 (lr=8.4338e-05) (hash(x)=26281676) +2409 train 7.114442 (lr=8.4308e-05) (hash(x)=24611098) +2410 train 7.181759 (lr=8.4278e-05) (hash(x)=21439671) +2411 train 7.088878 (lr=8.4248e-05) (hash(x)=24911831) +2412 train 7.226669 (lr=8.4218e-05) (hash(x)=26479565) +2413 train 7.283503 (lr=8.4188e-05) (hash(x)=25131300) +2414 train 6.944413 (lr=8.4157e-05) (hash(x)=23173449) +2415 train 7.128809 (lr=8.4127e-05) (hash(x)=23453491) +2416 train 7.110457 (lr=8.4097e-05) (hash(x)=21659918) +2417 train 7.157481 (lr=8.4067e-05) (hash(x)=22237612) +2418 train 7.349633 (lr=8.4037e-05) (hash(x)=24939751) +2419 train 7.190004 (lr=8.4006e-05) (hash(x)=23453396) +2420 train 6.945473 (lr=8.3976e-05) (hash(x)=23428815) +2421 train 7.483021 (lr=8.3946e-05) (hash(x)=25161278) +2422 train 7.374722 (lr=8.3915e-05) (hash(x)=26139263) +2423 train 7.313075 (lr=8.3885e-05) (hash(x)=23869612) +2424 train 7.357214 (lr=8.3855e-05) (hash(x)=29351182) +2425 train 7.502671 (lr=8.3824e-05) (hash(x)=28207741) +2426 train 7.230458 (lr=8.3794e-05) (hash(x)=26742336) +2427 train 7.404516 (lr=8.3763e-05) (hash(x)=26581590) +2428 train 6.982411 (lr=8.3733e-05) (hash(x)=19854534) +2429 train 7.357444 (lr=8.3702e-05) (hash(x)=25827863) +2430 train 7.211976 (lr=8.3672e-05) (hash(x)=26187830) +2431 train 7.273020 (lr=8.3641e-05) (hash(x)=28056342) +2432 train 7.243884 (lr=8.3611e-05) (hash(x)=25659043) +2433 train 7.236404 (lr=8.3580e-05) (hash(x)=23965470) +2434 train 7.234427 (lr=8.3550e-05) (hash(x)=26639165) +2435 train 7.233584 (lr=8.3519e-05) (hash(x)=25900866) +2436 train 7.246736 (lr=8.3488e-05) (hash(x)=25430698) +2437 train 7.230963 (lr=8.3458e-05) (hash(x)=27682625) +2438 train 7.328512 (lr=8.3427e-05) (hash(x)=24661627) +2439 train 7.230652 (lr=8.3396e-05) (hash(x)=24549177) +2440 train 7.083323 (lr=8.3366e-05) (hash(x)=21460850) +2441 train 7.313270 (lr=8.3335e-05) (hash(x)=24193076) +2442 train 7.178795 (lr=8.3304e-05) (hash(x)=25133839) +2443 train 7.211262 (lr=8.3273e-05) (hash(x)=28239583) +2444 train 7.342114 (lr=8.3242e-05) (hash(x)=23833431) +2445 train 7.130609 (lr=8.3212e-05) (hash(x)=20885864) +2446 train 7.366229 (lr=8.3181e-05) (hash(x)=27321870) +2447 train 6.947831 (lr=8.3150e-05) (hash(x)=23223554) +2448 train 7.390687 (lr=8.3119e-05) (hash(x)=28007972) +2449 train 7.296884 (lr=8.3088e-05) (hash(x)=27425770) +2450 val loss 7.1745 +2450 val perplexity 1305.6847 +2450 train 7.303941 (lr=8.3057e-05) (hash(x)=24080235) +2451 train 7.072614 (lr=8.3026e-05) (hash(x)=24793480) +2452 train 7.271441 (lr=8.2995e-05) (hash(x)=24590670) +2453 train 7.251443 (lr=8.2964e-05) (hash(x)=26949097) +2454 train 7.051985 (lr=8.2933e-05) (hash(x)=23814995) +2455 train 7.061759 (lr=8.2902e-05) (hash(x)=25415570) +2456 train 7.229250 (lr=8.2871e-05) (hash(x)=22920200) +2457 train 7.177470 (lr=8.2840e-05) (hash(x)=24985634) +2458 train 7.219414 (lr=8.2809e-05) (hash(x)=25637457) +2459 train 7.321407 (lr=8.2778e-05) (hash(x)=24425760) +2460 train 7.327223 (lr=8.2746e-05) (hash(x)=25538618) +2461 train 7.456150 (lr=8.2715e-05) (hash(x)=29154578) +2462 train 7.324570 (lr=8.2684e-05) (hash(x)=27939259) +2463 train 7.111709 (lr=8.2653e-05) (hash(x)=23707134) +2464 train 7.325341 (lr=8.2621e-05) (hash(x)=31623877) +2465 train 7.157858 (lr=8.2590e-05) (hash(x)=20049335) +2466 train 7.097840 (lr=8.2559e-05) (hash(x)=25265312) +2467 train 7.469930 (lr=8.2528e-05) (hash(x)=28321697) +2468 train 7.222690 (lr=8.2496e-05) (hash(x)=24596431) +2469 train 7.108521 (lr=8.2465e-05) (hash(x)=21497535) +2470 train 7.092927 (lr=8.2434e-05) (hash(x)=24024557) +2471 train 7.238832 (lr=8.2402e-05) (hash(x)=23434031) +2472 train 7.173915 (lr=8.2371e-05) (hash(x)=25858759) +2473 train 7.123327 (lr=8.2339e-05) (hash(x)=27469117) +2474 train 7.145515 (lr=8.2308e-05) (hash(x)=25759281) +2475 train 7.147477 (lr=8.2276e-05) (hash(x)=27003481) +2476 train 7.298072 (lr=8.2245e-05) (hash(x)=22691119) +2477 train 7.086026 (lr=8.2213e-05) (hash(x)=17850370) +2478 train 7.118179 (lr=8.2182e-05) (hash(x)=25327160) +2479 train 7.159022 (lr=8.2150e-05) (hash(x)=22236893) +2480 train 6.958368 (lr=8.2119e-05) (hash(x)=23852346) +2481 train 7.184137 (lr=8.2087e-05) (hash(x)=25764691) +2482 train 7.306741 (lr=8.2055e-05) (hash(x)=23856238) +2483 train 7.219365 (lr=8.2024e-05) (hash(x)=26857458) +2484 train 7.135070 (lr=8.1992e-05) (hash(x)=23139455) +2485 train 7.126210 (lr=8.1960e-05) (hash(x)=25654849) +2486 train 7.152228 (lr=8.1929e-05) (hash(x)=25652110) +2487 train 7.360889 (lr=8.1897e-05) (hash(x)=26413122) +2488 train 7.435430 (lr=8.1865e-05) (hash(x)=22784033) +2489 train 7.591192 (lr=8.1833e-05) (hash(x)=24507726) +2490 train 7.554671 (lr=8.1801e-05) (hash(x)=25624751) +2491 train 7.423277 (lr=8.1770e-05) (hash(x)=27696537) +2492 train 7.311639 (lr=8.1738e-05) (hash(x)=28274576) +2493 train 7.196962 (lr=8.1706e-05) (hash(x)=21602520) +2494 train 7.159349 (lr=8.1674e-05) (hash(x)=28060542) +2495 train 7.174066 (lr=8.1642e-05) (hash(x)=21950234) +2496 train 7.381862 (lr=8.1610e-05) (hash(x)=26770105) +2497 train 7.068842 (lr=8.1578e-05) (hash(x)=26064895) +2498 train 7.219670 (lr=8.1546e-05) (hash(x)=25029447) +2499 train 7.237486 (lr=8.1514e-05) (hash(x)=24051952) +2500 val loss 7.1656 +2500 val perplexity 1294.1154 +2500 train 7.391327 (lr=8.1482e-05) (hash(x)=21510847) +2501 train 7.253193 (lr=8.1450e-05) (hash(x)=23898545) +2502 train 7.114427 (lr=8.1418e-05) (hash(x)=24179564) +2503 train 7.168822 (lr=8.1386e-05) (hash(x)=24029939) +2504 train 7.032897 (lr=8.1354e-05) (hash(x)=24678605) +2505 train 7.115179 (lr=8.1322e-05) (hash(x)=25044563) +2506 train 8.147507 (lr=8.1290e-05) (hash(x)=35911595) +2507 train 7.015535 (lr=8.1258e-05) (hash(x)=24393346) +2508 train 7.183788 (lr=8.1226e-05) (hash(x)=22744936) +2509 train 7.181791 (lr=8.1193e-05) (hash(x)=28452609) +2510 train 7.273105 (lr=8.1161e-05) (hash(x)=25512003) +2511 train 7.423882 (lr=8.1129e-05) (hash(x)=26985352) +2512 train 6.776753 (lr=8.1097e-05) (hash(x)=17526152) +2513 train 7.086362 (lr=8.1064e-05) (hash(x)=26394568) +2514 train 7.268895 (lr=8.1032e-05) (hash(x)=25318486) +2515 train 6.925374 (lr=8.1000e-05) (hash(x)=19493265) +2516 train 6.959375 (lr=8.0967e-05) (hash(x)=24507451) +2517 train 6.995267 (lr=8.0935e-05) (hash(x)=21230587) +2518 train 7.311614 (lr=8.0903e-05) (hash(x)=27738855) +2519 train 7.234279 (lr=8.0870e-05) (hash(x)=23944010) +2520 train 7.318421 (lr=8.0838e-05) (hash(x)=26372006) +2521 train 7.451145 (lr=8.0806e-05) (hash(x)=30456809) +2522 train 7.339991 (lr=8.0773e-05) (hash(x)=24781245) +2523 train 7.204538 (lr=8.0741e-05) (hash(x)=21517435) +2524 train 7.092310 (lr=8.0708e-05) (hash(x)=24233710) +2525 train 7.093257 (lr=8.0676e-05) (hash(x)=24353917) +2526 train 7.219058 (lr=8.0643e-05) (hash(x)=24562870) +2527 train 6.976722 (lr=8.0611e-05) (hash(x)=25025868) +2528 train 7.137135 (lr=8.0578e-05) (hash(x)=24219951) +2529 train 7.068253 (lr=8.0545e-05) (hash(x)=22273663) +2530 train 7.034078 (lr=8.0513e-05) (hash(x)=27580667) +2531 train 7.124922 (lr=8.0480e-05) (hash(x)=22940997) +2532 train 7.165699 (lr=8.0447e-05) (hash(x)=26593649) +2533 train 7.401766 (lr=8.0415e-05) (hash(x)=29402781) +2534 train 7.191475 (lr=8.0382e-05) (hash(x)=23894879) +2535 train 7.241145 (lr=8.0349e-05) (hash(x)=25864840) +2536 train 7.231831 (lr=8.0317e-05) (hash(x)=24089358) +2537 train 7.110505 (lr=8.0284e-05) (hash(x)=26245998) +2538 train 7.157732 (lr=8.0251e-05) (hash(x)=24817993) +2539 train 7.078913 (lr=8.0218e-05) (hash(x)=24682151) +2540 train 6.883096 (lr=8.0186e-05) (hash(x)=22148775) +2541 train 6.917375 (lr=8.0153e-05) (hash(x)=23622029) +2542 train 7.206985 (lr=8.0120e-05) (hash(x)=26226059) +2543 train 7.181632 (lr=8.0087e-05) (hash(x)=27055330) +2544 train 7.171484 (lr=8.0054e-05) (hash(x)=27209598) +2545 train 7.093736 (lr=8.0021e-05) (hash(x)=22125662) +2546 train 7.250359 (lr=7.9988e-05) (hash(x)=23334240) +2547 train 7.019696 (lr=7.9955e-05) (hash(x)=22705710) +2548 train 7.149312 (lr=7.9922e-05) (hash(x)=24423227) +2549 train 7.242525 (lr=7.9889e-05) (hash(x)=23426381) +2550 val loss 7.1476 +2550 val perplexity 1271.1132 +2550 train 7.127257 (lr=7.9856e-05) (hash(x)=23820445) +2551 train 7.359364 (lr=7.9823e-05) (hash(x)=26775238) +2552 train 7.344414 (lr=7.9790e-05) (hash(x)=26105993) +2553 train 7.551596 (lr=7.9757e-05) (hash(x)=28659494) +2554 train 7.366953 (lr=7.9724e-05) (hash(x)=27792588) +2555 train 7.121459 (lr=7.9691e-05) (hash(x)=21734331) +2556 train 6.969855 (lr=7.9658e-05) (hash(x)=20836230) +2557 train 7.257843 (lr=7.9625e-05) (hash(x)=26149297) +2558 train 6.880837 (lr=7.9592e-05) (hash(x)=24034094) +2559 train 7.275964 (lr=7.9559e-05) (hash(x)=25693442) +2560 train 7.199361 (lr=7.9525e-05) (hash(x)=27009150) +2561 train 7.188879 (lr=7.9492e-05) (hash(x)=25256537) +2562 train 7.245702 (lr=7.9459e-05) (hash(x)=26564639) +2563 train 7.141736 (lr=7.9426e-05) (hash(x)=25290454) +2564 train 7.001990 (lr=7.9392e-05) (hash(x)=20763052) +2565 train 7.130435 (lr=7.9359e-05) (hash(x)=22481385) +2566 train 7.266097 (lr=7.9326e-05) (hash(x)=24594175) +2567 train 7.187111 (lr=7.9292e-05) (hash(x)=25699860) +2568 train 7.046445 (lr=7.9259e-05) (hash(x)=21538194) +2569 train 7.283809 (lr=7.9226e-05) (hash(x)=24776432) +2570 train 7.726623 (lr=7.9192e-05) (hash(x)=27952241) +2571 train 7.312758 (lr=7.9159e-05) (hash(x)=19919115) +2572 train 7.290566 (lr=7.9126e-05) (hash(x)=26105338) +2573 train 7.596270 (lr=7.9092e-05) (hash(x)=33107169) +2574 train 7.449737 (lr=7.9059e-05) (hash(x)=28823558) +2575 train 7.166577 (lr=7.9025e-05) (hash(x)=25586967) +2576 train 7.240879 (lr=7.8992e-05) (hash(x)=24609028) +2577 train 7.165030 (lr=7.8958e-05) (hash(x)=25317418) +2578 train 6.887137 (lr=7.8925e-05) (hash(x)=22025412) +2579 train 7.135890 (lr=7.8891e-05) (hash(x)=25373506) +2580 train 7.170462 (lr=7.8858e-05) (hash(x)=24226292) +2581 train 7.074203 (lr=7.8824e-05) (hash(x)=24099329) +2582 train 7.048363 (lr=7.8790e-05) (hash(x)=24350062) +2583 train 7.103444 (lr=7.8757e-05) (hash(x)=26496148) +2584 train 7.316407 (lr=7.8723e-05) (hash(x)=27625348) +2585 train 7.358396 (lr=7.8689e-05) (hash(x)=26240306) +2586 train 7.103921 (lr=7.8656e-05) (hash(x)=22788078) +2587 train 7.108786 (lr=7.8622e-05) (hash(x)=27395083) +2588 train 7.686983 (lr=7.8588e-05) (hash(x)=24962594) +2589 train 7.328556 (lr=7.8555e-05) (hash(x)=25664921) +2590 train 7.286868 (lr=7.8521e-05) (hash(x)=27454780) +2591 train 7.337517 (lr=7.8487e-05) (hash(x)=27389709) +2592 train 7.303250 (lr=7.8453e-05) (hash(x)=27094712) +2593 train 7.157904 (lr=7.8420e-05) (hash(x)=25036495) +2594 train 7.224780 (lr=7.8386e-05) (hash(x)=27088330) +2595 train 7.376536 (lr=7.8352e-05) (hash(x)=29172968) +2596 train 7.150148 (lr=7.8318e-05) (hash(x)=25995084) +2597 train 7.185501 (lr=7.8284e-05) (hash(x)=26559640) +2598 train 6.989820 (lr=7.8250e-05) (hash(x)=21968289) +2599 train 7.375011 (lr=7.8216e-05) (hash(x)=25464920) +2600 val loss 7.1450 +2600 val perplexity 1267.7380 +2600 train 7.433627 (lr=7.8182e-05) (hash(x)=27680219) +2601 train 7.193132 (lr=7.8148e-05) (hash(x)=25661701) +2602 train 7.243361 (lr=7.8114e-05) (hash(x)=24366700) +2603 train 7.060373 (lr=7.8080e-05) (hash(x)=25992320) +2604 train 7.601971 (lr=7.8046e-05) (hash(x)=29637054) +2605 train 7.187252 (lr=7.8012e-05) (hash(x)=25002688) +2606 train 7.037930 (lr=7.7978e-05) (hash(x)=26328463) +2607 train 6.998982 (lr=7.7944e-05) (hash(x)=24949509) +2608 train 6.995113 (lr=7.7910e-05) (hash(x)=23896318) +2609 train 7.540289 (lr=7.7876e-05) (hash(x)=32106793) +2610 train 7.274927 (lr=7.7842e-05) (hash(x)=22286002) +2611 train 7.154877 (lr=7.7808e-05) (hash(x)=25615151) +2612 train 7.060394 (lr=7.7774e-05) (hash(x)=25318304) +2613 train 7.393459 (lr=7.7740e-05) (hash(x)=31092520) +2614 train 7.163917 (lr=7.7705e-05) (hash(x)=25512238) +2615 train 7.178760 (lr=7.7671e-05) (hash(x)=27923548) +2616 train 7.285130 (lr=7.7637e-05) (hash(x)=26987079) +2617 train 7.068187 (lr=7.7603e-05) (hash(x)=20502148) +2618 train 7.289448 (lr=7.7569e-05) (hash(x)=25897090) +2619 train 7.340645 (lr=7.7534e-05) (hash(x)=26387848) +2620 train 7.174161 (lr=7.7500e-05) (hash(x)=25667615) +2621 train 7.346449 (lr=7.7466e-05) (hash(x)=27095086) +2622 train 7.150818 (lr=7.7431e-05) (hash(x)=22578578) +2623 train 7.024772 (lr=7.7397e-05) (hash(x)=22863518) +2624 train 7.127355 (lr=7.7363e-05) (hash(x)=24032373) +2625 train 7.082104 (lr=7.7328e-05) (hash(x)=22344972) +2626 train 7.159901 (lr=7.7294e-05) (hash(x)=26864577) +2627 train 7.151373 (lr=7.7260e-05) (hash(x)=20869581) +2628 train 7.317741 (lr=7.7225e-05) (hash(x)=26912443) +2629 train 7.648344 (lr=7.7191e-05) (hash(x)=30598301) +2630 train 7.302490 (lr=7.7156e-05) (hash(x)=24589527) +2631 train 6.911885 (lr=7.7122e-05) (hash(x)=18133606) +2632 train 7.168349 (lr=7.7087e-05) (hash(x)=25090392) +2633 train 7.135244 (lr=7.7053e-05) (hash(x)=25235010) +2634 train 7.052093 (lr=7.7018e-05) (hash(x)=24935365) +2635 train 7.294057 (lr=7.6984e-05) (hash(x)=28736122) +2636 train 6.890079 (lr=7.6949e-05) (hash(x)=18582531) +2637 train 7.285850 (lr=7.6914e-05) (hash(x)=31964687) +2638 train 7.278292 (lr=7.6880e-05) (hash(x)=26235680) +2639 train 7.158658 (lr=7.6845e-05) (hash(x)=25528329) +2640 train 7.134980 (lr=7.6811e-05) (hash(x)=24965563) +2641 train 7.341951 (lr=7.6776e-05) (hash(x)=25714091) +2642 train 7.371178 (lr=7.6741e-05) (hash(x)=27707039) +2643 train 6.999064 (lr=7.6707e-05) (hash(x)=24020765) +2644 train 7.193438 (lr=7.6672e-05) (hash(x)=26015275) +2645 train 7.224504 (lr=7.6637e-05) (hash(x)=25992253) +2646 train 7.288233 (lr=7.6603e-05) (hash(x)=25844953) +2647 train 7.374435 (lr=7.6568e-05) (hash(x)=27792245) +2648 train 7.278100 (lr=7.6533e-05) (hash(x)=24061711) +2649 train 7.377602 (lr=7.6498e-05) (hash(x)=26073593) +2650 val loss 7.1382 +2650 val perplexity 1259.1963 +2650 train 7.312843 (lr=7.6463e-05) (hash(x)=29291251) +2651 train 7.154681 (lr=7.6429e-05) (hash(x)=28287635) +2652 train 7.068658 (lr=7.6394e-05) (hash(x)=22377141) +2653 train 7.128459 (lr=7.6359e-05) (hash(x)=26552691) +2654 train 7.050528 (lr=7.6324e-05) (hash(x)=21087948) +2655 train 6.893328 (lr=7.6289e-05) (hash(x)=20951206) +2656 train 7.298576 (lr=7.6254e-05) (hash(x)=25424360) +2657 train 7.109382 (lr=7.6219e-05) (hash(x)=24242534) +2658 train 7.169592 (lr=7.6184e-05) (hash(x)=23296703) +2659 train 6.753182 (lr=7.6150e-05) (hash(x)=22356452) +2660 train 7.123079 (lr=7.6115e-05) (hash(x)=24132282) +2661 train 7.164443 (lr=7.6080e-05) (hash(x)=26498154) +2662 train 7.057655 (lr=7.6045e-05) (hash(x)=25971622) +2663 train 7.208268 (lr=7.6010e-05) (hash(x)=24385170) +2664 train 7.243530 (lr=7.5975e-05) (hash(x)=28607035) +2665 train 7.256281 (lr=7.5940e-05) (hash(x)=28364745) +2666 train 7.281982 (lr=7.5904e-05) (hash(x)=28992889) +2667 train 7.136155 (lr=7.5869e-05) (hash(x)=23455854) +2668 train 7.236181 (lr=7.5834e-05) (hash(x)=24714995) +2669 train 7.256351 (lr=7.5799e-05) (hash(x)=26454794) +2670 train 7.088077 (lr=7.5764e-05) (hash(x)=23191758) +2671 train 7.214157 (lr=7.5729e-05) (hash(x)=21589405) +2672 train 7.200648 (lr=7.5694e-05) (hash(x)=26344506) +2673 train 7.184308 (lr=7.5659e-05) (hash(x)=25445166) +2674 train 7.200822 (lr=7.5623e-05) (hash(x)=26743203) +2675 train 7.228069 (lr=7.5588e-05) (hash(x)=24698150) +2676 train 7.135400 (lr=7.5553e-05) (hash(x)=25678105) +2677 train 7.095736 (lr=7.5518e-05) (hash(x)=21795788) +2678 train 7.076100 (lr=7.5482e-05) (hash(x)=22670004) +2679 train 7.391670 (lr=7.5447e-05) (hash(x)=28010836) +2680 train 7.336234 (lr=7.5412e-05) (hash(x)=27401111) +2681 train 7.278785 (lr=7.5377e-05) (hash(x)=26255418) +2682 train 7.353325 (lr=7.5341e-05) (hash(x)=27086915) +2683 train 7.257329 (lr=7.5306e-05) (hash(x)=25427381) +2684 train 7.030216 (lr=7.5271e-05) (hash(x)=20350564) +2685 train 7.118751 (lr=7.5235e-05) (hash(x)=25804914) +2686 train 7.292121 (lr=7.5200e-05) (hash(x)=27781879) +2687 train 7.602841 (lr=7.5165e-05) (hash(x)=27478557) +2688 train 7.205929 (lr=7.5129e-05) (hash(x)=22915560) +2689 train 7.139463 (lr=7.5094e-05) (hash(x)=28532986) +2690 train 7.291741 (lr=7.5058e-05) (hash(x)=26294839) +2691 train 7.026261 (lr=7.5023e-05) (hash(x)=23865569) +2692 train 7.175889 (lr=7.4987e-05) (hash(x)=24164657) +2693 train 7.161234 (lr=7.4952e-05) (hash(x)=23365484) +2694 train 7.215548 (lr=7.4916e-05) (hash(x)=28053451) +2695 train 7.564241 (lr=7.4881e-05) (hash(x)=23407132) +2696 train 7.203429 (lr=7.4845e-05) (hash(x)=26820895) +2697 train 7.213493 (lr=7.4810e-05) (hash(x)=26750510) +2698 train 7.114863 (lr=7.4774e-05) (hash(x)=24131963) +2699 train 6.958038 (lr=7.4739e-05) (hash(x)=20253664) +2700 val loss 7.1198 +2700 val perplexity 1236.1774 +2700 train 7.359799 (lr=7.4703e-05) (hash(x)=31820468) +2701 train 7.067460 (lr=7.4667e-05) (hash(x)=24619408) +2702 train 7.087581 (lr=7.4632e-05) (hash(x)=24784107) +2703 train 6.905770 (lr=7.4596e-05) (hash(x)=21087928) +2704 train 7.169781 (lr=7.4560e-05) (hash(x)=25341703) +2705 train 7.301047 (lr=7.4525e-05) (hash(x)=28800595) +2706 train 7.205158 (lr=7.4489e-05) (hash(x)=25317118) +2707 train 7.022150 (lr=7.4453e-05) (hash(x)=25957589) +2708 train 7.117942 (lr=7.4418e-05) (hash(x)=25584592) +2709 train 7.126017 (lr=7.4382e-05) (hash(x)=24519649) +2710 train 7.046060 (lr=7.4346e-05) (hash(x)=24159131) +2711 train 7.247517 (lr=7.4310e-05) (hash(x)=27008610) +2712 train 7.141481 (lr=7.4275e-05) (hash(x)=25966593) +2713 train 7.316144 (lr=7.4239e-05) (hash(x)=25803040) +2714 train 7.282173 (lr=7.4203e-05) (hash(x)=26495218) +2715 train 7.142389 (lr=7.4167e-05) (hash(x)=27580265) +2716 train 7.323714 (lr=7.4131e-05) (hash(x)=30677288) +2717 train 7.277944 (lr=7.4096e-05) (hash(x)=29873037) +2718 train 7.245564 (lr=7.4060e-05) (hash(x)=26547966) +2719 train 7.093216 (lr=7.4024e-05) (hash(x)=24244798) +2720 train 7.209274 (lr=7.3988e-05) (hash(x)=25125564) +2721 train 7.116995 (lr=7.3952e-05) (hash(x)=22449713) +2722 train 7.051967 (lr=7.3916e-05) (hash(x)=24406712) +2723 train 7.022468 (lr=7.3880e-05) (hash(x)=24535871) +2724 train 7.295430 (lr=7.3844e-05) (hash(x)=26963614) +2725 train 7.453255 (lr=7.3808e-05) (hash(x)=30278191) +2726 train 7.087826 (lr=7.3772e-05) (hash(x)=25679475) +2727 train 7.178803 (lr=7.3736e-05) (hash(x)=27558681) +2728 train 7.112467 (lr=7.3700e-05) (hash(x)=25956094) +2729 train 7.167939 (lr=7.3664e-05) (hash(x)=25299486) +2730 train 7.157706 (lr=7.3628e-05) (hash(x)=23223432) +2731 train 6.998250 (lr=7.3592e-05) (hash(x)=21152793) +2732 train 7.072412 (lr=7.3556e-05) (hash(x)=26668399) +2733 train 7.124871 (lr=7.3520e-05) (hash(x)=24197830) +2734 train 7.004214 (lr=7.3484e-05) (hash(x)=21372114) +2735 train 7.109778 (lr=7.3448e-05) (hash(x)=28147005) +2736 train 7.148192 (lr=7.3412e-05) (hash(x)=26091722) +2737 train 7.316685 (lr=7.3375e-05) (hash(x)=27700158) +2738 train 7.097456 (lr=7.3339e-05) (hash(x)=23150914) +2739 train 7.134608 (lr=7.3303e-05) (hash(x)=21933180) +2740 train 6.964076 (lr=7.3267e-05) (hash(x)=28593884) +2741 train 7.144698 (lr=7.3231e-05) (hash(x)=23470482) +2742 train 7.190634 (lr=7.3195e-05) (hash(x)=22692875) +2743 train 7.262658 (lr=7.3158e-05) (hash(x)=24735895) +2744 train 7.395190 (lr=7.3122e-05) (hash(x)=26435203) +2745 train 7.055308 (lr=7.3086e-05) (hash(x)=22148167) +2746 train 7.083636 (lr=7.3050e-05) (hash(x)=23537482) +2747 train 7.163141 (lr=7.3013e-05) (hash(x)=26209948) +2748 train 7.529992 (lr=7.2977e-05) (hash(x)=27804754) +2749 train 7.140906 (lr=7.2941e-05) (hash(x)=25646265) +2750 val loss 7.1136 +2750 val perplexity 1228.5774 +2750 train 7.039555 (lr=7.2904e-05) (hash(x)=22778204) +2751 train 6.971928 (lr=7.2868e-05) (hash(x)=23358313) +2752 train 7.236411 (lr=7.2832e-05) (hash(x)=25138681) +2753 train 7.206803 (lr=7.2795e-05) (hash(x)=25220289) +2754 train 7.119372 (lr=7.2759e-05) (hash(x)=25250267) +2755 train 6.902025 (lr=7.2723e-05) (hash(x)=22398001) +2756 train 6.939284 (lr=7.2686e-05) (hash(x)=22961844) +2757 train 6.886943 (lr=7.2650e-05) (hash(x)=23695664) +2758 train 7.138713 (lr=7.2613e-05) (hash(x)=25646845) +2759 train 7.054502 (lr=7.2577e-05) (hash(x)=23724957) +2760 train 6.728616 (lr=7.2540e-05) (hash(x)=21856644) +2761 train 7.111165 (lr=7.2504e-05) (hash(x)=25267537) +2762 train 7.261471 (lr=7.2467e-05) (hash(x)=29361370) +2763 train 7.212037 (lr=7.2431e-05) (hash(x)=23083514) +2764 train 7.068272 (lr=7.2394e-05) (hash(x)=23833787) +2765 train 7.084921 (lr=7.2358e-05) (hash(x)=24396585) +2766 train 6.995615 (lr=7.2321e-05) (hash(x)=25984999) +2767 train 6.657747 (lr=7.2285e-05) (hash(x)=16016924) +2768 train 7.060876 (lr=7.2248e-05) (hash(x)=26986291) +2769 train 7.348170 (lr=7.2212e-05) (hash(x)=28879986) +2770 train 7.346087 (lr=7.2175e-05) (hash(x)=27981347) +2771 train 7.161458 (lr=7.2138e-05) (hash(x)=27173674) +2772 train 6.878279 (lr=7.2102e-05) (hash(x)=22205514) +2773 train 6.831034 (lr=7.2065e-05) (hash(x)=22231485) +2774 train 6.972695 (lr=7.2028e-05) (hash(x)=22986074) +2775 train 7.382450 (lr=7.1992e-05) (hash(x)=28056250) +2776 train 7.370347 (lr=7.1955e-05) (hash(x)=24387849) +2777 train 7.153148 (lr=7.1918e-05) (hash(x)=23755137) +2778 train 6.970447 (lr=7.1882e-05) (hash(x)=20487254) +2779 train 7.083184 (lr=7.1845e-05) (hash(x)=22233617) +2780 train 6.913477 (lr=7.1808e-05) (hash(x)=18599249) +2781 train 7.225690 (lr=7.1772e-05) (hash(x)=26090483) +2782 train 7.669339 (lr=7.1735e-05) (hash(x)=36705946) +2783 train 7.130580 (lr=7.1698e-05) (hash(x)=23777908) +2784 train 7.124979 (lr=7.1661e-05) (hash(x)=27222983) +2785 train 7.174994 (lr=7.1624e-05) (hash(x)=22709741) +2786 train 7.087955 (lr=7.1588e-05) (hash(x)=24900228) +2787 train 7.286755 (lr=7.1551e-05) (hash(x)=27842849) +2788 train 7.192001 (lr=7.1514e-05) (hash(x)=26932678) +2789 train 7.310761 (lr=7.1477e-05) (hash(x)=27855572) +2790 train 7.264565 (lr=7.1440e-05) (hash(x)=25188536) +2791 train 7.104185 (lr=7.1403e-05) (hash(x)=23711679) +2792 train 7.004334 (lr=7.1367e-05) (hash(x)=27589949) +2793 train 7.153604 (lr=7.1330e-05) (hash(x)=25543906) +2794 train 7.179337 (lr=7.1293e-05) (hash(x)=24766996) +2795 train 6.685174 (lr=7.1256e-05) (hash(x)=17204843) +2796 train 7.108594 (lr=7.1219e-05) (hash(x)=24751586) +2797 train 8.079808 (lr=7.1182e-05) (hash(x)=48147671) +2798 train 7.138357 (lr=7.1145e-05) (hash(x)=25435777) +2799 train 7.053960 (lr=7.1108e-05) (hash(x)=23909800) +2800 val loss 7.1131 +2800 val perplexity 1227.8875 +2800 train 7.109431 (lr=7.1071e-05) (hash(x)=28988340) +2801 train 7.179190 (lr=7.1034e-05) (hash(x)=24704097) +2802 train 7.171924 (lr=7.0997e-05) (hash(x)=23610257) +2803 train 7.219848 (lr=7.0960e-05) (hash(x)=25033286) +2804 train 7.769409 (lr=7.0923e-05) (hash(x)=28352541) +2805 train 7.697886 (lr=7.0886e-05) (hash(x)=24783577) +2806 train 7.315625 (lr=7.0849e-05) (hash(x)=24188526) +2807 train 7.110697 (lr=7.0812e-05) (hash(x)=23608371) +2808 train 7.379767 (lr=7.0775e-05) (hash(x)=24600812) +2809 train 7.099454 (lr=7.0738e-05) (hash(x)=25216084) +2810 train 7.201097 (lr=7.0701e-05) (hash(x)=25556167) +2811 train 7.390532 (lr=7.0663e-05) (hash(x)=23654625) +2812 train 7.200296 (lr=7.0626e-05) (hash(x)=25727830) +2813 train 7.069022 (lr=7.0589e-05) (hash(x)=25503100) +2814 train 6.966120 (lr=7.0552e-05) (hash(x)=23760249) +2815 train 7.097826 (lr=7.0515e-05) (hash(x)=22633313) +2816 train 7.252917 (lr=7.0478e-05) (hash(x)=26833493) +2817 train 7.178475 (lr=7.0441e-05) (hash(x)=27176235) +2818 train 7.127602 (lr=7.0403e-05) (hash(x)=27322950) +2819 train 7.004464 (lr=7.0366e-05) (hash(x)=24267011) +2820 train 7.322798 (lr=7.0329e-05) (hash(x)=26296064) +2821 train 6.808381 (lr=7.0292e-05) (hash(x)=21370796) +2822 train 7.217861 (lr=7.0254e-05) (hash(x)=28375028) +2823 train 6.963778 (lr=7.0217e-05) (hash(x)=23449416) +2824 train 7.112195 (lr=7.0180e-05) (hash(x)=25969848) +2825 train 7.309223 (lr=7.0143e-05) (hash(x)=26968187) +2826 train 7.532830 (lr=7.0105e-05) (hash(x)=27436973) +2827 train 7.437667 (lr=7.0068e-05) (hash(x)=28527906) +2828 train 7.100572 (lr=7.0031e-05) (hash(x)=23594458) +2829 train 6.990276 (lr=6.9993e-05) (hash(x)=21982691) +2830 train 7.081229 (lr=6.9956e-05) (hash(x)=25289815) +2831 train 7.001233 (lr=6.9919e-05) (hash(x)=21189075) +2832 train 6.981747 (lr=6.9881e-05) (hash(x)=22445556) +2833 train 7.068398 (lr=6.9844e-05) (hash(x)=25354290) +2834 train 7.184958 (lr=6.9806e-05) (hash(x)=30706366) +2835 train 7.160089 (lr=6.9769e-05) (hash(x)=25278645) +2836 train 7.817674 (lr=6.9732e-05) (hash(x)=32797871) +2837 train 7.794554 (lr=6.9694e-05) (hash(x)=31347747) +2838 train 7.365408 (lr=6.9657e-05) (hash(x)=23537177) +2839 train 7.116446 (lr=6.9619e-05) (hash(x)=23654290) +2840 train 7.033980 (lr=6.9582e-05) (hash(x)=23183433) +2841 train 7.141096 (lr=6.9544e-05) (hash(x)=25683179) +2842 train 7.169446 (lr=6.9507e-05) (hash(x)=23378935) +2843 train 7.113379 (lr=6.9469e-05) (hash(x)=24571139) +2844 train 7.129110 (lr=6.9432e-05) (hash(x)=25663997) +2845 train 7.113995 (lr=6.9394e-05) (hash(x)=25012625) +2846 train 7.294854 (lr=6.9357e-05) (hash(x)=24984061) +2847 train 7.198738 (lr=6.9319e-05) (hash(x)=26203172) +2848 train 7.138857 (lr=6.9282e-05) (hash(x)=22817936) +2849 train 7.233060 (lr=6.9244e-05) (hash(x)=28259689) +2850 val loss 7.1036 +2850 val perplexity 1216.3937 +2850 train 7.143612 (lr=6.9207e-05) (hash(x)=22454445) +2851 train 6.856483 (lr=6.9169e-05) (hash(x)=19623503) +2852 train 7.221316 (lr=6.9132e-05) (hash(x)=27559822) +2853 train 7.226075 (lr=6.9094e-05) (hash(x)=21925406) +2854 train 7.050541 (lr=6.9056e-05) (hash(x)=28415736) +2855 train 6.739853 (lr=6.9019e-05) (hash(x)=23970545) +2856 train 7.011313 (lr=6.8981e-05) (hash(x)=24222112) +2857 train 7.223263 (lr=6.8943e-05) (hash(x)=26075181) +2858 train 7.307463 (lr=6.8906e-05) (hash(x)=28695466) +2859 train 7.570036 (lr=6.8868e-05) (hash(x)=25724900) +2860 train 7.266008 (lr=6.8830e-05) (hash(x)=27577472) +2861 train 7.233219 (lr=6.8793e-05) (hash(x)=25450376) +2862 train 7.194363 (lr=6.8755e-05) (hash(x)=27632908) +2863 train 7.077578 (lr=6.8717e-05) (hash(x)=23245421) +2864 train 7.275576 (lr=6.8680e-05) (hash(x)=25708400) +2865 train 7.196597 (lr=6.8642e-05) (hash(x)=26868795) +2866 train 7.030096 (lr=6.8604e-05) (hash(x)=24631556) +2867 train 6.891261 (lr=6.8566e-05) (hash(x)=24087537) +2868 train 7.070589 (lr=6.8529e-05) (hash(x)=21207038) +2869 train 6.717180 (lr=6.8491e-05) (hash(x)=22792495) +2870 train 7.180302 (lr=6.8453e-05) (hash(x)=25409896) +2871 train 7.195190 (lr=6.8415e-05) (hash(x)=25549646) +2872 train 7.033807 (lr=6.8377e-05) (hash(x)=25413623) +2873 train 7.146914 (lr=6.8340e-05) (hash(x)=27281086) +2874 train 7.131459 (lr=6.8302e-05) (hash(x)=25711227) +2875 train 7.246386 (lr=6.8264e-05) (hash(x)=26406563) +2876 train 6.989913 (lr=6.8226e-05) (hash(x)=25407278) +2877 train 7.321360 (lr=6.8188e-05) (hash(x)=24171804) +2878 train 7.190355 (lr=6.8150e-05) (hash(x)=27612885) +2879 train 7.175694 (lr=6.8113e-05) (hash(x)=23972429) +2880 train 7.375980 (lr=6.8075e-05) (hash(x)=28743403) +2881 train 7.199496 (lr=6.8037e-05) (hash(x)=27360494) +2882 train 7.210298 (lr=6.7999e-05) (hash(x)=24859883) +2883 train 7.128422 (lr=6.7961e-05) (hash(x)=26378040) +2884 train 7.110373 (lr=6.7923e-05) (hash(x)=24744059) +2885 train 7.118390 (lr=6.7885e-05) (hash(x)=22806400) +2886 train 7.034291 (lr=6.7847e-05) (hash(x)=26899184) +2887 train 7.183012 (lr=6.7809e-05) (hash(x)=24618531) +2888 train 7.337387 (lr=6.7771e-05) (hash(x)=30193423) +2889 train 7.000320 (lr=6.7733e-05) (hash(x)=22365122) +2890 train 6.947804 (lr=6.7695e-05) (hash(x)=21689063) +2891 train 7.073735 (lr=6.7657e-05) (hash(x)=20135714) +2892 train 7.183514 (lr=6.7619e-05) (hash(x)=26104873) +2893 train 7.452075 (lr=6.7581e-05) (hash(x)=28352366) +2894 train 7.095661 (lr=6.7543e-05) (hash(x)=22710450) +2895 train 7.161798 (lr=6.7505e-05) (hash(x)=26490981) +2896 train 7.546399 (lr=6.7467e-05) (hash(x)=24864419) +2897 train 7.224113 (lr=6.7429e-05) (hash(x)=26473954) +2898 train 7.134730 (lr=6.7391e-05) (hash(x)=24326793) +2899 train 7.158359 (lr=6.7353e-05) (hash(x)=23927567) +2900 val loss 7.0987 +2900 val perplexity 1210.4012 +2900 train 7.145919 (lr=6.7315e-05) (hash(x)=26191045) +2901 train 7.095780 (lr=6.7277e-05) (hash(x)=23353619) +2902 train 7.005343 (lr=6.7239e-05) (hash(x)=27188285) +2903 train 7.144923 (lr=6.7201e-05) (hash(x)=27943609) +2904 train 7.164307 (lr=6.7162e-05) (hash(x)=24274388) +2905 train 6.901326 (lr=6.7124e-05) (hash(x)=22453474) +2906 train 7.379522 (lr=6.7086e-05) (hash(x)=31469316) +2907 train 7.078804 (lr=6.7048e-05) (hash(x)=22962561) +2908 train 7.139342 (lr=6.7010e-05) (hash(x)=23332118) +2909 train 7.251254 (lr=6.6972e-05) (hash(x)=27351426) +2910 train 7.216393 (lr=6.6933e-05) (hash(x)=24699099) +2911 train 7.167078 (lr=6.6895e-05) (hash(x)=24772257) +2912 train 7.133317 (lr=6.6857e-05) (hash(x)=26831636) +2913 train 6.886562 (lr=6.6819e-05) (hash(x)=21308028) +2914 train 7.288272 (lr=6.6781e-05) (hash(x)=25064642) +2915 train 7.113736 (lr=6.6742e-05) (hash(x)=25539761) +2916 train 7.304723 (lr=6.6704e-05) (hash(x)=26926121) +2917 train 7.393400 (lr=6.6666e-05) (hash(x)=26855802) +2918 train 7.426879 (lr=6.6628e-05) (hash(x)=29472224) +2919 train 6.963257 (lr=6.6589e-05) (hash(x)=23316262) +2920 train 7.080901 (lr=6.6551e-05) (hash(x)=25576111) +2921 train 6.863098 (lr=6.6513e-05) (hash(x)=21271807) +2922 train 7.002831 (lr=6.6475e-05) (hash(x)=24542517) +2923 train 7.177152 (lr=6.6436e-05) (hash(x)=23857558) +2924 train 7.285799 (lr=6.6398e-05) (hash(x)=29686711) +2925 train 7.295919 (lr=6.6360e-05) (hash(x)=26381255) +2926 train 7.062678 (lr=6.6321e-05) (hash(x)=28105073) +2927 train 7.178257 (lr=6.6283e-05) (hash(x)=30252690) +2928 train 7.279229 (lr=6.6245e-05) (hash(x)=25872958) +2929 train 6.973211 (lr=6.6206e-05) (hash(x)=23502359) +2930 train 7.493521 (lr=6.6168e-05) (hash(x)=30656009) +2931 train 7.437894 (lr=6.6130e-05) (hash(x)=30590162) +2932 train 7.301476 (lr=6.6091e-05) (hash(x)=25210533) +2933 train 7.198205 (lr=6.6053e-05) (hash(x)=24592932) +2934 train 7.037464 (lr=6.6015e-05) (hash(x)=23603016) +2935 train 7.164939 (lr=6.5976e-05) (hash(x)=25015721) +2936 train 7.305921 (lr=6.5938e-05) (hash(x)=28132535) +2937 train 7.342859 (lr=6.5899e-05) (hash(x)=25131959) +2938 train 7.117686 (lr=6.5861e-05) (hash(x)=21056777) +2939 train 7.250761 (lr=6.5822e-05) (hash(x)=28639679) +2940 train 7.174246 (lr=6.5784e-05) (hash(x)=24674878) +2941 train 7.014574 (lr=6.5746e-05) (hash(x)=23994413) +2942 train 7.134312 (lr=6.5707e-05) (hash(x)=27715763) +2943 train 7.144169 (lr=6.5669e-05) (hash(x)=26199058) +2944 train 7.240438 (lr=6.5630e-05) (hash(x)=26984744) +2945 train 7.265382 (lr=6.5592e-05) (hash(x)=28292328) +2946 train 6.966965 (lr=6.5553e-05) (hash(x)=22399977) +2947 train 7.212810 (lr=6.5515e-05) (hash(x)=28907461) +2948 train 6.868952 (lr=6.5476e-05) (hash(x)=19675299) +2949 train 7.213043 (lr=6.5438e-05) (hash(x)=25827028) +2950 val loss 7.0796 +2950 val perplexity 1187.4763 +2950 train 7.170292 (lr=6.5399e-05) (hash(x)=27871847) +2951 train 7.367013 (lr=6.5361e-05) (hash(x)=26466915) +2952 train 7.246146 (lr=6.5322e-05) (hash(x)=25495489) +2953 train 7.282350 (lr=6.5283e-05) (hash(x)=31790001) +2954 train 7.337534 (lr=6.5245e-05) (hash(x)=26613552) +2955 train 7.036229 (lr=6.5206e-05) (hash(x)=20332613) +2956 train 7.134063 (lr=6.5168e-05) (hash(x)=27031988) +2957 train 7.183058 (lr=6.5129e-05) (hash(x)=26669544) +2958 train 7.150077 (lr=6.5091e-05) (hash(x)=24124032) +2959 train 7.040040 (lr=6.5052e-05) (hash(x)=26766470) +2960 train 7.197265 (lr=6.5013e-05) (hash(x)=22993426) +2961 train 6.583334 (lr=6.4975e-05) (hash(x)=25199942) +2962 train 7.248134 (lr=6.4936e-05) (hash(x)=25162205) +2963 train 7.158560 (lr=6.4898e-05) (hash(x)=26722145) +2964 train 7.268967 (lr=6.4859e-05) (hash(x)=26409139) +2965 train 7.150236 (lr=6.4820e-05) (hash(x)=25974032) +2966 train 7.168652 (lr=6.4782e-05) (hash(x)=26149203) +2967 train 6.905927 (lr=6.4743e-05) (hash(x)=21222489) +2968 train 7.253827 (lr=6.4704e-05) (hash(x)=24867636) +2969 train 7.148646 (lr=6.4666e-05) (hash(x)=24233280) +2970 train 7.527970 (lr=6.4627e-05) (hash(x)=29172610) +2971 train 7.055676 (lr=6.4588e-05) (hash(x)=24662435) +2972 train 7.235189 (lr=6.4550e-05) (hash(x)=24363528) +2973 train 6.892556 (lr=6.4511e-05) (hash(x)=22803397) +2974 train 7.003064 (lr=6.4472e-05) (hash(x)=20510241) +2975 train 7.203615 (lr=6.4433e-05) (hash(x)=24308927) +2976 train 7.314330 (lr=6.4395e-05) (hash(x)=24909028) +2977 train 6.964289 (lr=6.4356e-05) (hash(x)=20018414) +2978 train 6.916954 (lr=6.4317e-05) (hash(x)=22885050) +2979 train 6.929680 (lr=6.4279e-05) (hash(x)=28442502) +2980 train 6.957334 (lr=6.4240e-05) (hash(x)=19111217) +2981 train 7.143986 (lr=6.4201e-05) (hash(x)=26005705) +2982 train 7.132718 (lr=6.4162e-05) (hash(x)=26355565) +2983 train 7.044518 (lr=6.4123e-05) (hash(x)=22810435) +2984 train 7.135304 (lr=6.4085e-05) (hash(x)=25613029) +2985 train 7.224648 (lr=6.4046e-05) (hash(x)=23706225) +2986 train 7.143549 (lr=6.4007e-05) (hash(x)=25469856) +2987 train 7.370838 (lr=6.3968e-05) (hash(x)=30486518) +2988 train 7.501690 (lr=6.3930e-05) (hash(x)=33354988) +2989 train 7.250714 (lr=6.3891e-05) (hash(x)=26566879) +2990 train 6.925130 (lr=6.3852e-05) (hash(x)=23919299) +2991 train 7.249581 (lr=6.3813e-05) (hash(x)=22688712) +2992 train 7.368007 (lr=6.3774e-05) (hash(x)=30642515) +2993 train 7.073614 (lr=6.3735e-05) (hash(x)=26847937) +2994 train 7.012392 (lr=6.3697e-05) (hash(x)=24177890) +2995 train 6.886161 (lr=6.3658e-05) (hash(x)=20712962) +2996 train 7.126774 (lr=6.3619e-05) (hash(x)=24910994) +2997 train 6.602560 (lr=6.3580e-05) (hash(x)=13526184) +2998 train 6.785256 (lr=6.3541e-05) (hash(x)=22334600) +2999 train 7.254969 (lr=6.3502e-05) (hash(x)=27490086) +3000 val loss 7.0705 +3000 val perplexity 1176.7810 +3000 train 6.833480 (lr=6.3463e-05) (hash(x)=21495031) +3001 train 7.018267 (lr=6.3424e-05) (hash(x)=25021203) +3002 train 6.969484 (lr=6.3385e-05) (hash(x)=25335474) +3003 train 6.993707 (lr=6.3347e-05) (hash(x)=23973908) +3004 train 7.005569 (lr=6.3308e-05) (hash(x)=21568359) +3005 train 7.024937 (lr=6.3269e-05) (hash(x)=24588031) +3006 train 7.116082 (lr=6.3230e-05) (hash(x)=23607819) +3007 train 7.294597 (lr=6.3191e-05) (hash(x)=29132401) +3008 train 7.058313 (lr=6.3152e-05) (hash(x)=28736940) +3009 train 7.180933 (lr=6.3113e-05) (hash(x)=25773639) +3010 train 7.117705 (lr=6.3074e-05) (hash(x)=26493275) +3011 train 7.090205 (lr=6.3035e-05) (hash(x)=27386700) +3012 train 7.522358 (lr=6.2996e-05) (hash(x)=29149408) +3013 train 6.926042 (lr=6.2957e-05) (hash(x)=25032643) +3014 train 7.056662 (lr=6.2918e-05) (hash(x)=25351040) +3015 train 7.120739 (lr=6.2879e-05) (hash(x)=24268614) +3016 train 7.195973 (lr=6.2840e-05) (hash(x)=26542132) +3017 train 7.249311 (lr=6.2801e-05) (hash(x)=27673003) +3018 train 7.224711 (lr=6.2762e-05) (hash(x)=26038620) +3019 train 7.144063 (lr=6.2723e-05) (hash(x)=27378387) +3020 train 7.005506 (lr=6.2684e-05) (hash(x)=24974861) +3021 train 6.936824 (lr=6.2645e-05) (hash(x)=24801098) +3022 train 6.961440 (lr=6.2606e-05) (hash(x)=23464631) +3023 train 7.005506 (lr=6.2567e-05) (hash(x)=22529400) +3024 train 6.867283 (lr=6.2528e-05) (hash(x)=22151422) +3025 train 6.958689 (lr=6.2489e-05) (hash(x)=22008715) +3026 train 7.225776 (lr=6.2450e-05) (hash(x)=28440666) +3027 train 7.192701 (lr=6.2411e-05) (hash(x)=27586989) +3028 train 7.125301 (lr=6.2372e-05) (hash(x)=21902541) +3029 train 7.001275 (lr=6.2333e-05) (hash(x)=23439588) +3030 train 6.998279 (lr=6.2294e-05) (hash(x)=21943405) +3031 train 6.926756 (lr=6.2255e-05) (hash(x)=22336349) +3032 train 7.250276 (lr=6.2216e-05) (hash(x)=25645313) +3033 train 6.843487 (lr=6.2176e-05) (hash(x)=22235357) +3034 train 6.962631 (lr=6.2137e-05) (hash(x)=22710523) +3035 train 7.120121 (lr=6.2098e-05) (hash(x)=26147854) +3036 train 6.978627 (lr=6.2059e-05) (hash(x)=21375006) +3037 train 7.232534 (lr=6.2020e-05) (hash(x)=28013003) +3038 train 7.158670 (lr=6.1981e-05) (hash(x)=27062804) +3039 train 7.122963 (lr=6.1942e-05) (hash(x)=25346788) +3040 train 6.949322 (lr=6.1903e-05) (hash(x)=24661327) +3041 train 7.177011 (lr=6.1863e-05) (hash(x)=29551719) +3042 train 7.352951 (lr=6.1824e-05) (hash(x)=34784102) +3043 train 7.357386 (lr=6.1785e-05) (hash(x)=25956855) +3044 train 6.899632 (lr=6.1746e-05) (hash(x)=22047289) +3045 train 7.231477 (lr=6.1707e-05) (hash(x)=28873527) +3046 train 7.171756 (lr=6.1668e-05) (hash(x)=25117562) +3047 train 7.206427 (lr=6.1629e-05) (hash(x)=24367780) +3048 train 6.882249 (lr=6.1589e-05) (hash(x)=24831846) +3049 train 7.117007 (lr=6.1550e-05) (hash(x)=27682151) +3050 val loss 7.0638 +3050 val perplexity 1168.8978 +3050 train 7.083647 (lr=6.1511e-05) (hash(x)=22223775) +3051 train 7.043193 (lr=6.1472e-05) (hash(x)=26084462) +3052 train 7.249960 (lr=6.1433e-05) (hash(x)=29273202) +3053 train 7.105753 (lr=6.1393e-05) (hash(x)=24782887) +3054 train 6.978706 (lr=6.1354e-05) (hash(x)=20434348) +3055 train 7.154954 (lr=6.1315e-05) (hash(x)=26702459) +3056 train 7.015691 (lr=6.1276e-05) (hash(x)=26194884) +3057 train 6.985871 (lr=6.1237e-05) (hash(x)=25413684) +3058 train 7.143908 (lr=6.1197e-05) (hash(x)=23691848) +3059 train 7.038680 (lr=6.1158e-05) (hash(x)=25717976) +3060 train 7.024402 (lr=6.1119e-05) (hash(x)=25634206) +3061 train 6.866108 (lr=6.1080e-05) (hash(x)=20092522) +3062 train 7.091331 (lr=6.1040e-05) (hash(x)=24098395) +3063 train 6.930559 (lr=6.1001e-05) (hash(x)=22141366) +3064 train 7.246756 (lr=6.0962e-05) (hash(x)=25195782) +3065 train 7.247055 (lr=6.0923e-05) (hash(x)=25655198) +3066 train 7.130992 (lr=6.0883e-05) (hash(x)=23104704) +3067 train 7.152681 (lr=6.0844e-05) (hash(x)=24652423) +3068 train 7.093440 (lr=6.0805e-05) (hash(x)=26098808) +3069 train 7.042016 (lr=6.0766e-05) (hash(x)=24387630) +3070 train 7.102718 (lr=6.0726e-05) (hash(x)=25565362) +3071 train 7.357607 (lr=6.0687e-05) (hash(x)=30911699) +3072 train 7.104855 (lr=6.0648e-05) (hash(x)=23108416) +3073 train 6.969051 (lr=6.0609e-05) (hash(x)=25683298) +3074 train 7.255268 (lr=6.0569e-05) (hash(x)=25035622) +3075 train 7.155193 (lr=6.0530e-05) (hash(x)=22076954) +3076 train 6.919008 (lr=6.0491e-05) (hash(x)=25936067) +3077 train 7.539710 (lr=6.0451e-05) (hash(x)=31181390) +3078 train 7.595080 (lr=6.0412e-05) (hash(x)=30427728) +3079 train 7.090101 (lr=6.0373e-05) (hash(x)=21586769) +3080 train 7.606948 (lr=6.0333e-05) (hash(x)=34422021) +3081 train 6.887702 (lr=6.0294e-05) (hash(x)=23624698) +3082 train 7.035964 (lr=6.0255e-05) (hash(x)=26759098) +3083 train 7.062651 (lr=6.0215e-05) (hash(x)=21994337) +3084 train 6.917957 (lr=6.0176e-05) (hash(x)=22673785) +3085 train 7.302892 (lr=6.0137e-05) (hash(x)=28469977) +3086 train 7.076916 (lr=6.0097e-05) (hash(x)=24847065) +3087 train 7.146261 (lr=6.0058e-05) (hash(x)=25454145) +3088 train 7.020196 (lr=6.0019e-05) (hash(x)=26065968) +3089 train 6.912988 (lr=5.9979e-05) (hash(x)=21129257) +3090 train 7.321800 (lr=5.9940e-05) (hash(x)=30436197) +3091 train 7.276009 (lr=5.9901e-05) (hash(x)=23239550) +3092 train 7.466880 (lr=5.9861e-05) (hash(x)=26579905) +3093 train 7.273931 (lr=5.9822e-05) (hash(x)=27585808) +3094 train 7.097183 (lr=5.9783e-05) (hash(x)=27227738) +3095 train 7.016455 (lr=5.9743e-05) (hash(x)=23565926) +3096 train 6.921458 (lr=5.9704e-05) (hash(x)=19742002) +3097 train 6.975246 (lr=5.9664e-05) (hash(x)=25975387) +3098 train 7.295929 (lr=5.9625e-05) (hash(x)=27889390) +3099 train 7.004890 (lr=5.9586e-05) (hash(x)=24705563) +3100 val loss 7.0651 +3100 val perplexity 1170.3484 +3100 train 6.981955 (lr=5.9546e-05) (hash(x)=23338227) +3101 train 7.060351 (lr=5.9507e-05) (hash(x)=25184317) +3102 train 6.903929 (lr=5.9467e-05) (hash(x)=22183319) +3103 train 7.613403 (lr=5.9428e-05) (hash(x)=27671095) +3104 train 7.674304 (lr=5.9389e-05) (hash(x)=28244583) +3105 train 7.118837 (lr=5.9349e-05) (hash(x)=25646369) +3106 train 7.189912 (lr=5.9310e-05) (hash(x)=26879691) +3107 train 7.124923 (lr=5.9270e-05) (hash(x)=26254303) +3108 train 7.003799 (lr=5.9231e-05) (hash(x)=24095204) +3109 train 7.071867 (lr=5.9192e-05) (hash(x)=22812689) +3110 train 6.905422 (lr=5.9152e-05) (hash(x)=21647865) +3111 train 7.063748 (lr=5.9113e-05) (hash(x)=27454020) +3112 train 7.070248 (lr=5.9073e-05) (hash(x)=25030447) +3113 train 7.059807 (lr=5.9034e-05) (hash(x)=24788080) +3114 train 6.948843 (lr=5.8994e-05) (hash(x)=21735476) +3115 train 6.943042 (lr=5.8955e-05) (hash(x)=24394565) +3116 train 6.846053 (lr=5.8915e-05) (hash(x)=24642575) +3117 train 6.929960 (lr=5.8876e-05) (hash(x)=23961786) +3118 train 6.948310 (lr=5.8837e-05) (hash(x)=21408799) +3119 train 6.951184 (lr=5.8797e-05) (hash(x)=21780199) +3120 train 7.000794 (lr=5.8758e-05) (hash(x)=21526613) +3121 train 7.095047 (lr=5.8718e-05) (hash(x)=24418202) +3122 train 6.862711 (lr=5.8679e-05) (hash(x)=21109230) +3123 train 7.178697 (lr=5.8639e-05) (hash(x)=28296896) +3124 train 7.216402 (lr=5.8600e-05) (hash(x)=27248343) +3125 train 6.891456 (lr=5.8560e-05) (hash(x)=21091322) +3126 train 7.301996 (lr=5.8521e-05) (hash(x)=34998924) +3127 train 7.354755 (lr=5.8481e-05) (hash(x)=26766303) +3128 train 7.090303 (lr=5.8442e-05) (hash(x)=24526029) +3129 train 7.046604 (lr=5.8402e-05) (hash(x)=26470612) +3130 train 7.064979 (lr=5.8363e-05) (hash(x)=25031689) +3131 train 6.961995 (lr=5.8323e-05) (hash(x)=21599973) +3132 train 7.735252 (lr=5.8284e-05) (hash(x)=36255638) +3133 train 7.292521 (lr=5.8244e-05) (hash(x)=31207925) +3134 train 7.188593 (lr=5.8205e-05) (hash(x)=22962349) +3135 train 7.102589 (lr=5.8165e-05) (hash(x)=24969360) +3136 train 6.832817 (lr=5.8126e-05) (hash(x)=21506615) +3137 train 8.581432 (lr=5.8086e-05) (hash(x)=41298231) +3138 train 6.906928 (lr=5.8047e-05) (hash(x)=23851179) +3139 train 7.007612 (lr=5.8007e-05) (hash(x)=24382006) +3140 train 7.075797 (lr=5.7968e-05) (hash(x)=25856060) +3141 train 6.795348 (lr=5.7928e-05) (hash(x)=23267882) +3142 train 7.151570 (lr=5.7889e-05) (hash(x)=21416998) +3143 train 6.850509 (lr=5.7849e-05) (hash(x)=22009299) +3144 train 6.476461 (lr=5.7810e-05) (hash(x)=14030305) +3145 train 6.834867 (lr=5.7770e-05) (hash(x)=23980457) +3146 train 6.899731 (lr=5.7731e-05) (hash(x)=23808351) +3147 train 6.917997 (lr=5.7691e-05) (hash(x)=22376569) +3148 train 6.996455 (lr=5.7652e-05) (hash(x)=25235353) +3149 train 7.025919 (lr=5.7612e-05) (hash(x)=25511406) +3150 val loss 7.0609 +3150 val perplexity 1165.4817 +3150 train 6.885031 (lr=5.7573e-05) (hash(x)=24295759) +3151 train 7.036718 (lr=5.7533e-05) (hash(x)=28166843) +3152 train 7.134992 (lr=5.7494e-05) (hash(x)=26005029) +3153 train 7.104211 (lr=5.7454e-05) (hash(x)=25581630) +3154 train 7.078456 (lr=5.7414e-05) (hash(x)=26068290) +3155 train 7.806046 (lr=5.7375e-05) (hash(x)=28230119) +3156 train 7.300308 (lr=5.7335e-05) (hash(x)=24497579) +3157 train 7.163908 (lr=5.7296e-05) (hash(x)=26479441) +3158 train 7.281183 (lr=5.7256e-05) (hash(x)=23940105) +3159 train 7.185017 (lr=5.7217e-05) (hash(x)=26207465) +3160 train 7.706760 (lr=5.7177e-05) (hash(x)=34020077) +3161 train 7.382083 (lr=5.7138e-05) (hash(x)=25903778) +3162 train 7.084586 (lr=5.7098e-05) (hash(x)=24463061) +3163 train 7.045472 (lr=5.7058e-05) (hash(x)=24748118) +3164 train 7.323070 (lr=5.7019e-05) (hash(x)=36051125) +3165 train 7.118176 (lr=5.6979e-05) (hash(x)=25300507) +3166 train 7.133942 (lr=5.6940e-05) (hash(x)=28076910) +3167 train 7.228106 (lr=5.6900e-05) (hash(x)=27033802) +3168 train 7.399522 (lr=5.6861e-05) (hash(x)=30388751) +3169 train 6.993217 (lr=5.6821e-05) (hash(x)=24888803) +3170 train 7.056894 (lr=5.6782e-05) (hash(x)=21911287) +3171 train 7.066662 (lr=5.6742e-05) (hash(x)=28788047) +3172 train 7.057181 (lr=5.6702e-05) (hash(x)=24915549) +3173 train 7.012778 (lr=5.6663e-05) (hash(x)=23609078) +3174 train 6.987920 (lr=5.6623e-05) (hash(x)=27036363) +3175 train 6.865319 (lr=5.6584e-05) (hash(x)=22185099) +3176 train 7.584452 (lr=5.6544e-05) (hash(x)=31299333) +3177 train 7.212507 (lr=5.6505e-05) (hash(x)=26805248) +3178 train 6.959774 (lr=5.6465e-05) (hash(x)=23530260) +3179 train 7.030415 (lr=5.6425e-05) (hash(x)=21585136) +3180 train 7.071499 (lr=5.6386e-05) (hash(x)=26577204) +3181 train 6.815914 (lr=5.6346e-05) (hash(x)=21098074) +3182 train 7.009998 (lr=5.6307e-05) (hash(x)=24719109) +3183 train 7.182714 (lr=5.6267e-05) (hash(x)=27691968) +3184 train 7.167598 (lr=5.6227e-05) (hash(x)=25616543) +3185 train 6.965566 (lr=5.6188e-05) (hash(x)=22407092) +3186 train 7.041196 (lr=5.6148e-05) (hash(x)=23057931) +3187 train 7.007481 (lr=5.6109e-05) (hash(x)=23706103) +3188 train 6.779938 (lr=5.6069e-05) (hash(x)=20986476) +3189 train 6.789217 (lr=5.6030e-05) (hash(x)=25335816) +3190 train 7.008707 (lr=5.5990e-05) (hash(x)=20620920) +3191 train 6.970979 (lr=5.5950e-05) (hash(x)=27918030) +3192 train 7.285606 (lr=5.5911e-05) (hash(x)=25706727) +3193 train 7.037993 (lr=5.5871e-05) (hash(x)=23707924) +3194 train 7.228066 (lr=5.5832e-05) (hash(x)=22929819) +3195 train 6.923023 (lr=5.5792e-05) (hash(x)=23127886) +3196 train 6.975598 (lr=5.5752e-05) (hash(x)=26921653) +3197 train 7.306389 (lr=5.5713e-05) (hash(x)=30330131) +3198 train 7.240682 (lr=5.5673e-05) (hash(x)=25553105) +3199 train 7.039191 (lr=5.5634e-05) (hash(x)=26197070) +3200 val loss 7.0520 +3200 val perplexity 1155.1608 +3200 train 7.317898 (lr=5.5594e-05) (hash(x)=30227184) +3201 train 7.126397 (lr=5.5554e-05) (hash(x)=26375139) +3202 train 7.193658 (lr=5.5515e-05) (hash(x)=25590383) +3203 train 7.075184 (lr=5.5475e-05) (hash(x)=26463005) +3204 train 7.156113 (lr=5.5436e-05) (hash(x)=29629632) +3205 train 7.253687 (lr=5.5396e-05) (hash(x)=31602829) +3206 train 6.957973 (lr=5.5356e-05) (hash(x)=23820121) +3207 train 6.943742 (lr=5.5317e-05) (hash(x)=19160134) +3208 train 7.253316 (lr=5.5277e-05) (hash(x)=29638766) +3209 train 6.938910 (lr=5.5238e-05) (hash(x)=24597655) +3210 train 6.883130 (lr=5.5198e-05) (hash(x)=24664066) +3211 train 7.101751 (lr=5.5158e-05) (hash(x)=23699136) +3212 train 7.044877 (lr=5.5119e-05) (hash(x)=26303417) +3213 train 7.077448 (lr=5.5079e-05) (hash(x)=26748789) +3214 train 7.081821 (lr=5.5040e-05) (hash(x)=22716410) +3215 train 7.162025 (lr=5.5000e-05) (hash(x)=25353051) +3216 train 7.168632 (lr=5.4960e-05) (hash(x)=24557361) +3217 train 7.076397 (lr=5.4921e-05) (hash(x)=24780312) +3218 train 7.001111 (lr=5.4881e-05) (hash(x)=27148011) +3219 train 6.880056 (lr=5.4842e-05) (hash(x)=21558484) +3220 train 7.016747 (lr=5.4802e-05) (hash(x)=23347051) +3221 train 6.803345 (lr=5.4762e-05) (hash(x)=21468281) +3222 train 6.954985 (lr=5.4723e-05) (hash(x)=24815837) +3223 train 7.052740 (lr=5.4683e-05) (hash(x)=22828380) +3224 train 7.072252 (lr=5.4644e-05) (hash(x)=25479526) +3225 train 6.716595 (lr=5.4604e-05) (hash(x)=19071259) +3226 train 7.199160 (lr=5.4564e-05) (hash(x)=25496699) +3227 train 7.180113 (lr=5.4525e-05) (hash(x)=24623811) +3228 train 7.235985 (lr=5.4485e-05) (hash(x)=33758715) +3229 train 7.260635 (lr=5.4446e-05) (hash(x)=24877432) +3230 train 7.198291 (lr=5.4406e-05) (hash(x)=27908161) +3231 train 7.213285 (lr=5.4366e-05) (hash(x)=25410299) +3232 train 7.057876 (lr=5.4327e-05) (hash(x)=23941914) +3233 train 7.075563 (lr=5.4287e-05) (hash(x)=23472652) +3234 train 7.031828 (lr=5.4248e-05) (hash(x)=25984122) +3235 train 7.243257 (lr=5.4208e-05) (hash(x)=26046091) +3236 train 7.512278 (lr=5.4168e-05) (hash(x)=30660596) +3237 train 7.084706 (lr=5.4129e-05) (hash(x)=25823748) +3238 train 6.917494 (lr=5.4089e-05) (hash(x)=23683470) +3239 train 7.372498 (lr=5.4050e-05) (hash(x)=29887482) +3240 train 7.039867 (lr=5.4010e-05) (hash(x)=22313381) +3241 train 6.898648 (lr=5.3970e-05) (hash(x)=23604733) +3242 train 6.873994 (lr=5.3931e-05) (hash(x)=23457146) +3243 train 7.000731 (lr=5.3891e-05) (hash(x)=21809706) +3244 train 7.311467 (lr=5.3852e-05) (hash(x)=29867000) +3245 train 7.239337 (lr=5.3812e-05) (hash(x)=26739602) +3246 train 6.920229 (lr=5.3773e-05) (hash(x)=23270777) +3247 train 6.902588 (lr=5.3733e-05) (hash(x)=23712872) +3248 train 7.067240 (lr=5.3693e-05) (hash(x)=26485865) +3249 train 6.793910 (lr=5.3654e-05) (hash(x)=23412256) +3250 val loss 7.0480 +3250 val perplexity 1150.5009 +3250 train 7.116586 (lr=5.3614e-05) (hash(x)=27193330) +3251 train 6.918986 (lr=5.3575e-05) (hash(x)=25875103) +3252 train 7.010747 (lr=5.3535e-05) (hash(x)=23708477) +3253 train 6.970057 (lr=5.3495e-05) (hash(x)=26452480) +3254 train 6.787685 (lr=5.3456e-05) (hash(x)=20562478) +3255 train 6.970342 (lr=5.3416e-05) (hash(x)=23736441) +3256 train 6.914515 (lr=5.3377e-05) (hash(x)=23908899) +3257 train 7.003254 (lr=5.3337e-05) (hash(x)=23730269) +3258 train 7.162685 (lr=5.3298e-05) (hash(x)=24825774) +3259 train 7.051586 (lr=5.3258e-05) (hash(x)=25093883) +3260 train 6.935509 (lr=5.3218e-05) (hash(x)=24709218) +3261 train 7.060837 (lr=5.3179e-05) (hash(x)=25880656) +3262 train 6.985859 (lr=5.3139e-05) (hash(x)=22967282) +3263 train 6.942455 (lr=5.3100e-05) (hash(x)=23692325) +3264 train 6.847132 (lr=5.3060e-05) (hash(x)=21861732) +3265 train 6.801069 (lr=5.3021e-05) (hash(x)=19897671) +3266 train 6.938746 (lr=5.2981e-05) (hash(x)=22770802) +3267 train 6.874383 (lr=5.2942e-05) (hash(x)=23061082) +3268 train 6.917635 (lr=5.2902e-05) (hash(x)=23495551) +3269 train 6.936480 (lr=5.2862e-05) (hash(x)=25016605) +3270 train 7.080236 (lr=5.2823e-05) (hash(x)=24414422) +3271 train 7.132563 (lr=5.2783e-05) (hash(x)=26094253) +3272 train 6.934623 (lr=5.2744e-05) (hash(x)=23235796) +3273 train 7.081641 (lr=5.2704e-05) (hash(x)=26257920) +3274 train 7.160674 (lr=5.2665e-05) (hash(x)=26109537) +3275 train 7.388673 (lr=5.2625e-05) (hash(x)=27327886) +3276 train 6.989637 (lr=5.2586e-05) (hash(x)=24031809) +3277 train 6.947139 (lr=5.2546e-05) (hash(x)=17980284) +3278 train 7.058540 (lr=5.2506e-05) (hash(x)=24328670) +3279 train 7.159397 (lr=5.2467e-05) (hash(x)=26186143) +3280 train 6.985338 (lr=5.2427e-05) (hash(x)=23620433) +3281 train 7.006047 (lr=5.2388e-05) (hash(x)=26383776) +3282 train 6.980510 (lr=5.2348e-05) (hash(x)=25119724) +3283 train 7.109516 (lr=5.2309e-05) (hash(x)=25336043) +3284 train 7.162280 (lr=5.2269e-05) (hash(x)=29533717) +3285 train 7.009147 (lr=5.2230e-05) (hash(x)=25878996) +3286 train 7.052569 (lr=5.2190e-05) (hash(x)=23302539) +3287 train 7.059145 (lr=5.2151e-05) (hash(x)=22811468) +3288 train 6.952055 (lr=5.2111e-05) (hash(x)=21672176) +3289 train 6.996230 (lr=5.2072e-05) (hash(x)=21632628) +3290 train 6.960443 (lr=5.2032e-05) (hash(x)=25568414) +3291 train 7.333171 (lr=5.1993e-05) (hash(x)=27925831) +3292 train 7.186440 (lr=5.1953e-05) (hash(x)=28006499) +3293 train 6.939250 (lr=5.1914e-05) (hash(x)=23914950) +3294 train 7.074133 (lr=5.1874e-05) (hash(x)=24532165) +3295 train 7.389215 (lr=5.1835e-05) (hash(x)=35528108) +3296 train 7.120163 (lr=5.1795e-05) (hash(x)=20757754) +3297 train 7.009212 (lr=5.1756e-05) (hash(x)=25766841) +3298 train 7.058306 (lr=5.1716e-05) (hash(x)=24998585) +3299 train 7.320002 (lr=5.1677e-05) (hash(x)=24949421) +3300 val loss 7.0362 +3300 val perplexity 1137.0532 +3300 train 6.904527 (lr=5.1637e-05) (hash(x)=27849873) +3301 train 6.889128 (lr=5.1598e-05) (hash(x)=22078476) +3302 train 6.789419 (lr=5.1558e-05) (hash(x)=24495589) +3303 train 6.935535 (lr=5.1519e-05) (hash(x)=22845735) +3304 train 6.921756 (lr=5.1479e-05) (hash(x)=24322392) +3305 train 6.760559 (lr=5.1440e-05) (hash(x)=22161685) +3306 train 7.091697 (lr=5.1400e-05) (hash(x)=24755182) +3307 train 7.224423 (lr=5.1361e-05) (hash(x)=28138281) +3308 train 6.909122 (lr=5.1321e-05) (hash(x)=24707707) +3309 train 7.043723 (lr=5.1282e-05) (hash(x)=25747726) +3310 train 7.185359 (lr=5.1242e-05) (hash(x)=27027610) +3311 train 7.120043 (lr=5.1203e-05) (hash(x)=29038360) +3312 train 6.997764 (lr=5.1163e-05) (hash(x)=23238597) +3313 train 7.068131 (lr=5.1124e-05) (hash(x)=25751789) +3314 train 7.042071 (lr=5.1085e-05) (hash(x)=25766851) +3315 train 7.043346 (lr=5.1045e-05) (hash(x)=22827903) +3316 train 6.889724 (lr=5.1006e-05) (hash(x)=24421917) +3317 train 7.235100 (lr=5.0966e-05) (hash(x)=27684827) +3318 train 7.045572 (lr=5.0927e-05) (hash(x)=29121769) +3319 train 7.227843 (lr=5.0887e-05) (hash(x)=24647015) +3320 train 7.144913 (lr=5.0848e-05) (hash(x)=27728407) +3321 train 7.047964 (lr=5.0808e-05) (hash(x)=25635037) +3322 train 7.000487 (lr=5.0769e-05) (hash(x)=24756433) +3323 train 6.802424 (lr=5.0730e-05) (hash(x)=20477804) +3324 train 7.017987 (lr=5.0690e-05) (hash(x)=25480910) +3325 train 6.884693 (lr=5.0651e-05) (hash(x)=23226570) +3326 train 6.817525 (lr=5.0611e-05) (hash(x)=21354883) +3327 train 7.125363 (lr=5.0572e-05) (hash(x)=26692640) +3328 train 6.898609 (lr=5.0533e-05) (hash(x)=22755928) +3329 train 7.223949 (lr=5.0493e-05) (hash(x)=30505094) +3330 train 6.880313 (lr=5.0454e-05) (hash(x)=18352418) +3331 train 7.222175 (lr=5.0414e-05) (hash(x)=27388794) +3332 train 7.435069 (lr=5.0375e-05) (hash(x)=26251471) +3333 train 7.240795 (lr=5.0336e-05) (hash(x)=26464796) +3334 train 7.290353 (lr=5.0296e-05) (hash(x)=35216057) +3335 train 7.262412 (lr=5.0257e-05) (hash(x)=25265875) +3336 train 7.142174 (lr=5.0217e-05) (hash(x)=24613853) +3337 train 6.993114 (lr=5.0178e-05) (hash(x)=25144290) +3338 train 6.935064 (lr=5.0139e-05) (hash(x)=25961546) +3339 train 6.831015 (lr=5.0099e-05) (hash(x)=21841888) +3340 train 7.301369 (lr=5.0060e-05) (hash(x)=29479990) +3341 train 7.061290 (lr=5.0021e-05) (hash(x)=26454000) +3342 train 6.887791 (lr=4.9981e-05) (hash(x)=23387126) +3343 train 6.963981 (lr=4.9942e-05) (hash(x)=19809196) +3344 train 7.799233 (lr=4.9903e-05) (hash(x)=32976656) +3345 train 6.935190 (lr=4.9863e-05) (hash(x)=21882489) +3346 train 6.983994 (lr=4.9824e-05) (hash(x)=22792760) +3347 train 6.868369 (lr=4.9785e-05) (hash(x)=23007945) +3348 train 7.221648 (lr=4.9745e-05) (hash(x)=27150582) +3349 train 6.969105 (lr=4.9706e-05) (hash(x)=21321491) +3350 val loss 7.0345 +3350 val perplexity 1135.1517 +3350 train 7.067655 (lr=4.9667e-05) (hash(x)=25070101) +3351 train 7.042022 (lr=4.9627e-05) (hash(x)=24079409) +3352 train 6.993802 (lr=4.9588e-05) (hash(x)=26192970) +3353 train 7.033311 (lr=4.9549e-05) (hash(x)=27458572) +3354 train 6.990561 (lr=4.9509e-05) (hash(x)=24719147) +3355 train 7.055043 (lr=4.9470e-05) (hash(x)=25874533) +3356 train 6.908219 (lr=4.9431e-05) (hash(x)=22668921) +3357 train 7.023440 (lr=4.9391e-05) (hash(x)=24203734) +3358 train 6.867283 (lr=4.9352e-05) (hash(x)=23390948) +3359 train 6.891124 (lr=4.9313e-05) (hash(x)=23660106) +3360 train 7.080787 (lr=4.9274e-05) (hash(x)=24913248) +3361 train 6.999951 (lr=4.9234e-05) (hash(x)=24560828) +3362 train 6.971600 (lr=4.9195e-05) (hash(x)=24651947) +3363 train 8.534739 (lr=4.9156e-05) (hash(x)=41821329) +3364 train 7.531628 (lr=4.9117e-05) (hash(x)=21023418) +3365 train 6.912955 (lr=4.9077e-05) (hash(x)=22773275) +3366 train 6.722629 (lr=4.9038e-05) (hash(x)=23140594) +3367 train 6.994877 (lr=4.8999e-05) (hash(x)=25763899) +3368 train 6.930009 (lr=4.8960e-05) (hash(x)=19159140) +3369 train 6.761847 (lr=4.8920e-05) (hash(x)=21182890) +3370 train 6.886913 (lr=4.8881e-05) (hash(x)=21066030) +3371 train 6.995246 (lr=4.8842e-05) (hash(x)=28584111) +3372 train 7.315542 (lr=4.8803e-05) (hash(x)=25984822) +3373 train 7.381159 (lr=4.8763e-05) (hash(x)=28121891) +3374 train 7.303965 (lr=4.8724e-05) (hash(x)=31680444) +3375 train 7.383036 (lr=4.8685e-05) (hash(x)=25559887) +3376 train 7.187758 (lr=4.8646e-05) (hash(x)=24885474) +3377 train 7.352780 (lr=4.8607e-05) (hash(x)=28704301) +3378 train 6.970425 (lr=4.8567e-05) (hash(x)=25777437) +3379 train 7.032382 (lr=4.8528e-05) (hash(x)=26886377) +3380 train 7.063574 (lr=4.8489e-05) (hash(x)=20865187) +3381 train 6.874053 (lr=4.8450e-05) (hash(x)=20211916) +3382 train 7.086098 (lr=4.8411e-05) (hash(x)=29358238) +3383 train 7.356088 (lr=4.8371e-05) (hash(x)=26461895) +3384 train 6.983999 (lr=4.8332e-05) (hash(x)=25305290) +3385 train 7.129596 (lr=4.8293e-05) (hash(x)=27618136) +3386 train 7.201121 (lr=4.8254e-05) (hash(x)=28828628) +3387 train 7.204042 (lr=4.8215e-05) (hash(x)=23018827) +3388 train 6.930276 (lr=4.8176e-05) (hash(x)=23247351) +3389 train 6.907752 (lr=4.8137e-05) (hash(x)=24662809) +3390 train 6.872720 (lr=4.8097e-05) (hash(x)=23802669) +3391 train 7.019616 (lr=4.8058e-05) (hash(x)=24375035) +3392 train 6.842764 (lr=4.8019e-05) (hash(x)=22905287) +3393 train 7.159176 (lr=4.7980e-05) (hash(x)=25006551) +3394 train 7.224483 (lr=4.7941e-05) (hash(x)=26876607) +3395 train 7.095677 (lr=4.7902e-05) (hash(x)=26431670) +3396 train 6.982816 (lr=4.7863e-05) (hash(x)=27288095) +3397 train 6.985673 (lr=4.7824e-05) (hash(x)=25525366) +3398 train 6.668773 (lr=4.7784e-05) (hash(x)=18705467) +3399 train 7.108893 (lr=4.7745e-05) (hash(x)=25033511) +3400 val loss 7.0272 +3400 val perplexity 1126.9233 +3400 train 7.169763 (lr=4.7706e-05) (hash(x)=25039815) +3401 train 7.062247 (lr=4.7667e-05) (hash(x)=24224002) +3402 train 7.017007 (lr=4.7628e-05) (hash(x)=25886169) +3403 train 7.084895 (lr=4.7589e-05) (hash(x)=25602577) +3404 train 7.069758 (lr=4.7550e-05) (hash(x)=21838175) +3405 train 6.912978 (lr=4.7511e-05) (hash(x)=20716276) +3406 train 6.911898 (lr=4.7472e-05) (hash(x)=22169391) +3407 train 7.079569 (lr=4.7433e-05) (hash(x)=23316582) +3408 train 6.989109 (lr=4.7394e-05) (hash(x)=29305666) +3409 train 7.201202 (lr=4.7355e-05) (hash(x)=23849620) +3410 train 7.307643 (lr=4.7316e-05) (hash(x)=26560546) +3411 train 7.009809 (lr=4.7277e-05) (hash(x)=22470095) +3412 train 7.071264 (lr=4.7238e-05) (hash(x)=24541250) +3413 train 6.932021 (lr=4.7199e-05) (hash(x)=22569035) +3414 train 7.057468 (lr=4.7160e-05) (hash(x)=23445307) +3415 train 6.930976 (lr=4.7121e-05) (hash(x)=25089202) +3416 train 6.996592 (lr=4.7082e-05) (hash(x)=26877686) +3417 train 6.934944 (lr=4.7043e-05) (hash(x)=25943303) +3418 train 6.737918 (lr=4.7004e-05) (hash(x)=20229886) +3419 train 7.084611 (lr=4.6965e-05) (hash(x)=26243247) +3420 train 7.232037 (lr=4.6926e-05) (hash(x)=23684111) +3421 train 7.199408 (lr=4.6887e-05) (hash(x)=25379406) +3422 train 7.068997 (lr=4.6848e-05) (hash(x)=23629812) +3423 train 6.753982 (lr=4.6809e-05) (hash(x)=22231144) +3424 train 6.784393 (lr=4.6770e-05) (hash(x)=23902576) +3425 train 6.846725 (lr=4.6731e-05) (hash(x)=19695756) +3426 train 6.948664 (lr=4.6692e-05) (hash(x)=23325741) +3427 train 7.207928 (lr=4.6653e-05) (hash(x)=27646564) +3428 train 7.017262 (lr=4.6615e-05) (hash(x)=24963136) +3429 train 7.302223 (lr=4.6576e-05) (hash(x)=31873056) +3430 train 7.098701 (lr=4.6537e-05) (hash(x)=25880203) +3431 train 7.012811 (lr=4.6498e-05) (hash(x)=23889875) +3432 train 7.053018 (lr=4.6459e-05) (hash(x)=25180150) +3433 train 7.068274 (lr=4.6420e-05) (hash(x)=20646304) +3434 train 7.120459 (lr=4.6381e-05) (hash(x)=26843667) +3435 train 6.791471 (lr=4.6342e-05) (hash(x)=25255240) +3436 train 7.542686 (lr=4.6303e-05) (hash(x)=30823096) +3437 train 7.233779 (lr=4.6265e-05) (hash(x)=27612424) +3438 train 6.976048 (lr=4.6226e-05) (hash(x)=22024252) +3439 train 6.813447 (lr=4.6187e-05) (hash(x)=23883299) +3440 train 7.138597 (lr=4.6148e-05) (hash(x)=28935436) +3441 train 7.335240 (lr=4.6109e-05) (hash(x)=25842452) +3442 train 7.151721 (lr=4.6070e-05) (hash(x)=25637938) +3443 train 6.699936 (lr=4.6032e-05) (hash(x)=18463841) +3444 train 7.063839 (lr=4.5993e-05) (hash(x)=25965113) +3445 train 6.969124 (lr=4.5954e-05) (hash(x)=24032346) +3446 train 7.144542 (lr=4.5915e-05) (hash(x)=26100560) +3447 train 7.355524 (lr=4.5877e-05) (hash(x)=30657762) +3448 train 6.975741 (lr=4.5838e-05) (hash(x)=27080799) +3449 train 7.053169 (lr=4.5799e-05) (hash(x)=25199653) +3450 val loss 7.0268 +3450 val perplexity 1126.4204 +3450 train 6.884265 (lr=4.5760e-05) (hash(x)=23938764) +3451 train 7.126322 (lr=4.5721e-05) (hash(x)=25288079) +3452 train 7.013430 (lr=4.5683e-05) (hash(x)=24324699) +3453 train 6.832617 (lr=4.5644e-05) (hash(x)=24683122) +3454 train 6.929455 (lr=4.5605e-05) (hash(x)=24176673) +3455 train 7.533874 (lr=4.5567e-05) (hash(x)=28979310) +3456 train 7.497318 (lr=4.5528e-05) (hash(x)=26276588) +3457 train 7.403347 (lr=4.5489e-05) (hash(x)=27746311) +3458 train 6.998119 (lr=4.5450e-05) (hash(x)=22646933) +3459 train 7.266072 (lr=4.5412e-05) (hash(x)=30254991) +3460 train 7.076299 (lr=4.5373e-05) (hash(x)=24215682) +3461 train 7.098858 (lr=4.5334e-05) (hash(x)=25961003) +3462 train 7.136226 (lr=4.5296e-05) (hash(x)=26898825) +3463 train 7.089587 (lr=4.5257e-05) (hash(x)=27274653) +3464 train 7.188399 (lr=4.5218e-05) (hash(x)=25124915) +3465 train 7.010214 (lr=4.5180e-05) (hash(x)=22056827) +3466 train 7.163256 (lr=4.5141e-05) (hash(x)=25862799) +3467 train 6.911669 (lr=4.5102e-05) (hash(x)=23026066) +3468 train 6.951881 (lr=4.5064e-05) (hash(x)=27478448) +3469 train 7.012440 (lr=4.5025e-05) (hash(x)=22601747) +3470 train 7.569739 (lr=4.4987e-05) (hash(x)=29691656) +3471 train 6.546454 (lr=4.4948e-05) (hash(x)=14001963) +3472 train 6.502352 (lr=4.4909e-05) (hash(x)=22423819) +3473 train 7.282757 (lr=4.4871e-05) (hash(x)=24657381) +3474 train 6.989754 (lr=4.4832e-05) (hash(x)=23487914) +3475 train 6.856672 (lr=4.4794e-05) (hash(x)=21988054) +3476 train 6.878434 (lr=4.4755e-05) (hash(x)=23482066) +3477 train 6.933931 (lr=4.4717e-05) (hash(x)=23512676) +3478 train 7.144040 (lr=4.4678e-05) (hash(x)=27653921) +3479 train 7.138589 (lr=4.4639e-05) (hash(x)=26241099) +3480 train 7.261430 (lr=4.4601e-05) (hash(x)=27170183) +3481 train 7.191864 (lr=4.4562e-05) (hash(x)=28067098) +3482 train 7.040093 (lr=4.4524e-05) (hash(x)=28216519) +3483 train 7.004029 (lr=4.4485e-05) (hash(x)=26209722) +3484 train 7.049874 (lr=4.4447e-05) (hash(x)=26135814) +3485 train 6.872158 (lr=4.4408e-05) (hash(x)=20837675) +3486 train 6.769418 (lr=4.4370e-05) (hash(x)=23102053) +3487 train 7.218399 (lr=4.4331e-05) (hash(x)=26928312) +3488 train 6.995386 (lr=4.4293e-05) (hash(x)=21672241) +3489 train 6.873796 (lr=4.4254e-05) (hash(x)=23532064) +3490 train 7.174824 (lr=4.4216e-05) (hash(x)=27181359) +3491 train 7.152770 (lr=4.4178e-05) (hash(x)=23563272) +3492 train 6.962228 (lr=4.4139e-05) (hash(x)=20402698) +3493 train 6.981053 (lr=4.4101e-05) (hash(x)=22303154) +3494 train 7.010015 (lr=4.4062e-05) (hash(x)=23648561) +3495 train 7.006309 (lr=4.4024e-05) (hash(x)=25704828) +3496 train 7.051533 (lr=4.3985e-05) (hash(x)=24651266) +3497 train 7.718776 (lr=4.3947e-05) (hash(x)=29405359) +3498 train 7.271686 (lr=4.3909e-05) (hash(x)=32499194) +3499 train 6.939398 (lr=4.3870e-05) (hash(x)=22498992) +3500 val loss 7.0271 +3500 val perplexity 1126.8142 +3500 train 7.063154 (lr=4.3832e-05) (hash(x)=29382425) +3501 train 8.024718 (lr=4.3794e-05) (hash(x)=38527461) +3502 train 7.505740 (lr=4.3755e-05) (hash(x)=25238253) +3503 train 7.070151 (lr=4.3717e-05) (hash(x)=22895918) +3504 train 6.858355 (lr=4.3679e-05) (hash(x)=24505897) +3505 train 7.018619 (lr=4.3640e-05) (hash(x)=21037854) +3506 train 7.023180 (lr=4.3602e-05) (hash(x)=24364717) +3507 train 6.950942 (lr=4.3564e-05) (hash(x)=24404283) +3508 train 6.955704 (lr=4.3525e-05) (hash(x)=24512699) +3509 train 6.931005 (lr=4.3487e-05) (hash(x)=26403949) +3510 train 7.120795 (lr=4.3449e-05) (hash(x)=22694338) +3511 train 6.929613 (lr=4.3411e-05) (hash(x)=26663932) +3512 train 7.069646 (lr=4.3372e-05) (hash(x)=26372406) +3513 train 7.302646 (lr=4.3334e-05) (hash(x)=27229413) +3514 train 7.202935 (lr=4.3296e-05) (hash(x)=22401373) +3515 train 6.787464 (lr=4.3258e-05) (hash(x)=22805316) +3516 train 7.175944 (lr=4.3219e-05) (hash(x)=26383120) +3517 train 7.161105 (lr=4.3181e-05) (hash(x)=25330877) +3518 train 7.102962 (lr=4.3143e-05) (hash(x)=23075615) +3519 train 7.002855 (lr=4.3105e-05) (hash(x)=23344466) +3520 train 7.097054 (lr=4.3067e-05) (hash(x)=27308918) +3521 train 7.258555 (lr=4.3028e-05) (hash(x)=25732529) +3522 train 6.816115 (lr=4.2990e-05) (hash(x)=22541257) +3523 train 6.924736 (lr=4.2952e-05) (hash(x)=20966940) +3524 train 6.865541 (lr=4.2914e-05) (hash(x)=23927091) +3525 train 7.113027 (lr=4.2876e-05) (hash(x)=26665336) +3526 train 6.845038 (lr=4.2838e-05) (hash(x)=24356512) +3527 train 7.292319 (lr=4.2799e-05) (hash(x)=27422664) +3528 train 7.114187 (lr=4.2761e-05) (hash(x)=21462165) +3529 train 7.215401 (lr=4.2723e-05) (hash(x)=28555665) +3530 train 7.061654 (lr=4.2685e-05) (hash(x)=25476891) +3531 train 6.851202 (lr=4.2647e-05) (hash(x)=22116510) +3532 train 6.760751 (lr=4.2609e-05) (hash(x)=23586588) +3533 train 6.937365 (lr=4.2571e-05) (hash(x)=27863790) +3534 train 7.131085 (lr=4.2533e-05) (hash(x)=24547211) +3535 train 6.998311 (lr=4.2495e-05) (hash(x)=27269633) +3536 train 6.819408 (lr=4.2457e-05) (hash(x)=21341882) +3537 train 6.997824 (lr=4.2419e-05) (hash(x)=26916967) +3538 train 6.883479 (lr=4.2381e-05) (hash(x)=24203252) +3539 train 7.450083 (lr=4.2343e-05) (hash(x)=27157711) +3540 train 7.134289 (lr=4.2305e-05) (hash(x)=21940125) +3541 train 7.164945 (lr=4.2267e-05) (hash(x)=25865703) +3542 train 7.046383 (lr=4.2229e-05) (hash(x)=23580162) +3543 train 7.101500 (lr=4.2191e-05) (hash(x)=22774645) +3544 train 6.918360 (lr=4.2153e-05) (hash(x)=24919123) +3545 train 6.952514 (lr=4.2115e-05) (hash(x)=26162270) +3546 train 7.182765 (lr=4.2077e-05) (hash(x)=27294843) +3547 train 6.972903 (lr=4.2039e-05) (hash(x)=22143146) +3548 train 7.150700 (lr=4.2001e-05) (hash(x)=31418679) +3549 train 7.006457 (lr=4.1963e-05) (hash(x)=22202257) +3550 val loss 7.0154 +3550 val perplexity 1113.6848 +3550 train 6.884249 (lr=4.1925e-05) (hash(x)=22120172) +3551 train 6.887019 (lr=4.1887e-05) (hash(x)=22356438) +3552 train 6.308196 (lr=4.1850e-05) (hash(x)=14734614) +3553 train 6.699656 (lr=4.1812e-05) (hash(x)=22331898) +3554 train 7.113677 (lr=4.1774e-05) (hash(x)=28322513) +3555 train 6.755105 (lr=4.1736e-05) (hash(x)=23172158) +3556 train 6.964622 (lr=4.1698e-05) (hash(x)=24943602) +3557 train 6.793839 (lr=4.1660e-05) (hash(x)=22578434) +3558 train 6.915329 (lr=4.1623e-05) (hash(x)=22875229) +3559 train 7.338540 (lr=4.1585e-05) (hash(x)=26971690) +3560 train 7.077733 (lr=4.1547e-05) (hash(x)=22252174) +3561 train 6.983966 (lr=4.1509e-05) (hash(x)=26760739) +3562 train 7.142836 (lr=4.1471e-05) (hash(x)=27214389) +3563 train 7.012368 (lr=4.1434e-05) (hash(x)=24851922) +3564 train 6.842740 (lr=4.1396e-05) (hash(x)=23221125) +3565 train 6.873462 (lr=4.1358e-05) (hash(x)=22854700) +3566 train 7.087169 (lr=4.1320e-05) (hash(x)=24132529) +3567 train 6.803973 (lr=4.1283e-05) (hash(x)=21017641) +3568 train 6.983958 (lr=4.1245e-05) (hash(x)=24379310) +3569 train 7.140498 (lr=4.1207e-05) (hash(x)=24141269) +3570 train 6.967762 (lr=4.1170e-05) (hash(x)=21775022) +3571 train 7.019370 (lr=4.1132e-05) (hash(x)=28186957) +3572 train 6.839401 (lr=4.1094e-05) (hash(x)=24119427) +3573 train 7.093470 (lr=4.1057e-05) (hash(x)=27125863) +3574 train 7.175613 (lr=4.1019e-05) (hash(x)=27166001) +3575 train 7.071189 (lr=4.0981e-05) (hash(x)=25661082) +3576 train 6.773602 (lr=4.0944e-05) (hash(x)=23850014) +3577 train 7.089741 (lr=4.0906e-05) (hash(x)=27131591) +3578 train 6.988893 (lr=4.0868e-05) (hash(x)=25248284) +3579 train 6.934066 (lr=4.0831e-05) (hash(x)=25462781) +3580 train 6.937100 (lr=4.0793e-05) (hash(x)=25383701) +3581 train 6.636343 (lr=4.0756e-05) (hash(x)=19079257) +3582 train 6.985761 (lr=4.0718e-05) (hash(x)=28124151) +3583 train 6.999379 (lr=4.0681e-05) (hash(x)=21774374) +3584 train 6.977815 (lr=4.0643e-05) (hash(x)=22951481) +3585 train 6.841699 (lr=4.0606e-05) (hash(x)=21349365) +3586 train 6.933343 (lr=4.0568e-05) (hash(x)=23062153) +3587 train 6.871959 (lr=4.0531e-05) (hash(x)=23657055) +3588 train 6.702544 (lr=4.0493e-05) (hash(x)=19893340) +3589 train 6.824933 (lr=4.0456e-05) (hash(x)=27273804) +3590 train 7.452913 (lr=4.0418e-05) (hash(x)=30812065) +3591 train 6.808600 (lr=4.0381e-05) (hash(x)=23604050) +3592 train 6.930243 (lr=4.0343e-05) (hash(x)=22622368) +3593 train 7.226229 (lr=4.0306e-05) (hash(x)=28419053) +3594 train 7.326530 (lr=4.0268e-05) (hash(x)=34147079) +3595 train 7.837342 (lr=4.0231e-05) (hash(x)=31534071) +3596 train 7.192648 (lr=4.0194e-05) (hash(x)=25309945) +3597 train 6.994538 (lr=4.0156e-05) (hash(x)=22037495) +3598 train 7.242580 (lr=4.0119e-05) (hash(x)=24786809) +3599 train 7.098888 (lr=4.0081e-05) (hash(x)=24183732) +3600 val loss 7.0379 +3600 val perplexity 1139.0317 +3600 train 7.063380 (lr=4.0044e-05) (hash(x)=26678478) +3601 train 6.978196 (lr=4.0007e-05) (hash(x)=23379513) +3602 train 6.948547 (lr=3.9969e-05) (hash(x)=22367536) +3603 train 7.114498 (lr=3.9932e-05) (hash(x)=23384280) +3604 train 6.765381 (lr=3.9895e-05) (hash(x)=23259350) +3605 train 6.825930 (lr=3.9857e-05) (hash(x)=21744922) +3606 train 7.034158 (lr=3.9820e-05) (hash(x)=26149204) +3607 train 6.846539 (lr=3.9783e-05) (hash(x)=21975928) +3608 train 6.860563 (lr=3.9746e-05) (hash(x)=24076970) +3609 train 6.793097 (lr=3.9708e-05) (hash(x)=24851195) +3610 train 6.908426 (lr=3.9671e-05) (hash(x)=26106166) +3611 train 6.913798 (lr=3.9634e-05) (hash(x)=25281674) +3612 train 6.843208 (lr=3.9597e-05) (hash(x)=19597014) +3613 train 6.848255 (lr=3.9559e-05) (hash(x)=25118947) +3614 train 6.850504 (lr=3.9522e-05) (hash(x)=21854141) +3615 train 6.852892 (lr=3.9485e-05) (hash(x)=22947712) +3616 train 6.785120 (lr=3.9448e-05) (hash(x)=23176418) +3617 train 7.045259 (lr=3.9411e-05) (hash(x)=27044644) +3618 train 7.004564 (lr=3.9374e-05) (hash(x)=24390864) +3619 train 6.896336 (lr=3.9337e-05) (hash(x)=24853977) +3620 train 7.192677 (lr=3.9299e-05) (hash(x)=25629731) +3621 train 6.960494 (lr=3.9262e-05) (hash(x)=23245430) +3622 train 6.941579 (lr=3.9225e-05) (hash(x)=22511067) +3623 train 6.853236 (lr=3.9188e-05) (hash(x)=23696470) +3624 train 7.003309 (lr=3.9151e-05) (hash(x)=26413767) +3625 train 7.236856 (lr=3.9114e-05) (hash(x)=28348662) +3626 train 6.796279 (lr=3.9077e-05) (hash(x)=23805449) +3627 train 7.003625 (lr=3.9040e-05) (hash(x)=27489711) +3628 train 6.847478 (lr=3.9003e-05) (hash(x)=23658876) +3629 train 6.953667 (lr=3.8966e-05) (hash(x)=25608370) +3630 train 6.923476 (lr=3.8929e-05) (hash(x)=23442938) +3631 train 6.946843 (lr=3.8892e-05) (hash(x)=28050163) +3632 train 6.636434 (lr=3.8855e-05) (hash(x)=23626089) +3633 train 6.788297 (lr=3.8818e-05) (hash(x)=22615841) +3634 train 6.845800 (lr=3.8781e-05) (hash(x)=22880424) +3635 train 6.898326 (lr=3.8744e-05) (hash(x)=26996807) +3636 train 7.110447 (lr=3.8707e-05) (hash(x)=29795232) +3637 train 7.563588 (lr=3.8670e-05) (hash(x)=28780071) +3638 train 6.978346 (lr=3.8633e-05) (hash(x)=25917382) +3639 train 7.138615 (lr=3.8597e-05) (hash(x)=28626495) +3640 train 7.162885 (lr=3.8560e-05) (hash(x)=26063175) +3641 train 6.714699 (lr=3.8523e-05) (hash(x)=18380174) +3642 train 6.935418 (lr=3.8486e-05) (hash(x)=23983451) +3643 train 6.884152 (lr=3.8449e-05) (hash(x)=24783242) +3644 train 6.799418 (lr=3.8412e-05) (hash(x)=26036718) +3645 train 6.619464 (lr=3.8376e-05) (hash(x)=19411545) +3646 train 7.266976 (lr=3.8339e-05) (hash(x)=27166200) +3647 train 6.975992 (lr=3.8302e-05) (hash(x)=25832479) +3648 train 6.828329 (lr=3.8265e-05) (hash(x)=24798180) +3649 train 6.824256 (lr=3.8228e-05) (hash(x)=25202518) +3650 val loss 7.0060 +3650 val perplexity 1103.2339 +3650 train 6.610044 (lr=3.8192e-05) (hash(x)=21318466) +3651 train 6.854732 (lr=3.8155e-05) (hash(x)=23522137) +3652 train 6.918856 (lr=3.8118e-05) (hash(x)=26825118) +3653 train 7.436130 (lr=3.8082e-05) (hash(x)=28917794) +3654 train 7.216088 (lr=3.8045e-05) (hash(x)=23550494) +3655 train 6.989756 (lr=3.8008e-05) (hash(x)=26731973) +3656 train 6.998230 (lr=3.7972e-05) (hash(x)=25609302) +3657 train 7.187620 (lr=3.7935e-05) (hash(x)=26458975) +3658 train 7.456898 (lr=3.7898e-05) (hash(x)=29604116) +3659 train 6.993906 (lr=3.7862e-05) (hash(x)=26019142) +3660 train 6.969752 (lr=3.7825e-05) (hash(x)=23916481) +3661 train 6.876457 (lr=3.7788e-05) (hash(x)=24158545) +3662 train 7.100803 (lr=3.7752e-05) (hash(x)=24761648) +3663 train 6.961161 (lr=3.7715e-05) (hash(x)=25081877) +3664 train 7.029405 (lr=3.7679e-05) (hash(x)=30304149) +3665 train 7.154036 (lr=3.7642e-05) (hash(x)=29097664) +3666 train 6.954261 (lr=3.7606e-05) (hash(x)=24266623) +3667 train 7.022751 (lr=3.7569e-05) (hash(x)=23843571) +3668 train 7.033317 (lr=3.7533e-05) (hash(x)=24894741) +3669 train 6.990809 (lr=3.7496e-05) (hash(x)=22737047) +3670 train 7.248010 (lr=3.7460e-05) (hash(x)=26303095) +3671 train 7.010853 (lr=3.7423e-05) (hash(x)=26805739) +3672 train 6.905322 (lr=3.7387e-05) (hash(x)=22851082) +3673 train 6.981287 (lr=3.7350e-05) (hash(x)=22934009) +3674 train 6.885735 (lr=3.7314e-05) (hash(x)=25754460) +3675 train 7.149680 (lr=3.7277e-05) (hash(x)=27169927) +3676 train 6.975949 (lr=3.7241e-05) (hash(x)=28830379) +3677 train 6.747789 (lr=3.7205e-05) (hash(x)=20554517) +3678 train 7.108166 (lr=3.7168e-05) (hash(x)=27004910) +3679 train 7.235135 (lr=3.7132e-05) (hash(x)=26545491) +3680 train 6.942085 (lr=3.7096e-05) (hash(x)=23157780) +3681 train 6.907789 (lr=3.7059e-05) (hash(x)=24911153) +3682 train 7.307094 (lr=3.7023e-05) (hash(x)=28005975) +3683 train 7.001322 (lr=3.6987e-05) (hash(x)=25179497) +3684 train 6.940269 (lr=3.6950e-05) (hash(x)=24498432) +3685 train 7.125250 (lr=3.6914e-05) (hash(x)=27193267) +3686 train 6.855743 (lr=3.6878e-05) (hash(x)=23762517) +3687 train 6.982560 (lr=3.6842e-05) (hash(x)=27085003) +3688 train 6.955306 (lr=3.6805e-05) (hash(x)=25602670) +3689 train 6.922949 (lr=3.6769e-05) (hash(x)=24828956) +3690 train 7.035444 (lr=3.6733e-05) (hash(x)=24971143) +3691 train 6.979311 (lr=3.6697e-05) (hash(x)=24558202) +3692 train 7.119990 (lr=3.6661e-05) (hash(x)=26574617) +3693 train 7.038069 (lr=3.6625e-05) (hash(x)=24656329) +3694 train 7.125579 (lr=3.6588e-05) (hash(x)=25543675) +3695 train 7.106938 (lr=3.6552e-05) (hash(x)=25317684) +3696 train 7.022963 (lr=3.6516e-05) (hash(x)=23921505) +3697 train 7.201932 (lr=3.6480e-05) (hash(x)=24853134) +3698 train 6.944520 (lr=3.6444e-05) (hash(x)=26803457) +3699 train 6.879069 (lr=3.6408e-05) (hash(x)=27104868) +3700 val loss 7.0038 +3700 val perplexity 1100.8140 +3700 train 7.244817 (lr=3.6372e-05) (hash(x)=29554134) +3701 train 7.078413 (lr=3.6336e-05) (hash(x)=24353634) +3702 train 6.886790 (lr=3.6300e-05) (hash(x)=24259019) +3703 train 7.011237 (lr=3.6264e-05) (hash(x)=24806274) +3704 train 6.878655 (lr=3.6228e-05) (hash(x)=24980112) +3705 train 7.077221 (lr=3.6192e-05) (hash(x)=27625217) +3706 train 7.246045 (lr=3.6156e-05) (hash(x)=28729128) +3707 train 7.150772 (lr=3.6120e-05) (hash(x)=24341937) +3708 train 6.816309 (lr=3.6084e-05) (hash(x)=21697871) +3709 train 7.072949 (lr=3.6048e-05) (hash(x)=26362971) +3710 train 6.909365 (lr=3.6012e-05) (hash(x)=21209140) +3711 train 6.740526 (lr=3.5976e-05) (hash(x)=22736558) +3712 train 6.824562 (lr=3.5940e-05) (hash(x)=19835086) +3713 train 6.901261 (lr=3.5904e-05) (hash(x)=26287113) +3714 train 6.860481 (lr=3.5869e-05) (hash(x)=23701414) +3715 train 7.053046 (lr=3.5833e-05) (hash(x)=23843744) +3716 train 6.977330 (lr=3.5797e-05) (hash(x)=23013949) +3717 train 6.917340 (lr=3.5761e-05) (hash(x)=24509223) +3718 train 7.040696 (lr=3.5725e-05) (hash(x)=25778863) +3719 train 7.141436 (lr=3.5690e-05) (hash(x)=27218468) +3720 train 7.036628 (lr=3.5654e-05) (hash(x)=27330382) +3721 train 6.982131 (lr=3.5618e-05) (hash(x)=22348365) +3722 train 6.996292 (lr=3.5582e-05) (hash(x)=25557954) +3723 train 6.917221 (lr=3.5547e-05) (hash(x)=26042053) +3724 train 7.216719 (lr=3.5511e-05) (hash(x)=27956533) +3725 train 6.793272 (lr=3.5475e-05) (hash(x)=25652715) +3726 train 6.954996 (lr=3.5440e-05) (hash(x)=24871264) +3727 train 7.050185 (lr=3.5404e-05) (hash(x)=25776082) +3728 train 6.989244 (lr=3.5368e-05) (hash(x)=24604995) +3729 train 6.758866 (lr=3.5333e-05) (hash(x)=22229606) +3730 train 7.043065 (lr=3.5297e-05) (hash(x)=25518638) +3731 train 6.740432 (lr=3.5261e-05) (hash(x)=21594447) +3732 train 6.857718 (lr=3.5226e-05) (hash(x)=24049225) +3733 train 7.078269 (lr=3.5190e-05) (hash(x)=23722987) +3734 train 6.885130 (lr=3.5155e-05) (hash(x)=22538896) +3735 train 6.902701 (lr=3.5119e-05) (hash(x)=21674469) +3736 train 6.745103 (lr=3.5084e-05) (hash(x)=23633119) +3737 train 6.757509 (lr=3.5048e-05) (hash(x)=21200087) +3738 train 6.985134 (lr=3.5013e-05) (hash(x)=25076156) +3739 train 6.925500 (lr=3.4977e-05) (hash(x)=26213966) +3740 train 6.772228 (lr=3.4942e-05) (hash(x)=22052502) +3741 train 6.913461 (lr=3.4906e-05) (hash(x)=23103626) +3742 train 6.896711 (lr=3.4871e-05) (hash(x)=24920844) +3743 train 6.926880 (lr=3.4835e-05) (hash(x)=23770702) +3744 train 6.886733 (lr=3.4800e-05) (hash(x)=22965430) +3745 train 7.003337 (lr=3.4765e-05) (hash(x)=26139229) +3746 train 6.869942 (lr=3.4729e-05) (hash(x)=25738110) +3747 train 7.136833 (lr=3.4694e-05) (hash(x)=27829878) +3748 train 6.783828 (lr=3.4659e-05) (hash(x)=20576987) +3749 train 7.245632 (lr=3.4623e-05) (hash(x)=27221940) +3750 val loss 7.0004 +3750 val perplexity 1097.0620 +3750 train 6.803485 (lr=3.4588e-05) (hash(x)=25272042) +3751 train 7.424125 (lr=3.4553e-05) (hash(x)=29177278) +3752 train 6.832457 (lr=3.4518e-05) (hash(x)=22186169) +3753 train 7.199778 (lr=3.4482e-05) (hash(x)=26418252) +3754 train 7.068993 (lr=3.4447e-05) (hash(x)=26354367) +3755 train 6.975552 (lr=3.4412e-05) (hash(x)=26020089) +3756 train 6.943202 (lr=3.4377e-05) (hash(x)=26102649) +3757 train 6.959518 (lr=3.4341e-05) (hash(x)=24114078) +3758 train 6.907604 (lr=3.4306e-05) (hash(x)=21065534) +3759 train 6.872297 (lr=3.4271e-05) (hash(x)=24676475) +3760 train 6.993692 (lr=3.4236e-05) (hash(x)=23258275) +3761 train 7.208983 (lr=3.4201e-05) (hash(x)=30538340) +3762 train 6.860467 (lr=3.4166e-05) (hash(x)=24264874) +3763 train 6.722604 (lr=3.4131e-05) (hash(x)=24056174) +3764 train 6.882074 (lr=3.4096e-05) (hash(x)=22087466) +3765 train 7.179797 (lr=3.4060e-05) (hash(x)=23937392) +3766 train 7.086600 (lr=3.4025e-05) (hash(x)=24839143) +3767 train 6.905819 (lr=3.3990e-05) (hash(x)=21887514) +3768 train 7.142268 (lr=3.3955e-05) (hash(x)=27733168) +3769 train 7.019330 (lr=3.3920e-05) (hash(x)=24617463) +3770 train 6.914895 (lr=3.3885e-05) (hash(x)=24850107) +3771 train 6.828997 (lr=3.3850e-05) (hash(x)=24196100) +3772 train 6.839148 (lr=3.3816e-05) (hash(x)=23547632) +3773 train 7.096403 (lr=3.3781e-05) (hash(x)=26719200) +3774 train 7.066538 (lr=3.3746e-05) (hash(x)=24789657) +3775 train 6.877238 (lr=3.3711e-05) (hash(x)=25700093) +3776 train 7.109982 (lr=3.3676e-05) (hash(x)=25702686) +3777 train 6.970923 (lr=3.3641e-05) (hash(x)=25253145) +3778 train 7.278764 (lr=3.3606e-05) (hash(x)=30032123) +3779 train 7.034159 (lr=3.3571e-05) (hash(x)=24365834) +3780 train 7.045212 (lr=3.3537e-05) (hash(x)=25472287) +3781 train 6.897025 (lr=3.3502e-05) (hash(x)=23331500) +3782 train 6.934497 (lr=3.3467e-05) (hash(x)=25195327) +3783 train 6.883172 (lr=3.3432e-05) (hash(x)=25631786) +3784 train 6.943790 (lr=3.3397e-05) (hash(x)=23174094) +3785 train 7.124619 (lr=3.3363e-05) (hash(x)=26627700) +3786 train 7.066641 (lr=3.3328e-05) (hash(x)=22636814) +3787 train 7.021708 (lr=3.3293e-05) (hash(x)=24452345) +3788 train 6.748012 (lr=3.3259e-05) (hash(x)=24474970) +3789 train 6.495606 (lr=3.3224e-05) (hash(x)=21063302) +3790 train 6.909263 (lr=3.3189e-05) (hash(x)=26114864) +3791 train 6.797575 (lr=3.3155e-05) (hash(x)=21465330) +3792 train 6.824315 (lr=3.3120e-05) (hash(x)=23377832) +3793 train 6.965265 (lr=3.3086e-05) (hash(x)=23031979) +3794 train 6.819570 (lr=3.3051e-05) (hash(x)=23424300) +3795 train 6.853019 (lr=3.3016e-05) (hash(x)=20427493) +3796 train 6.691071 (lr=3.2982e-05) (hash(x)=22165520) +3797 train 6.854826 (lr=3.2947e-05) (hash(x)=23476688) +3798 train 7.062336 (lr=3.2913e-05) (hash(x)=16631115) +3799 train 7.052804 (lr=3.2878e-05) (hash(x)=25439720) +3800 val loss 6.9989 +3800 val perplexity 1095.3815 +3800 train 7.228255 (lr=3.2844e-05) (hash(x)=27737064) +3801 train 6.972730 (lr=3.2809e-05) (hash(x)=26682690) +3802 train 6.981718 (lr=3.2775e-05) (hash(x)=29288247) +3803 train 6.726912 (lr=3.2740e-05) (hash(x)=21652988) +3804 train 6.916104 (lr=3.2706e-05) (hash(x)=25159500) +3805 train 6.967492 (lr=3.2672e-05) (hash(x)=26679136) +3806 train 6.823355 (lr=3.2637e-05) (hash(x)=24323038) +3807 train 6.987748 (lr=3.2603e-05) (hash(x)=22546779) +3808 train 6.980465 (lr=3.2569e-05) (hash(x)=24696198) +3809 train 6.888307 (lr=3.2534e-05) (hash(x)=25183353) +3810 train 6.750370 (lr=3.2500e-05) (hash(x)=22113763) +3811 train 6.502545 (lr=3.2466e-05) (hash(x)=20855736) +3812 train 6.905979 (lr=3.2431e-05) (hash(x)=24961706) +3813 train 6.727654 (lr=3.2397e-05) (hash(x)=20906769) +3814 train 7.184781 (lr=3.2363e-05) (hash(x)=27261849) +3815 train 7.080838 (lr=3.2329e-05) (hash(x)=27725873) +3816 train 7.219382 (lr=3.2295e-05) (hash(x)=23330476) +3817 train 6.896088 (lr=3.2260e-05) (hash(x)=25108332) +3818 train 7.032520 (lr=3.2226e-05) (hash(x)=25657859) +3819 train 7.085965 (lr=3.2192e-05) (hash(x)=24582989) +3820 train 6.875481 (lr=3.2158e-05) (hash(x)=23349707) +3821 train 6.920106 (lr=3.2124e-05) (hash(x)=22469417) +3822 train 7.008485 (lr=3.2090e-05) (hash(x)=25509306) +3823 train 6.902013 (lr=3.2056e-05) (hash(x)=24822372) +3824 train 6.818079 (lr=3.2022e-05) (hash(x)=23983201) +3825 train 7.049995 (lr=3.1988e-05) (hash(x)=26039874) +3826 train 6.917629 (lr=3.1954e-05) (hash(x)=22517876) +3827 train 7.070213 (lr=3.1920e-05) (hash(x)=25624588) +3828 train 6.912342 (lr=3.1886e-05) (hash(x)=22319601) +3829 train 6.758627 (lr=3.1852e-05) (hash(x)=24225722) +3830 train 6.909115 (lr=3.1818e-05) (hash(x)=25483578) +3831 train 7.045035 (lr=3.1784e-05) (hash(x)=23566489) +3832 train 6.891909 (lr=3.1750e-05) (hash(x)=21390177) +3833 train 7.042117 (lr=3.1716e-05) (hash(x)=28993619) +3834 train 7.416618 (lr=3.1682e-05) (hash(x)=26281157) +3835 train 7.011750 (lr=3.1648e-05) (hash(x)=28117387) +3836 train 6.811311 (lr=3.1614e-05) (hash(x)=23750652) +3837 train 6.909554 (lr=3.1580e-05) (hash(x)=26294682) +3838 train 6.899766 (lr=3.1547e-05) (hash(x)=21421993) +3839 train 6.860967 (lr=3.1513e-05) (hash(x)=26874283) +3840 train 6.895229 (lr=3.1479e-05) (hash(x)=21539486) +3841 train 6.586864 (lr=3.1445e-05) (hash(x)=20610535) +3842 train 6.974123 (lr=3.1412e-05) (hash(x)=24529403) +3843 train 7.086892 (lr=3.1378e-05) (hash(x)=28570123) +3844 train 6.989537 (lr=3.1344e-05) (hash(x)=20561973) +3845 train 6.908232 (lr=3.1311e-05) (hash(x)=24386170) +3846 train 7.001653 (lr=3.1277e-05) (hash(x)=24162470) +3847 train 7.008426 (lr=3.1243e-05) (hash(x)=24807017) +3848 train 6.933250 (lr=3.1210e-05) (hash(x)=22676021) +3849 train 6.863270 (lr=3.1176e-05) (hash(x)=23678981) +3850 val loss 6.9892 +3850 val perplexity 1084.8895 +3850 train 6.835201 (lr=3.1142e-05) (hash(x)=22922754) +3851 train 6.976474 (lr=3.1109e-05) (hash(x)=25189993) +3852 train 7.149497 (lr=3.1075e-05) (hash(x)=26428613) +3853 train 6.723887 (lr=3.1042e-05) (hash(x)=21889553) +3854 train 7.034813 (lr=3.1008e-05) (hash(x)=22267059) +3855 train 7.082170 (lr=3.0975e-05) (hash(x)=29202226) +3856 train 7.162560 (lr=3.0941e-05) (hash(x)=26773985) +3857 train 6.851045 (lr=3.0908e-05) (hash(x)=22117007) +3858 train 7.394241 (lr=3.0874e-05) (hash(x)=28554085) +3859 train 7.351748 (lr=3.0841e-05) (hash(x)=26060713) +3860 train 6.943299 (lr=3.0808e-05) (hash(x)=22760237) +3861 train 6.950159 (lr=3.0774e-05) (hash(x)=21459371) +3862 train 7.497411 (lr=3.0741e-05) (hash(x)=29904475) +3863 train 7.010041 (lr=3.0708e-05) (hash(x)=23053285) +3864 train 7.192776 (lr=3.0674e-05) (hash(x)=25230185) +3865 train 7.173987 (lr=3.0641e-05) (hash(x)=27336585) +3866 train 6.987420 (lr=3.0608e-05) (hash(x)=23794687) +3867 train 6.824502 (lr=3.0574e-05) (hash(x)=21968481) +3868 train 7.025908 (lr=3.0541e-05) (hash(x)=29534235) +3869 train 7.027002 (lr=3.0508e-05) (hash(x)=28089468) +3870 train 6.964838 (lr=3.0475e-05) (hash(x)=25562718) +3871 train 6.704401 (lr=3.0441e-05) (hash(x)=24492698) +3872 train 6.764126 (lr=3.0408e-05) (hash(x)=21966131) +3873 train 6.813470 (lr=3.0375e-05) (hash(x)=24244858) +3874 train 6.964007 (lr=3.0342e-05) (hash(x)=23933180) +3875 train 7.124620 (lr=3.0309e-05) (hash(x)=25760806) +3876 train 6.858150 (lr=3.0276e-05) (hash(x)=23692433) +3877 train 6.933171 (lr=3.0243e-05) (hash(x)=28695065) +3878 train 7.057056 (lr=3.0210e-05) (hash(x)=23940798) +3879 train 7.040542 (lr=3.0177e-05) (hash(x)=27417392) +3880 train 6.721780 (lr=3.0144e-05) (hash(x)=19572409) +3881 train 6.813513 (lr=3.0111e-05) (hash(x)=23855495) +3882 train 7.101345 (lr=3.0078e-05) (hash(x)=20398052) +3883 train 7.083921 (lr=3.0045e-05) (hash(x)=26767105) +3884 train 7.189790 (lr=3.0012e-05) (hash(x)=29008178) +3885 train 7.052906 (lr=2.9979e-05) (hash(x)=28544187) +3886 train 6.822002 (lr=2.9946e-05) (hash(x)=30138063) +3887 train 6.923417 (lr=2.9913e-05) (hash(x)=25117678) +3888 train 6.961937 (lr=2.9880e-05) (hash(x)=26634522) +3889 train 6.895927 (lr=2.9847e-05) (hash(x)=23552401) +3890 train 6.995353 (lr=2.9814e-05) (hash(x)=26340139) +3891 train 6.705128 (lr=2.9782e-05) (hash(x)=24233758) +3892 train 6.915027 (lr=2.9749e-05) (hash(x)=23126166) +3893 train 6.812975 (lr=2.9716e-05) (hash(x)=21618887) +3894 train 7.021302 (lr=2.9683e-05) (hash(x)=25175000) +3895 train 7.109831 (lr=2.9651e-05) (hash(x)=29907634) +3896 train 6.508181 (lr=2.9618e-05) (hash(x)=21646970) +3897 train 6.773864 (lr=2.9585e-05) (hash(x)=20462990) +3898 train 6.824211 (lr=2.9553e-05) (hash(x)=24677361) +3899 train 6.822552 (lr=2.9520e-05) (hash(x)=23552436) +3900 val loss 6.9868 +3900 val perplexity 1082.2823 +3900 train 6.896564 (lr=2.9487e-05) (hash(x)=25011036) +3901 train 7.166780 (lr=2.9455e-05) (hash(x)=24794800) +3902 train 7.159143 (lr=2.9422e-05) (hash(x)=26425104) +3903 train 7.063701 (lr=2.9389e-05) (hash(x)=28610406) +3904 train 7.030314 (lr=2.9357e-05) (hash(x)=25811870) +3905 train 6.961246 (lr=2.9324e-05) (hash(x)=24281320) +3906 train 6.788930 (lr=2.9292e-05) (hash(x)=24391439) +3907 train 7.030170 (lr=2.9259e-05) (hash(x)=23858212) +3908 train 6.914542 (lr=2.9227e-05) (hash(x)=23817740) +3909 train 6.861315 (lr=2.9194e-05) (hash(x)=24304509) +3910 train 6.910767 (lr=2.9162e-05) (hash(x)=23243601) +3911 train 6.696640 (lr=2.9130e-05) (hash(x)=20567764) +3912 train 6.772080 (lr=2.9097e-05) (hash(x)=23519078) +3913 train 6.842932 (lr=2.9065e-05) (hash(x)=26873246) +3914 train 6.793762 (lr=2.9033e-05) (hash(x)=23062298) +3915 train 6.965460 (lr=2.9000e-05) (hash(x)=29631106) +3916 train 6.650682 (lr=2.8968e-05) (hash(x)=21648452) +3917 train 7.028261 (lr=2.8936e-05) (hash(x)=25305791) +3918 train 6.875042 (lr=2.8903e-05) (hash(x)=22307623) +3919 train 6.730922 (lr=2.8871e-05) (hash(x)=19843564) +3920 train 7.128493 (lr=2.8839e-05) (hash(x)=22655517) +3921 train 6.938476 (lr=2.8807e-05) (hash(x)=25101224) +3922 train 7.004921 (lr=2.8774e-05) (hash(x)=25032974) +3923 train 6.803657 (lr=2.8742e-05) (hash(x)=22589891) +3924 train 6.832834 (lr=2.8710e-05) (hash(x)=25489784) +3925 train 6.827435 (lr=2.8678e-05) (hash(x)=24533991) +3926 train 6.649607 (lr=2.8646e-05) (hash(x)=18969890) +3927 train 6.797976 (lr=2.8614e-05) (hash(x)=21183943) +3928 train 7.051636 (lr=2.8582e-05) (hash(x)=24000198) +3929 train 6.871773 (lr=2.8550e-05) (hash(x)=25008761) +3930 train 6.864887 (lr=2.8518e-05) (hash(x)=23398221) +3931 train 6.840998 (lr=2.8486e-05) (hash(x)=26152241) +3932 train 6.933160 (lr=2.8454e-05) (hash(x)=25486070) +3933 train 6.929671 (lr=2.8422e-05) (hash(x)=26276234) +3934 train 6.970470 (lr=2.8390e-05) (hash(x)=23622107) +3935 train 6.907416 (lr=2.8358e-05) (hash(x)=22700785) +3936 train 6.838680 (lr=2.8326e-05) (hash(x)=22802001) +3937 train 6.903844 (lr=2.8294e-05) (hash(x)=24096486) +3938 train 7.136917 (lr=2.8262e-05) (hash(x)=24578737) +3939 train 7.680916 (lr=2.8230e-05) (hash(x)=29611280) +3940 train 7.892274 (lr=2.8199e-05) (hash(x)=30218145) +3941 train 7.115595 (lr=2.8167e-05) (hash(x)=22812890) +3942 train 6.898833 (lr=2.8135e-05) (hash(x)=25982513) +3943 train 6.954537 (lr=2.8103e-05) (hash(x)=25972823) +3944 train 6.965639 (lr=2.8071e-05) (hash(x)=24058871) +3945 train 6.954925 (lr=2.8040e-05) (hash(x)=24988300) +3946 train 6.752119 (lr=2.8008e-05) (hash(x)=21496420) +3947 train 7.153917 (lr=2.7976e-05) (hash(x)=23447782) +3948 train 6.921391 (lr=2.7945e-05) (hash(x)=25663935) +3949 train 6.731948 (lr=2.7913e-05) (hash(x)=22871262) +3950 val loss 6.9897 +3950 val perplexity 1085.3470 +3950 train 7.172297 (lr=2.7881e-05) (hash(x)=27258546) +3951 train 6.789629 (lr=2.7850e-05) (hash(x)=22578453) +3952 train 7.109826 (lr=2.7818e-05) (hash(x)=25302485) +3953 train 6.695348 (lr=2.7787e-05) (hash(x)=22754287) +3954 train 6.921797 (lr=2.7755e-05) (hash(x)=24109427) +3955 train 6.869189 (lr=2.7724e-05) (hash(x)=25474622) +3956 train 6.861272 (lr=2.7692e-05) (hash(x)=25921397) +3957 train 7.011418 (lr=2.7661e-05) (hash(x)=28567887) +3958 train 6.891508 (lr=2.7629e-05) (hash(x)=25888915) +3959 train 7.103224 (lr=2.7598e-05) (hash(x)=22965762) +3960 train 7.080009 (lr=2.7566e-05) (hash(x)=26762050) +3961 train 7.181523 (lr=2.7535e-05) (hash(x)=27712097) +3962 train 6.898777 (lr=2.7504e-05) (hash(x)=23977862) +3963 train 6.875031 (lr=2.7472e-05) (hash(x)=26116321) +3964 train 6.735009 (lr=2.7441e-05) (hash(x)=19842263) +3965 train 6.866656 (lr=2.7410e-05) (hash(x)=24709237) +3966 train 7.061601 (lr=2.7379e-05) (hash(x)=26220194) +3967 train 6.954724 (lr=2.7347e-05) (hash(x)=25934549) +3968 train 6.911651 (lr=2.7316e-05) (hash(x)=24540497) +3969 train 6.700384 (lr=2.7285e-05) (hash(x)=21680120) +3970 train 7.005052 (lr=2.7254e-05) (hash(x)=22464414) +3971 train 6.696832 (lr=2.7222e-05) (hash(x)=23937495) +3972 train 6.776632 (lr=2.7191e-05) (hash(x)=21201514) +3973 train 7.094729 (lr=2.7160e-05) (hash(x)=25113226) +3974 train 7.046938 (lr=2.7129e-05) (hash(x)=20678432) +3975 train 7.182269 (lr=2.7098e-05) (hash(x)=26286442) +3976 train 6.958183 (lr=2.7067e-05) (hash(x)=25162164) +3977 train 7.324676 (lr=2.7036e-05) (hash(x)=30334549) +3978 train 7.215158 (lr=2.7005e-05) (hash(x)=30405517) +3979 train 7.458497 (lr=2.6974e-05) (hash(x)=32737711) +3980 train 6.755850 (lr=2.6943e-05) (hash(x)=25779685) +3981 train 6.676857 (lr=2.6912e-05) (hash(x)=23732519) +3982 train 7.282479 (lr=2.6881e-05) (hash(x)=29480838) +3983 train 6.762989 (lr=2.6850e-05) (hash(x)=20563613) +3984 train 7.242198 (lr=2.6819e-05) (hash(x)=25419620) +3985 train 7.093184 (lr=2.6788e-05) (hash(x)=21731597) +3986 train 7.221135 (lr=2.6758e-05) (hash(x)=26755619) +3987 train 7.028098 (lr=2.6727e-05) (hash(x)=26234770) +3988 train 7.100254 (lr=2.6696e-05) (hash(x)=23467797) +3989 train 6.987297 (lr=2.6665e-05) (hash(x)=25615077) +3990 train 6.758433 (lr=2.6634e-05) (hash(x)=23955961) +3991 train 7.279406 (lr=2.6604e-05) (hash(x)=26179422) +3992 train 6.971691 (lr=2.6573e-05) (hash(x)=25081971) +3993 train 6.923120 (lr=2.6542e-05) (hash(x)=23938333) +3994 train 7.130087 (lr=2.6512e-05) (hash(x)=27208446) +3995 train 6.850878 (lr=2.6481e-05) (hash(x)=23289651) +3996 train 6.969748 (lr=2.6450e-05) (hash(x)=21880796) +3997 train 7.216251 (lr=2.6420e-05) (hash(x)=28250152) +3998 train 7.283556 (lr=2.6389e-05) (hash(x)=28828426) +3999 train 7.812660 (lr=2.6359e-05) (hash(x)=36436617) +4000 val loss 6.9850 +4000 val perplexity 1080.3555 +4000 train 6.998662 (lr=2.6328e-05) (hash(x)=23888872) +4001 train 6.992237 (lr=2.6298e-05) (hash(x)=24720781) +4002 train 6.831406 (lr=2.6267e-05) (hash(x)=23403672) +4003 train 6.832037 (lr=2.6237e-05) (hash(x)=24854398) +4004 train 7.245891 (lr=2.6206e-05) (hash(x)=32863622) +4005 train 7.015443 (lr=2.6176e-05) (hash(x)=22482108) +4006 train 6.898789 (lr=2.6145e-05) (hash(x)=22039371) +4007 train 6.962081 (lr=2.6115e-05) (hash(x)=25162669) +4008 train 6.764720 (lr=2.6085e-05) (hash(x)=21133209) +4009 train 6.936925 (lr=2.6054e-05) (hash(x)=24940321) +4010 train 7.015144 (lr=2.6024e-05) (hash(x)=25627362) +4011 train 6.625923 (lr=2.5994e-05) (hash(x)=20845671) +4012 train 7.093245 (lr=2.5963e-05) (hash(x)=26577501) +4013 train 7.127881 (lr=2.5933e-05) (hash(x)=24442121) +4014 train 6.847826 (lr=2.5903e-05) (hash(x)=21961508) +4015 train 6.920000 (lr=2.5873e-05) (hash(x)=23276958) +4016 train 6.673059 (lr=2.5843e-05) (hash(x)=18141943) +4017 train 6.692845 (lr=2.5812e-05) (hash(x)=20427388) +4018 train 7.130217 (lr=2.5782e-05) (hash(x)=25028032) +4019 train 6.733696 (lr=2.5752e-05) (hash(x)=22544363) +4020 train 6.868767 (lr=2.5722e-05) (hash(x)=24869419) +4021 train 6.854231 (lr=2.5692e-05) (hash(x)=26034883) +4022 train 6.873932 (lr=2.5662e-05) (hash(x)=24214272) +4023 train 6.826472 (lr=2.5632e-05) (hash(x)=22559566) +4024 train 6.982373 (lr=2.5602e-05) (hash(x)=21635164) +4025 train 6.824398 (lr=2.5572e-05) (hash(x)=25153242) +4026 train 6.839007 (lr=2.5542e-05) (hash(x)=23522887) +4027 train 6.960725 (lr=2.5512e-05) (hash(x)=24102231) +4028 train 6.956476 (lr=2.5482e-05) (hash(x)=23669103) +4029 train 6.961106 (lr=2.5452e-05) (hash(x)=24901920) +4030 train 7.144661 (lr=2.5423e-05) (hash(x)=26829824) +4031 train 7.004456 (lr=2.5393e-05) (hash(x)=26376027) +4032 train 6.763034 (lr=2.5363e-05) (hash(x)=25110789) +4033 train 7.330034 (lr=2.5333e-05) (hash(x)=27062064) +4034 train 6.968922 (lr=2.5303e-05) (hash(x)=22656832) +4035 train 6.817292 (lr=2.5274e-05) (hash(x)=22471591) +4036 train 7.151025 (lr=2.5244e-05) (hash(x)=29098044) +4037 train 6.800630 (lr=2.5214e-05) (hash(x)=23441436) +4038 train 6.865825 (lr=2.5185e-05) (hash(x)=25091462) +4039 train 6.932598 (lr=2.5155e-05) (hash(x)=25526310) +4040 train 7.018860 (lr=2.5125e-05) (hash(x)=25468387) +4041 train 6.883294 (lr=2.5096e-05) (hash(x)=24779462) +4042 train 6.916968 (lr=2.5066e-05) (hash(x)=25278229) +4043 train 6.922520 (lr=2.5037e-05) (hash(x)=25749229) +4044 train 6.976815 (lr=2.5007e-05) (hash(x)=25938623) +4045 train 7.100609 (lr=2.4978e-05) (hash(x)=27410703) +4046 train 7.085639 (lr=2.4948e-05) (hash(x)=23944021) +4047 train 6.902534 (lr=2.4919e-05) (hash(x)=26163080) +4048 train 6.950209 (lr=2.4889e-05) (hash(x)=25650588) +4049 train 7.079254 (lr=2.4860e-05) (hash(x)=26163104) +4050 val loss 6.9825 +4050 val perplexity 1077.6389 +4050 train 7.129238 (lr=2.4830e-05) (hash(x)=27568757) +4051 train 6.767622 (lr=2.4801e-05) (hash(x)=25983824) +4052 train 6.876596 (lr=2.4772e-05) (hash(x)=21663626) +4053 train 6.887404 (lr=2.4742e-05) (hash(x)=24363656) +4054 train 6.683924 (lr=2.4713e-05) (hash(x)=22503583) +4055 train 6.927454 (lr=2.4684e-05) (hash(x)=22782927) +4056 train 6.963979 (lr=2.4654e-05) (hash(x)=25997900) +4057 train 7.162549 (lr=2.4625e-05) (hash(x)=21280677) +4058 train 6.747827 (lr=2.4596e-05) (hash(x)=22449510) +4059 train 7.127892 (lr=2.4567e-05) (hash(x)=27342614) +4060 train 6.951757 (lr=2.4538e-05) (hash(x)=24698672) +4061 train 7.051161 (lr=2.4509e-05) (hash(x)=24784010) +4062 train 6.928738 (lr=2.4479e-05) (hash(x)=23201473) +4063 train 7.140646 (lr=2.4450e-05) (hash(x)=31792461) +4064 train 6.893345 (lr=2.4421e-05) (hash(x)=25303707) +4065 train 7.591387 (lr=2.4392e-05) (hash(x)=32012132) +4066 train 6.810688 (lr=2.4363e-05) (hash(x)=28948253) +4067 train 6.939274 (lr=2.4334e-05) (hash(x)=24579444) +4068 train 6.804227 (lr=2.4305e-05) (hash(x)=22379856) +4069 train 6.819317 (lr=2.4276e-05) (hash(x)=24219393) +4070 train 7.129419 (lr=2.4247e-05) (hash(x)=24065309) +4071 train 6.880698 (lr=2.4218e-05) (hash(x)=26027784) +4072 train 7.007773 (lr=2.4190e-05) (hash(x)=25977319) +4073 train 6.773194 (lr=2.4161e-05) (hash(x)=24563059) +4074 train 6.931722 (lr=2.4132e-05) (hash(x)=23679988) +4075 train 6.763746 (lr=2.4103e-05) (hash(x)=23796407) +4076 train 6.873153 (lr=2.4074e-05) (hash(x)=22843653) +4077 train 7.015880 (lr=2.4046e-05) (hash(x)=24465024) +4078 train 6.769198 (lr=2.4017e-05) (hash(x)=21805049) +4079 train 6.945394 (lr=2.3988e-05) (hash(x)=25098715) +4080 train 7.022408 (lr=2.3959e-05) (hash(x)=23686798) +4081 train 6.888316 (lr=2.3931e-05) (hash(x)=23492430) +4082 train 6.749174 (lr=2.3902e-05) (hash(x)=23660827) +4083 train 6.882393 (lr=2.3874e-05) (hash(x)=25277692) +4084 train 6.925210 (lr=2.3845e-05) (hash(x)=25977302) +4085 train 6.798039 (lr=2.3816e-05) (hash(x)=24546014) +4086 train 6.798044 (lr=2.3788e-05) (hash(x)=23927922) +4087 train 6.788037 (lr=2.3759e-05) (hash(x)=20733689) +4088 train 6.923127 (lr=2.3731e-05) (hash(x)=23237687) +4089 train 6.886834 (lr=2.3702e-05) (hash(x)=24203337) +4090 train 6.953207 (lr=2.3674e-05) (hash(x)=22511355) +4091 train 6.780158 (lr=2.3646e-05) (hash(x)=21858565) +4092 train 6.865053 (lr=2.3617e-05) (hash(x)=25946762) +4093 train 6.424269 (lr=2.3589e-05) (hash(x)=18440304) +4094 train 6.946508 (lr=2.3560e-05) (hash(x)=27890065) +4095 train 6.950907 (lr=2.3532e-05) (hash(x)=25012219) +4096 train 6.786717 (lr=2.3504e-05) (hash(x)=23731919) +4097 train 6.928146 (lr=2.3476e-05) (hash(x)=24082398) +4098 train 6.884003 (lr=2.3447e-05) (hash(x)=25816243) +4099 train 7.188100 (lr=2.3419e-05) (hash(x)=25365357) +4100 val loss 6.9824 +4100 val perplexity 1077.4924 +4100 train 6.893736 (lr=2.3391e-05) (hash(x)=22754363) +4101 train 6.812254 (lr=2.3363e-05) (hash(x)=23424625) +4102 train 6.950535 (lr=2.3335e-05) (hash(x)=24250485) +4103 train 6.947751 (lr=2.3306e-05) (hash(x)=22952042) +4104 train 6.850920 (lr=2.3278e-05) (hash(x)=25742281) +4105 train 6.776904 (lr=2.3250e-05) (hash(x)=25054382) +4106 train 7.209136 (lr=2.3222e-05) (hash(x)=27346323) +4107 train 6.995317 (lr=2.3194e-05) (hash(x)=23755293) +4108 train 6.865750 (lr=2.3166e-05) (hash(x)=23471296) +4109 train 6.964656 (lr=2.3138e-05) (hash(x)=25792926) +4110 train 6.985290 (lr=2.3110e-05) (hash(x)=24484961) +4111 train 6.996823 (lr=2.3082e-05) (hash(x)=23549853) +4112 train 6.988874 (lr=2.3054e-05) (hash(x)=26199638) +4113 train 6.688270 (lr=2.3027e-05) (hash(x)=23260060) +4114 train 6.927149 (lr=2.2999e-05) (hash(x)=26379145) +4115 train 7.461271 (lr=2.2971e-05) (hash(x)=28187393) +4116 train 6.817246 (lr=2.2943e-05) (hash(x)=22394746) +4117 train 6.967495 (lr=2.2915e-05) (hash(x)=26535767) +4118 train 6.834301 (lr=2.2888e-05) (hash(x)=22614475) +4119 train 6.961668 (lr=2.2860e-05) (hash(x)=24001909) +4120 train 7.030167 (lr=2.2832e-05) (hash(x)=28069697) +4121 train 6.946171 (lr=2.2804e-05) (hash(x)=24772352) +4122 train 7.282460 (lr=2.2777e-05) (hash(x)=28547203) +4123 train 6.872657 (lr=2.2749e-05) (hash(x)=24662903) +4124 train 6.677070 (lr=2.2722e-05) (hash(x)=20160775) +4125 train 6.956312 (lr=2.2694e-05) (hash(x)=27264395) +4126 train 6.933598 (lr=2.2666e-05) (hash(x)=25479509) +4127 train 6.952979 (lr=2.2639e-05) (hash(x)=25011798) +4128 train 6.747194 (lr=2.2611e-05) (hash(x)=25744518) +4129 train 6.784750 (lr=2.2584e-05) (hash(x)=25339108) +4130 train 6.874533 (lr=2.2556e-05) (hash(x)=24595675) +4131 train 6.752941 (lr=2.2529e-05) (hash(x)=22266963) +4132 train 6.961336 (lr=2.2502e-05) (hash(x)=23513916) +4133 train 6.582082 (lr=2.2474e-05) (hash(x)=24723976) +4134 train 6.841199 (lr=2.2447e-05) (hash(x)=23260347) +4135 train 7.043193 (lr=2.2420e-05) (hash(x)=28052131) +4136 train 6.972075 (lr=2.2392e-05) (hash(x)=24039711) +4137 train 6.837603 (lr=2.2365e-05) (hash(x)=23848221) +4138 train 7.032197 (lr=2.2338e-05) (hash(x)=24747105) +4139 train 7.067894 (lr=2.2310e-05) (hash(x)=27364904) +4140 train 6.968752 (lr=2.2283e-05) (hash(x)=23060568) +4141 train 6.882252 (lr=2.2256e-05) (hash(x)=25030412) +4142 train 6.855037 (lr=2.2229e-05) (hash(x)=22462143) +4143 train 6.968240 (lr=2.2202e-05) (hash(x)=25527764) +4144 train 6.900857 (lr=2.2175e-05) (hash(x)=24917732) +4145 train 7.210274 (lr=2.2148e-05) (hash(x)=26607434) +4146 train 6.949368 (lr=2.2121e-05) (hash(x)=23805495) +4147 train 7.186942 (lr=2.2094e-05) (hash(x)=31557726) +4148 train 6.930531 (lr=2.2067e-05) (hash(x)=24792046) +4149 train 7.127240 (lr=2.2040e-05) (hash(x)=27110417) +4150 val loss 6.9820 +4150 val perplexity 1077.0764 +4150 train 6.935597 (lr=2.2013e-05) (hash(x)=23812638) +4151 train 6.882813 (lr=2.1986e-05) (hash(x)=23822119) +4152 train 6.735543 (lr=2.1959e-05) (hash(x)=23288684) +4153 train 6.681854 (lr=2.1932e-05) (hash(x)=22477165) +4154 train 6.985380 (lr=2.1905e-05) (hash(x)=30211681) +4155 train 6.785485 (lr=2.1878e-05) (hash(x)=21026034) +4156 train 6.920280 (lr=2.1852e-05) (hash(x)=25237015) +4157 train 6.714746 (lr=2.1825e-05) (hash(x)=23084445) +4158 train 6.719799 (lr=2.1798e-05) (hash(x)=23550270) +4159 train 6.933856 (lr=2.1771e-05) (hash(x)=25878395) +4160 train 6.897473 (lr=2.1745e-05) (hash(x)=25142805) +4161 train 6.880381 (lr=2.1718e-05) (hash(x)=25928298) +4162 train 7.293832 (lr=2.1691e-05) (hash(x)=24304343) +4163 train 6.804551 (lr=2.1665e-05) (hash(x)=22911010) +4164 train 6.825936 (lr=2.1638e-05) (hash(x)=23593283) +4165 train 6.959734 (lr=2.1612e-05) (hash(x)=22504637) +4166 train 6.807169 (lr=2.1585e-05) (hash(x)=23896829) +4167 train 6.922854 (lr=2.1558e-05) (hash(x)=26993263) +4168 train 7.274817 (lr=2.1532e-05) (hash(x)=30806534) +4169 train 6.948352 (lr=2.1506e-05) (hash(x)=23411126) +4170 train 6.930604 (lr=2.1479e-05) (hash(x)=24251549) +4171 train 6.727427 (lr=2.1453e-05) (hash(x)=23899619) +4172 train 6.715750 (lr=2.1426e-05) (hash(x)=24298532) +4173 train 6.960453 (lr=2.1400e-05) (hash(x)=25643027) +4174 train 6.832264 (lr=2.1374e-05) (hash(x)=21440632) +4175 train 6.981296 (lr=2.1347e-05) (hash(x)=23119758) +4176 train 7.193402 (lr=2.1321e-05) (hash(x)=25213587) +4177 train 6.863149 (lr=2.1295e-05) (hash(x)=22277032) +4178 train 6.948827 (lr=2.1269e-05) (hash(x)=23148627) +4179 train 7.310722 (lr=2.1242e-05) (hash(x)=30897645) +4180 train 7.052209 (lr=2.1216e-05) (hash(x)=21977825) +4181 train 6.793787 (lr=2.1190e-05) (hash(x)=20997528) +4182 train 6.795938 (lr=2.1164e-05) (hash(x)=19751176) +4183 train 7.049752 (lr=2.1138e-05) (hash(x)=24425875) +4184 train 7.166653 (lr=2.1112e-05) (hash(x)=22684492) +4185 train 6.725319 (lr=2.1086e-05) (hash(x)=24089962) +4186 train 6.898177 (lr=2.1060e-05) (hash(x)=22821539) +4187 train 7.050748 (lr=2.1034e-05) (hash(x)=28253341) +4188 train 7.137774 (lr=2.1008e-05) (hash(x)=24483642) +4189 train 7.081694 (lr=2.0982e-05) (hash(x)=25382746) +4190 train 7.076509 (lr=2.0956e-05) (hash(x)=25475873) +4191 train 6.944168 (lr=2.0930e-05) (hash(x)=23403513) +4192 train 7.043818 (lr=2.0904e-05) (hash(x)=28701704) +4193 train 7.096530 (lr=2.0878e-05) (hash(x)=24574442) +4194 train 7.095617 (lr=2.0853e-05) (hash(x)=28759403) +4195 train 7.033293 (lr=2.0827e-05) (hash(x)=24994995) +4196 train 6.711761 (lr=2.0801e-05) (hash(x)=23060032) +4197 train 7.144372 (lr=2.0775e-05) (hash(x)=26721799) +4198 train 7.321858 (lr=2.0750e-05) (hash(x)=30706190) +4199 train 7.195271 (lr=2.0724e-05) (hash(x)=24751625) +4200 val loss 6.9779 +4200 val perplexity 1072.6364 +4200 train 6.890409 (lr=2.0698e-05) (hash(x)=27731310) +4201 train 7.138705 (lr=2.0673e-05) (hash(x)=25708316) +4202 train 6.938560 (lr=2.0647e-05) (hash(x)=22854783) +4203 train 6.716111 (lr=2.0622e-05) (hash(x)=24569689) +4204 train 6.677046 (lr=2.0596e-05) (hash(x)=21289331) +4205 train 6.654178 (lr=2.0570e-05) (hash(x)=20503047) +4206 train 6.804740 (lr=2.0545e-05) (hash(x)=23395376) +4207 train 7.034083 (lr=2.0520e-05) (hash(x)=25589724) +4208 train 6.920739 (lr=2.0494e-05) (hash(x)=23229539) +4209 train 6.865462 (lr=2.0469e-05) (hash(x)=22717216) +4210 train 6.859317 (lr=2.0443e-05) (hash(x)=24375489) +4211 train 6.906359 (lr=2.0418e-05) (hash(x)=26240309) +4212 train 6.811561 (lr=2.0393e-05) (hash(x)=25835592) +4213 train 6.834336 (lr=2.0367e-05) (hash(x)=20674151) +4214 train 6.954495 (lr=2.0342e-05) (hash(x)=29588582) +4215 train 7.128484 (lr=2.0317e-05) (hash(x)=27287150) +4216 train 6.854025 (lr=2.0292e-05) (hash(x)=24594186) +4217 train 6.987412 (lr=2.0266e-05) (hash(x)=26302259) +4218 train 7.150728 (lr=2.0241e-05) (hash(x)=22937308) +4219 train 6.776382 (lr=2.0216e-05) (hash(x)=21620160) +4220 train 6.995052 (lr=2.0191e-05) (hash(x)=25884337) +4221 train 6.854055 (lr=2.0166e-05) (hash(x)=19948407) +4222 train 6.921988 (lr=2.0141e-05) (hash(x)=25199121) +4223 train 7.000987 (lr=2.0116e-05) (hash(x)=25909048) +4224 train 6.805536 (lr=2.0091e-05) (hash(x)=20171092) +4225 train 6.983148 (lr=2.0066e-05) (hash(x)=26199182) +4226 train 7.228117 (lr=2.0041e-05) (hash(x)=28968813) +4227 train 6.844213 (lr=2.0016e-05) (hash(x)=24988924) +4228 train 6.948812 (lr=1.9991e-05) (hash(x)=26987620) +4229 train 6.931849 (lr=1.9966e-05) (hash(x)=24051167) +4230 train 6.990993 (lr=1.9941e-05) (hash(x)=24225864) +4231 train 6.713086 (lr=1.9917e-05) (hash(x)=21749184) +4232 train 6.832623 (lr=1.9892e-05) (hash(x)=21242537) +4233 train 6.954305 (lr=1.9867e-05) (hash(x)=24959243) +4234 train 6.759676 (lr=1.9842e-05) (hash(x)=25457559) +4235 train 6.973918 (lr=1.9818e-05) (hash(x)=28016509) +4236 train 6.946700 (lr=1.9793e-05) (hash(x)=26972689) +4237 train 6.755084 (lr=1.9768e-05) (hash(x)=24963855) +4238 train 6.960756 (lr=1.9744e-05) (hash(x)=26438819) +4239 train 6.566227 (lr=1.9719e-05) (hash(x)=16968685) +4240 train 6.844315 (lr=1.9694e-05) (hash(x)=25351350) +4241 train 7.047826 (lr=1.9670e-05) (hash(x)=24744756) +4242 train 6.903722 (lr=1.9645e-05) (hash(x)=19694178) +4243 train 6.670654 (lr=1.9621e-05) (hash(x)=23250948) +4244 train 7.052841 (lr=1.9596e-05) (hash(x)=23742260) +4245 train 6.850719 (lr=1.9572e-05) (hash(x)=21033881) +4246 train 6.893710 (lr=1.9548e-05) (hash(x)=23609357) +4247 train 6.868445 (lr=1.9523e-05) (hash(x)=29704860) +4248 train 7.038063 (lr=1.9499e-05) (hash(x)=23749636) +4249 train 6.727242 (lr=1.9475e-05) (hash(x)=23068363) +4250 val loss 6.9739 +4250 val perplexity 1068.4066 +4250 train 6.557707 (lr=1.9450e-05) (hash(x)=20771670) +4251 train 6.814130 (lr=1.9426e-05) (hash(x)=23631523) +4252 train 7.096972 (lr=1.9402e-05) (hash(x)=26852519) +4253 train 7.023328 (lr=1.9378e-05) (hash(x)=23414648) +4254 train 6.914050 (lr=1.9353e-05) (hash(x)=28210484) +4255 train 6.660613 (lr=1.9329e-05) (hash(x)=23371548) +4256 train 6.897535 (lr=1.9305e-05) (hash(x)=32365249) +4257 train 7.056584 (lr=1.9281e-05) (hash(x)=25884825) +4258 train 6.982232 (lr=1.9257e-05) (hash(x)=27066161) +4259 train 6.657751 (lr=1.9233e-05) (hash(x)=23135296) +4260 train 6.896335 (lr=1.9209e-05) (hash(x)=25081364) +4261 train 6.740841 (lr=1.9185e-05) (hash(x)=24686637) +4262 train 6.721993 (lr=1.9161e-05) (hash(x)=21374749) +4263 train 6.834920 (lr=1.9137e-05) (hash(x)=23680607) +4264 train 7.060061 (lr=1.9113e-05) (hash(x)=25164153) +4265 train 6.772034 (lr=1.9089e-05) (hash(x)=22871659) +4266 train 6.709760 (lr=1.9065e-05) (hash(x)=22541829) +4267 train 6.841505 (lr=1.9042e-05) (hash(x)=25216320) +4268 train 6.988495 (lr=1.9018e-05) (hash(x)=26311404) +4269 train 6.920850 (lr=1.8994e-05) (hash(x)=26470755) +4270 train 6.977463 (lr=1.8970e-05) (hash(x)=26872581) +4271 train 6.819581 (lr=1.8947e-05) (hash(x)=24136535) +4272 train 6.889787 (lr=1.8923e-05) (hash(x)=21616327) +4273 train 7.013144 (lr=1.8899e-05) (hash(x)=29383906) +4274 train 7.420208 (lr=1.8876e-05) (hash(x)=28095903) +4275 train 6.695823 (lr=1.8852e-05) (hash(x)=24617268) +4276 train 6.942631 (lr=1.8828e-05) (hash(x)=26788479) +4277 train 6.911702 (lr=1.8805e-05) (hash(x)=25403205) +4278 train 6.803558 (lr=1.8781e-05) (hash(x)=24295823) +4279 train 6.785613 (lr=1.8758e-05) (hash(x)=24291572) +4280 train 6.834525 (lr=1.8734e-05) (hash(x)=21606938) +4281 train 6.862778 (lr=1.8711e-05) (hash(x)=28146936) +4282 train 7.095978 (lr=1.8688e-05) (hash(x)=28851234) +4283 train 6.829030 (lr=1.8664e-05) (hash(x)=25526717) +4284 train 7.015430 (lr=1.8641e-05) (hash(x)=25217943) +4285 train 6.691682 (lr=1.8618e-05) (hash(x)=22240570) +4286 train 6.789533 (lr=1.8594e-05) (hash(x)=26572462) +4287 train 7.047129 (lr=1.8571e-05) (hash(x)=25870938) +4288 train 6.843897 (lr=1.8548e-05) (hash(x)=25302109) +4289 train 6.713566 (lr=1.8525e-05) (hash(x)=22962888) +4290 train 6.845227 (lr=1.8501e-05) (hash(x)=20085773) +4291 train 6.645203 (lr=1.8478e-05) (hash(x)=21716336) +4292 train 6.797299 (lr=1.8455e-05) (hash(x)=21045672) +4293 train 6.917006 (lr=1.8432e-05) (hash(x)=24563963) +4294 train 6.874293 (lr=1.8409e-05) (hash(x)=27144130) +4295 train 7.069573 (lr=1.8386e-05) (hash(x)=23613060) +4296 train 7.069130 (lr=1.8363e-05) (hash(x)=30130128) +4297 train 6.976974 (lr=1.8340e-05) (hash(x)=27364688) +4298 train 6.702613 (lr=1.8317e-05) (hash(x)=22983508) +4299 train 6.667240 (lr=1.8294e-05) (hash(x)=24139659) +4300 val loss 6.9744 +4300 val perplexity 1068.9213 +4300 train 6.931429 (lr=1.8271e-05) (hash(x)=25218666) +4301 train 7.258739 (lr=1.8248e-05) (hash(x)=26640743) +4302 train 6.928111 (lr=1.8225e-05) (hash(x)=24084098) +4303 train 6.751441 (lr=1.8203e-05) (hash(x)=23278075) +4304 train 7.000899 (lr=1.8180e-05) (hash(x)=26571053) +4305 train 6.747225 (lr=1.8157e-05) (hash(x)=20591951) +4306 train 6.868339 (lr=1.8134e-05) (hash(x)=24443041) +4307 train 6.636283 (lr=1.8112e-05) (hash(x)=20279799) +4308 train 6.928843 (lr=1.8089e-05) (hash(x)=27092069) +4309 train 6.706892 (lr=1.8066e-05) (hash(x)=24045703) +4310 train 6.853042 (lr=1.8044e-05) (hash(x)=25360189) +4311 train 6.867193 (lr=1.8021e-05) (hash(x)=22273288) +4312 train 6.909819 (lr=1.7999e-05) (hash(x)=22142901) +4313 train 7.151307 (lr=1.7976e-05) (hash(x)=24818246) +4314 train 7.087914 (lr=1.7954e-05) (hash(x)=25672352) +4315 train 6.779258 (lr=1.7931e-05) (hash(x)=23823738) +4316 train 6.801879 (lr=1.7909e-05) (hash(x)=24007341) +4317 train 7.420997 (lr=1.7886e-05) (hash(x)=29371345) +4318 train 6.863397 (lr=1.7864e-05) (hash(x)=27710420) +4319 train 6.859536 (lr=1.7842e-05) (hash(x)=23986451) +4320 train 6.939004 (lr=1.7819e-05) (hash(x)=25310095) +4321 train 6.973058 (lr=1.7797e-05) (hash(x)=26487840) +4322 train 6.815505 (lr=1.7775e-05) (hash(x)=22305036) +4323 train 6.861199 (lr=1.7752e-05) (hash(x)=22007606) +4324 train 6.742104 (lr=1.7730e-05) (hash(x)=23967063) +4325 train 6.571010 (lr=1.7708e-05) (hash(x)=21805011) +4326 train 6.821456 (lr=1.7686e-05) (hash(x)=24486636) +4327 train 6.669281 (lr=1.7664e-05) (hash(x)=26005846) +4328 train 6.718630 (lr=1.7642e-05) (hash(x)=21610448) +4329 train 6.869566 (lr=1.7620e-05) (hash(x)=22609993) +4330 train 6.814145 (lr=1.7598e-05) (hash(x)=23183024) +4331 train 6.689408 (lr=1.7576e-05) (hash(x)=21124146) +4332 train 7.239170 (lr=1.7554e-05) (hash(x)=30512535) +4333 train 6.997063 (lr=1.7532e-05) (hash(x)=25757491) +4334 train 6.994525 (lr=1.7510e-05) (hash(x)=23569736) +4335 train 6.750982 (lr=1.7488e-05) (hash(x)=26393576) +4336 train 6.686584 (lr=1.7466e-05) (hash(x)=24896330) +4337 train 6.867863 (lr=1.7444e-05) (hash(x)=26252028) +4338 train 6.887578 (lr=1.7422e-05) (hash(x)=27386936) +4339 train 6.872812 (lr=1.7401e-05) (hash(x)=23905543) +4340 train 6.804368 (lr=1.7379e-05) (hash(x)=23364632) +4341 train 7.454045 (lr=1.7357e-05) (hash(x)=28689501) +4342 train 6.916865 (lr=1.7335e-05) (hash(x)=24663231) +4343 train 7.173394 (lr=1.7314e-05) (hash(x)=33296423) +4344 train 7.125051 (lr=1.7292e-05) (hash(x)=25497517) +4345 train 6.772633 (lr=1.7271e-05) (hash(x)=26161975) +4346 train 6.824221 (lr=1.7249e-05) (hash(x)=25937843) +4347 train 6.994617 (lr=1.7228e-05) (hash(x)=26612719) +4348 train 6.891436 (lr=1.7206e-05) (hash(x)=24455131) +4349 train 6.652983 (lr=1.7185e-05) (hash(x)=22842285) +4350 val loss 6.9742 +4350 val perplexity 1068.6874 +4350 train 7.079115 (lr=1.7163e-05) (hash(x)=27931313) +4351 train 6.939875 (lr=1.7142e-05) (hash(x)=26513425) +4352 train 6.964952 (lr=1.7120e-05) (hash(x)=24201459) +4353 train 6.866683 (lr=1.7099e-05) (hash(x)=21284018) +4354 train 6.800931 (lr=1.7078e-05) (hash(x)=24367707) +4355 train 6.908837 (lr=1.7056e-05) (hash(x)=26987888) +4356 train 6.868203 (lr=1.7035e-05) (hash(x)=24928818) +4357 train 6.866924 (lr=1.7014e-05) (hash(x)=24050563) +4358 train 6.897917 (lr=1.6993e-05) (hash(x)=25389890) +4359 train 6.678201 (lr=1.6971e-05) (hash(x)=23231269) +4360 train 6.747256 (lr=1.6950e-05) (hash(x)=21380877) +4361 train 7.205585 (lr=1.6929e-05) (hash(x)=26970987) +4362 train 7.218522 (lr=1.6908e-05) (hash(x)=25245269) +4363 train 7.289506 (lr=1.6887e-05) (hash(x)=24910068) +4364 train 6.916201 (lr=1.6866e-05) (hash(x)=26692459) +4365 train 6.665393 (lr=1.6845e-05) (hash(x)=21475124) +4366 train 6.615934 (lr=1.6824e-05) (hash(x)=22717431) +4367 train 6.823417 (lr=1.6803e-05) (hash(x)=22312912) +4368 train 6.872872 (lr=1.6782e-05) (hash(x)=24990050) +4369 train 6.803082 (lr=1.6761e-05) (hash(x)=25202491) +4370 train 6.892229 (lr=1.6740e-05) (hash(x)=24144633) +4371 train 6.983183 (lr=1.6719e-05) (hash(x)=28451492) +4372 train 6.939317 (lr=1.6699e-05) (hash(x)=22821810) +4373 train 7.009575 (lr=1.6678e-05) (hash(x)=26662729) +4374 train 6.769855 (lr=1.6657e-05) (hash(x)=24202447) +4375 train 6.720835 (lr=1.6636e-05) (hash(x)=21194753) +4376 train 7.289568 (lr=1.6616e-05) (hash(x)=25571299) +4377 train 6.922635 (lr=1.6595e-05) (hash(x)=26218321) +4378 train 6.825409 (lr=1.6574e-05) (hash(x)=22411026) +4379 train 6.907009 (lr=1.6554e-05) (hash(x)=23880312) +4380 train 6.783860 (lr=1.6533e-05) (hash(x)=22532092) +4381 train 6.889909 (lr=1.6513e-05) (hash(x)=23217194) +4382 train 6.765792 (lr=1.6492e-05) (hash(x)=26233330) +4383 train 6.847762 (lr=1.6472e-05) (hash(x)=26803143) +4384 train 6.696793 (lr=1.6451e-05) (hash(x)=21823248) +4385 train 6.880379 (lr=1.6431e-05) (hash(x)=23427249) +4386 train 6.815756 (lr=1.6410e-05) (hash(x)=25488580) +4387 train 6.762797 (lr=1.6390e-05) (hash(x)=24147822) +4388 train 6.560263 (lr=1.6370e-05) (hash(x)=23483022) +4389 train 6.733420 (lr=1.6350e-05) (hash(x)=21491600) +4390 train 6.792593 (lr=1.6329e-05) (hash(x)=21655173) +4391 train 6.894414 (lr=1.6309e-05) (hash(x)=22868399) +4392 train 6.514053 (lr=1.6289e-05) (hash(x)=24232955) +4393 train 6.906802 (lr=1.6269e-05) (hash(x)=23119732) +4394 train 7.083749 (lr=1.6248e-05) (hash(x)=28964917) +4395 train 6.726044 (lr=1.6228e-05) (hash(x)=24666868) +4396 train 6.777651 (lr=1.6208e-05) (hash(x)=23813669) +4397 train 6.826147 (lr=1.6188e-05) (hash(x)=23299873) +4398 train 6.969268 (lr=1.6168e-05) (hash(x)=26234265) +4399 train 7.078852 (lr=1.6148e-05) (hash(x)=25668453) +4400 val loss 6.9692 +4400 val perplexity 1063.3480 +4400 train 6.696326 (lr=1.6128e-05) (hash(x)=22792643) +4401 train 6.947500 (lr=1.6108e-05) (hash(x)=24617431) +4402 train 7.047215 (lr=1.6088e-05) (hash(x)=26958453) +4403 train 6.959738 (lr=1.6069e-05) (hash(x)=28461208) +4404 train 7.039156 (lr=1.6049e-05) (hash(x)=23235698) +4405 train 6.797198 (lr=1.6029e-05) (hash(x)=26589581) +4406 train 6.836309 (lr=1.6009e-05) (hash(x)=28646133) +4407 train 6.564791 (lr=1.5989e-05) (hash(x)=24580038) +4408 train 6.789688 (lr=1.5970e-05) (hash(x)=24051767) +4409 train 6.735814 (lr=1.5950e-05) (hash(x)=22232039) +4410 train 7.060139 (lr=1.5930e-05) (hash(x)=28479353) +4411 train 6.717703 (lr=1.5911e-05) (hash(x)=22703857) +4412 train 6.795832 (lr=1.5891e-05) (hash(x)=24445973) +4413 train 6.817857 (lr=1.5871e-05) (hash(x)=22100323) +4414 train 6.900712 (lr=1.5852e-05) (hash(x)=23660633) +4415 train 6.932615 (lr=1.5832e-05) (hash(x)=25695897) +4416 train 6.975669 (lr=1.5813e-05) (hash(x)=24604080) +4417 train 6.685110 (lr=1.5793e-05) (hash(x)=22730308) +4418 train 7.086121 (lr=1.5774e-05) (hash(x)=25641174) +4419 train 6.746381 (lr=1.5755e-05) (hash(x)=23634054) +4420 train 6.742598 (lr=1.5735e-05) (hash(x)=26513268) +4421 train 7.003204 (lr=1.5716e-05) (hash(x)=27573268) +4422 train 6.736137 (lr=1.5697e-05) (hash(x)=22891103) +4423 train 6.923093 (lr=1.5677e-05) (hash(x)=25682723) +4424 train 6.968533 (lr=1.5658e-05) (hash(x)=25791125) +4425 train 6.541458 (lr=1.5639e-05) (hash(x)=23585532) +4426 train 6.631673 (lr=1.5620e-05) (hash(x)=25948723) +4427 train 6.790668 (lr=1.5601e-05) (hash(x)=22983818) +4428 train 7.043502 (lr=1.5581e-05) (hash(x)=27489824) +4429 train 7.103889 (lr=1.5562e-05) (hash(x)=23962560) +4430 train 6.942185 (lr=1.5543e-05) (hash(x)=23802688) +4431 train 6.928871 (lr=1.5524e-05) (hash(x)=25231749) +4432 train 6.910032 (lr=1.5505e-05) (hash(x)=28110264) +4433 train 6.745342 (lr=1.5486e-05) (hash(x)=22504975) +4434 train 6.585304 (lr=1.5467e-05) (hash(x)=18167940) +4435 train 6.675123 (lr=1.5449e-05) (hash(x)=22602033) +4436 train 7.047508 (lr=1.5430e-05) (hash(x)=25547734) +4437 train 7.001968 (lr=1.5411e-05) (hash(x)=28369634) +4438 train 7.249568 (lr=1.5392e-05) (hash(x)=30572716) +4439 train 7.074210 (lr=1.5373e-05) (hash(x)=27646283) +4440 train 6.667136 (lr=1.5354e-05) (hash(x)=22185738) +4441 train 7.031108 (lr=1.5336e-05) (hash(x)=25752645) +4442 train 6.362743 (lr=1.5317e-05) (hash(x)=16335769) +4443 train 6.660172 (lr=1.5298e-05) (hash(x)=24225306) +4444 train 6.750661 (lr=1.5280e-05) (hash(x)=21536256) +4445 train 6.994555 (lr=1.5261e-05) (hash(x)=27837497) +4446 train 7.084785 (lr=1.5243e-05) (hash(x)=26340510) +4447 train 6.721139 (lr=1.5224e-05) (hash(x)=25310638) +4448 train 7.114968 (lr=1.5206e-05) (hash(x)=27562096) +4449 train 6.948390 (lr=1.5187e-05) (hash(x)=21822104) +4450 val loss 6.9697 +4450 val perplexity 1063.8917 +4450 train 6.808414 (lr=1.5169e-05) (hash(x)=23373839) +4451 train 7.084526 (lr=1.5150e-05) (hash(x)=26638313) +4452 train 6.793658 (lr=1.5132e-05) (hash(x)=20638335) +4453 train 7.417368 (lr=1.5114e-05) (hash(x)=32404659) +4454 train 6.938943 (lr=1.5095e-05) (hash(x)=26280758) +4455 train 6.871789 (lr=1.5077e-05) (hash(x)=23412334) +4456 train 6.889907 (lr=1.5059e-05) (hash(x)=22962570) +4457 train 6.613852 (lr=1.5040e-05) (hash(x)=21916690) +4458 train 7.197921 (lr=1.5022e-05) (hash(x)=25037197) +4459 train 6.907106 (lr=1.5004e-05) (hash(x)=23936809) +4460 train 6.863311 (lr=1.4986e-05) (hash(x)=24887124) +4461 train 6.820173 (lr=1.4968e-05) (hash(x)=24602728) +4462 train 6.670404 (lr=1.4950e-05) (hash(x)=23433273) +4463 train 6.910185 (lr=1.4932e-05) (hash(x)=27829482) +4464 train 6.821253 (lr=1.4914e-05) (hash(x)=25969594) +4465 train 6.685933 (lr=1.4896e-05) (hash(x)=19382426) +4466 train 7.025496 (lr=1.4878e-05) (hash(x)=24934849) +4467 train 6.813564 (lr=1.4860e-05) (hash(x)=22773307) +4468 train 7.072294 (lr=1.4842e-05) (hash(x)=24926482) +4469 train 6.938667 (lr=1.4824e-05) (hash(x)=26772134) +4470 train 6.577705 (lr=1.4806e-05) (hash(x)=20062224) +4471 train 6.888284 (lr=1.4789e-05) (hash(x)=25784576) +4472 train 6.912758 (lr=1.4771e-05) (hash(x)=24998258) +4473 train 6.689596 (lr=1.4753e-05) (hash(x)=23086245) +4474 train 6.852445 (lr=1.4735e-05) (hash(x)=23073697) +4475 train 6.733917 (lr=1.4718e-05) (hash(x)=24228273) +4476 train 7.064919 (lr=1.4700e-05) (hash(x)=25182395) +4477 train 6.873761 (lr=1.4682e-05) (hash(x)=26187461) +4478 train 7.237193 (lr=1.4665e-05) (hash(x)=27869663) +4479 train 7.023027 (lr=1.4647e-05) (hash(x)=28563822) +4480 train 6.988755 (lr=1.4630e-05) (hash(x)=29772723) +4481 train 6.898922 (lr=1.4612e-05) (hash(x)=24672684) +4482 train 6.976464 (lr=1.4595e-05) (hash(x)=24186582) +4483 train 6.770374 (lr=1.4577e-05) (hash(x)=22613352) +4484 train 7.009506 (lr=1.4560e-05) (hash(x)=21988584) +4485 train 6.928655 (lr=1.4543e-05) (hash(x)=23785827) +4486 train 6.870027 (lr=1.4525e-05) (hash(x)=24743580) +4487 train 6.794141 (lr=1.4508e-05) (hash(x)=26277740) +4488 train 7.025149 (lr=1.4491e-05) (hash(x)=24414336) +4489 train 7.026216 (lr=1.4474e-05) (hash(x)=26103115) +4490 train 6.957793 (lr=1.4456e-05) (hash(x)=24247829) +4491 train 7.002135 (lr=1.4439e-05) (hash(x)=25910468) +4492 train 6.938821 (lr=1.4422e-05) (hash(x)=23035523) +4493 train 6.901908 (lr=1.4405e-05) (hash(x)=25036040) +4494 train 6.737618 (lr=1.4388e-05) (hash(x)=23742647) +4495 train 7.073360 (lr=1.4371e-05) (hash(x)=25973739) +4496 train 6.945685 (lr=1.4354e-05) (hash(x)=25988151) +4497 train 7.230287 (lr=1.4337e-05) (hash(x)=29686377) +4498 train 7.825242 (lr=1.4320e-05) (hash(x)=34295460) +4499 train 6.595088 (lr=1.4303e-05) (hash(x)=21974495) +4500 val loss 6.9648 +4500 val perplexity 1058.7313 +4500 train 6.891386 (lr=1.4286e-05) (hash(x)=26050769) +4501 train 6.826066 (lr=1.4269e-05) (hash(x)=26055960) +4502 train 6.853901 (lr=1.4252e-05) (hash(x)=24501814) +4503 train 6.840253 (lr=1.4236e-05) (hash(x)=24048226) +4504 train 6.405354 (lr=1.4219e-05) (hash(x)=23492861) +4505 train 6.873875 (lr=1.4202e-05) (hash(x)=26408832) +4506 train 7.112230 (lr=1.4186e-05) (hash(x)=26771989) +4507 train 7.125079 (lr=1.4169e-05) (hash(x)=31689089) +4508 train 6.965782 (lr=1.4152e-05) (hash(x)=24874804) +4509 train 6.786936 (lr=1.4136e-05) (hash(x)=25221725) +4510 train 6.944361 (lr=1.4119e-05) (hash(x)=24482119) +4511 train 6.826603 (lr=1.4103e-05) (hash(x)=23209952) +4512 train 6.690516 (lr=1.4086e-05) (hash(x)=19180586) +4513 train 6.871523 (lr=1.4070e-05) (hash(x)=25975211) +4514 train 7.316276 (lr=1.4053e-05) (hash(x)=31450093) +4515 train 6.734814 (lr=1.4037e-05) (hash(x)=24836505) +4516 train 7.225059 (lr=1.4020e-05) (hash(x)=31115605) +4517 train 6.974825 (lr=1.4004e-05) (hash(x)=29081003) +4518 train 7.068652 (lr=1.3988e-05) (hash(x)=25633419) +4519 train 6.762940 (lr=1.3971e-05) (hash(x)=24929260) +4520 train 6.893869 (lr=1.3955e-05) (hash(x)=25088572) +4521 train 7.267303 (lr=1.3939e-05) (hash(x)=31355108) +4522 train 7.114799 (lr=1.3923e-05) (hash(x)=25068406) +4523 train 6.954459 (lr=1.3907e-05) (hash(x)=26776257) +4524 train 6.892721 (lr=1.3890e-05) (hash(x)=23307542) +4525 train 6.741121 (lr=1.3874e-05) (hash(x)=22466194) +4526 train 6.895305 (lr=1.3858e-05) (hash(x)=25030928) +4527 train 6.498191 (lr=1.3842e-05) (hash(x)=16899654) +4528 train 6.852286 (lr=1.3826e-05) (hash(x)=23999559) +4529 train 6.978397 (lr=1.3810e-05) (hash(x)=21389104) +4530 train 6.987710 (lr=1.3794e-05) (hash(x)=30558637) +4531 train 7.086897 (lr=1.3778e-05) (hash(x)=21875140) +4532 train 6.920078 (lr=1.3763e-05) (hash(x)=24902157) +4533 train 6.903161 (lr=1.3747e-05) (hash(x)=28022349) +4534 train 7.067341 (lr=1.3731e-05) (hash(x)=29456041) +4535 train 7.010371 (lr=1.3715e-05) (hash(x)=28701451) +4536 train 6.684434 (lr=1.3699e-05) (hash(x)=22874706) +4537 train 6.617290 (lr=1.3684e-05) (hash(x)=20174998) +4538 train 6.726650 (lr=1.3668e-05) (hash(x)=22643736) +4539 train 7.000022 (lr=1.3652e-05) (hash(x)=24430351) +4540 train 6.832619 (lr=1.3637e-05) (hash(x)=23915392) +4541 train 6.635722 (lr=1.3621e-05) (hash(x)=19353265) +4542 train 6.704335 (lr=1.3606e-05) (hash(x)=22419491) +4543 train 7.155138 (lr=1.3590e-05) (hash(x)=26805171) +4544 train 7.368014 (lr=1.3575e-05) (hash(x)=27147478) +4545 train 6.821487 (lr=1.3559e-05) (hash(x)=25684089) +4546 train 7.061756 (lr=1.3544e-05) (hash(x)=25501424) +4547 train 6.718489 (lr=1.3528e-05) (hash(x)=22971332) +4548 train 6.814478 (lr=1.3513e-05) (hash(x)=23772630) +4549 train 6.921009 (lr=1.3498e-05) (hash(x)=23430488) +4550 val loss 6.9664 +4550 val perplexity 1060.3475 +4550 train 6.819018 (lr=1.3482e-05) (hash(x)=25389402) +4551 train 6.890248 (lr=1.3467e-05) (hash(x)=23313042) +4552 train 6.564666 (lr=1.3452e-05) (hash(x)=23625720) +4553 train 6.916408 (lr=1.3437e-05) (hash(x)=23152055) +4554 train 6.776188 (lr=1.3422e-05) (hash(x)=23643199) +4555 train 6.687548 (lr=1.3407e-05) (hash(x)=25651770) +4556 train 6.676005 (lr=1.3391e-05) (hash(x)=22219315) +4557 train 6.971007 (lr=1.3376e-05) (hash(x)=25076930) +4558 train 7.323937 (lr=1.3361e-05) (hash(x)=31787246) +4559 train 7.109982 (lr=1.3346e-05) (hash(x)=21621425) +4560 train 6.923514 (lr=1.3331e-05) (hash(x)=28836715) +4561 train 6.844891 (lr=1.3316e-05) (hash(x)=23028096) +4562 train 6.821447 (lr=1.3301e-05) (hash(x)=25664497) +4563 train 6.863053 (lr=1.3287e-05) (hash(x)=25104779) +4564 train 6.887776 (lr=1.3272e-05) (hash(x)=27507283) +4565 train 7.237133 (lr=1.3257e-05) (hash(x)=26484624) +4566 train 6.897272 (lr=1.3242e-05) (hash(x)=24836151) +4567 train 7.087552 (lr=1.3227e-05) (hash(x)=30109204) +4568 train 6.646326 (lr=1.3213e-05) (hash(x)=24267037) +4569 train 6.947662 (lr=1.3198e-05) (hash(x)=19707952) +4570 train 6.905703 (lr=1.3183e-05) (hash(x)=24677643) +4571 train 6.858934 (lr=1.3169e-05) (hash(x)=25317075) +4572 train 6.676261 (lr=1.3154e-05) (hash(x)=25191498) +4573 train 7.309587 (lr=1.3140e-05) (hash(x)=26848392) +4574 train 7.107043 (lr=1.3125e-05) (hash(x)=26202222) +4575 train 6.915378 (lr=1.3111e-05) (hash(x)=22341233) +4576 train 6.892946 (lr=1.3096e-05) (hash(x)=24349007) +4577 train 7.129251 (lr=1.3082e-05) (hash(x)=30059041) +4578 train 7.244252 (lr=1.3067e-05) (hash(x)=26107179) +4579 train 6.865200 (lr=1.3053e-05) (hash(x)=25850406) +4580 train 6.814491 (lr=1.3039e-05) (hash(x)=26496160) +4581 train 6.539027 (lr=1.3024e-05) (hash(x)=23340008) +4582 train 6.726964 (lr=1.3010e-05) (hash(x)=22137910) +4583 train 6.798411 (lr=1.2996e-05) (hash(x)=23732439) +4584 train 6.736813 (lr=1.2982e-05) (hash(x)=22063327) +4585 train 6.780525 (lr=1.2968e-05) (hash(x)=22629233) +4586 train 6.777255 (lr=1.2954e-05) (hash(x)=20363154) +4587 train 6.658440 (lr=1.2939e-05) (hash(x)=20890194) +4588 train 6.673826 (lr=1.2925e-05) (hash(x)=21133576) +4589 train 6.686024 (lr=1.2911e-05) (hash(x)=17617224) +4590 train 7.450271 (lr=1.2897e-05) (hash(x)=36927425) +4591 train 7.248208 (lr=1.2883e-05) (hash(x)=23302742) +4592 train 6.884362 (lr=1.2869e-05) (hash(x)=26149010) +4593 train 6.953883 (lr=1.2856e-05) (hash(x)=25768565) +4594 train 6.762185 (lr=1.2842e-05) (hash(x)=21162451) +4595 train 7.213804 (lr=1.2828e-05) (hash(x)=27134148) +4596 train 7.337763 (lr=1.2814e-05) (hash(x)=28646304) +4597 train 7.301623 (lr=1.2800e-05) (hash(x)=32041599) +4598 train 7.558914 (lr=1.2787e-05) (hash(x)=32791607) +4599 train 7.075627 (lr=1.2773e-05) (hash(x)=23262927) +4600 val loss 6.9723 +4600 val perplexity 1066.7227 +4600 train 6.850286 (lr=1.2759e-05) (hash(x)=24952007) +4601 train 6.708328 (lr=1.2746e-05) (hash(x)=21711657) +4602 train 6.842629 (lr=1.2732e-05) (hash(x)=24362530) +4603 train 6.920321 (lr=1.2718e-05) (hash(x)=28382544) +4604 train 7.125317 (lr=1.2705e-05) (hash(x)=29987122) +4605 train 7.327727 (lr=1.2691e-05) (hash(x)=26618651) +4606 train 6.730045 (lr=1.2678e-05) (hash(x)=22061506) +4607 train 7.100269 (lr=1.2664e-05) (hash(x)=30322804) +4608 train 6.920593 (lr=1.2651e-05) (hash(x)=23027458) +4609 train 6.959279 (lr=1.2638e-05) (hash(x)=22959915) +4610 train 6.881336 (lr=1.2624e-05) (hash(x)=25857145) +4611 train 6.854269 (lr=1.2611e-05) (hash(x)=24743366) +4612 train 6.979505 (lr=1.2598e-05) (hash(x)=25161787) +4613 train 6.633598 (lr=1.2584e-05) (hash(x)=23923395) +4614 train 7.697025 (lr=1.2571e-05) (hash(x)=25344762) +4615 train 6.829912 (lr=1.2558e-05) (hash(x)=26026937) +4616 train 6.772565 (lr=1.2545e-05) (hash(x)=19631904) +4617 train 6.648699 (lr=1.2532e-05) (hash(x)=18767284) +4618 train 6.939476 (lr=1.2519e-05) (hash(x)=24548153) +4619 train 7.157719 (lr=1.2506e-05) (hash(x)=27467591) +4620 train 6.876421 (lr=1.2493e-05) (hash(x)=25582248) +4621 train 6.738840 (lr=1.2480e-05) (hash(x)=17302241) +4622 train 6.819852 (lr=1.2467e-05) (hash(x)=27112605) +4623 train 6.917722 (lr=1.2454e-05) (hash(x)=22135596) +4624 train 6.906565 (lr=1.2441e-05) (hash(x)=23715941) +4625 train 6.929236 (lr=1.2428e-05) (hash(x)=25475640) +4626 train 6.822870 (lr=1.2415e-05) (hash(x)=24166270) +4627 train 6.835571 (lr=1.2402e-05) (hash(x)=24733333) +4628 train 6.899876 (lr=1.2390e-05) (hash(x)=23362130) +4629 train 7.191310 (lr=1.2377e-05) (hash(x)=29134326) +4630 train 7.329089 (lr=1.2364e-05) (hash(x)=22943282) +4631 train 6.824479 (lr=1.2352e-05) (hash(x)=25355718) +4632 train 7.059755 (lr=1.2339e-05) (hash(x)=28747908) +4633 train 6.740908 (lr=1.2326e-05) (hash(x)=20883581) +4634 train 6.673107 (lr=1.2314e-05) (hash(x)=20312611) +4635 train 6.659022 (lr=1.2301e-05) (hash(x)=21985459) +4636 train 6.706663 (lr=1.2289e-05) (hash(x)=22572927) +4637 train 7.015360 (lr=1.2276e-05) (hash(x)=24786229) +4638 train 6.886757 (lr=1.2264e-05) (hash(x)=25937020) +4639 train 6.865285 (lr=1.2252e-05) (hash(x)=22036120) +4640 train 6.895279 (lr=1.2239e-05) (hash(x)=24687165) +4641 train 6.858377 (lr=1.2227e-05) (hash(x)=23176408) +4642 train 6.929137 (lr=1.2215e-05) (hash(x)=25285954) +4643 train 6.759052 (lr=1.2202e-05) (hash(x)=21175158) +4644 train 7.074765 (lr=1.2190e-05) (hash(x)=21870295) +4645 train 6.758831 (lr=1.2178e-05) (hash(x)=24293642) +4646 train 6.839602 (lr=1.2166e-05) (hash(x)=25383408) +4647 train 6.913771 (lr=1.2154e-05) (hash(x)=27609191) +4648 train 6.973628 (lr=1.2142e-05) (hash(x)=24525729) +4649 train 6.602471 (lr=1.2130e-05) (hash(x)=21053202) +4650 val loss 6.9613 +4650 val perplexity 1055.0262 +4650 train 6.509602 (lr=1.2118e-05) (hash(x)=20812412) +4651 train 6.673811 (lr=1.2106e-05) (hash(x)=23392029) +4652 train 6.750944 (lr=1.2094e-05) (hash(x)=19081898) +4653 train 6.841918 (lr=1.2082e-05) (hash(x)=23420997) +4654 train 7.327412 (lr=1.2070e-05) (hash(x)=24652208) +4655 train 6.821573 (lr=1.2058e-05) (hash(x)=23209578) +4656 train 6.741953 (lr=1.2046e-05) (hash(x)=25376744) +4657 train 7.008820 (lr=1.2034e-05) (hash(x)=29242161) +4658 train 7.198038 (lr=1.2023e-05) (hash(x)=27360485) +4659 train 6.768539 (lr=1.2011e-05) (hash(x)=24824528) +4660 train 6.802795 (lr=1.1999e-05) (hash(x)=22938842) +4661 train 6.946303 (lr=1.1988e-05) (hash(x)=27199401) +4662 train 7.257877 (lr=1.1976e-05) (hash(x)=29148627) +4663 train 6.874947 (lr=1.1964e-05) (hash(x)=24964626) +4664 train 6.817442 (lr=1.1953e-05) (hash(x)=26761990) +4665 train 6.787203 (lr=1.1941e-05) (hash(x)=23023484) +4666 train 6.772225 (lr=1.1930e-05) (hash(x)=26062015) +4667 train 7.123747 (lr=1.1918e-05) (hash(x)=28428887) +4668 train 6.749483 (lr=1.1907e-05) (hash(x)=23945512) +4669 train 7.047117 (lr=1.1896e-05) (hash(x)=19422223) +4670 train 6.840196 (lr=1.1884e-05) (hash(x)=24825184) +4671 train 6.883069 (lr=1.1873e-05) (hash(x)=26789021) +4672 train 6.985728 (lr=1.1862e-05) (hash(x)=25431844) +4673 train 6.960752 (lr=1.1850e-05) (hash(x)=26055887) +4674 train 7.208810 (lr=1.1839e-05) (hash(x)=25239899) +4675 train 6.735182 (lr=1.1828e-05) (hash(x)=22695968) +4676 train 6.952649 (lr=1.1817e-05) (hash(x)=24889127) +4677 train 6.861620 (lr=1.1806e-05) (hash(x)=20254044) +4678 train 6.811129 (lr=1.1795e-05) (hash(x)=26509174) +4679 train 6.707788 (lr=1.1783e-05) (hash(x)=21215047) +4680 train 6.772672 (lr=1.1772e-05) (hash(x)=22276078) +4681 train 6.966071 (lr=1.1761e-05) (hash(x)=24417502) +4682 train 6.788373 (lr=1.1751e-05) (hash(x)=24831012) +4683 train 7.048466 (lr=1.1740e-05) (hash(x)=25223052) +4684 train 6.859437 (lr=1.1729e-05) (hash(x)=27387700) +4685 train 7.058130 (lr=1.1718e-05) (hash(x)=26998654) +4686 train 6.751233 (lr=1.1707e-05) (hash(x)=21023223) +4687 train 6.959468 (lr=1.1696e-05) (hash(x)=28701940) +4688 train 6.994571 (lr=1.1685e-05) (hash(x)=27322792) +4689 train 7.079694 (lr=1.1675e-05) (hash(x)=25397088) +4690 train 6.589725 (lr=1.1664e-05) (hash(x)=22912781) +4691 train 6.946557 (lr=1.1653e-05) (hash(x)=26562495) +4692 train 7.046905 (lr=1.1643e-05) (hash(x)=25001363) +4693 train 7.049283 (lr=1.1632e-05) (hash(x)=23225946) +4694 train 6.891617 (lr=1.1622e-05) (hash(x)=23813266) +4695 train 7.345803 (lr=1.1611e-05) (hash(x)=26076238) +4696 train 6.803102 (lr=1.1601e-05) (hash(x)=22490186) +4697 train 6.637075 (lr=1.1590e-05) (hash(x)=21946864) +4698 train 6.998821 (lr=1.1580e-05) (hash(x)=30047438) +4699 train 6.687720 (lr=1.1569e-05) (hash(x)=23513415) +4700 val loss 6.9614 +4700 val perplexity 1055.1248 +4700 train 6.954099 (lr=1.1559e-05) (hash(x)=29122666) +4701 train 6.845087 (lr=1.1549e-05) (hash(x)=21972630) +4702 train 6.925329 (lr=1.1538e-05) (hash(x)=26521041) +4703 train 6.591690 (lr=1.1528e-05) (hash(x)=23641242) +4704 train 6.801403 (lr=1.1518e-05) (hash(x)=22326293) +4705 train 6.685749 (lr=1.1508e-05) (hash(x)=22847346) +4706 train 6.696795 (lr=1.1498e-05) (hash(x)=27075766) +4707 train 7.193315 (lr=1.1488e-05) (hash(x)=29534561) +4708 train 6.953235 (lr=1.1477e-05) (hash(x)=24938611) +4709 train 6.791047 (lr=1.1467e-05) (hash(x)=23786763) +4710 train 7.018243 (lr=1.1457e-05) (hash(x)=26431267) +4711 train 6.855796 (lr=1.1447e-05) (hash(x)=19651622) +4712 train 6.848139 (lr=1.1437e-05) (hash(x)=25764043) +4713 train 7.183380 (lr=1.1428e-05) (hash(x)=30718836) +4714 train 6.836038 (lr=1.1418e-05) (hash(x)=24614221) +4715 train 7.015583 (lr=1.1408e-05) (hash(x)=26304955) +4716 train 6.832888 (lr=1.1398e-05) (hash(x)=27393349) +4717 train 7.012623 (lr=1.1388e-05) (hash(x)=26638096) +4718 train 7.213504 (lr=1.1379e-05) (hash(x)=27095877) +4719 train 7.146487 (lr=1.1369e-05) (hash(x)=29051604) +4720 train 6.978865 (lr=1.1359e-05) (hash(x)=26222919) +4721 train 6.692417 (lr=1.1349e-05) (hash(x)=26482518) +4722 train 6.893521 (lr=1.1340e-05) (hash(x)=22110278) +4723 train 6.870579 (lr=1.1330e-05) (hash(x)=25159711) +4724 train 6.874373 (lr=1.1321e-05) (hash(x)=27774300) +4725 train 6.943691 (lr=1.1311e-05) (hash(x)=27894029) +4726 train 6.745396 (lr=1.1302e-05) (hash(x)=22588789) +4727 train 6.768561 (lr=1.1292e-05) (hash(x)=26612189) +4728 train 6.873029 (lr=1.1283e-05) (hash(x)=23008801) +4729 train 7.175762 (lr=1.1274e-05) (hash(x)=27309306) +4730 train 6.885209 (lr=1.1264e-05) (hash(x)=23382803) +4731 train 6.903436 (lr=1.1255e-05) (hash(x)=21236021) +4732 train 6.817565 (lr=1.1246e-05) (hash(x)=22968681) +4733 train 6.915474 (lr=1.1236e-05) (hash(x)=26453996) +4734 train 6.995929 (lr=1.1227e-05) (hash(x)=25223320) +4735 train 7.058559 (lr=1.1218e-05) (hash(x)=19482110) +4736 train 7.101011 (lr=1.1209e-05) (hash(x)=24458120) +4737 train 6.988177 (lr=1.1200e-05) (hash(x)=27366737) +4738 train 6.967304 (lr=1.1191e-05) (hash(x)=25309421) +4739 train 7.283796 (lr=1.1182e-05) (hash(x)=28566856) +4740 train 6.730426 (lr=1.1173e-05) (hash(x)=24065282) +4741 train 7.106112 (lr=1.1164e-05) (hash(x)=27797472) +4742 train 7.125160 (lr=1.1155e-05) (hash(x)=27079020) +4743 train 6.924893 (lr=1.1146e-05) (hash(x)=22327217) +4744 train 6.908294 (lr=1.1137e-05) (hash(x)=23026175) +4745 train 6.856627 (lr=1.1128e-05) (hash(x)=23720739) +4746 train 6.950387 (lr=1.1119e-05) (hash(x)=24655150) +4747 train 6.992280 (lr=1.1111e-05) (hash(x)=23533293) +4748 train 7.114931 (lr=1.1102e-05) (hash(x)=25193449) +4749 train 7.059598 (lr=1.1093e-05) (hash(x)=26937554) +4750 val loss 6.9612 +4750 val perplexity 1054.8562 +4750 train 7.215066 (lr=1.1085e-05) (hash(x)=25175996) +4751 train 6.842413 (lr=1.1076e-05) (hash(x)=26321048) +4752 train 6.952955 (lr=1.1067e-05) (hash(x)=24713460) +4753 train 6.798446 (lr=1.1059e-05) (hash(x)=21567145) +4754 train 6.804088 (lr=1.1050e-05) (hash(x)=21955317) +4755 train 6.985171 (lr=1.1042e-05) (hash(x)=24935086) +4756 train 6.973877 (lr=1.1033e-05) (hash(x)=24960618) +4757 train 6.913272 (lr=1.1025e-05) (hash(x)=20992234) +4758 train 7.043581 (lr=1.1017e-05) (hash(x)=27827997) +4759 train 6.953818 (lr=1.1008e-05) (hash(x)=26245668) +4760 train 6.640664 (lr=1.1000e-05) (hash(x)=18605235) +4761 train 6.774374 (lr=1.0992e-05) (hash(x)=23116316) +4762 train 7.139150 (lr=1.0983e-05) (hash(x)=21486416) +4763 train 6.884209 (lr=1.0975e-05) (hash(x)=24222780) +4764 train 6.859202 (lr=1.0967e-05) (hash(x)=22978954) +4765 train 6.927893 (lr=1.0959e-05) (hash(x)=23764952) +4766 train 6.957288 (lr=1.0951e-05) (hash(x)=26271374) +4767 train 6.969489 (lr=1.0943e-05) (hash(x)=22736761) +4768 train 7.016775 (lr=1.0935e-05) (hash(x)=24314603) +4769 train 7.008019 (lr=1.0927e-05) (hash(x)=26463399) +4770 train 7.175884 (lr=1.0919e-05) (hash(x)=27071943) +4771 train 7.179111 (lr=1.0911e-05) (hash(x)=29885869) +4772 train 7.184554 (lr=1.0903e-05) (hash(x)=25957755) +4773 train 6.998923 (lr=1.0895e-05) (hash(x)=24675759) +4774 train 6.890428 (lr=1.0887e-05) (hash(x)=25057589) +4775 train 6.970256 (lr=1.0879e-05) (hash(x)=24701749) +4776 train 6.812175 (lr=1.0871e-05) (hash(x)=25036725) +4777 train 7.042739 (lr=1.0864e-05) (hash(x)=25120286) +4778 train 6.870480 (lr=1.0856e-05) (hash(x)=25829552) +4779 train 7.200616 (lr=1.0848e-05) (hash(x)=27611501) +4780 train 6.987544 (lr=1.0841e-05) (hash(x)=28167272) +4781 train 6.864229 (lr=1.0833e-05) (hash(x)=24943881) +4782 train 7.022636 (lr=1.0826e-05) (hash(x)=26607112) +4783 train 6.992006 (lr=1.0818e-05) (hash(x)=23865952) +4784 train 6.923318 (lr=1.0810e-05) (hash(x)=26457444) +4785 train 7.457359 (lr=1.0803e-05) (hash(x)=28042679) +4786 train 7.140428 (lr=1.0796e-05) (hash(x)=26331287) +4787 train 7.133376 (lr=1.0788e-05) (hash(x)=28592301) +4788 train 6.970944 (lr=1.0781e-05) (hash(x)=23735941) +4789 train 7.165514 (lr=1.0774e-05) (hash(x)=26698961) +4790 train 7.030948 (lr=1.0766e-05) (hash(x)=24993350) +4791 train 7.114132 (lr=1.0759e-05) (hash(x)=24914468) +4792 train 6.953350 (lr=1.0752e-05) (hash(x)=27507785) +4793 train 6.923174 (lr=1.0745e-05) (hash(x)=23370468) +4794 train 6.872120 (lr=1.0737e-05) (hash(x)=24092258) +4795 train 6.899823 (lr=1.0730e-05) (hash(x)=24384388) +4796 train 7.216817 (lr=1.0723e-05) (hash(x)=28711454) +4797 train 6.931817 (lr=1.0716e-05) (hash(x)=27913989) +4798 train 6.972664 (lr=1.0709e-05) (hash(x)=25163695) +4799 train 6.870176 (lr=1.0702e-05) (hash(x)=26315175) +4800 val loss 6.9555 +4800 val perplexity 1048.9170 +4800 train 7.112363 (lr=1.0695e-05) (hash(x)=25508455) +4801 train 7.383558 (lr=1.0688e-05) (hash(x)=28274242) +4802 train 7.180920 (lr=1.0681e-05) (hash(x)=28351168) +4803 train 6.915812 (lr=1.0675e-05) (hash(x)=22918470) +4804 train 7.063314 (lr=1.0668e-05) (hash(x)=23327707) +4805 train 6.985356 (lr=1.0661e-05) (hash(x)=23125925) +4806 train 6.757033 (lr=1.0654e-05) (hash(x)=26735602) +4807 train 7.138710 (lr=1.0647e-05) (hash(x)=27937309) +4808 train 7.347835 (lr=1.0641e-05) (hash(x)=22490761) +4809 train 6.974715 (lr=1.0634e-05) (hash(x)=25195068) +4810 train 6.957470 (lr=1.0628e-05) (hash(x)=21904722) +4811 train 7.150328 (lr=1.0621e-05) (hash(x)=27886968) +4812 train 7.049417 (lr=1.0614e-05) (hash(x)=29433556) +4813 train 6.960558 (lr=1.0608e-05) (hash(x)=23485347) +4814 train 6.719496 (lr=1.0601e-05) (hash(x)=22493606) +4815 train 7.415329 (lr=1.0595e-05) (hash(x)=34599262) +4816 train 7.200050 (lr=1.0589e-05) (hash(x)=30036062) +4817 train 6.805438 (lr=1.0582e-05) (hash(x)=20353349) +4818 train 7.016630 (lr=1.0576e-05) (hash(x)=25760669) +4819 train 7.068934 (lr=1.0570e-05) (hash(x)=25334969) +4820 train 7.066276 (lr=1.0563e-05) (hash(x)=27117336) +4821 train 7.114846 (lr=1.0557e-05) (hash(x)=25699316) +4822 train 7.324994 (lr=1.0551e-05) (hash(x)=23911830) +4823 train 7.025381 (lr=1.0545e-05) (hash(x)=24324896) +4824 train 7.520222 (lr=1.0539e-05) (hash(x)=25360579) +4825 train 7.362942 (lr=1.0533e-05) (hash(x)=26929072) +4826 train 7.114655 (lr=1.0526e-05) (hash(x)=26096902) +4827 train 7.044709 (lr=1.0520e-05) (hash(x)=26313083) +4828 train 6.947339 (lr=1.0514e-05) (hash(x)=20152619) +4829 train 6.995601 (lr=1.0509e-05) (hash(x)=25438870) +4830 train 7.036768 (lr=1.0503e-05) (hash(x)=25289162) +4831 train 6.986620 (lr=1.0497e-05) (hash(x)=26055347) +4832 train 7.087822 (lr=1.0491e-05) (hash(x)=23627679) +4833 train 7.024423 (lr=1.0485e-05) (hash(x)=24235722) +4834 train 6.892416 (lr=1.0479e-05) (hash(x)=24876480) +4835 train 6.901860 (lr=1.0474e-05) (hash(x)=21210095) +4836 train 6.929774 (lr=1.0468e-05) (hash(x)=22798140) +4837 train 7.089196 (lr=1.0462e-05) (hash(x)=26018160) +4838 train 7.098590 (lr=1.0456e-05) (hash(x)=24654150) +4839 train 7.073565 (lr=1.0451e-05) (hash(x)=25357824) +4840 train 6.902812 (lr=1.0445e-05) (hash(x)=25346455) +4841 train 6.986578 (lr=1.0440e-05) (hash(x)=24845093) +4842 train 7.051216 (lr=1.0434e-05) (hash(x)=27675298) +4843 train 6.999079 (lr=1.0429e-05) (hash(x)=26632445) +4844 train 7.207441 (lr=1.0423e-05) (hash(x)=25194529) +4845 train 6.746006 (lr=1.0418e-05) (hash(x)=23101760) +4846 train 7.183877 (lr=1.0413e-05) (hash(x)=27950939) +4847 train 6.904833 (lr=1.0407e-05) (hash(x)=25344330) +4848 train 6.783312 (lr=1.0402e-05) (hash(x)=25486355) +4849 train 6.749489 (lr=1.0397e-05) (hash(x)=21521108) +4850 val loss 6.9527 +4850 val perplexity 1045.9786 +4850 train 6.936283 (lr=1.0391e-05) (hash(x)=26944327) +4851 train 6.924330 (lr=1.0386e-05) (hash(x)=24385783) +4852 train 7.070485 (lr=1.0381e-05) (hash(x)=23779118) +4853 train 6.944572 (lr=1.0376e-05) (hash(x)=21789023) +4854 train 7.116402 (lr=1.0371e-05) (hash(x)=26376972) +4855 train 7.142378 (lr=1.0366e-05) (hash(x)=26624604) +4856 train 6.853792 (lr=1.0361e-05) (hash(x)=22943939) +4857 train 6.874419 (lr=1.0356e-05) (hash(x)=26621084) +4858 train 6.944930 (lr=1.0351e-05) (hash(x)=22344979) +4859 train 6.773872 (lr=1.0346e-05) (hash(x)=25046324) +4860 train 6.991370 (lr=1.0341e-05) (hash(x)=22143304) +4861 train 7.040466 (lr=1.0336e-05) (hash(x)=24690201) +4862 train 7.607337 (lr=1.0331e-05) (hash(x)=31493562) +4863 train 7.530196 (lr=1.0327e-05) (hash(x)=34680076) +4864 train 7.474307 (lr=1.0322e-05) (hash(x)=31511201) +4865 train 7.486077 (lr=1.0317e-05) (hash(x)=29510291) +4866 train 7.626288 (lr=1.0313e-05) (hash(x)=34492741) +4867 train 7.266383 (lr=1.0308e-05) (hash(x)=26107052) +4868 train 7.158564 (lr=1.0303e-05) (hash(x)=27554702) +4869 train 7.040504 (lr=1.0299e-05) (hash(x)=24784210) +4870 train 6.770037 (lr=1.0294e-05) (hash(x)=23108340) +4871 train 7.013083 (lr=1.0290e-05) (hash(x)=24137475) +4872 train 6.855292 (lr=1.0285e-05) (hash(x)=22077480) +4873 train 7.079734 (lr=1.0281e-05) (hash(x)=27346373) +4874 train 6.873365 (lr=1.0276e-05) (hash(x)=25068050) +4875 train 6.970398 (lr=1.0272e-05) (hash(x)=24653821) +4876 train 6.917609 (lr=1.0268e-05) (hash(x)=24110242) +4877 train 7.000069 (lr=1.0263e-05) (hash(x)=21433979) +4878 train 7.003600 (lr=1.0259e-05) (hash(x)=22251777) +4879 train 7.076632 (lr=1.0255e-05) (hash(x)=26335191) +4880 train 6.930717 (lr=1.0251e-05) (hash(x)=22961140) +4881 train 6.832988 (lr=1.0247e-05) (hash(x)=21415049) +4882 train 7.108089 (lr=1.0242e-05) (hash(x)=25647138) +4883 train 7.168374 (lr=1.0238e-05) (hash(x)=27318715) +4884 train 6.787203 (lr=1.0234e-05) (hash(x)=27014767) +4885 train 6.869328 (lr=1.0230e-05) (hash(x)=26967264) +4886 train 7.521601 (lr=1.0226e-05) (hash(x)=32130680) +4887 train 7.120662 (lr=1.0222e-05) (hash(x)=22779375) +4888 train 7.244483 (lr=1.0218e-05) (hash(x)=21943332) +4889 train 7.243980 (lr=1.0215e-05) (hash(x)=29516471) +4890 train 7.023873 (lr=1.0211e-05) (hash(x)=22236777) +4891 train 7.010372 (lr=1.0207e-05) (hash(x)=27926071) +4892 train 7.037083 (lr=1.0203e-05) (hash(x)=26996604) +4893 train 6.827411 (lr=1.0199e-05) (hash(x)=27403718) +4894 train 6.891100 (lr=1.0196e-05) (hash(x)=23287371) +4895 train 7.083688 (lr=1.0192e-05) (hash(x)=29420094) +4896 train 7.035002 (lr=1.0188e-05) (hash(x)=27609315) +4897 train 6.900700 (lr=1.0185e-05) (hash(x)=27362231) +4898 train 7.197384 (lr=1.0181e-05) (hash(x)=29741057) +4899 train 6.831742 (lr=1.0178e-05) (hash(x)=24724693) +4900 val loss 6.9522 +4900 val perplexity 1045.3972 +4900 train 7.048506 (lr=1.0174e-05) (hash(x)=25588946) +4901 train 7.021612 (lr=1.0171e-05) (hash(x)=26134002) +4902 train 6.960299 (lr=1.0167e-05) (hash(x)=21920337) +4903 train 6.903522 (lr=1.0164e-05) (hash(x)=25530610) +4904 train 7.304024 (lr=1.0160e-05) (hash(x)=30778880) +4905 train 6.881444 (lr=1.0157e-05) (hash(x)=22707499) +4906 train 6.959158 (lr=1.0154e-05) (hash(x)=26191644) +4907 train 7.067020 (lr=1.0151e-05) (hash(x)=24576066) +4908 train 7.134920 (lr=1.0147e-05) (hash(x)=25162926) +4909 train 6.974176 (lr=1.0144e-05) (hash(x)=22984864) +4910 train 6.900990 (lr=1.0141e-05) (hash(x)=22973380) +4911 train 7.082401 (lr=1.0138e-05) (hash(x)=24790903) +4912 train 7.175430 (lr=1.0135e-05) (hash(x)=26290724) +4913 train 6.979912 (lr=1.0132e-05) (hash(x)=24664220) +4914 train 6.725129 (lr=1.0129e-05) (hash(x)=24589979) +4915 train 6.802532 (lr=1.0126e-05) (hash(x)=23458862) +4916 train 7.208334 (lr=1.0123e-05) (hash(x)=30400028) +4917 train 7.259372 (lr=1.0120e-05) (hash(x)=27652913) +4918 train 7.010773 (lr=1.0117e-05) (hash(x)=24316879) +4919 train 7.151761 (lr=1.0114e-05) (hash(x)=24772439) +4920 train 6.968824 (lr=1.0111e-05) (hash(x)=24069548) +4921 train 7.023286 (lr=1.0109e-05) (hash(x)=26262696) +4922 train 7.154816 (lr=1.0106e-05) (hash(x)=27952317) +4923 train 6.961348 (lr=1.0103e-05) (hash(x)=24746143) +4924 train 6.888829 (lr=1.0101e-05) (hash(x)=24492187) +4925 train 6.937669 (lr=1.0098e-05) (hash(x)=20511054) +4926 train 6.893367 (lr=1.0095e-05) (hash(x)=20713568) +4927 train 6.818015 (lr=1.0093e-05) (hash(x)=24375937) +4928 train 6.798318 (lr=1.0090e-05) (hash(x)=25113375) +4929 train 7.056814 (lr=1.0088e-05) (hash(x)=28464631) +4930 train 6.923739 (lr=1.0085e-05) (hash(x)=22495620) +4931 train 6.818449 (lr=1.0083e-05) (hash(x)=24488508) +4932 train 6.999438 (lr=1.0081e-05) (hash(x)=26647302) +4933 train 7.033787 (lr=1.0078e-05) (hash(x)=24587565) +4934 train 6.974543 (lr=1.0076e-05) (hash(x)=22935230) +4935 train 7.029748 (lr=1.0074e-05) (hash(x)=32753768) +4936 train 6.976800 (lr=1.0071e-05) (hash(x)=24471729) +4937 train 6.928137 (lr=1.0069e-05) (hash(x)=24132259) +4938 train 7.063094 (lr=1.0067e-05) (hash(x)=25884855) +4939 train 6.978056 (lr=1.0065e-05) (hash(x)=23771552) +4940 train 6.951464 (lr=1.0063e-05) (hash(x)=24391635) +4941 train 6.931946 (lr=1.0061e-05) (hash(x)=28525125) +4942 train 7.052317 (lr=1.0059e-05) (hash(x)=29288233) +4943 train 7.103358 (lr=1.0057e-05) (hash(x)=25921960) +4944 train 7.029310 (lr=1.0055e-05) (hash(x)=24750726) +4945 train 6.932392 (lr=1.0053e-05) (hash(x)=23100325) +4946 train 6.892759 (lr=1.0051e-05) (hash(x)=21912752) +4947 train 7.145092 (lr=1.0049e-05) (hash(x)=25935286) +4948 train 7.147433 (lr=1.0047e-05) (hash(x)=25626296) +4949 train 7.548201 (lr=1.0045e-05) (hash(x)=28217068) +4950 val loss 6.9505 +4950 val perplexity 1043.6550 +4950 train 6.945826 (lr=1.0044e-05) (hash(x)=19718801) +4951 train 7.092341 (lr=1.0042e-05) (hash(x)=21297332) +4952 train 7.116221 (lr=1.0040e-05) (hash(x)=26220102) +4953 train 6.915048 (lr=1.0038e-05) (hash(x)=25231284) +4954 train 6.930328 (lr=1.0037e-05) (hash(x)=21976453) +4955 train 7.054571 (lr=1.0035e-05) (hash(x)=23289133) +4956 train 7.077882 (lr=1.0034e-05) (hash(x)=26094218) +4957 train 6.917418 (lr=1.0032e-05) (hash(x)=24065141) +4958 train 7.117614 (lr=1.0031e-05) (hash(x)=24630785) +4959 train 6.881522 (lr=1.0029e-05) (hash(x)=22772079) +4960 train 6.864551 (lr=1.0028e-05) (hash(x)=20892794) +4961 train 6.935585 (lr=1.0026e-05) (hash(x)=17700344) +4962 train 6.888575 (lr=1.0025e-05) (hash(x)=18375850) +4963 train 6.920497 (lr=1.0024e-05) (hash(x)=23930354) +4964 train 7.062681 (lr=1.0023e-05) (hash(x)=26051426) +4965 train 7.274683 (lr=1.0021e-05) (hash(x)=31777609) +4966 train 6.999597 (lr=1.0020e-05) (hash(x)=23731877) +4967 train 6.967369 (lr=1.0019e-05) (hash(x)=24716940) +4968 train 7.071697 (lr=1.0018e-05) (hash(x)=26867707) +4969 train 6.899502 (lr=1.0017e-05) (hash(x)=22583493) +4970 train 6.764853 (lr=1.0016e-05) (hash(x)=22307538) +4971 train 6.901988 (lr=1.0015e-05) (hash(x)=23069742) +4972 train 7.054138 (lr=1.0014e-05) (hash(x)=26883443) +4973 train 6.734006 (lr=1.0013e-05) (hash(x)=24452580) +4974 train 6.850268 (lr=1.0012e-05) (hash(x)=26095064) +4975 train 6.900187 (lr=1.0011e-05) (hash(x)=20707899) +4976 train 6.916434 (lr=1.0010e-05) (hash(x)=29389932) +4977 train 7.090816 (lr=1.0009e-05) (hash(x)=25291392) +4978 train 7.005438 (lr=1.0008e-05) (hash(x)=26594498) +4979 train 6.889277 (lr=1.0008e-05) (hash(x)=24393903) +4980 train 7.025754 (lr=1.0007e-05) (hash(x)=24885810) +4981 train 7.122817 (lr=1.0006e-05) (hash(x)=28354988) +4982 train 6.935091 (lr=1.0006e-05) (hash(x)=24443616) +4983 train 7.128795 (lr=1.0005e-05) (hash(x)=27117479) +4984 train 6.750600 (lr=1.0004e-05) (hash(x)=20094160) +4985 train 7.153171 (lr=1.0004e-05) (hash(x)=23580999) +4986 train 6.946617 (lr=1.0003e-05) (hash(x)=28725805) +4987 train 6.986676 (lr=1.0003e-05) (hash(x)=24301798) +4988 train 7.042890 (lr=1.0003e-05) (hash(x)=28678215) +4989 train 6.991450 (lr=1.0002e-05) (hash(x)=25414024) +4990 train 7.069447 (lr=1.0002e-05) (hash(x)=28925598) +4991 train 6.774611 (lr=1.0001e-05) (hash(x)=22931350) +4992 train 6.958855 (lr=1.0001e-05) (hash(x)=27012668) +4993 train 6.856398 (lr=1.0001e-05) (hash(x)=24584825) +4994 train 6.974177 (lr=1.0001e-05) (hash(x)=25408780) +4995 train 7.033619 (lr=1.0000e-05) (hash(x)=25191623) +4996 train 7.097935 (lr=1.0000e-05) (hash(x)=24025482) +4997 train 6.888766 (lr=1.0000e-05) (hash(x)=26166513) +4998 train 7.067951 (lr=1.0000e-05) (hash(x)=23481468) +4999 val loss 6.9468 +4999 val perplexity 1039.7750 +4999 train 7.067119 (lr=1.0000e-05) (hash(x)=30307737)