diff --git "a/lr1e-4_total_batch_size5120_seq_len128/log2.txt" "b/lr1e-4_total_batch_size5120_seq_len128/log2.txt" --- "a/lr1e-4_total_batch_size5120_seq_len128/log2.txt" +++ "b/lr1e-4_total_batch_size5120_seq_len128/log2.txt" @@ -1,1043 +1,5203 @@ -max_steps: 1000 -0 val loss 11.6870 -0 val perplexity 119016.5000 -0 train 11.683437 (lr=3.4965e-07) (hash(x)=6154740) -1 train 11.701447 (lr=6.9930e-07) (hash(x)=6605789) -2 train 11.709952 (lr=1.0490e-06) (hash(x)=6696707) -3 train 11.728244 (lr=1.3986e-06) (hash(x)=5113283) -4 train 11.673847 (lr=1.7483e-06) (hash(x)=5607069) -5 train 11.670259 (lr=2.0979e-06) (hash(x)=7007748) -6 train 11.695046 (lr=2.4476e-06) (hash(x)=7643299) -7 train 11.662629 (lr=2.7972e-06) (hash(x)=5534142) -8 train 11.666996 (lr=3.1469e-06) (hash(x)=6539293) -9 train 11.685373 (lr=3.4965e-06) (hash(x)=5974274) -10 train 11.685617 (lr=3.8462e-06) (hash(x)=7199085) -11 train 11.642393 (lr=4.1958e-06) (hash(x)=6763231) -12 train 11.633266 (lr=4.5455e-06) (hash(x)=6720398) -13 train 11.602768 (lr=4.8951e-06) (hash(x)=6706513) -14 train 11.632250 (lr=5.2448e-06) (hash(x)=5727925) -15 train 11.626501 (lr=5.5944e-06) (hash(x)=6328012) -16 train 11.565728 (lr=5.9441e-06) (hash(x)=5812722) -17 train 11.569908 (lr=6.2937e-06) (hash(x)=6183012) -18 train 11.581360 (lr=6.6434e-06) (hash(x)=5952539) -19 train 11.552618 (lr=6.9930e-06) (hash(x)=7052161) -20 train 11.499270 (lr=7.3427e-06) (hash(x)=5810871) -21 train 11.514858 (lr=7.6923e-06) (hash(x)=6586466) -22 train 11.460441 (lr=8.0420e-06) (hash(x)=5061781) -23 train 11.505838 (lr=8.3916e-06) (hash(x)=5556098) -24 train 11.504732 (lr=8.7413e-06) (hash(x)=7268535) -25 train 11.448575 (lr=9.0909e-06) (hash(x)=8155572) -26 train 11.364543 (lr=9.4406e-06) (hash(x)=5019590) -27 train 11.377727 (lr=9.7902e-06) (hash(x)=4696943) -28 train 11.318115 (lr=1.0140e-05) (hash(x)=5984010) -29 train 11.371592 (lr=1.0490e-05) (hash(x)=7649389) -30 train 11.277213 (lr=1.0839e-05) (hash(x)=6332817) -31 train 11.220524 (lr=1.1189e-05) (hash(x)=6219138) -32 train 11.280869 (lr=1.1538e-05) (hash(x)=6895681) -33 train 11.173092 (lr=1.1888e-05) (hash(x)=7075794) -34 train 11.126132 (lr=1.2238e-05) (hash(x)=5024163) -35 train 11.177309 (lr=1.2587e-05) (hash(x)=6049878) -36 train 11.140380 (lr=1.2937e-05) (hash(x)=4774943) -37 train 11.152130 (lr=1.3287e-05) (hash(x)=6385927) -38 train 11.048912 (lr=1.3636e-05) (hash(x)=5070217) -39 train 11.002838 (lr=1.3986e-05) (hash(x)=5491972) -40 train 10.997484 (lr=1.4336e-05) (hash(x)=5695751) -41 train 10.987585 (lr=1.4685e-05) (hash(x)=6061420) -42 train 10.907567 (lr=1.5035e-05) (hash(x)=7836710) -43 train 10.945772 (lr=1.5385e-05) (hash(x)=8075458) -44 train 10.788487 (lr=1.5734e-05) (hash(x)=7190584) -45 train 10.773737 (lr=1.6084e-05) (hash(x)=7238769) -46 train 10.944681 (lr=1.6434e-05) (hash(x)=4931205) -47 train 10.751847 (lr=1.6783e-05) (hash(x)=5917741) -48 train 10.725172 (lr=1.7133e-05) (hash(x)=5530785) -49 train 10.773060 (lr=1.7483e-05) (hash(x)=5430605) -50 val loss 10.7180 -50 val perplexity 45160.4727 -50 train 10.730648 (lr=1.7832e-05) (hash(x)=6056774) -51 train 10.664007 (lr=1.8182e-05) (hash(x)=5750403) -52 train 10.637162 (lr=1.8531e-05) (hash(x)=6187497) -53 train 10.625744 (lr=1.8881e-05) (hash(x)=4792640) -54 train 10.667566 (lr=1.9231e-05) (hash(x)=6868430) -55 train 10.561627 (lr=1.9580e-05) (hash(x)=6112458) -56 train 10.507975 (lr=1.9930e-05) (hash(x)=5523601) -57 train 10.489607 (lr=2.0280e-05) (hash(x)=5801122) -58 train 10.546032 (lr=2.0629e-05) (hash(x)=6826295) -59 train 10.643409 (lr=2.0979e-05) (hash(x)=5806490) -60 train 10.500026 (lr=2.1329e-05) (hash(x)=6223100) -61 train 10.468657 (lr=2.1678e-05) (hash(x)=5754140) -62 train 10.431216 (lr=2.2028e-05) (hash(x)=6675367) -63 train 10.347210 (lr=2.2378e-05) (hash(x)=6568379) -64 train 10.241240 (lr=2.2727e-05) (hash(x)=5648233) -65 train 10.382004 (lr=2.3077e-05) (hash(x)=7134932) -66 train 10.388586 (lr=2.3427e-05) (hash(x)=5242536) -67 train 10.398359 (lr=2.3776e-05) (hash(x)=7212403) -68 train 10.251167 (lr=2.4126e-05) (hash(x)=5342967) -69 train 10.373273 (lr=2.4476e-05) (hash(x)=7720703) -70 train 10.296332 (lr=2.4825e-05) (hash(x)=7351337) -71 train 10.359861 (lr=2.5175e-05) (hash(x)=7386082) -72 train 10.237795 (lr=2.5524e-05) (hash(x)=6931318) -73 train 10.269487 (lr=2.5874e-05) (hash(x)=6848513) -74 train 10.281620 (lr=2.6224e-05) (hash(x)=7714274) -75 train 10.331904 (lr=2.6573e-05) (hash(x)=6359743) -76 train 10.186793 (lr=2.6923e-05) (hash(x)=6801650) -77 train 10.159056 (lr=2.7273e-05) (hash(x)=7536538) -78 train 10.271311 (lr=2.7622e-05) (hash(x)=6957410) -79 train 10.272377 (lr=2.7972e-05) (hash(x)=6151674) -80 train 10.304167 (lr=2.8322e-05) (hash(x)=6033844) -81 train 10.202504 (lr=2.8671e-05) (hash(x)=6317099) -82 train 10.186020 (lr=2.9021e-05) (hash(x)=5357844) -83 train 10.228599 (lr=2.9371e-05) (hash(x)=7168704) -84 train 10.276993 (lr=2.9720e-05) (hash(x)=7157938) -85 train 10.200202 (lr=3.0070e-05) (hash(x)=6736092) -86 train 10.133011 (lr=3.0420e-05) (hash(x)=5383012) -87 train 10.168591 (lr=3.0769e-05) (hash(x)=7859060) -88 train 10.181328 (lr=3.1119e-05) (hash(x)=5869288) -89 train 10.183464 (lr=3.1469e-05) (hash(x)=6958223) -90 train 10.095276 (lr=3.1818e-05) (hash(x)=6731344) -91 train 10.005728 (lr=3.2168e-05) (hash(x)=6976239) -92 train 10.092417 (lr=3.2517e-05) (hash(x)=7769441) -93 train 10.087194 (lr=3.2867e-05) (hash(x)=6956845) -94 train 10.240938 (lr=3.3217e-05) (hash(x)=6638037) -95 train 10.048953 (lr=3.3566e-05) (hash(x)=6391506) -96 train 10.231106 (lr=3.3916e-05) (hash(x)=7319928) -97 train 10.215558 (lr=3.4266e-05) (hash(x)=6113701) -98 train 9.963608 (lr=3.4615e-05) (hash(x)=6246453) -99 train 10.004500 (lr=3.4965e-05) (hash(x)=5245999) -100 val loss 10.0708 -100 val perplexity 23641.6328 -100 train 10.026407 (lr=3.5315e-05) (hash(x)=6227256) -101 train 10.051454 (lr=3.5664e-05) (hash(x)=5774189) -102 train 9.976475 (lr=3.6014e-05) (hash(x)=5588220) -103 train 10.144259 (lr=3.6364e-05) (hash(x)=5985675) -104 train 9.987902 (lr=3.6713e-05) (hash(x)=6259214) -105 train 10.022779 (lr=3.7063e-05) (hash(x)=6451776) -106 train 9.833879 (lr=3.7413e-05) (hash(x)=4940406) -107 train 9.955966 (lr=3.7762e-05) (hash(x)=4355733) -108 train 9.987179 (lr=3.8112e-05) (hash(x)=6186065) -109 train 9.949672 (lr=3.8462e-05) (hash(x)=6669188) -110 train 10.551204 (lr=3.8811e-05) (hash(x)=7118997) -111 train 9.955225 (lr=3.9161e-05) (hash(x)=6984772) -112 train 9.846657 (lr=3.9510e-05) (hash(x)=6472877) -113 train 9.950330 (lr=3.9860e-05) (hash(x)=7440580) -114 train 9.998182 (lr=4.0210e-05) (hash(x)=6378428) -115 train 9.934498 (lr=4.0559e-05) (hash(x)=6244096) -116 train 9.909740 (lr=4.0909e-05) (hash(x)=9100578) -117 train 10.045992 (lr=4.1259e-05) (hash(x)=8381560) -118 train 9.915628 (lr=4.1608e-05) (hash(x)=6066072) -119 train 9.835567 (lr=4.1958e-05) (hash(x)=6603717) -120 train 9.830457 (lr=4.2308e-05) (hash(x)=5138438) -121 train 9.764811 (lr=4.2657e-05) (hash(x)=6437516) -122 train 9.854247 (lr=4.3007e-05) (hash(x)=5743807) -123 train 9.733787 (lr=4.3357e-05) (hash(x)=5669522) -124 train 9.775227 (lr=4.3706e-05) (hash(x)=5963623) -125 train 9.643219 (lr=4.4056e-05) (hash(x)=5505889) -126 train 9.813313 (lr=4.4406e-05) (hash(x)=7607512) -127 train 9.710666 (lr=4.4755e-05) (hash(x)=6190579) -128 train 9.756684 (lr=4.5105e-05) (hash(x)=7444834) -129 train 9.783804 (lr=4.5455e-05) (hash(x)=5153196) -130 train 9.735364 (lr=4.5804e-05) (hash(x)=6495326) -131 train 9.835108 (lr=4.6154e-05) (hash(x)=4912983) -132 train 9.780792 (lr=4.6503e-05) (hash(x)=7094046) -133 train 9.626433 (lr=4.6853e-05) (hash(x)=5109125) -134 train 9.509993 (lr=4.7203e-05) (hash(x)=7119136) -135 train 9.539289 (lr=4.7552e-05) (hash(x)=7276303) -136 train 9.683184 (lr=4.7902e-05) (hash(x)=9147123) -137 train 9.723872 (lr=4.8252e-05) (hash(x)=6645716) -138 train 9.674371 (lr=4.8601e-05) (hash(x)=6347875) -139 train 9.533283 (lr=4.8951e-05) (hash(x)=5479947) -140 train 9.694362 (lr=4.9301e-05) (hash(x)=5832595) -141 train 9.743492 (lr=4.9650e-05) (hash(x)=7850360) -142 train 9.915167 (lr=5.0000e-05) (hash(x)=8499683) -143 train 9.578230 (lr=5.0350e-05) (hash(x)=6630378) -144 train 9.603836 (lr=5.0699e-05) (hash(x)=5340846) -145 train 9.543981 (lr=5.1049e-05) (hash(x)=6295358) -146 train 9.593748 (lr=5.1399e-05) (hash(x)=5974729) -147 train 9.724045 (lr=5.1748e-05) (hash(x)=8097010) -148 train 9.585273 (lr=5.2098e-05) (hash(x)=6681250) -149 train 9.462402 (lr=5.2448e-05) (hash(x)=3958188) -150 val loss 9.4606 -150 val perplexity 12843.6973 -150 train 9.477177 (lr=5.2797e-05) (hash(x)=5975539) -151 train 10.229183 (lr=5.3147e-05) (hash(x)=9989744) -152 train 9.803961 (lr=5.3497e-05) (hash(x)=6748487) -153 train 9.318254 (lr=5.3846e-05) (hash(x)=6343832) -154 train 9.287389 (lr=5.4196e-05) (hash(x)=5688949) -155 train 9.621956 (lr=5.4545e-05) (hash(x)=6694932) -156 train 9.373390 (lr=5.4895e-05) (hash(x)=5872835) -157 train 9.357368 (lr=5.5245e-05) (hash(x)=6429137) -158 train 9.382727 (lr=5.5594e-05) (hash(x)=6999390) -159 train 9.275611 (lr=5.5944e-05) (hash(x)=6317894) -160 train 9.154601 (lr=5.6294e-05) (hash(x)=5813657) -161 train 9.182790 (lr=5.6643e-05) (hash(x)=5165595) -162 train 9.196783 (lr=5.6993e-05) (hash(x)=5682633) -163 train 9.299721 (lr=5.7343e-05) (hash(x)=5046327) -164 train 9.453293 (lr=5.7692e-05) (hash(x)=6195808) -165 train 9.282996 (lr=5.8042e-05) (hash(x)=7060363) -166 train 9.196607 (lr=5.8392e-05) (hash(x)=5837126) -167 train 9.196543 (lr=5.8741e-05) (hash(x)=7947703) -168 train 8.967360 (lr=5.9091e-05) (hash(x)=5277865) -169 train 9.108420 (lr=5.9441e-05) (hash(x)=5971240) -170 train 8.965173 (lr=5.9790e-05) (hash(x)=6590408) -171 train 9.102263 (lr=6.0140e-05) (hash(x)=5916068) -172 train 9.095510 (lr=6.0490e-05) (hash(x)=6069727) -173 train 9.018456 (lr=6.0839e-05) (hash(x)=7426277) -174 train 9.192665 (lr=6.1189e-05) (hash(x)=5356513) -175 train 9.054554 (lr=6.1538e-05) (hash(x)=5777498) -176 train 9.146186 (lr=6.1888e-05) (hash(x)=5989756) -177 train 8.976686 (lr=6.2238e-05) (hash(x)=6403331) -178 train 8.884194 (lr=6.2587e-05) (hash(x)=7650667) -179 train 8.930778 (lr=6.2937e-05) (hash(x)=5753092) -180 train 8.980077 (lr=6.3287e-05) (hash(x)=5751457) -181 train 8.834116 (lr=6.3636e-05) (hash(x)=5981486) -182 train 8.881734 (lr=6.3986e-05) (hash(x)=5918229) -183 train 8.959071 (lr=6.4336e-05) (hash(x)=7723226) -184 train 8.907303 (lr=6.4685e-05) (hash(x)=6111721) -185 train 8.760362 (lr=6.5035e-05) (hash(x)=6069558) -186 train 8.823500 (lr=6.5385e-05) (hash(x)=5626336) -187 train 8.986224 (lr=6.5734e-05) (hash(x)=7007016) -188 train 8.726435 (lr=6.6084e-05) (hash(x)=5883013) -189 train 8.688654 (lr=6.6434e-05) (hash(x)=5027958) -190 train 8.813662 (lr=6.6783e-05) (hash(x)=5474948) -191 train 8.644381 (lr=6.7133e-05) (hash(x)=6491229) -192 train 8.735765 (lr=6.7483e-05) (hash(x)=5518341) -193 train 8.654070 (lr=6.7832e-05) (hash(x)=7036653) -194 train 8.744479 (lr=6.8182e-05) (hash(x)=5527616) -195 train 8.875869 (lr=6.8531e-05) (hash(x)=6390752) -196 train 8.714663 (lr=6.8881e-05) (hash(x)=6032557) -197 train 9.129579 (lr=6.9231e-05) (hash(x)=7758167) -198 train 9.012741 (lr=6.9580e-05) (hash(x)=7968070) -199 train 8.680666 (lr=6.9930e-05) (hash(x)=6019389) -200 val loss 8.6735 -200 val perplexity 5845.6514 -200 train 8.806306 (lr=7.0280e-05) (hash(x)=7276744) -201 train 8.693282 (lr=7.0629e-05) (hash(x)=6503191) -202 train 8.518047 (lr=7.0979e-05) (hash(x)=6006880) -203 train 8.699960 (lr=7.1329e-05) (hash(x)=7662067) -204 train 8.512116 (lr=7.1678e-05) (hash(x)=6297345) -205 train 8.710117 (lr=7.2028e-05) (hash(x)=7901992) -206 train 8.788494 (lr=7.2378e-05) (hash(x)=6579950) -207 train 8.454700 (lr=7.2727e-05) (hash(x)=4648609) -208 train 8.594735 (lr=7.3077e-05) (hash(x)=6903216) -209 train 8.436447 (lr=7.3427e-05) (hash(x)=5897288) -210 train 8.508020 (lr=7.3776e-05) (hash(x)=7300160) -211 train 8.409782 (lr=7.4126e-05) (hash(x)=4725966) -212 train 8.142715 (lr=7.4476e-05) (hash(x)=5060060) -213 train 8.648943 (lr=7.4825e-05) (hash(x)=6243442) -214 train 8.396324 (lr=7.5175e-05) (hash(x)=5893816) -215 train 8.436845 (lr=7.5524e-05) (hash(x)=5558355) -216 train 8.528525 (lr=7.5874e-05) (hash(x)=4378747) -217 train 8.382231 (lr=7.6224e-05) (hash(x)=5400407) -218 train 8.404837 (lr=7.6573e-05) (hash(x)=6900554) -219 train 8.476917 (lr=7.6923e-05) (hash(x)=6524933) -220 train 8.367265 (lr=7.7273e-05) (hash(x)=5409944) -221 train 8.482551 (lr=7.7622e-05) (hash(x)=5889724) -222 train 8.440649 (lr=7.7972e-05) (hash(x)=4970496) -223 train 8.251564 (lr=7.8322e-05) (hash(x)=6369326) -224 train 8.260094 (lr=7.8671e-05) (hash(x)=6563975) -225 train 8.292129 (lr=7.9021e-05) (hash(x)=5911906) -226 train 8.404962 (lr=7.9371e-05) (hash(x)=6111462) -227 train 8.430389 (lr=7.9720e-05) (hash(x)=6022625) -228 train 8.231339 (lr=8.0070e-05) (hash(x)=5884663) -229 train 8.163726 (lr=8.0420e-05) (hash(x)=6584810) -230 train 8.263556 (lr=8.0769e-05) (hash(x)=5289998) -231 train 8.202457 (lr=8.1119e-05) (hash(x)=4906853) -232 train 8.133245 (lr=8.1469e-05) (hash(x)=5862071) -233 train 7.748362 (lr=8.1818e-05) (hash(x)=4564564) -234 train 7.997213 (lr=8.2168e-05) (hash(x)=5723971) -235 train 8.036293 (lr=8.2517e-05) (hash(x)=5589269) -236 train 8.030647 (lr=8.2867e-05) (hash(x)=5683368) -237 train 8.283672 (lr=8.3217e-05) (hash(x)=6969180) -238 train 8.190210 (lr=8.3566e-05) (hash(x)=5341421) -239 train 8.051121 (lr=8.3916e-05) (hash(x)=6437376) -240 train 8.387665 (lr=8.4266e-05) (hash(x)=7527007) -241 train 8.235349 (lr=8.4615e-05) (hash(x)=7116258) -242 train 8.232341 (lr=8.4965e-05) (hash(x)=6463930) -243 train 8.263113 (lr=8.5315e-05) (hash(x)=7304892) -244 train 8.325236 (lr=8.5664e-05) (hash(x)=5881808) -245 train 8.155329 (lr=8.6014e-05) (hash(x)=7366721) -246 train 8.046780 (lr=8.6364e-05) (hash(x)=6457521) -247 train 8.401601 (lr=8.6713e-05) (hash(x)=7084093) -248 train 8.214803 (lr=8.7063e-05) (hash(x)=6015300) -249 train 8.324396 (lr=8.7413e-05) (hash(x)=7197652) -250 val loss 8.0874 -250 val perplexity 3253.0769 -250 train 8.282703 (lr=8.7762e-05) (hash(x)=4830828) -251 train 8.108204 (lr=8.8112e-05) (hash(x)=5908178) -252 train 8.038308 (lr=8.8462e-05) (hash(x)=6299092) -253 train 7.967640 (lr=8.8811e-05) (hash(x)=6349974) -254 train 8.027965 (lr=8.9161e-05) (hash(x)=5641494) -255 train 8.018302 (lr=8.9510e-05) (hash(x)=7048804) -256 train 8.156570 (lr=8.9860e-05) (hash(x)=7035244) -257 train 7.949112 (lr=9.0210e-05) (hash(x)=7909039) -258 train 8.147686 (lr=9.0559e-05) (hash(x)=5470939) -259 train 8.007073 (lr=9.0909e-05) (hash(x)=6085549) -260 train 8.191679 (lr=9.1259e-05) (hash(x)=5882649) -261 train 8.180864 (lr=9.1608e-05) (hash(x)=7463181) -262 train 8.310098 (lr=9.1958e-05) (hash(x)=5215574) -263 train 7.884139 (lr=9.2308e-05) (hash(x)=5752594) -264 train 7.993123 (lr=9.2657e-05) (hash(x)=6416619) -265 train 7.931797 (lr=9.3007e-05) (hash(x)=6114601) -266 train 7.894912 (lr=9.3357e-05) (hash(x)=5646171) -267 train 7.885094 (lr=9.3706e-05) (hash(x)=7662769) -268 train 8.050817 (lr=9.4056e-05) (hash(x)=6394376) -269 train 7.744252 (lr=9.4406e-05) (hash(x)=7485666) -270 train 7.764907 (lr=9.4755e-05) (hash(x)=6636823) -271 train 7.707733 (lr=9.5105e-05) (hash(x)=6393520) -272 train 7.923878 (lr=9.5455e-05) (hash(x)=5235659) -273 train 7.978837 (lr=9.5804e-05) (hash(x)=5586291) -274 train 8.206486 (lr=9.6154e-05) (hash(x)=7034674) -275 train 8.271257 (lr=9.6503e-05) (hash(x)=5942867) -276 train 7.996998 (lr=9.6853e-05) (hash(x)=7812344) -277 train 8.211689 (lr=9.7203e-05) (hash(x)=7574027) -278 train 8.162067 (lr=9.7552e-05) (hash(x)=5960216) -279 train 7.970027 (lr=9.7902e-05) (hash(x)=6793550) -280 train 7.949297 (lr=9.8252e-05) (hash(x)=6879965) -281 train 7.684564 (lr=9.8601e-05) (hash(x)=6264789) -282 train 7.876830 (lr=9.8951e-05) (hash(x)=5175356) -283 train 8.019979 (lr=9.9301e-05) (hash(x)=7105976) -284 train 8.018770 (lr=9.9650e-05) (hash(x)=7286386) -285 train 8.169221 (lr=1.0000e-04) (hash(x)=7244279) -286 train 7.774569 (lr=1.0000e-04) (hash(x)=4877247) -287 train 7.733827 (lr=1.0000e-04) (hash(x)=6581348) -288 train 7.750123 (lr=9.9998e-05) (hash(x)=6397208) -289 train 7.805733 (lr=9.9996e-05) (hash(x)=6543825) -290 train 7.592926 (lr=9.9993e-05) (hash(x)=6088993) -291 train 7.914358 (lr=9.9989e-05) (hash(x)=5555598) -292 train 7.928394 (lr=9.9984e-05) (hash(x)=6924240) -293 train 8.056400 (lr=9.9979e-05) (hash(x)=7254232) -294 train 7.738004 (lr=9.9972e-05) (hash(x)=7689743) -295 train 7.702261 (lr=9.9965e-05) (hash(x)=6235837) -296 train 7.895230 (lr=9.9956e-05) (hash(x)=5216883) -297 train 7.617748 (lr=9.9947e-05) (hash(x)=4738550) -298 train 7.724221 (lr=9.9937e-05) (hash(x)=5126918) -299 train 7.861851 (lr=9.9926e-05) (hash(x)=5591770) -300 val loss 7.8334 -300 val perplexity 2523.3894 -300 train 8.602486 (lr=9.9915e-05) (hash(x)=8001573) -301 train 8.379179 (lr=9.9902e-05) (hash(x)=8012491) -302 train 8.120238 (lr=9.9889e-05) (hash(x)=3997428) -303 train 7.463863 (lr=9.9874e-05) (hash(x)=7083021) -304 train 8.052033 (lr=9.9859e-05) (hash(x)=7177371) -305 train 7.831302 (lr=9.9843e-05) (hash(x)=6456022) -306 train 7.917401 (lr=9.9826e-05) (hash(x)=5238861) -307 train 7.898724 (lr=9.9808e-05) (hash(x)=7281348) -308 train 8.047001 (lr=9.9789e-05) (hash(x)=6848441) -309 train 8.124562 (lr=9.9770e-05) (hash(x)=7824794) -310 train 8.192617 (lr=9.9749e-05) (hash(x)=7440208) -311 train 8.025720 (lr=9.9728e-05) (hash(x)=6155821) -312 train 7.813764 (lr=9.9706e-05) (hash(x)=5350461) -313 train 7.999157 (lr=9.9683e-05) (hash(x)=7807564) -314 train 7.812797 (lr=9.9659e-05) (hash(x)=5992165) -315 train 7.770690 (lr=9.9634e-05) (hash(x)=5736241) -316 train 7.807963 (lr=9.9609e-05) (hash(x)=6536253) -317 train 7.960543 (lr=9.9582e-05) (hash(x)=5688415) -318 train 7.588665 (lr=9.9555e-05) (hash(x)=5839705) -319 train 7.811373 (lr=9.9526e-05) (hash(x)=5657123) -320 train 7.795663 (lr=9.9497e-05) (hash(x)=6354364) -321 train 7.827204 (lr=9.9467e-05) (hash(x)=6102985) -322 train 8.048637 (lr=9.9437e-05) (hash(x)=7161967) -323 train 7.984159 (lr=9.9405e-05) (hash(x)=6452095) -324 train 7.742224 (lr=9.9372e-05) (hash(x)=5547396) -325 train 8.033551 (lr=9.9339e-05) (hash(x)=5848921) -326 train 7.803688 (lr=9.9305e-05) (hash(x)=4890294) -327 train 7.431751 (lr=9.9270e-05) (hash(x)=5312267) -328 train 7.492071 (lr=9.9234e-05) (hash(x)=5348929) -329 train 7.450742 (lr=9.9197e-05) (hash(x)=5025297) -330 train 7.513348 (lr=9.9159e-05) (hash(x)=5670052) -331 train 7.389685 (lr=9.9121e-05) (hash(x)=5434493) -332 train 8.093664 (lr=9.9081e-05) (hash(x)=9122453) -333 train 7.859997 (lr=9.9041e-05) (hash(x)=5197474) -334 train 7.738406 (lr=9.9000e-05) (hash(x)=5550786) -335 train 7.786860 (lr=9.8958e-05) (hash(x)=6830813) -336 train 7.605169 (lr=9.8915e-05) (hash(x)=5258435) -337 train 7.636420 (lr=9.8872e-05) (hash(x)=5242548) -338 train 7.524803 (lr=9.8827e-05) (hash(x)=3754886) -339 train 7.473531 (lr=9.8782e-05) (hash(x)=4752771) -340 train 7.611681 (lr=9.8736e-05) (hash(x)=5926875) -341 train 8.027270 (lr=9.8689e-05) (hash(x)=6691249) -342 train 7.807855 (lr=9.8641e-05) (hash(x)=7514623) -343 train 7.844025 (lr=9.8592e-05) (hash(x)=6424933) -344 train 7.837926 (lr=9.8543e-05) (hash(x)=6347757) -345 train 7.808481 (lr=9.8492e-05) (hash(x)=6960120) -346 train 7.791016 (lr=9.8441e-05) (hash(x)=7597197) -347 train 7.738278 (lr=9.8389e-05) (hash(x)=5786517) -348 train 7.762140 (lr=9.8336e-05) (hash(x)=6424363) -349 train 7.865269 (lr=9.8282e-05) (hash(x)=7229689) -350 val loss 7.7649 -350 val perplexity 2356.4268 -350 train 7.978086 (lr=9.8228e-05) (hash(x)=6772284) -351 train 8.060165 (lr=9.8172e-05) (hash(x)=6680023) -352 train 7.940126 (lr=9.8116e-05) (hash(x)=6218520) -353 train 7.980777 (lr=9.8059e-05) (hash(x)=7688393) -354 train 7.853170 (lr=9.8001e-05) (hash(x)=6327977) -355 train 7.745524 (lr=9.7942e-05) (hash(x)=6474729) -356 train 7.840765 (lr=9.7882e-05) (hash(x)=6657266) -357 train 7.882431 (lr=9.7822e-05) (hash(x)=5946650) -358 train 7.803625 (lr=9.7761e-05) (hash(x)=6734878) -359 train 7.823937 (lr=9.7699e-05) (hash(x)=7523279) -360 train 7.694506 (lr=9.7636e-05) (hash(x)=6179478) -361 train 7.715381 (lr=9.7572e-05) (hash(x)=5531605) -362 train 7.737763 (lr=9.7507e-05) (hash(x)=5844980) -363 train 7.427846 (lr=9.7442e-05) (hash(x)=5508768) -364 train 7.320523 (lr=9.7376e-05) (hash(x)=6337190) -365 train 8.740232 (lr=9.7309e-05) (hash(x)=6415982) -366 train 7.884411 (lr=9.7241e-05) (hash(x)=6828959) -367 train 7.844289 (lr=9.7172e-05) (hash(x)=6635925) -368 train 7.595047 (lr=9.7103e-05) (hash(x)=6358540) -369 train 7.947254 (lr=9.7032e-05) (hash(x)=5923706) -370 train 7.587069 (lr=9.6961e-05) (hash(x)=4843320) -371 train 7.852147 (lr=9.6889e-05) (hash(x)=6663801) -372 train 7.675485 (lr=9.6817e-05) (hash(x)=5583287) -373 train 7.666986 (lr=9.6743e-05) (hash(x)=6113540) -374 train 7.778663 (lr=9.6669e-05) (hash(x)=6389936) -375 train 7.744994 (lr=9.6593e-05) (hash(x)=5869441) -376 train 7.783211 (lr=9.6518e-05) (hash(x)=5148617) -377 train 8.031755 (lr=9.6441e-05) (hash(x)=6913454) -378 train 7.797727 (lr=9.6363e-05) (hash(x)=5356233) -379 train 7.759981 (lr=9.6285e-05) (hash(x)=6698878) -380 train 7.710612 (lr=9.6206e-05) (hash(x)=6280665) -381 train 7.928174 (lr=9.6126e-05) (hash(x)=6094899) -382 train 7.469923 (lr=9.6045e-05) (hash(x)=6249746) -383 train 7.795187 (lr=9.5963e-05) (hash(x)=6349004) -384 train 7.716205 (lr=9.5881e-05) (hash(x)=7013468) -385 train 7.679176 (lr=9.5798e-05) (hash(x)=6045933) -386 train 7.997610 (lr=9.5714e-05) (hash(x)=6571735) -387 train 7.631792 (lr=9.5629e-05) (hash(x)=4986137) -388 train 7.279845 (lr=9.5544e-05) (hash(x)=5244912) -389 train 7.664468 (lr=9.5457e-05) (hash(x)=4798229) -390 train 7.678345 (lr=9.5370e-05) (hash(x)=5815783) -391 train 7.499672 (lr=9.5282e-05) (hash(x)=6008454) -392 train 7.718896 (lr=9.5194e-05) (hash(x)=6407333) -393 train 7.603030 (lr=9.5104e-05) (hash(x)=5938362) -394 train 7.461483 (lr=9.5014e-05) (hash(x)=6077124) -395 train 7.748454 (lr=9.4923e-05) (hash(x)=6550770) -396 train 7.594069 (lr=9.4831e-05) (hash(x)=6181528) -397 train 7.849744 (lr=9.4739e-05) (hash(x)=7055344) -398 train 7.957032 (lr=9.4646e-05) (hash(x)=7689348) -399 train 7.891578 (lr=9.4551e-05) (hash(x)=7682741) -400 val loss 7.7547 -400 val perplexity 2332.5579 -400 train 7.702816 (lr=9.4457e-05) (hash(x)=5189401) -401 train 7.731054 (lr=9.4361e-05) (hash(x)=7372095) -402 train 7.800513 (lr=9.4265e-05) (hash(x)=6838219) -403 train 8.290697 (lr=9.4168e-05) (hash(x)=7892158) -404 train 7.937255 (lr=9.4070e-05) (hash(x)=5677077) -405 train 7.560299 (lr=9.3971e-05) (hash(x)=5929740) -406 train 7.709442 (lr=9.3872e-05) (hash(x)=5285055) -407 train 7.789811 (lr=9.3772e-05) (hash(x)=7794028) -408 train 7.892147 (lr=9.3671e-05) (hash(x)=6640802) -409 train 7.984076 (lr=9.3569e-05) (hash(x)=6839923) -410 train 7.444740 (lr=9.3467e-05) (hash(x)=4020997) -411 train 7.626997 (lr=9.3364e-05) (hash(x)=7093523) -412 train 7.887685 (lr=9.3260e-05) (hash(x)=7370045) -413 train 7.634565 (lr=9.3155e-05) (hash(x)=5341312) -414 train 7.669347 (lr=9.3050e-05) (hash(x)=5589312) -415 train 8.130575 (lr=9.2944e-05) (hash(x)=6166062) -416 train 8.037578 (lr=9.2837e-05) (hash(x)=8354149) -417 train 7.656298 (lr=9.2729e-05) (hash(x)=5992164) -418 train 7.656220 (lr=9.2621e-05) (hash(x)=4748657) -419 train 7.700554 (lr=9.2512e-05) (hash(x)=6645781) -420 train 7.939510 (lr=9.2402e-05) (hash(x)=6689147) -421 train 7.779636 (lr=9.2292e-05) (hash(x)=6207724) -422 train 7.736643 (lr=9.2181e-05) (hash(x)=6232863) -423 train 7.500404 (lr=9.2069e-05) (hash(x)=4811192) -424 train 7.523778 (lr=9.1956e-05) (hash(x)=6211761) -425 train 7.711971 (lr=9.1843e-05) (hash(x)=6906335) -426 train 7.616197 (lr=9.1729e-05) (hash(x)=4922365) -427 train 7.694466 (lr=9.1614e-05) (hash(x)=5970866) -428 train 7.592412 (lr=9.1499e-05) (hash(x)=6417833) -429 train 7.683228 (lr=9.1382e-05) (hash(x)=5238015) -430 train 7.621742 (lr=9.1266e-05) (hash(x)=5375451) -431 train 7.730532 (lr=9.1148e-05) (hash(x)=7822680) -432 train 7.770816 (lr=9.1030e-05) (hash(x)=6173200) -433 train 7.541699 (lr=9.0911e-05) (hash(x)=5478019) -434 train 7.754510 (lr=9.0791e-05) (hash(x)=5597859) -435 train 7.574602 (lr=9.0671e-05) (hash(x)=6317317) -436 train 7.763556 (lr=9.0550e-05) (hash(x)=7120467) -437 train 7.872753 (lr=9.0428e-05) (hash(x)=5832344) -438 train 7.758370 (lr=9.0306e-05) (hash(x)=6813802) -439 train 7.797694 (lr=9.0182e-05) (hash(x)=6431409) -440 train 7.877748 (lr=9.0059e-05) (hash(x)=5886861) -441 train 7.618858 (lr=8.9934e-05) (hash(x)=5900130) -442 train 7.868795 (lr=8.9809e-05) (hash(x)=6061563) -443 train 7.843869 (lr=8.9683e-05) (hash(x)=6653337) -444 train 7.757221 (lr=8.9557e-05) (hash(x)=6575992) -445 train 7.719529 (lr=8.9430e-05) (hash(x)=6696784) -446 train 7.844862 (lr=8.9302e-05) (hash(x)=6242161) -447 train 7.716222 (lr=8.9173e-05) (hash(x)=5323032) -448 train 7.494566 (lr=8.9044e-05) (hash(x)=6439367) -449 train 7.750771 (lr=8.8914e-05) (hash(x)=5372100) -450 val loss 7.7471 -450 val perplexity 2314.9055 -450 train 7.785188 (lr=8.8784e-05) (hash(x)=6344849) -451 train 7.432173 (lr=8.8653e-05) (hash(x)=5125339) -452 train 7.436845 (lr=8.8521e-05) (hash(x)=4876156) -453 train 7.575974 (lr=8.8388e-05) (hash(x)=5664463) -454 train 7.459610 (lr=8.8255e-05) (hash(x)=6010042) -455 train 7.651673 (lr=8.8122e-05) (hash(x)=7363286) -456 train 8.262292 (lr=8.7987e-05) (hash(x)=4873268) -457 train 7.971287 (lr=8.7852e-05) (hash(x)=7444468) -458 train 7.984036 (lr=8.7717e-05) (hash(x)=6698134) -459 train 7.822166 (lr=8.7580e-05) (hash(x)=7670050) -460 train 7.819763 (lr=8.7444e-05) (hash(x)=6280866) -461 train 7.682568 (lr=8.7306e-05) (hash(x)=8189420) -462 train 7.818572 (lr=8.7168e-05) (hash(x)=6878292) -463 train 7.553231 (lr=8.7029e-05) (hash(x)=5616075) -464 train 7.756614 (lr=8.6890e-05) (hash(x)=5839939) -465 train 7.611830 (lr=8.6750e-05) (hash(x)=6360924) -466 train 8.035023 (lr=8.6609e-05) (hash(x)=6466475) -467 train 7.829970 (lr=8.6468e-05) (hash(x)=6593764) -468 train 8.253963 (lr=8.6326e-05) (hash(x)=7389698) -469 train 7.942793 (lr=8.6184e-05) (hash(x)=6764377) -470 train 7.674744 (lr=8.6041e-05) (hash(x)=7293570) -471 train 7.721032 (lr=8.5897e-05) (hash(x)=5672608) -472 train 7.525622 (lr=8.5753e-05) (hash(x)=5587975) -473 train 7.443876 (lr=8.5608e-05) (hash(x)=6985256) -474 train 8.038188 (lr=8.5462e-05) (hash(x)=6549231) -475 train 7.758385 (lr=8.5316e-05) (hash(x)=6828653) -476 train 7.570188 (lr=8.5170e-05) (hash(x)=5478970) -477 train 7.613185 (lr=8.5022e-05) (hash(x)=5199845) -478 train 7.688290 (lr=8.4875e-05) (hash(x)=6482073) -479 train 7.783101 (lr=8.4726e-05) (hash(x)=6839867) -480 train 7.767344 (lr=8.4577e-05) (hash(x)=7073454) -481 train 8.007269 (lr=8.4428e-05) (hash(x)=6928712) -482 train 7.753805 (lr=8.4278e-05) (hash(x)=5962982) -483 train 7.868116 (lr=8.4127e-05) (hash(x)=8426992) -484 train 7.781707 (lr=8.3976e-05) (hash(x)=6422394) -485 train 7.719588 (lr=8.3824e-05) (hash(x)=5330355) -486 train 7.182526 (lr=8.3672e-05) (hash(x)=4111491) -487 train 7.198468 (lr=8.3519e-05) (hash(x)=4916928) -488 train 7.408064 (lr=8.3366e-05) (hash(x)=6610244) -489 train 7.905384 (lr=8.3212e-05) (hash(x)=7287928) -490 train 7.769965 (lr=8.3057e-05) (hash(x)=6525083) -491 train 7.722730 (lr=8.2902e-05) (hash(x)=6484050) -492 train 7.878792 (lr=8.2746e-05) (hash(x)=6573424) -493 train 7.748869 (lr=8.2590e-05) (hash(x)=5062850) -494 train 7.713262 (lr=8.2434e-05) (hash(x)=6215995) -495 train 7.849191 (lr=8.2276e-05) (hash(x)=8353379) -496 train 7.726857 (lr=8.2119e-05) (hash(x)=6344823) -497 train 7.707977 (lr=8.1960e-05) (hash(x)=6805358) -498 train 7.587737 (lr=8.1801e-05) (hash(x)=6018070) -499 train 7.865748 (lr=8.1642e-05) (hash(x)=6552510) -500 val loss 7.7215 -500 val perplexity 2256.2434 -500 train 7.630629 (lr=8.1482e-05) (hash(x)=7218108) -501 train 7.823636 (lr=8.1322e-05) (hash(x)=5105545) -502 train 7.795105 (lr=8.1161e-05) (hash(x)=5997860) -503 train 7.628949 (lr=8.1000e-05) (hash(x)=4838871) -504 train 7.658935 (lr=8.0838e-05) (hash(x)=7105888) -505 train 7.964713 (lr=8.0676e-05) (hash(x)=5945286) -506 train 7.223932 (lr=8.0513e-05) (hash(x)=4381720) -507 train 6.906151 (lr=8.0349e-05) (hash(x)=3021697) -508 train 7.288069 (lr=8.0186e-05) (hash(x)=6826973) -509 train 7.846550 (lr=8.0021e-05) (hash(x)=6443070) -510 train 7.537453 (lr=7.9856e-05) (hash(x)=5520637) -511 train 7.809089 (lr=7.9691e-05) (hash(x)=6795665) -512 train 7.586171 (lr=7.9525e-05) (hash(x)=6063891) -513 train 8.085600 (lr=7.9359e-05) (hash(x)=7683068) -514 train 7.399718 (lr=7.9192e-05) (hash(x)=5526694) -515 train 7.420993 (lr=7.9025e-05) (hash(x)=5486935) -516 train 7.774826 (lr=7.8858e-05) (hash(x)=6002252) -517 train 7.737309 (lr=7.8689e-05) (hash(x)=6115232) -518 train 8.058794 (lr=7.8521e-05) (hash(x)=9039136) -519 train 7.677821 (lr=7.8352e-05) (hash(x)=6678038) -520 train 7.838614 (lr=7.8182e-05) (hash(x)=5383926) -521 train 7.904171 (lr=7.8012e-05) (hash(x)=5747629) -522 train 7.752782 (lr=7.7842e-05) (hash(x)=7090040) -523 train 7.976059 (lr=7.7671e-05) (hash(x)=6657714) -524 train 7.639609 (lr=7.7500e-05) (hash(x)=5414034) -525 train 7.712417 (lr=7.7328e-05) (hash(x)=6190642) -526 train 7.870664 (lr=7.7156e-05) (hash(x)=7431177) -527 train 7.743874 (lr=7.6984e-05) (hash(x)=6112215) -528 train 7.858221 (lr=7.6811e-05) (hash(x)=6785874) -529 train 7.610793 (lr=7.6637e-05) (hash(x)=7314989) -530 train 7.822162 (lr=7.6463e-05) (hash(x)=6222614) -531 train 7.893299 (lr=7.6289e-05) (hash(x)=8353143) -532 train 7.979729 (lr=7.6115e-05) (hash(x)=6752498) -533 train 7.731093 (lr=7.5940e-05) (hash(x)=5912570) -534 train 7.872529 (lr=7.5764e-05) (hash(x)=5621785) -535 train 7.766974 (lr=7.5588e-05) (hash(x)=5915361) -536 train 7.659195 (lr=7.5412e-05) (hash(x)=6853672) -537 train 7.632804 (lr=7.5235e-05) (hash(x)=6369494) -538 train 7.768328 (lr=7.5058e-05) (hash(x)=6039652) -539 train 7.900849 (lr=7.4881e-05) (hash(x)=6254885) -540 train 7.761768 (lr=7.4703e-05) (hash(x)=5829860) -541 train 7.659716 (lr=7.4525e-05) (hash(x)=5425120) -542 train 7.438613 (lr=7.4346e-05) (hash(x)=5209746) -543 train 8.009092 (lr=7.4167e-05) (hash(x)=5771588) -544 train 7.724377 (lr=7.3988e-05) (hash(x)=8298790) -545 train 7.804965 (lr=7.3808e-05) (hash(x)=6763967) -546 train 7.768277 (lr=7.3628e-05) (hash(x)=4882397) -547 train 7.554984 (lr=7.3448e-05) (hash(x)=5561507) -548 train 7.551970 (lr=7.3267e-05) (hash(x)=5762755) -549 train 7.669227 (lr=7.3086e-05) (hash(x)=7081151) -550 val loss 7.7134 -550 val perplexity 2238.1143 -550 train 7.605166 (lr=7.2904e-05) (hash(x)=5047520) -551 train 7.745546 (lr=7.2723e-05) (hash(x)=5688829) -552 train 7.620098 (lr=7.2540e-05) (hash(x)=7008925) -553 train 7.705698 (lr=7.2358e-05) (hash(x)=7821554) -554 train 7.748119 (lr=7.2175e-05) (hash(x)=6469035) -555 train 7.552913 (lr=7.1992e-05) (hash(x)=5371951) -556 train 7.843101 (lr=7.1808e-05) (hash(x)=6436050) -557 train 7.776985 (lr=7.1624e-05) (hash(x)=8120149) -558 train 8.032511 (lr=7.1440e-05) (hash(x)=6189935) -559 train 7.731899 (lr=7.1256e-05) (hash(x)=5443305) -560 train 7.817446 (lr=7.1071e-05) (hash(x)=6294312) -561 train 7.437525 (lr=7.0886e-05) (hash(x)=7066030) -562 train 7.855394 (lr=7.0701e-05) (hash(x)=7744989) -563 train 8.021390 (lr=7.0515e-05) (hash(x)=5016757) -564 train 7.841383 (lr=7.0329e-05) (hash(x)=8001284) -565 train 7.767554 (lr=7.0143e-05) (hash(x)=6296163) -566 train 7.859457 (lr=6.9956e-05) (hash(x)=6027688) -567 train 7.775316 (lr=6.9769e-05) (hash(x)=6901933) -568 train 7.624760 (lr=6.9582e-05) (hash(x)=5124305) -569 train 7.781159 (lr=6.9394e-05) (hash(x)=8056633) -570 train 7.814128 (lr=6.9207e-05) (hash(x)=6677566) -571 train 7.860510 (lr=6.9019e-05) (hash(x)=6019085) -572 train 7.575006 (lr=6.8830e-05) (hash(x)=5924495) -573 train 7.706306 (lr=6.8642e-05) (hash(x)=7003893) -574 train 7.646411 (lr=6.8453e-05) (hash(x)=5563075) -575 train 7.482473 (lr=6.8264e-05) (hash(x)=4294425) -576 train 7.691881 (lr=6.8075e-05) (hash(x)=5677870) -577 train 7.580290 (lr=6.7885e-05) (hash(x)=6568540) -578 train 7.803429 (lr=6.7695e-05) (hash(x)=7473394) -579 train 7.830765 (lr=6.7505e-05) (hash(x)=6095229) -580 train 7.819236 (lr=6.7315e-05) (hash(x)=6946168) -581 train 7.631917 (lr=6.7124e-05) (hash(x)=5512150) -582 train 7.265512 (lr=6.6933e-05) (hash(x)=4380268) -583 train 7.343980 (lr=6.6742e-05) (hash(x)=4363941) -584 train 7.482111 (lr=6.6551e-05) (hash(x)=4836009) -585 train 7.792867 (lr=6.6360e-05) (hash(x)=6457783) -586 train 7.658160 (lr=6.6168e-05) (hash(x)=6378784) -587 train 7.570757 (lr=6.5976e-05) (hash(x)=4693798) -588 train 7.884872 (lr=6.5784e-05) (hash(x)=9193310) -589 train 8.569563 (lr=6.5592e-05) (hash(x)=8759806) -590 train 8.923375 (lr=6.5399e-05) (hash(x)=9176140) -591 train 7.619113 (lr=6.5206e-05) (hash(x)=5486335) -592 train 7.894166 (lr=6.5013e-05) (hash(x)=7868436) -593 train 7.786195 (lr=6.4820e-05) (hash(x)=6964993) -594 train 8.004015 (lr=6.4627e-05) (hash(x)=6741270) -595 train 8.277512 (lr=6.4433e-05) (hash(x)=7907450) -596 train 8.092323 (lr=6.4240e-05) (hash(x)=6443452) -597 train 7.645813 (lr=6.4046e-05) (hash(x)=5236642) -598 train 7.792857 (lr=6.3852e-05) (hash(x)=5604795) -599 train 7.746115 (lr=6.3658e-05) (hash(x)=7295165) -600 val loss 7.6955 -600 val perplexity 2198.4209 -600 train 7.721638 (lr=6.3463e-05) (hash(x)=6034549) -601 train 7.735798 (lr=6.3269e-05) (hash(x)=4913602) -602 train 7.679343 (lr=6.3074e-05) (hash(x)=6271294) -603 train 7.846909 (lr=6.2879e-05) (hash(x)=6814026) -604 train 7.734879 (lr=6.2684e-05) (hash(x)=6848040) -605 train 8.057933 (lr=6.2489e-05) (hash(x)=7042051) -606 train 7.944062 (lr=6.2294e-05) (hash(x)=6481002) -607 train 7.588020 (lr=6.2098e-05) (hash(x)=6267424) -608 train 7.913720 (lr=6.1903e-05) (hash(x)=7665306) -609 train 7.783406 (lr=6.1707e-05) (hash(x)=5614727) -610 train 7.795950 (lr=6.1511e-05) (hash(x)=7039197) -611 train 7.833235 (lr=6.1315e-05) (hash(x)=8086437) -612 train 7.941370 (lr=6.1119e-05) (hash(x)=6993846) -613 train 7.943892 (lr=6.0923e-05) (hash(x)=5900143) -614 train 7.855207 (lr=6.0726e-05) (hash(x)=4841318) -615 train 7.826779 (lr=6.0530e-05) (hash(x)=5270452) -616 train 7.706651 (lr=6.0333e-05) (hash(x)=5955026) -617 train 7.824933 (lr=6.0137e-05) (hash(x)=8617707) -618 train 7.657619 (lr=5.9940e-05) (hash(x)=5159401) -619 train 7.646924 (lr=5.9743e-05) (hash(x)=6420820) -620 train 7.630338 (lr=5.9546e-05) (hash(x)=6628863) -621 train 7.426697 (lr=5.9349e-05) (hash(x)=6215930) -622 train 7.761342 (lr=5.9152e-05) (hash(x)=5248645) -623 train 7.644173 (lr=5.8955e-05) (hash(x)=6305297) -624 train 8.213631 (lr=5.8758e-05) (hash(x)=6989704) -625 train 7.742881 (lr=5.8560e-05) (hash(x)=4026682) -626 train 7.592980 (lr=5.8363e-05) (hash(x)=6367688) -627 train 7.689666 (lr=5.8165e-05) (hash(x)=7889849) -628 train 7.854695 (lr=5.7968e-05) (hash(x)=7334719) -629 train 7.964388 (lr=5.7770e-05) (hash(x)=6141721) -630 train 8.760984 (lr=5.7573e-05) (hash(x)=5056572) -631 train 8.175771 (lr=5.7375e-05) (hash(x)=6040077) -632 train 8.277700 (lr=5.7177e-05) (hash(x)=6866651) -633 train 8.584437 (lr=5.6979e-05) (hash(x)=6155449) -634 train 8.119123 (lr=5.6782e-05) (hash(x)=6690174) -635 train 7.749737 (lr=5.6584e-05) (hash(x)=5652497) -636 train 7.764595 (lr=5.6386e-05) (hash(x)=5931050) -637 train 7.846677 (lr=5.6188e-05) (hash(x)=6961314) -638 train 7.671052 (lr=5.5990e-05) (hash(x)=5973636) -639 train 7.702141 (lr=5.5792e-05) (hash(x)=7130251) -640 train 7.470479 (lr=5.5594e-05) (hash(x)=7503390) -641 train 7.548436 (lr=5.5396e-05) (hash(x)=5927461) -642 train 7.729150 (lr=5.5198e-05) (hash(x)=6196741) -643 train 7.664162 (lr=5.5000e-05) (hash(x)=6610177) -644 train 7.649590 (lr=5.4802e-05) (hash(x)=6635147) -645 train 7.878681 (lr=5.4604e-05) (hash(x)=7277580) -646 train 7.505372 (lr=5.4406e-05) (hash(x)=5050080) -647 train 7.597687 (lr=5.4208e-05) (hash(x)=6508350) -648 train 7.799048 (lr=5.4010e-05) (hash(x)=5276338) -649 train 7.926001 (lr=5.3812e-05) (hash(x)=6536034) -650 val loss 7.7069 -650 val perplexity 2223.7351 -650 train 7.738086 (lr=5.3614e-05) (hash(x)=6944772) -651 train 7.771226 (lr=5.3416e-05) (hash(x)=6994983) -652 train 7.742393 (lr=5.3218e-05) (hash(x)=7172017) -653 train 7.818169 (lr=5.3021e-05) (hash(x)=8700721) -654 train 7.777443 (lr=5.2823e-05) (hash(x)=6774360) -655 train 7.646158 (lr=5.2625e-05) (hash(x)=5859576) -656 train 7.336699 (lr=5.2427e-05) (hash(x)=5899275) -657 train 7.280589 (lr=5.2230e-05) (hash(x)=5264962) -658 train 7.073446 (lr=5.2032e-05) (hash(x)=5679861) -659 train 7.514309 (lr=5.1835e-05) (hash(x)=5487065) -660 train 7.287186 (lr=5.1637e-05) (hash(x)=4239476) -661 train 7.589615 (lr=5.1440e-05) (hash(x)=5731624) -662 train 7.704318 (lr=5.1242e-05) (hash(x)=5883465) -663 train 7.496695 (lr=5.1045e-05) (hash(x)=4892065) -664 train 7.341777 (lr=5.0848e-05) (hash(x)=5858782) -665 train 7.631145 (lr=5.0651e-05) (hash(x)=5489496) -666 train 7.322380 (lr=5.0454e-05) (hash(x)=4485195) -667 train 7.357772 (lr=5.0257e-05) (hash(x)=4933674) -668 train 7.625730 (lr=5.0060e-05) (hash(x)=5746292) -669 train 7.645675 (lr=4.9863e-05) (hash(x)=7021003) -670 train 7.800535 (lr=4.9667e-05) (hash(x)=5876710) -671 train 7.828298 (lr=4.9470e-05) (hash(x)=7317289) -672 train 7.922224 (lr=4.9274e-05) (hash(x)=5598226) -673 train 7.740124 (lr=4.9077e-05) (hash(x)=7869305) -674 train 7.811048 (lr=4.8881e-05) (hash(x)=6611408) -675 train 7.792580 (lr=4.8685e-05) (hash(x)=6811522) -676 train 7.747264 (lr=4.8489e-05) (hash(x)=6704714) -677 train 7.619981 (lr=4.8293e-05) (hash(x)=6601423) -678 train 7.863634 (lr=4.8097e-05) (hash(x)=6726071) -679 train 7.320654 (lr=4.7902e-05) (hash(x)=5510218) -680 train 8.089325 (lr=4.7706e-05) (hash(x)=7950952) -681 train 7.819820 (lr=4.7511e-05) (hash(x)=7180298) -682 train 7.619933 (lr=4.7316e-05) (hash(x)=6068813) -683 train 7.757200 (lr=4.7121e-05) (hash(x)=7304235) -684 train 7.808416 (lr=4.6926e-05) (hash(x)=7441806) -685 train 7.911201 (lr=4.6731e-05) (hash(x)=8111920) -686 train 8.522529 (lr=4.6537e-05) (hash(x)=6222783) -687 train 7.747676 (lr=4.6342e-05) (hash(x)=6752265) -688 train 7.546983 (lr=4.6148e-05) (hash(x)=6147634) -689 train 7.614676 (lr=4.5954e-05) (hash(x)=6788720) -690 train 7.741381 (lr=4.5760e-05) (hash(x)=6413518) -691 train 7.652423 (lr=4.5567e-05) (hash(x)=5994476) -692 train 7.556926 (lr=4.5373e-05) (hash(x)=5462082) -693 train 7.582242 (lr=4.5180e-05) (hash(x)=5862533) -694 train 7.726602 (lr=4.4987e-05) (hash(x)=7132796) -695 train 7.636469 (lr=4.4794e-05) (hash(x)=6530867) -696 train 7.705276 (lr=4.4601e-05) (hash(x)=7932207) -697 train 7.633253 (lr=4.4408e-05) (hash(x)=5914734) -698 train 7.815759 (lr=4.4216e-05) (hash(x)=6361594) -699 train 7.784986 (lr=4.4024e-05) (hash(x)=5746260) -700 val loss 7.6796 -700 val perplexity 2163.6875 -700 train 7.711780 (lr=4.3832e-05) (hash(x)=7065743) -701 train 7.642722 (lr=4.3640e-05) (hash(x)=6856097) -702 train 7.710251 (lr=4.3449e-05) (hash(x)=7588648) -703 train 7.619558 (lr=4.3258e-05) (hash(x)=5790078) -704 train 7.648414 (lr=4.3067e-05) (hash(x)=6069422) -705 train 7.986873 (lr=4.2876e-05) (hash(x)=5805002) -706 train 7.672440 (lr=4.2685e-05) (hash(x)=5344711) -707 train 7.533229 (lr=4.2495e-05) (hash(x)=6430135) -708 train 7.646186 (lr=4.2305e-05) (hash(x)=6317763) -709 train 7.543816 (lr=4.2115e-05) (hash(x)=6156715) -710 train 7.940332 (lr=4.1925e-05) (hash(x)=6321494) -711 train 7.972737 (lr=4.1736e-05) (hash(x)=7614023) -712 train 7.921884 (lr=4.1547e-05) (hash(x)=6740380) -713 train 7.738816 (lr=4.1358e-05) (hash(x)=4861744) -714 train 7.632679 (lr=4.1170e-05) (hash(x)=6542179) -715 train 7.713099 (lr=4.0981e-05) (hash(x)=5244861) -716 train 7.808039 (lr=4.0793e-05) (hash(x)=7306636) -717 train 7.647733 (lr=4.0606e-05) (hash(x)=7163697) -718 train 7.870760 (lr=4.0418e-05) (hash(x)=6421642) -719 train 7.642736 (lr=4.0231e-05) (hash(x)=5245146) -720 train 7.712700 (lr=4.0044e-05) (hash(x)=6046027) -721 train 7.502840 (lr=3.9857e-05) (hash(x)=6153866) -722 train 7.678772 (lr=3.9671e-05) (hash(x)=5827481) -723 train 7.627296 (lr=3.9485e-05) (hash(x)=6415565) -724 train 7.751038 (lr=3.9299e-05) (hash(x)=6409570) -725 train 8.182779 (lr=3.9114e-05) (hash(x)=7835853) -726 train 7.351697 (lr=3.8929e-05) (hash(x)=4827589) -727 train 7.483222 (lr=3.8744e-05) (hash(x)=5786972) -728 train 7.873793 (lr=3.8560e-05) (hash(x)=6736612) -729 train 7.735463 (lr=3.8376e-05) (hash(x)=6733560) -730 train 7.901821 (lr=3.8192e-05) (hash(x)=4877208) -731 train 7.403782 (lr=3.8008e-05) (hash(x)=6131703) -732 train 7.551181 (lr=3.7825e-05) (hash(x)=6533769) -733 train 7.479488 (lr=3.7642e-05) (hash(x)=6001331) -734 train 8.035430 (lr=3.7460e-05) (hash(x)=10602643) -735 train 7.950204 (lr=3.7277e-05) (hash(x)=6346459) -736 train 7.654514 (lr=3.7096e-05) (hash(x)=6728215) -737 train 7.987059 (lr=3.6914e-05) (hash(x)=8943770) -738 train 7.788762 (lr=3.6733e-05) (hash(x)=7141912) -739 train 7.722995 (lr=3.6552e-05) (hash(x)=6504131) -740 train 7.601144 (lr=3.6372e-05) (hash(x)=6461667) -741 train 7.816743 (lr=3.6192e-05) (hash(x)=5869339) -742 train 8.188843 (lr=3.6012e-05) (hash(x)=7948065) -743 train 7.434481 (lr=3.5833e-05) (hash(x)=5209234) -744 train 7.563751 (lr=3.5654e-05) (hash(x)=6372244) -745 train 7.750163 (lr=3.5475e-05) (hash(x)=7678937) -746 train 7.666525 (lr=3.5297e-05) (hash(x)=6519438) -747 train 7.738029 (lr=3.5119e-05) (hash(x)=6163272) -748 train 7.778108 (lr=3.4942e-05) (hash(x)=7025209) -749 train 7.621389 (lr=3.4765e-05) (hash(x)=5774172) -750 val loss 7.6733 -750 val perplexity 2150.1157 -750 train 7.772177 (lr=3.4588e-05) (hash(x)=5327301) -751 train 7.528878 (lr=3.4412e-05) (hash(x)=5676768) -752 train 7.240673 (lr=3.4236e-05) (hash(x)=4823304) -753 train 7.363310 (lr=3.4060e-05) (hash(x)=6443895) -754 train 8.195238 (lr=3.3885e-05) (hash(x)=8032890) -755 train 8.256121 (lr=3.3711e-05) (hash(x)=6090561) -756 train 7.571077 (lr=3.3537e-05) (hash(x)=4514262) -757 train 8.051496 (lr=3.3363e-05) (hash(x)=7788628) -758 train 7.969385 (lr=3.3189e-05) (hash(x)=7239456) -759 train 8.007385 (lr=3.3016e-05) (hash(x)=5863092) -760 train 7.673955 (lr=3.2844e-05) (hash(x)=5572628) -761 train 7.754914 (lr=3.2672e-05) (hash(x)=7141354) -762 train 7.977323 (lr=3.2500e-05) (hash(x)=7272638) -763 train 7.810363 (lr=3.2329e-05) (hash(x)=7201312) -764 train 7.825765 (lr=3.2158e-05) (hash(x)=6015388) -765 train 7.891021 (lr=3.1988e-05) (hash(x)=6414278) -766 train 7.651104 (lr=3.1818e-05) (hash(x)=7137466) -767 train 8.223488 (lr=3.1648e-05) (hash(x)=7019489) -768 train 7.766088 (lr=3.1479e-05) (hash(x)=7233453) -769 train 7.532125 (lr=3.1311e-05) (hash(x)=7914626) -770 train 7.628759 (lr=3.1142e-05) (hash(x)=5764080) -771 train 7.651288 (lr=3.0975e-05) (hash(x)=6225608) -772 train 7.757124 (lr=3.0808e-05) (hash(x)=8097255) -773 train 7.765531 (lr=3.0641e-05) (hash(x)=5998078) -774 train 7.879177 (lr=3.0475e-05) (hash(x)=5416254) -775 train 7.555988 (lr=3.0309e-05) (hash(x)=5483019) -776 train 7.386785 (lr=3.0144e-05) (hash(x)=4702208) -777 train 7.680641 (lr=2.9979e-05) (hash(x)=5911642) -778 train 7.725726 (lr=2.9814e-05) (hash(x)=6132487) -779 train 7.871939 (lr=2.9651e-05) (hash(x)=5903258) -780 train 7.792637 (lr=2.9487e-05) (hash(x)=7915382) -781 train 7.814367 (lr=2.9324e-05) (hash(x)=5632006) -782 train 7.600195 (lr=2.9162e-05) (hash(x)=6518211) -783 train 7.689114 (lr=2.9000e-05) (hash(x)=5968716) -784 train 7.804308 (lr=2.8839e-05) (hash(x)=7344525) -785 train 7.699021 (lr=2.8678e-05) (hash(x)=6401968) -786 train 7.628079 (lr=2.8518e-05) (hash(x)=6276127) -787 train 7.738458 (lr=2.8358e-05) (hash(x)=5778017) -788 train 7.262368 (lr=2.8199e-05) (hash(x)=5387306) -789 train 7.219073 (lr=2.8040e-05) (hash(x)=5772567) -790 train 7.462823 (lr=2.7881e-05) (hash(x)=6383748) -791 train 7.780804 (lr=2.7724e-05) (hash(x)=7780194) -792 train 7.660501 (lr=2.7566e-05) (hash(x)=7119030) -793 train 7.773759 (lr=2.7410e-05) (hash(x)=6424771) -794 train 7.584406 (lr=2.7254e-05) (hash(x)=6540151) -795 train 7.564932 (lr=2.7098e-05) (hash(x)=6140998) -796 train 7.637936 (lr=2.6943e-05) (hash(x)=6208271) -797 train 7.491893 (lr=2.6788e-05) (hash(x)=7859566) -798 train 8.084792 (lr=2.6634e-05) (hash(x)=7064477) -799 train 7.343802 (lr=2.6481e-05) (hash(x)=3784321) -800 val loss 7.6582 -800 val perplexity 2117.9937 -800 train 7.621006 (lr=2.6328e-05) (hash(x)=4472758) -801 train 7.567871 (lr=2.6176e-05) (hash(x)=5557891) -802 train 7.742266 (lr=2.6024e-05) (hash(x)=7969325) -803 train 7.766358 (lr=2.5873e-05) (hash(x)=5860821) -804 train 7.779501 (lr=2.5722e-05) (hash(x)=6750848) -805 train 7.706462 (lr=2.5572e-05) (hash(x)=5674826) -806 train 7.489059 (lr=2.5423e-05) (hash(x)=5529163) -807 train 7.921141 (lr=2.5274e-05) (hash(x)=7774109) -808 train 7.672556 (lr=2.5125e-05) (hash(x)=6762509) -809 train 7.769102 (lr=2.4978e-05) (hash(x)=5466449) -810 train 7.630760 (lr=2.4830e-05) (hash(x)=7046935) -811 train 8.432259 (lr=2.4684e-05) (hash(x)=7997664) -812 train 7.813199 (lr=2.4538e-05) (hash(x)=6882594) -813 train 7.983698 (lr=2.4392e-05) (hash(x)=7006517) -814 train 7.847879 (lr=2.4247e-05) (hash(x)=6832530) -815 train 7.689321 (lr=2.4103e-05) (hash(x)=6576749) -816 train 7.772837 (lr=2.3959e-05) (hash(x)=8276629) -817 train 7.566218 (lr=2.3816e-05) (hash(x)=6896198) -818 train 7.786208 (lr=2.3674e-05) (hash(x)=5829252) -819 train 7.970734 (lr=2.3532e-05) (hash(x)=7266655) -820 train 7.669348 (lr=2.3391e-05) (hash(x)=6015975) -821 train 7.651598 (lr=2.3250e-05) (hash(x)=5696696) -822 train 7.663073 (lr=2.3110e-05) (hash(x)=5411666) -823 train 7.923930 (lr=2.2971e-05) (hash(x)=7072404) -824 train 7.543594 (lr=2.2832e-05) (hash(x)=4910095) -825 train 7.683859 (lr=2.2694e-05) (hash(x)=6590657) -826 train 7.632721 (lr=2.2556e-05) (hash(x)=7665574) -827 train 7.674030 (lr=2.2420e-05) (hash(x)=6626459) -828 train 7.721012 (lr=2.2283e-05) (hash(x)=6731971) -829 train 7.716840 (lr=2.2148e-05) (hash(x)=5644977) -830 train 7.671655 (lr=2.2013e-05) (hash(x)=6238654) -831 train 7.563114 (lr=2.1878e-05) (hash(x)=6556025) -832 train 7.885883 (lr=2.1745e-05) (hash(x)=7175563) -833 train 7.781804 (lr=2.1612e-05) (hash(x)=6407492) -834 train 7.559549 (lr=2.1479e-05) (hash(x)=4934335) -835 train 7.587574 (lr=2.1347e-05) (hash(x)=5942129) -836 train 7.640697 (lr=2.1216e-05) (hash(x)=5995643) -837 train 7.689251 (lr=2.1086e-05) (hash(x)=6012163) -838 train 7.793689 (lr=2.0956e-05) (hash(x)=8464831) -839 train 8.021312 (lr=2.0827e-05) (hash(x)=7325027) -840 train 7.877116 (lr=2.0698e-05) (hash(x)=6785865) -841 train 7.798633 (lr=2.0570e-05) (hash(x)=4425520) -842 train 7.575806 (lr=2.0443e-05) (hash(x)=5388267) -843 train 7.856617 (lr=2.0317e-05) (hash(x)=7322467) -844 train 7.645762 (lr=2.0191e-05) (hash(x)=6681766) -845 train 7.710856 (lr=2.0066e-05) (hash(x)=7482800) -846 train 7.666755 (lr=1.9941e-05) (hash(x)=5554493) -847 train 7.874363 (lr=1.9818e-05) (hash(x)=6373412) -848 train 7.249459 (lr=1.9694e-05) (hash(x)=5117517) -849 train 7.534847 (lr=1.9572e-05) (hash(x)=6981426) -850 val loss 7.6547 -850 val perplexity 2110.5022 -850 train 7.510384 (lr=1.9450e-05) (hash(x)=6886188) -851 train 7.706790 (lr=1.9329e-05) (hash(x)=7332255) -852 train 7.707869 (lr=1.9209e-05) (hash(x)=6172042) -853 train 7.850852 (lr=1.9089e-05) (hash(x)=5930894) -854 train 7.913106 (lr=1.8970e-05) (hash(x)=7448958) -855 train 7.687988 (lr=1.8852e-05) (hash(x)=5262868) -856 train 7.568910 (lr=1.8734e-05) (hash(x)=5558427) -857 train 7.460382 (lr=1.8618e-05) (hash(x)=5585769) -858 train 7.371536 (lr=1.8501e-05) (hash(x)=5838081) -859 train 7.521458 (lr=1.8386e-05) (hash(x)=5688247) -860 train 7.673971 (lr=1.8271e-05) (hash(x)=5162020) -861 train 7.813965 (lr=1.8157e-05) (hash(x)=7462079) -862 train 7.682695 (lr=1.8044e-05) (hash(x)=6516108) -863 train 7.465949 (lr=1.7931e-05) (hash(x)=8055563) -864 train 7.664862 (lr=1.7819e-05) (hash(x)=6271901) -865 train 7.716033 (lr=1.7708e-05) (hash(x)=6221701) -866 train 7.694732 (lr=1.7598e-05) (hash(x)=5772861) -867 train 7.680919 (lr=1.7488e-05) (hash(x)=5352405) -868 train 7.723236 (lr=1.7379e-05) (hash(x)=6111630) -869 train 7.769263 (lr=1.7271e-05) (hash(x)=6730666) -870 train 7.926922 (lr=1.7163e-05) (hash(x)=8698315) -871 train 7.600670 (lr=1.7056e-05) (hash(x)=5932790) -872 train 7.973807 (lr=1.6950e-05) (hash(x)=8099892) -873 train 7.608833 (lr=1.6845e-05) (hash(x)=6223114) -874 train 7.716807 (lr=1.6740e-05) (hash(x)=5798363) -875 train 7.604270 (lr=1.6636e-05) (hash(x)=6249312) -876 train 7.713293 (lr=1.6533e-05) (hash(x)=6929692) -877 train 7.791829 (lr=1.6431e-05) (hash(x)=7242827) -878 train 7.553535 (lr=1.6329e-05) (hash(x)=6332123) -879 train 7.467490 (lr=1.6228e-05) (hash(x)=5680154) -880 train 7.870937 (lr=1.6128e-05) (hash(x)=6352331) -881 train 7.659013 (lr=1.6029e-05) (hash(x)=6332332) -882 train 7.759612 (lr=1.5930e-05) (hash(x)=6180674) -883 train 7.678062 (lr=1.5832e-05) (hash(x)=8156280) -884 train 7.746185 (lr=1.5735e-05) (hash(x)=5874247) -885 train 7.656021 (lr=1.5639e-05) (hash(x)=6659781) -886 train 7.788992 (lr=1.5543e-05) (hash(x)=5780147) -887 train 7.597503 (lr=1.5449e-05) (hash(x)=5914217) -888 train 7.435068 (lr=1.5354e-05) (hash(x)=5411762) -889 train 7.725708 (lr=1.5261e-05) (hash(x)=6714110) -890 train 7.435064 (lr=1.5169e-05) (hash(x)=5999685) -891 train 7.630649 (lr=1.5077e-05) (hash(x)=7120215) -892 train 7.878129 (lr=1.4986e-05) (hash(x)=6546587) -893 train 7.632555 (lr=1.4896e-05) (hash(x)=6593413) -894 train 7.741621 (lr=1.4806e-05) (hash(x)=6369927) -895 train 7.642912 (lr=1.4718e-05) (hash(x)=6424128) -896 train 7.609522 (lr=1.4630e-05) (hash(x)=5736158) -897 train 7.412637 (lr=1.4543e-05) (hash(x)=5903043) -898 train 7.534304 (lr=1.4456e-05) (hash(x)=4419128) -899 train 7.325389 (lr=1.4371e-05) (hash(x)=4390027) -900 val loss 7.6431 -900 val perplexity 2086.2512 -900 train 7.598150 (lr=1.4286e-05) (hash(x)=6728135) -901 train 7.698533 (lr=1.4202e-05) (hash(x)=6945760) -902 train 7.681007 (lr=1.4119e-05) (hash(x)=6081534) -903 train 7.753824 (lr=1.4037e-05) (hash(x)=7804089) -904 train 7.760136 (lr=1.3955e-05) (hash(x)=6225832) -905 train 7.819795 (lr=1.3874e-05) (hash(x)=6273417) -906 train 7.870361 (lr=1.3794e-05) (hash(x)=7775633) -907 train 7.835398 (lr=1.3715e-05) (hash(x)=7130267) -908 train 7.604505 (lr=1.3637e-05) (hash(x)=6554076) -909 train 7.735264 (lr=1.3559e-05) (hash(x)=6140697) -910 train 7.558895 (lr=1.3482e-05) (hash(x)=6128181) -911 train 7.629247 (lr=1.3407e-05) (hash(x)=6490149) -912 train 7.222819 (lr=1.3331e-05) (hash(x)=5422426) -913 train 7.649173 (lr=1.3257e-05) (hash(x)=4847733) -914 train 7.653976 (lr=1.3183e-05) (hash(x)=6349747) -915 train 7.927680 (lr=1.3111e-05) (hash(x)=9276378) -916 train 7.541157 (lr=1.3039e-05) (hash(x)=6869524) -917 train 7.589217 (lr=1.2968e-05) (hash(x)=7082053) -918 train 7.645258 (lr=1.2897e-05) (hash(x)=7799351) -919 train 7.801645 (lr=1.2828e-05) (hash(x)=6283540) -920 train 7.587108 (lr=1.2759e-05) (hash(x)=6660860) -921 train 7.530860 (lr=1.2691e-05) (hash(x)=5200956) -922 train 7.624091 (lr=1.2624e-05) (hash(x)=5653241) -923 train 7.766058 (lr=1.2558e-05) (hash(x)=5781680) -924 train 7.760087 (lr=1.2493e-05) (hash(x)=6146666) -925 train 7.595194 (lr=1.2428e-05) (hash(x)=8652907) -926 train 7.395506 (lr=1.2364e-05) (hash(x)=5311546) -927 train 7.565045 (lr=1.2301e-05) (hash(x)=5728337) -928 train 7.538977 (lr=1.2239e-05) (hash(x)=5413240) -929 train 7.634708 (lr=1.2178e-05) (hash(x)=5832401) -930 train 7.357700 (lr=1.2118e-05) (hash(x)=7420230) -931 train 7.722661 (lr=1.2058e-05) (hash(x)=6278202) -932 train 7.626976 (lr=1.1999e-05) (hash(x)=6189873) -933 train 7.733199 (lr=1.1941e-05) (hash(x)=7403868) -934 train 7.591636 (lr=1.1884e-05) (hash(x)=6867459) -935 train 7.771249 (lr=1.1828e-05) (hash(x)=7400272) -936 train 7.788975 (lr=1.1772e-05) (hash(x)=7936275) -937 train 7.493584 (lr=1.1718e-05) (hash(x)=5943413) -938 train 7.716563 (lr=1.1664e-05) (hash(x)=5442166) -939 train 7.632943 (lr=1.1611e-05) (hash(x)=5795128) -940 train 7.856045 (lr=1.1559e-05) (hash(x)=6831680) -941 train 7.515475 (lr=1.1508e-05) (hash(x)=5519980) -942 train 7.548639 (lr=1.1457e-05) (hash(x)=6765461) -943 train 7.519236 (lr=1.1408e-05) (hash(x)=6473432) -944 train 7.469529 (lr=1.1359e-05) (hash(x)=6490395) -945 train 7.694402 (lr=1.1311e-05) (hash(x)=5484669) -946 train 7.697118 (lr=1.1264e-05) (hash(x)=7278970) -947 train 7.655480 (lr=1.1218e-05) (hash(x)=5201502) -948 train 7.894952 (lr=1.1173e-05) (hash(x)=7277915) -949 train 7.615733 (lr=1.1128e-05) (hash(x)=7227057) -950 val loss 7.6369 -950 val perplexity 2073.3569 -950 train 7.830536 (lr=1.1085e-05) (hash(x)=8178996) -951 train 7.962353 (lr=1.1042e-05) (hash(x)=6922646) -952 train 7.524120 (lr=1.1000e-05) (hash(x)=5941772) -953 train 7.490892 (lr=1.0959e-05) (hash(x)=6056673) -954 train 7.865421 (lr=1.0919e-05) (hash(x)=6912178) -955 train 7.394458 (lr=1.0879e-05) (hash(x)=5484641) -956 train 7.726378 (lr=1.0841e-05) (hash(x)=5121117) -957 train 7.765845 (lr=1.0803e-05) (hash(x)=7100865) -958 train 7.468468 (lr=1.0766e-05) (hash(x)=5334280) -959 train 7.542262 (lr=1.0730e-05) (hash(x)=7277141) -960 train 7.549524 (lr=1.0695e-05) (hash(x)=6401960) -961 train 7.603185 (lr=1.0661e-05) (hash(x)=6407603) -962 train 7.751517 (lr=1.0628e-05) (hash(x)=5786089) -963 train 7.619198 (lr=1.0595e-05) (hash(x)=5604614) -964 train 7.632313 (lr=1.0563e-05) (hash(x)=5454287) -965 train 7.724827 (lr=1.0533e-05) (hash(x)=6200612) -966 train 7.727278 (lr=1.0503e-05) (hash(x)=5691759) -967 train 7.679711 (lr=1.0474e-05) (hash(x)=7443124) -968 train 7.697671 (lr=1.0445e-05) (hash(x)=6711366) -969 train 7.616602 (lr=1.0418e-05) (hash(x)=6728764) -970 train 7.914454 (lr=1.0391e-05) (hash(x)=6870240) -971 train 7.596965 (lr=1.0366e-05) (hash(x)=5601968) -972 train 7.412313 (lr=1.0341e-05) (hash(x)=5311504) -973 train 7.627693 (lr=1.0317e-05) (hash(x)=6877761) -974 train 7.719584 (lr=1.0294e-05) (hash(x)=6457033) -975 train 7.675742 (lr=1.0272e-05) (hash(x)=5632735) -976 train 7.833461 (lr=1.0251e-05) (hash(x)=6024880) -977 train 7.541535 (lr=1.0230e-05) (hash(x)=5658845) -978 train 7.423663 (lr=1.0211e-05) (hash(x)=6089461) -979 train 7.525606 (lr=1.0192e-05) (hash(x)=5594810) -980 train 7.306229 (lr=1.0174e-05) (hash(x)=4667026) -981 train 7.150718 (lr=1.0157e-05) (hash(x)=4738523) -982 train 7.461303 (lr=1.0141e-05) (hash(x)=7451876) -983 train 7.737097 (lr=1.0126e-05) (hash(x)=5881015) -984 train 7.708655 (lr=1.0111e-05) (hash(x)=6255031) -985 train 7.520625 (lr=1.0098e-05) (hash(x)=5263325) -986 train 7.531429 (lr=1.0085e-05) (hash(x)=6654585) -987 train 7.642078 (lr=1.0074e-05) (hash(x)=6865361) -988 train 7.718599 (lr=1.0063e-05) (hash(x)=6978986) -989 train 7.803397 (lr=1.0053e-05) (hash(x)=5644619) -990 train 7.634764 (lr=1.0044e-05) (hash(x)=6551023) -991 train 7.602814 (lr=1.0035e-05) (hash(x)=5809411) -992 train 7.659393 (lr=1.0028e-05) (hash(x)=5501837) -993 train 7.671577 (lr=1.0021e-05) (hash(x)=7044374) -994 train 7.636081 (lr=1.0016e-05) (hash(x)=6526130) -995 train 7.771150 (lr=1.0011e-05) (hash(x)=6293025) -996 train 7.749422 (lr=1.0007e-05) (hash(x)=6295768) -997 train 7.542537 (lr=1.0004e-05) (hash(x)=5189023) -998 train 7.383819 (lr=1.0002e-05) (hash(x)=6255467) -999 val loss 7.6337 -999 val perplexity 2066.6392 -999 train 7.753491 (lr=1.0000e-05) (hash(x)=7232964) +max_steps: 5000 +0 val loss 11.6964 +0 val perplexity 120134.1641 +0 train 11.681432 (lr=6.9930e-08) (hash(x)=22886834) +1 train 11.707855 (lr=1.3986e-07) (hash(x)=26375038) +2 train 11.697785 (lr=2.0979e-07) (hash(x)=30598777) +3 train 11.746068 (lr=2.7972e-07) (hash(x)=27234506) +4 train 11.667249 (lr=3.4965e-07) (hash(x)=27767880) +5 train 11.689628 (lr=4.1958e-07) (hash(x)=23702020) +6 train 11.695712 (lr=4.8951e-07) (hash(x)=31986844) +7 train 11.694219 (lr=5.5944e-07) (hash(x)=20782690) +8 train 11.682017 (lr=6.2937e-07) (hash(x)=25201599) +9 train 11.701687 (lr=6.9930e-07) (hash(x)=23094976) +10 train 11.719524 (lr=7.6923e-07) (hash(x)=23841096) +11 train 11.691272 (lr=8.3916e-07) (hash(x)=26532095) +12 train 11.679819 (lr=9.0909e-07) (hash(x)=24432298) +13 train 11.661159 (lr=9.7902e-07) (hash(x)=27151649) +14 train 11.706215 (lr=1.0490e-06) (hash(x)=24596846) +15 train 11.686604 (lr=1.1189e-06) (hash(x)=23890908) +16 train 11.676717 (lr=1.1888e-06) (hash(x)=28913955) +17 train 11.683827 (lr=1.2587e-06) (hash(x)=25588236) +18 train 11.703112 (lr=1.3287e-06) (hash(x)=23770034) +19 train 11.703272 (lr=1.3986e-06) (hash(x)=24011372) +20 train 11.673697 (lr=1.4685e-06) (hash(x)=25441898) +21 train 11.679000 (lr=1.5385e-06) (hash(x)=28375581) +22 train 11.651532 (lr=1.6084e-06) (hash(x)=24046679) +23 train 11.691457 (lr=1.6783e-06) (hash(x)=24611628) +24 train 11.689631 (lr=1.7483e-06) (hash(x)=26169030) +25 train 11.654218 (lr=1.8182e-06) (hash(x)=30298407) +26 train 11.602553 (lr=1.8881e-06) (hash(x)=23711112) +27 train 11.637504 (lr=1.9580e-06) (hash(x)=19245352) +28 train 11.650237 (lr=2.0280e-06) (hash(x)=21529136) +29 train 11.646011 (lr=2.0979e-06) (hash(x)=28936608) +30 train 11.628531 (lr=2.1678e-06) (hash(x)=24339013) +31 train 11.608597 (lr=2.2378e-06) (hash(x)=25767553) +32 train 11.621074 (lr=2.3077e-06) (hash(x)=26439905) +33 train 11.553171 (lr=2.3776e-06) (hash(x)=31093473) +34 train 11.534493 (lr=2.4476e-06) (hash(x)=25450374) +35 train 11.612979 (lr=2.5175e-06) (hash(x)=24809873) +36 train 11.600270 (lr=2.5874e-06) (hash(x)=23253252) +37 train 11.590937 (lr=2.6573e-06) (hash(x)=27852919) +38 train 11.553466 (lr=2.7273e-06) (hash(x)=23327497) +39 train 11.568993 (lr=2.7972e-06) (hash(x)=22512166) +40 train 11.607439 (lr=2.8671e-06) (hash(x)=22859419) +41 train 11.604158 (lr=2.9371e-06) (hash(x)=27620338) +42 train 11.560443 (lr=3.0070e-06) (hash(x)=26397837) +43 train 11.535918 (lr=3.0769e-06) (hash(x)=28092148) +44 train 11.483371 (lr=3.1469e-06) (hash(x)=24662703) +45 train 11.528278 (lr=3.2168e-06) (hash(x)=27938767) +46 train 11.564862 (lr=3.2867e-06) (hash(x)=26037988) +47 train 11.477984 (lr=3.3566e-06) (hash(x)=24732833) +48 train 11.486730 (lr=3.4266e-06) (hash(x)=25259526) +49 train 11.493329 (lr=3.4965e-06) (hash(x)=23200230) +50 val loss 11.4842 +50 val perplexity 97170.5000 +50 train 11.493132 (lr=3.5664e-06) (hash(x)=26721357) +51 train 11.494756 (lr=3.6364e-06) (hash(x)=22694718) +52 train 11.468366 (lr=3.7063e-06) (hash(x)=28066766) +53 train 11.478510 (lr=3.7762e-06) (hash(x)=23125151) +54 train 11.476964 (lr=3.8462e-06) (hash(x)=27193725) +55 train 11.456296 (lr=3.9161e-06) (hash(x)=25129410) +56 train 11.407587 (lr=3.9860e-06) (hash(x)=24263988) +57 train 11.416016 (lr=4.0559e-06) (hash(x)=23059154) +58 train 11.417663 (lr=4.1259e-06) (hash(x)=26063864) +59 train 11.443651 (lr=4.1958e-06) (hash(x)=27858570) +60 train 11.389420 (lr=4.2657e-06) (hash(x)=23874620) +61 train 11.351631 (lr=4.3357e-06) (hash(x)=22402617) +62 train 11.359116 (lr=4.4056e-06) (hash(x)=23600822) +63 train 11.318557 (lr=4.4755e-06) (hash(x)=26582391) +64 train 11.295123 (lr=4.5455e-06) (hash(x)=23225283) +65 train 11.305864 (lr=4.6154e-06) (hash(x)=26075451) +66 train 11.293687 (lr=4.6853e-06) (hash(x)=24723419) +67 train 11.346980 (lr=4.7552e-06) (hash(x)=27279806) +68 train 11.227622 (lr=4.8252e-06) (hash(x)=25870391) +69 train 11.256930 (lr=4.8951e-06) (hash(x)=26188136) +70 train 11.272212 (lr=4.9650e-06) (hash(x)=30373443) +71 train 11.277821 (lr=5.0350e-06) (hash(x)=26472336) +72 train 11.220775 (lr=5.1049e-06) (hash(x)=26651572) +73 train 11.223932 (lr=5.1748e-06) (hash(x)=26376212) +74 train 11.203940 (lr=5.2448e-06) (hash(x)=26733350) +75 train 11.223627 (lr=5.3147e-06) (hash(x)=28301589) +76 train 11.135572 (lr=5.3846e-06) (hash(x)=27599559) +77 train 11.141918 (lr=5.4545e-06) (hash(x)=28035221) +78 train 11.193738 (lr=5.5245e-06) (hash(x)=25016783) +79 train 11.137055 (lr=5.5944e-06) (hash(x)=27654289) +80 train 11.177922 (lr=5.6643e-06) (hash(x)=24597558) +81 train 11.102667 (lr=5.7343e-06) (hash(x)=21560904) +82 train 11.065352 (lr=5.8042e-06) (hash(x)=21983837) +83 train 11.115806 (lr=5.8741e-06) (hash(x)=24995715) +84 train 11.130313 (lr=5.9441e-06) (hash(x)=29876413) +85 train 11.040342 (lr=6.0140e-06) (hash(x)=23792508) +86 train 11.010483 (lr=6.0839e-06) (hash(x)=25509120) +87 train 11.060485 (lr=6.1538e-06) (hash(x)=26559876) +88 train 11.047167 (lr=6.2238e-06) (hash(x)=23569647) +89 train 11.018964 (lr=6.2937e-06) (hash(x)=25758852) +90 train 10.945205 (lr=6.3636e-06) (hash(x)=25706298) +91 train 10.867126 (lr=6.4336e-06) (hash(x)=28364895) +92 train 10.947328 (lr=6.5035e-06) (hash(x)=25304663) +93 train 10.938071 (lr=6.5734e-06) (hash(x)=25269299) +94 train 11.002284 (lr=6.6434e-06) (hash(x)=25870566) +95 train 10.875463 (lr=6.7133e-06) (hash(x)=21770329) +96 train 10.940558 (lr=6.7832e-06) (hash(x)=27595900) +97 train 10.983792 (lr=6.8531e-06) (hash(x)=24785397) +98 train 10.771827 (lr=6.9231e-06) (hash(x)=21521480) +99 train 10.809169 (lr=6.9930e-06) (hash(x)=24628606) +100 val loss 10.8283 +100 val perplexity 50426.1016 +100 train 10.812544 (lr=7.0629e-06) (hash(x)=24670150) +101 train 10.827269 (lr=7.1329e-06) (hash(x)=23181910) +102 train 10.778678 (lr=7.2028e-06) (hash(x)=22714991) +103 train 10.891918 (lr=7.2727e-06) (hash(x)=22723459) +104 train 10.766426 (lr=7.3427e-06) (hash(x)=21524316) +105 train 10.771110 (lr=7.4126e-06) (hash(x)=25506632) +106 train 10.604274 (lr=7.4825e-06) (hash(x)=21675672) +107 train 10.721609 (lr=7.5524e-06) (hash(x)=22897919) +108 train 10.719629 (lr=7.6224e-06) (hash(x)=23321631) +109 train 10.687320 (lr=7.6923e-06) (hash(x)=26546719) +110 train 11.123685 (lr=7.7622e-06) (hash(x)=31962348) +111 train 10.677440 (lr=7.8322e-06) (hash(x)=30338342) +112 train 10.632641 (lr=7.9021e-06) (hash(x)=23724471) +113 train 10.696601 (lr=7.9720e-06) (hash(x)=29175888) +114 train 10.719426 (lr=8.0420e-06) (hash(x)=23256716) +115 train 10.668437 (lr=8.1119e-06) (hash(x)=27063280) +116 train 10.638942 (lr=8.1818e-06) (hash(x)=31057659) +117 train 10.723846 (lr=8.2517e-06) (hash(x)=32915097) +118 train 10.645576 (lr=8.3217e-06) (hash(x)=28842717) +119 train 10.613378 (lr=8.3916e-06) (hash(x)=25678059) +120 train 10.584674 (lr=8.4615e-06) (hash(x)=21593510) +121 train 10.528899 (lr=8.5315e-06) (hash(x)=20083773) +122 train 10.591046 (lr=8.6014e-06) (hash(x)=23002820) +123 train 10.491305 (lr=8.6713e-06) (hash(x)=21853028) +124 train 10.572208 (lr=8.7413e-06) (hash(x)=26985625) +125 train 10.455043 (lr=8.8112e-06) (hash(x)=21808483) +126 train 10.562392 (lr=8.8811e-06) (hash(x)=28873251) +127 train 10.517394 (lr=8.9510e-06) (hash(x)=26109335) +128 train 10.545134 (lr=9.0210e-06) (hash(x)=26334674) +129 train 10.561358 (lr=9.0909e-06) (hash(x)=24916754) +130 train 10.526412 (lr=9.1608e-06) (hash(x)=25449624) +131 train 10.621987 (lr=9.2308e-06) (hash(x)=25334848) +132 train 10.575444 (lr=9.3007e-06) (hash(x)=27484863) +133 train 10.461125 (lr=9.3706e-06) (hash(x)=24917705) +134 train 10.328513 (lr=9.4406e-06) (hash(x)=25143449) +135 train 10.364721 (lr=9.5105e-06) (hash(x)=25044885) +136 train 10.473661 (lr=9.5804e-06) (hash(x)=27821028) +137 train 10.524271 (lr=9.6503e-06) (hash(x)=28747022) +138 train 10.509422 (lr=9.7203e-06) (hash(x)=27182888) +139 train 10.403497 (lr=9.7902e-06) (hash(x)=23678349) +140 train 10.546123 (lr=9.8601e-06) (hash(x)=23593235) +141 train 10.549876 (lr=9.9301e-06) (hash(x)=28529813) +142 train 10.678026 (lr=1.0000e-05) (hash(x)=32074661) +143 train 10.422575 (lr=1.0070e-05) (hash(x)=28870690) +144 train 10.448201 (lr=1.0140e-05) (hash(x)=27307705) +145 train 10.450505 (lr=1.0210e-05) (hash(x)=25044834) +146 train 10.475438 (lr=1.0280e-05) (hash(x)=23712023) +147 train 10.567437 (lr=1.0350e-05) (hash(x)=32982615) +148 train 10.484224 (lr=1.0420e-05) (hash(x)=30113660) +149 train 10.437676 (lr=1.0490e-05) (hash(x)=20970960) +150 val loss 10.3827 +150 val perplexity 32295.1172 +150 train 10.435656 (lr=1.0559e-05) (hash(x)=23132684) +151 train 10.778354 (lr=1.0629e-05) (hash(x)=35279941) +152 train 10.563399 (lr=1.0699e-05) (hash(x)=31227444) +153 train 10.294990 (lr=1.0769e-05) (hash(x)=25529472) +154 train 10.254424 (lr=1.0839e-05) (hash(x)=24350409) +155 train 10.535341 (lr=1.0909e-05) (hash(x)=26400041) +156 train 10.380445 (lr=1.0979e-05) (hash(x)=25262621) +157 train 10.357302 (lr=1.1049e-05) (hash(x)=24656138) +158 train 10.340491 (lr=1.1119e-05) (hash(x)=26803414) +159 train 10.281394 (lr=1.1189e-05) (hash(x)=25015923) +160 train 10.218238 (lr=1.1259e-05) (hash(x)=23581172) +161 train 10.254237 (lr=1.1329e-05) (hash(x)=22924885) +162 train 10.300623 (lr=1.1399e-05) (hash(x)=23414296) +163 train 10.287379 (lr=1.1469e-05) (hash(x)=24853586) +164 train 10.442863 (lr=1.1538e-05) (hash(x)=25000130) +165 train 10.335706 (lr=1.1608e-05) (hash(x)=27004780) +166 train 10.257785 (lr=1.1678e-05) (hash(x)=26148573) +167 train 10.309415 (lr=1.1748e-05) (hash(x)=26740855) +168 train 10.166774 (lr=1.1818e-05) (hash(x)=20965419) +169 train 10.280951 (lr=1.1888e-05) (hash(x)=23950114) +170 train 10.146571 (lr=1.1958e-05) (hash(x)=24951982) +171 train 10.251609 (lr=1.2028e-05) (hash(x)=24584116) +172 train 10.312800 (lr=1.2098e-05) (hash(x)=24378759) +173 train 10.199939 (lr=1.2168e-05) (hash(x)=25718516) +174 train 10.393836 (lr=1.2238e-05) (hash(x)=28424396) +175 train 10.298756 (lr=1.2308e-05) (hash(x)=22262151) +176 train 10.393409 (lr=1.2378e-05) (hash(x)=26438412) +177 train 10.241351 (lr=1.2448e-05) (hash(x)=23025303) +178 train 10.148528 (lr=1.2517e-05) (hash(x)=24190770) +179 train 10.175870 (lr=1.2587e-05) (hash(x)=26627860) +180 train 10.278007 (lr=1.2657e-05) (hash(x)=23663439) +181 train 10.169992 (lr=1.2727e-05) (hash(x)=23700532) +182 train 10.216712 (lr=1.2797e-05) (hash(x)=23075676) +183 train 10.267998 (lr=1.2867e-05) (hash(x)=26621834) +184 train 10.222518 (lr=1.2937e-05) (hash(x)=29426269) +185 train 10.162562 (lr=1.3007e-05) (hash(x)=21821465) +186 train 10.192737 (lr=1.3077e-05) (hash(x)=26506130) +187 train 10.302463 (lr=1.3147e-05) (hash(x)=26930630) +188 train 10.123102 (lr=1.3217e-05) (hash(x)=22993793) +189 train 10.145535 (lr=1.3287e-05) (hash(x)=19557946) +190 train 10.226542 (lr=1.3357e-05) (hash(x)=23572891) +191 train 10.103407 (lr=1.3427e-05) (hash(x)=23234741) +192 train 10.210139 (lr=1.3497e-05) (hash(x)=25547951) +193 train 10.155039 (lr=1.3566e-05) (hash(x)=26713563) +194 train 10.214169 (lr=1.3636e-05) (hash(x)=25913622) +195 train 10.239659 (lr=1.3706e-05) (hash(x)=28102443) +196 train 10.181754 (lr=1.3776e-05) (hash(x)=23093351) +197 train 10.477747 (lr=1.3846e-05) (hash(x)=31689122) +198 train 10.399048 (lr=1.3916e-05) (hash(x)=32252517) +199 train 10.202600 (lr=1.3986e-05) (hash(x)=25470563) +200 val loss 10.1887 +200 val perplexity 26599.6152 +200 train 10.344176 (lr=1.4056e-05) (hash(x)=25597614) +201 train 10.222078 (lr=1.4126e-05) (hash(x)=23757479) +202 train 10.037996 (lr=1.4196e-05) (hash(x)=25140048) +203 train 10.157918 (lr=1.4266e-05) (hash(x)=28282861) +204 train 10.082928 (lr=1.4336e-05) (hash(x)=24754885) +205 train 10.275352 (lr=1.4406e-05) (hash(x)=26731964) +206 train 10.337663 (lr=1.4476e-05) (hash(x)=26660561) +207 train 10.105743 (lr=1.4545e-05) (hash(x)=21799102) +208 train 10.216682 (lr=1.4615e-05) (hash(x)=27025986) +209 train 10.117465 (lr=1.4685e-05) (hash(x)=24672077) +210 train 10.145139 (lr=1.4755e-05) (hash(x)=25322984) +211 train 10.114175 (lr=1.4825e-05) (hash(x)=23471769) +212 train 9.899231 (lr=1.4895e-05) (hash(x)=20766491) +213 train 10.285530 (lr=1.4965e-05) (hash(x)=24058931) +214 train 10.135091 (lr=1.5035e-05) (hash(x)=23872843) +215 train 10.153305 (lr=1.5105e-05) (hash(x)=23275479) +216 train 10.248733 (lr=1.5175e-05) (hash(x)=24914695) +217 train 10.148845 (lr=1.5245e-05) (hash(x)=24364396) +218 train 10.041451 (lr=1.5315e-05) (hash(x)=27986474) +219 train 10.223360 (lr=1.5385e-05) (hash(x)=24473581) +220 train 10.104202 (lr=1.5455e-05) (hash(x)=22974689) +221 train 10.164145 (lr=1.5524e-05) (hash(x)=23774644) +222 train 10.145080 (lr=1.5594e-05) (hash(x)=23245327) +223 train 10.067250 (lr=1.5664e-05) (hash(x)=22091862) +224 train 10.062078 (lr=1.5734e-05) (hash(x)=24362839) +225 train 10.020669 (lr=1.5804e-05) (hash(x)=25482303) +226 train 10.179077 (lr=1.5874e-05) (hash(x)=24911853) +227 train 10.138840 (lr=1.5944e-05) (hash(x)=26018202) +228 train 10.032106 (lr=1.6014e-05) (hash(x)=26124495) +229 train 10.004419 (lr=1.6084e-05) (hash(x)=24560096) +230 train 10.107854 (lr=1.6154e-05) (hash(x)=24695331) +231 train 10.121604 (lr=1.6224e-05) (hash(x)=17430373) +232 train 10.065555 (lr=1.6294e-05) (hash(x)=21813345) +233 train 9.782409 (lr=1.6364e-05) (hash(x)=20098681) +234 train 9.880297 (lr=1.6434e-05) (hash(x)=25095928) +235 train 9.891715 (lr=1.6503e-05) (hash(x)=24078083) +236 train 9.974765 (lr=1.6573e-05) (hash(x)=22901505) +237 train 10.091905 (lr=1.6643e-05) (hash(x)=26595592) +238 train 10.012557 (lr=1.6713e-05) (hash(x)=27663196) +239 train 10.048629 (lr=1.6783e-05) (hash(x)=22954861) +240 train 10.107549 (lr=1.6853e-05) (hash(x)=30159234) +241 train 10.038472 (lr=1.6923e-05) (hash(x)=29294271) +242 train 10.041677 (lr=1.6993e-05) (hash(x)=23728322) +243 train 10.072212 (lr=1.7063e-05) (hash(x)=28695016) +244 train 10.096122 (lr=1.7133e-05) (hash(x)=26702728) +245 train 9.985259 (lr=1.7203e-05) (hash(x)=27100115) +246 train 9.871631 (lr=1.7273e-05) (hash(x)=25082752) +247 train 10.187572 (lr=1.7343e-05) (hash(x)=26671799) +248 train 10.112103 (lr=1.7413e-05) (hash(x)=23718946) +249 train 10.099586 (lr=1.7483e-05) (hash(x)=28137394) +250 val loss 9.9876 +250 val perplexity 21755.6738 +250 train 10.024165 (lr=1.7552e-05) (hash(x)=23893495) +251 train 9.984644 (lr=1.7622e-05) (hash(x)=23166092) +252 train 9.895572 (lr=1.7692e-05) (hash(x)=25907665) +253 train 9.827132 (lr=1.7762e-05) (hash(x)=25885986) +254 train 9.864460 (lr=1.7832e-05) (hash(x)=25262712) +255 train 9.922817 (lr=1.7902e-05) (hash(x)=26924723) +256 train 9.983249 (lr=1.7972e-05) (hash(x)=28744736) +257 train 9.915583 (lr=1.8042e-05) (hash(x)=26140590) +258 train 9.988982 (lr=1.8112e-05) (hash(x)=25780449) +259 train 9.975449 (lr=1.8182e-05) (hash(x)=25138659) +260 train 9.912649 (lr=1.8252e-05) (hash(x)=27244046) +261 train 10.113227 (lr=1.8322e-05) (hash(x)=27224685) +262 train 10.009444 (lr=1.8392e-05) (hash(x)=28274477) +263 train 9.838660 (lr=1.8462e-05) (hash(x)=23557495) +264 train 9.875276 (lr=1.8531e-05) (hash(x)=24680596) +265 train 9.703293 (lr=1.8601e-05) (hash(x)=23928957) +266 train 9.797968 (lr=1.8671e-05) (hash(x)=23761390) +267 train 9.866397 (lr=1.8741e-05) (hash(x)=25288123) +268 train 9.866086 (lr=1.8811e-05) (hash(x)=28705502) +269 train 9.776826 (lr=1.8881e-05) (hash(x)=23246294) +270 train 9.579136 (lr=1.8951e-05) (hash(x)=28639079) +271 train 9.542409 (lr=1.9021e-05) (hash(x)=27804380) +272 train 9.846028 (lr=1.9091e-05) (hash(x)=24172235) +273 train 9.927023 (lr=1.9161e-05) (hash(x)=23089140) +274 train 9.993320 (lr=1.9231e-05) (hash(x)=27163701) +275 train 9.994352 (lr=1.9301e-05) (hash(x)=26993263) +276 train 9.922236 (lr=1.9371e-05) (hash(x)=28224233) +277 train 10.018942 (lr=1.9441e-05) (hash(x)=27397203) +278 train 9.924547 (lr=1.9510e-05) (hash(x)=27923882) +279 train 9.898213 (lr=1.9580e-05) (hash(x)=26654908) +280 train 9.889999 (lr=1.9650e-05) (hash(x)=24213147) +281 train 9.787356 (lr=1.9720e-05) (hash(x)=21965022) +282 train 9.815357 (lr=1.9790e-05) (hash(x)=25465685) +283 train 9.789934 (lr=1.9860e-05) (hash(x)=27347722) +284 train 9.831992 (lr=1.9930e-05) (hash(x)=26732050) +285 train 9.858151 (lr=2.0000e-05) (hash(x)=28314127) +286 train 9.924502 (lr=2.0070e-05) (hash(x)=21471186) +287 train 9.827531 (lr=2.0140e-05) (hash(x)=23627518) +288 train 9.892580 (lr=2.0210e-05) (hash(x)=20870353) +289 train 9.816118 (lr=2.0280e-05) (hash(x)=25024764) +290 train 9.718612 (lr=2.0350e-05) (hash(x)=20683822) +291 train 9.861514 (lr=2.0420e-05) (hash(x)=21768671) +292 train 9.753032 (lr=2.0490e-05) (hash(x)=25557309) +293 train 9.810538 (lr=2.0559e-05) (hash(x)=25076667) +294 train 9.756408 (lr=2.0629e-05) (hash(x)=23765822) +295 train 9.736415 (lr=2.0699e-05) (hash(x)=21889990) +296 train 9.699062 (lr=2.0769e-05) (hash(x)=26339893) +297 train 9.741663 (lr=2.0839e-05) (hash(x)=20932794) +298 train 9.739882 (lr=2.0909e-05) (hash(x)=21750070) +299 train 9.697830 (lr=2.0979e-05) (hash(x)=23665838) +300 val loss 9.7396 +300 val perplexity 16977.4648 +300 train 10.137809 (lr=2.1049e-05) (hash(x)=32888061) +301 train 10.015384 (lr=2.1119e-05) (hash(x)=30223582) +302 train 9.929811 (lr=2.1189e-05) (hash(x)=26908418) +303 train 9.575731 (lr=2.1259e-05) (hash(x)=22528001) +304 train 9.844434 (lr=2.1329e-05) (hash(x)=27452187) +305 train 9.688341 (lr=2.1399e-05) (hash(x)=25181641) +306 train 9.766776 (lr=2.1469e-05) (hash(x)=25546593) +307 train 9.731621 (lr=2.1538e-05) (hash(x)=22487328) +308 train 9.719004 (lr=2.1608e-05) (hash(x)=27804274) +309 train 9.862328 (lr=2.1678e-05) (hash(x)=26544630) +310 train 9.801147 (lr=2.1748e-05) (hash(x)=27738934) +311 train 9.773450 (lr=2.1818e-05) (hash(x)=29248942) +312 train 9.729398 (lr=2.1888e-05) (hash(x)=25103452) +313 train 9.762523 (lr=2.1958e-05) (hash(x)=25052066) +314 train 9.638271 (lr=2.2028e-05) (hash(x)=24481302) +315 train 9.543474 (lr=2.2098e-05) (hash(x)=23543273) +316 train 9.654365 (lr=2.2168e-05) (hash(x)=25608244) +317 train 9.729671 (lr=2.2238e-05) (hash(x)=27451288) +318 train 9.461818 (lr=2.2308e-05) (hash(x)=22806491) +319 train 9.606830 (lr=2.2378e-05) (hash(x)=25533417) +320 train 9.505774 (lr=2.2448e-05) (hash(x)=24557997) +321 train 9.542974 (lr=2.2517e-05) (hash(x)=24432899) +322 train 9.535240 (lr=2.2587e-05) (hash(x)=27583287) +323 train 9.392192 (lr=2.2657e-05) (hash(x)=25552036) +324 train 9.423215 (lr=2.2727e-05) (hash(x)=24201868) +325 train 9.602681 (lr=2.2797e-05) (hash(x)=28149782) +326 train 9.632717 (lr=2.2867e-05) (hash(x)=25529698) +327 train 9.522736 (lr=2.2937e-05) (hash(x)=20612533) +328 train 9.583384 (lr=2.3007e-05) (hash(x)=20699000) +329 train 9.606219 (lr=2.3077e-05) (hash(x)=19774173) +330 train 9.567916 (lr=2.3147e-05) (hash(x)=21681646) +331 train 9.461167 (lr=2.3217e-05) (hash(x)=20216795) +332 train 9.717284 (lr=2.3287e-05) (hash(x)=27697998) +333 train 9.610751 (lr=2.3357e-05) (hash(x)=25896435) +334 train 9.572850 (lr=2.3427e-05) (hash(x)=21585310) +335 train 9.576425 (lr=2.3497e-05) (hash(x)=24677740) +336 train 9.577262 (lr=2.3566e-05) (hash(x)=22027900) +337 train 9.559190 (lr=2.3636e-05) (hash(x)=21835643) +338 train 9.490946 (lr=2.3706e-05) (hash(x)=20558462) +339 train 9.510977 (lr=2.3776e-05) (hash(x)=16722715) +340 train 9.457862 (lr=2.3846e-05) (hash(x)=20972655) +341 train 9.626658 (lr=2.3916e-05) (hash(x)=26303975) +342 train 9.567893 (lr=2.3986e-05) (hash(x)=22938170) +343 train 9.480678 (lr=2.4056e-05) (hash(x)=25347203) +344 train 9.484272 (lr=2.4126e-05) (hash(x)=27398686) +345 train 9.519094 (lr=2.4196e-05) (hash(x)=25973417) +346 train 9.392325 (lr=2.4266e-05) (hash(x)=26918389) +347 train 9.433317 (lr=2.4336e-05) (hash(x)=24272489) +348 train 9.474887 (lr=2.4406e-05) (hash(x)=25593714) +349 train 9.368212 (lr=2.4476e-05) (hash(x)=29260846) +350 val loss 9.4394 +350 val perplexity 12574.4062 +350 train 9.517937 (lr=2.4545e-05) (hash(x)=27951602) +351 train 9.504604 (lr=2.4615e-05) (hash(x)=28922363) +352 train 9.405248 (lr=2.4685e-05) (hash(x)=27210734) +353 train 9.296206 (lr=2.4755e-05) (hash(x)=26322572) +354 train 9.358275 (lr=2.4825e-05) (hash(x)=27084665) +355 train 9.399389 (lr=2.4895e-05) (hash(x)=25510798) +356 train 9.397660 (lr=2.4965e-05) (hash(x)=24970921) +357 train 9.475985 (lr=2.5035e-05) (hash(x)=24138948) +358 train 9.391288 (lr=2.5105e-05) (hash(x)=24790211) +359 train 9.381022 (lr=2.5175e-05) (hash(x)=25631397) +360 train 9.326781 (lr=2.5245e-05) (hash(x)=23226625) +361 train 9.274092 (lr=2.5315e-05) (hash(x)=24001903) +362 train 9.299150 (lr=2.5385e-05) (hash(x)=24587948) +363 train 9.165090 (lr=2.5455e-05) (hash(x)=21333676) +364 train 8.945796 (lr=2.5524e-05) (hash(x)=23673779) +365 train 9.706431 (lr=2.5594e-05) (hash(x)=30770484) +366 train 9.303835 (lr=2.5664e-05) (hash(x)=26564899) +367 train 9.344228 (lr=2.5734e-05) (hash(x)=26237983) +368 train 9.169441 (lr=2.5804e-05) (hash(x)=23764356) +369 train 9.358230 (lr=2.5874e-05) (hash(x)=26205744) +370 train 9.399714 (lr=2.5944e-05) (hash(x)=19208770) +371 train 9.309786 (lr=2.6014e-05) (hash(x)=25976502) +372 train 9.132744 (lr=2.6084e-05) (hash(x)=23983933) +373 train 9.245524 (lr=2.6154e-05) (hash(x)=24080636) +374 train 9.382028 (lr=2.6224e-05) (hash(x)=24404047) +375 train 9.299838 (lr=2.6294e-05) (hash(x)=24742645) +376 train 9.270110 (lr=2.6364e-05) (hash(x)=24159600) +377 train 9.381038 (lr=2.6434e-05) (hash(x)=28677257) +378 train 9.200220 (lr=2.6503e-05) (hash(x)=25604111) +379 train 9.147875 (lr=2.6573e-05) (hash(x)=27086333) +380 train 9.151735 (lr=2.6643e-05) (hash(x)=25188207) +381 train 9.234202 (lr=2.6713e-05) (hash(x)=27855233) +382 train 9.278663 (lr=2.6783e-05) (hash(x)=19470039) +383 train 9.220987 (lr=2.6853e-05) (hash(x)=26157660) +384 train 9.206967 (lr=2.6923e-05) (hash(x)=25291570) +385 train 9.239062 (lr=2.6993e-05) (hash(x)=25046062) +386 train 9.288394 (lr=2.7063e-05) (hash(x)=27020337) +387 train 9.099243 (lr=2.7133e-05) (hash(x)=23616370) +388 train 8.915375 (lr=2.7203e-05) (hash(x)=19113218) +389 train 9.098372 (lr=2.7273e-05) (hash(x)=24302232) +390 train 9.093818 (lr=2.7343e-05) (hash(x)=22188949) +391 train 8.954378 (lr=2.7413e-05) (hash(x)=22582169) +392 train 9.070833 (lr=2.7483e-05) (hash(x)=24700570) +393 train 9.052950 (lr=2.7552e-05) (hash(x)=22773833) +394 train 9.024012 (lr=2.7622e-05) (hash(x)=21875928) +395 train 9.012693 (lr=2.7692e-05) (hash(x)=26233189) +396 train 9.017140 (lr=2.7762e-05) (hash(x)=24321467) +397 train 9.164104 (lr=2.7832e-05) (hash(x)=26431507) +398 train 9.205391 (lr=2.7902e-05) (hash(x)=28690877) +399 train 9.181468 (lr=2.7972e-05) (hash(x)=26431960) +400 val loss 9.1038 +400 val perplexity 8989.1885 +400 train 9.062691 (lr=2.8042e-05) (hash(x)=24580300) +401 train 9.036905 (lr=2.8112e-05) (hash(x)=25112360) +402 train 9.143279 (lr=2.8182e-05) (hash(x)=27597243) +403 train 9.393620 (lr=2.8252e-05) (hash(x)=30707498) +404 train 9.072883 (lr=2.8322e-05) (hash(x)=28485465) +405 train 9.008262 (lr=2.8392e-05) (hash(x)=22586447) +406 train 9.128957 (lr=2.8462e-05) (hash(x)=23175270) +407 train 9.065299 (lr=2.8531e-05) (hash(x)=25716176) +408 train 9.039090 (lr=2.8601e-05) (hash(x)=26861373) +409 train 9.253157 (lr=2.8671e-05) (hash(x)=25118971) +410 train 8.954561 (lr=2.8741e-05) (hash(x)=19829066) +411 train 8.952271 (lr=2.8811e-05) (hash(x)=26256420) +412 train 9.050826 (lr=2.8881e-05) (hash(x)=27796153) +413 train 8.983848 (lr=2.8951e-05) (hash(x)=22633318) +414 train 8.927794 (lr=2.9021e-05) (hash(x)=22589383) +415 train 9.120270 (lr=2.9091e-05) (hash(x)=28019788) +416 train 9.075246 (lr=2.9161e-05) (hash(x)=28970440) +417 train 8.840324 (lr=2.9231e-05) (hash(x)=27396089) +418 train 8.962001 (lr=2.9301e-05) (hash(x)=21183513) +419 train 8.935692 (lr=2.9371e-05) (hash(x)=23510110) +420 train 9.029269 (lr=2.9441e-05) (hash(x)=28833467) +421 train 8.977241 (lr=2.9510e-05) (hash(x)=23646926) +422 train 8.939452 (lr=2.9580e-05) (hash(x)=24697272) +423 train 8.912483 (lr=2.9650e-05) (hash(x)=20382963) +424 train 8.838903 (lr=2.9720e-05) (hash(x)=23467595) +425 train 8.942658 (lr=2.9790e-05) (hash(x)=24304768) +426 train 8.878505 (lr=2.9860e-05) (hash(x)=21392328) +427 train 8.772201 (lr=2.9930e-05) (hash(x)=25339466) +428 train 8.785149 (lr=3.0000e-05) (hash(x)=22092542) +429 train 8.967366 (lr=3.0070e-05) (hash(x)=22088696) +430 train 8.939171 (lr=3.0140e-05) (hash(x)=22184471) +431 train 8.947220 (lr=3.0210e-05) (hash(x)=24489647) +432 train 8.871329 (lr=3.0280e-05) (hash(x)=26794132) +433 train 8.589770 (lr=3.0350e-05) (hash(x)=22940357) +434 train 8.915312 (lr=3.0420e-05) (hash(x)=23719522) +435 train 8.863053 (lr=3.0490e-05) (hash(x)=22927699) +436 train 8.838134 (lr=3.0559e-05) (hash(x)=26068576) +437 train 8.819413 (lr=3.0629e-05) (hash(x)=27631132) +438 train 8.748776 (lr=3.0699e-05) (hash(x)=26739991) +439 train 8.944855 (lr=3.0769e-05) (hash(x)=25128502) +440 train 8.878778 (lr=3.0839e-05) (hash(x)=25657260) +441 train 8.815660 (lr=3.0909e-05) (hash(x)=23576982) +442 train 8.830230 (lr=3.0979e-05) (hash(x)=27117886) +443 train 8.869071 (lr=3.1049e-05) (hash(x)=25808969) +444 train 8.789186 (lr=3.1119e-05) (hash(x)=24738238) +445 train 8.748731 (lr=3.1189e-05) (hash(x)=23429962) +446 train 8.855155 (lr=3.1259e-05) (hash(x)=25075165) +447 train 8.716443 (lr=3.1329e-05) (hash(x)=25231390) +448 train 8.601317 (lr=3.1399e-05) (hash(x)=22055054) +449 train 8.804755 (lr=3.1469e-05) (hash(x)=25395441) +450 val loss 8.7724 +450 val perplexity 6453.8081 +450 train 8.780978 (lr=3.1538e-05) (hash(x)=25863209) +451 train 8.663886 (lr=3.1608e-05) (hash(x)=21154388) +452 train 8.657265 (lr=3.1678e-05) (hash(x)=21600876) +453 train 8.726316 (lr=3.1748e-05) (hash(x)=24278611) +454 train 8.663086 (lr=3.1818e-05) (hash(x)=23221720) +455 train 8.730417 (lr=3.1888e-05) (hash(x)=22708977) +456 train 8.985160 (lr=3.1958e-05) (hash(x)=23637758) +457 train 8.787704 (lr=3.2028e-05) (hash(x)=28228490) +458 train 8.815386 (lr=3.2098e-05) (hash(x)=28638071) +459 train 8.743526 (lr=3.2168e-05) (hash(x)=27258353) +460 train 8.719093 (lr=3.2238e-05) (hash(x)=26604728) +461 train 8.731229 (lr=3.2308e-05) (hash(x)=23252199) +462 train 8.701331 (lr=3.2378e-05) (hash(x)=26441427) +463 train 8.578725 (lr=3.2448e-05) (hash(x)=24364920) +464 train 8.705615 (lr=3.2517e-05) (hash(x)=25623792) +465 train 8.671788 (lr=3.2587e-05) (hash(x)=23283905) +466 train 8.824508 (lr=3.2657e-05) (hash(x)=26025267) +467 train 8.691444 (lr=3.2727e-05) (hash(x)=27243972) +468 train 9.031491 (lr=3.2797e-05) (hash(x)=30449945) +469 train 8.805442 (lr=3.2867e-05) (hash(x)=28113043) +470 train 8.555623 (lr=3.2937e-05) (hash(x)=25182521) +471 train 8.612178 (lr=3.3007e-05) (hash(x)=24932925) +472 train 8.627097 (lr=3.3077e-05) (hash(x)=20353098) +473 train 8.635746 (lr=3.3147e-05) (hash(x)=19001259) +474 train 8.750648 (lr=3.3217e-05) (hash(x)=27585685) +475 train 8.684798 (lr=3.3287e-05) (hash(x)=26371091) +476 train 8.511451 (lr=3.3357e-05) (hash(x)=24891798) +477 train 8.604467 (lr=3.3427e-05) (hash(x)=24258817) +478 train 8.583812 (lr=3.3497e-05) (hash(x)=24330263) +479 train 8.610400 (lr=3.3566e-05) (hash(x)=26913684) +480 train 8.597602 (lr=3.3636e-05) (hash(x)=26338455) +481 train 8.847289 (lr=3.3706e-05) (hash(x)=27753043) +482 train 8.524753 (lr=3.3776e-05) (hash(x)=26123289) +483 train 8.582323 (lr=3.3846e-05) (hash(x)=29239611) +484 train 8.583716 (lr=3.3916e-05) (hash(x)=26553003) +485 train 8.612082 (lr=3.3986e-05) (hash(x)=22984557) +486 train 8.307033 (lr=3.4056e-05) (hash(x)=16947491) +487 train 8.281859 (lr=3.4126e-05) (hash(x)=18017792) +488 train 8.447225 (lr=3.4196e-05) (hash(x)=19918608) +489 train 8.715578 (lr=3.4266e-05) (hash(x)=23374526) +490 train 8.562832 (lr=3.4336e-05) (hash(x)=25009505) +491 train 8.474275 (lr=3.4406e-05) (hash(x)=27574089) +492 train 8.546386 (lr=3.4476e-05) (hash(x)=24122664) +493 train 8.607471 (lr=3.4545e-05) (hash(x)=26154906) +494 train 8.597936 (lr=3.4615e-05) (hash(x)=25192767) +495 train 8.592639 (lr=3.4685e-05) (hash(x)=28613882) +496 train 8.481599 (lr=3.4755e-05) (hash(x)=23547219) +497 train 8.532462 (lr=3.4825e-05) (hash(x)=25272182) +498 train 8.347560 (lr=3.4895e-05) (hash(x)=24992761) +499 train 8.592270 (lr=3.4965e-05) (hash(x)=26981914) +500 val loss 8.4961 +500 val perplexity 4895.6826 +500 train 8.428804 (lr=3.5035e-05) (hash(x)=22051933) +501 train 8.609790 (lr=3.5105e-05) (hash(x)=24232348) +502 train 8.565822 (lr=3.5175e-05) (hash(x)=23158331) +503 train 8.443835 (lr=3.5245e-05) (hash(x)=22652243) +504 train 8.496115 (lr=3.5315e-05) (hash(x)=23805602) +505 train 8.620769 (lr=3.5385e-05) (hash(x)=25411991) +506 train 8.248860 (lr=3.5455e-05) (hash(x)=18827215) +507 train 7.984775 (lr=3.5524e-05) (hash(x)=15446025) +508 train 8.200358 (lr=3.5594e-05) (hash(x)=20516263) +509 train 8.533538 (lr=3.5664e-05) (hash(x)=27846176) +510 train 8.324758 (lr=3.5734e-05) (hash(x)=23342449) +511 train 8.449046 (lr=3.5804e-05) (hash(x)=27194521) +512 train 8.371900 (lr=3.5874e-05) (hash(x)=23008284) +513 train 8.582606 (lr=3.5944e-05) (hash(x)=29430001) +514 train 8.167300 (lr=3.6014e-05) (hash(x)=22579319) +515 train 8.177211 (lr=3.6084e-05) (hash(x)=25264518) +516 train 8.479184 (lr=3.6154e-05) (hash(x)=25359075) +517 train 8.408844 (lr=3.6224e-05) (hash(x)=25568956) +518 train 8.635872 (lr=3.6294e-05) (hash(x)=32004108) +519 train 8.404801 (lr=3.6364e-05) (hash(x)=24936836) +520 train 8.402785 (lr=3.6434e-05) (hash(x)=27263338) +521 train 8.529941 (lr=3.6503e-05) (hash(x)=27452099) +522 train 8.466277 (lr=3.6573e-05) (hash(x)=25965406) +523 train 8.528533 (lr=3.6643e-05) (hash(x)=28197282) +524 train 8.379000 (lr=3.6713e-05) (hash(x)=22466209) +525 train 8.479697 (lr=3.6783e-05) (hash(x)=22931889) +526 train 8.556156 (lr=3.6853e-05) (hash(x)=26903920) +527 train 8.422318 (lr=3.6923e-05) (hash(x)=24765578) +528 train 8.398416 (lr=3.6993e-05) (hash(x)=27811359) +529 train 8.295047 (lr=3.7063e-05) (hash(x)=25078649) +530 train 8.465150 (lr=3.7133e-05) (hash(x)=25572416) +531 train 8.496520 (lr=3.7203e-05) (hash(x)=27448185) +532 train 8.536250 (lr=3.7273e-05) (hash(x)=25923719) +533 train 8.390975 (lr=3.7343e-05) (hash(x)=24804856) +534 train 8.358371 (lr=3.7413e-05) (hash(x)=23207829) +535 train 8.373326 (lr=3.7483e-05) (hash(x)=23107416) +536 train 8.188308 (lr=3.7552e-05) (hash(x)=26739531) +537 train 8.168931 (lr=3.7622e-05) (hash(x)=24960796) +538 train 8.403174 (lr=3.7692e-05) (hash(x)=24667802) +539 train 8.468207 (lr=3.7762e-05) (hash(x)=26755138) +540 train 8.360206 (lr=3.7832e-05) (hash(x)=25537132) +541 train 8.269073 (lr=3.7902e-05) (hash(x)=24542526) +542 train 8.236522 (lr=3.7972e-05) (hash(x)=21296355) +543 train 8.478026 (lr=3.8042e-05) (hash(x)=29314255) +544 train 8.246140 (lr=3.8112e-05) (hash(x)=26001799) +545 train 8.290828 (lr=3.8182e-05) (hash(x)=27347755) +546 train 8.318431 (lr=3.8252e-05) (hash(x)=25107798) +547 train 8.266337 (lr=3.8322e-05) (hash(x)=22112669) +548 train 8.171439 (lr=3.8392e-05) (hash(x)=21897967) +549 train 8.286361 (lr=3.8462e-05) (hash(x)=25161929) +550 val loss 8.3117 +550 val perplexity 4071.2004 +550 train 8.238869 (lr=3.8531e-05) (hash(x)=27465106) +551 train 8.383194 (lr=3.8601e-05) (hash(x)=24013079) +552 train 8.299677 (lr=3.8671e-05) (hash(x)=23142015) +553 train 8.278522 (lr=3.8741e-05) (hash(x)=26768629) +554 train 8.320086 (lr=3.8811e-05) (hash(x)=26393383) +555 train 7.955793 (lr=3.8881e-05) (hash(x)=22537194) +556 train 8.190642 (lr=3.8951e-05) (hash(x)=24046036) +557 train 8.186259 (lr=3.9021e-05) (hash(x)=24974360) +558 train 8.416999 (lr=3.9091e-05) (hash(x)=28379928) +559 train 8.324959 (lr=3.9161e-05) (hash(x)=25322001) +560 train 8.384386 (lr=3.9231e-05) (hash(x)=26622031) +561 train 8.156920 (lr=3.9301e-05) (hash(x)=20562247) +562 train 8.420367 (lr=3.9371e-05) (hash(x)=27381885) +563 train 8.515649 (lr=3.9441e-05) (hash(x)=27028126) +564 train 8.358388 (lr=3.9510e-05) (hash(x)=28882928) +565 train 8.338387 (lr=3.9580e-05) (hash(x)=25666355) +566 train 8.341403 (lr=3.9650e-05) (hash(x)=24330810) +567 train 8.295535 (lr=3.9720e-05) (hash(x)=26690440) +568 train 8.220592 (lr=3.9790e-05) (hash(x)=22923592) +569 train 8.246249 (lr=3.9860e-05) (hash(x)=27348418) +570 train 8.265984 (lr=3.9930e-05) (hash(x)=28849848) +571 train 8.287959 (lr=4.0000e-05) (hash(x)=26967331) +572 train 8.159039 (lr=4.0070e-05) (hash(x)=22831467) +573 train 8.225455 (lr=4.0140e-05) (hash(x)=24765121) +574 train 8.254517 (lr=4.0210e-05) (hash(x)=24331857) +575 train 8.113193 (lr=4.0280e-05) (hash(x)=22598512) +576 train 8.276932 (lr=4.0350e-05) (hash(x)=25149353) +577 train 8.104808 (lr=4.0420e-05) (hash(x)=23725598) +578 train 8.263265 (lr=4.0490e-05) (hash(x)=26449557) +579 train 8.302755 (lr=4.0559e-05) (hash(x)=24697985) +580 train 8.284915 (lr=4.0629e-05) (hash(x)=26923059) +581 train 8.140484 (lr=4.0699e-05) (hash(x)=25201962) +582 train 7.878253 (lr=4.0769e-05) (hash(x)=20931520) +583 train 8.015945 (lr=4.0839e-05) (hash(x)=18473911) +584 train 8.056000 (lr=4.0909e-05) (hash(x)=21306267) +585 train 8.297538 (lr=4.0979e-05) (hash(x)=25982840) +586 train 8.186488 (lr=4.1049e-05) (hash(x)=25364874) +587 train 8.133740 (lr=4.1119e-05) (hash(x)=23172124) +588 train 8.293689 (lr=4.1189e-05) (hash(x)=27876897) +589 train 8.751190 (lr=4.1259e-05) (hash(x)=34646114) +590 train 8.924373 (lr=4.1329e-05) (hash(x)=35153576) +591 train 8.055744 (lr=4.1399e-05) (hash(x)=22322442) +592 train 8.274869 (lr=4.1469e-05) (hash(x)=27907331) +593 train 8.161776 (lr=4.1538e-05) (hash(x)=26211794) +594 train 8.360485 (lr=4.1608e-05) (hash(x)=29291512) +595 train 8.484922 (lr=4.1678e-05) (hash(x)=29659121) +596 train 8.330873 (lr=4.1748e-05) (hash(x)=29674399) +597 train 8.154282 (lr=4.1818e-05) (hash(x)=23538306) +598 train 8.352252 (lr=4.1888e-05) (hash(x)=21991524) +599 train 8.155718 (lr=4.1958e-05) (hash(x)=26324153) +600 val loss 8.1787 +600 val perplexity 3564.2708 +600 train 8.159554 (lr=4.2028e-05) (hash(x)=23712082) +601 train 8.202866 (lr=4.2098e-05) (hash(x)=24910403) +602 train 8.172170 (lr=4.2168e-05) (hash(x)=26737205) +603 train 8.270312 (lr=4.2238e-05) (hash(x)=26939970) +604 train 8.131954 (lr=4.2308e-05) (hash(x)=27651943) +605 train 8.371119 (lr=4.2378e-05) (hash(x)=27515446) +606 train 8.361662 (lr=4.2448e-05) (hash(x)=26753129) +607 train 8.142289 (lr=4.2517e-05) (hash(x)=23446058) +608 train 8.303278 (lr=4.2587e-05) (hash(x)=27587849) +609 train 8.257315 (lr=4.2657e-05) (hash(x)=25308253) +610 train 8.224658 (lr=4.2727e-05) (hash(x)=26615098) +611 train 8.215995 (lr=4.2797e-05) (hash(x)=29981801) +612 train 8.247678 (lr=4.2867e-05) (hash(x)=29592345) +613 train 8.283841 (lr=4.2937e-05) (hash(x)=23470413) +614 train 8.212316 (lr=4.3007e-05) (hash(x)=24742370) +615 train 8.244349 (lr=4.3077e-05) (hash(x)=24843741) +616 train 8.177699 (lr=4.3147e-05) (hash(x)=25192548) +617 train 8.209544 (lr=4.3217e-05) (hash(x)=27176996) +618 train 8.113276 (lr=4.3287e-05) (hash(x)=23964552) +619 train 8.084664 (lr=4.3357e-05) (hash(x)=22855363) +620 train 8.039893 (lr=4.3427e-05) (hash(x)=26332996) +621 train 7.906789 (lr=4.3497e-05) (hash(x)=22960957) +622 train 8.185382 (lr=4.3566e-05) (hash(x)=22752597) +623 train 8.135989 (lr=4.3636e-05) (hash(x)=23197102) +624 train 8.496596 (lr=4.3706e-05) (hash(x)=27383319) +625 train 8.155235 (lr=4.3776e-05) (hash(x)=26132276) +626 train 8.051806 (lr=4.3846e-05) (hash(x)=19810497) +627 train 8.082873 (lr=4.3916e-05) (hash(x)=25704919) +628 train 8.252698 (lr=4.3986e-05) (hash(x)=27174264) +629 train 8.262381 (lr=4.4056e-05) (hash(x)=22280814) +630 train 8.872460 (lr=4.4126e-05) (hash(x)=24279448) +631 train 8.417569 (lr=4.4196e-05) (hash(x)=23054940) +632 train 8.518130 (lr=4.4266e-05) (hash(x)=23942400) +633 train 8.688696 (lr=4.4336e-05) (hash(x)=24712416) +634 train 8.401779 (lr=4.4406e-05) (hash(x)=24564658) +635 train 8.184661 (lr=4.4476e-05) (hash(x)=24909904) +636 train 8.190892 (lr=4.4545e-05) (hash(x)=23049534) +637 train 8.189476 (lr=4.4615e-05) (hash(x)=24321591) +638 train 7.957668 (lr=4.4685e-05) (hash(x)=26153298) +639 train 8.041369 (lr=4.4755e-05) (hash(x)=27140757) +640 train 7.897607 (lr=4.4825e-05) (hash(x)=25115907) +641 train 7.985477 (lr=4.4895e-05) (hash(x)=26563770) +642 train 8.084707 (lr=4.4965e-05) (hash(x)=28089252) +643 train 8.001521 (lr=4.5035e-05) (hash(x)=25993110) +644 train 7.962909 (lr=4.5105e-05) (hash(x)=25150008) +645 train 8.179292 (lr=4.5175e-05) (hash(x)=28520222) +646 train 7.956038 (lr=4.5245e-05) (hash(x)=21349943) +647 train 7.976102 (lr=4.5315e-05) (hash(x)=25149419) +648 train 8.116144 (lr=4.5385e-05) (hash(x)=25730641) +649 train 8.280522 (lr=4.5455e-05) (hash(x)=26112813) +650 val loss 8.0780 +650 val perplexity 3222.8735 +650 train 8.120615 (lr=4.5524e-05) (hash(x)=25907805) +651 train 8.114411 (lr=4.5594e-05) (hash(x)=27623643) +652 train 8.089355 (lr=4.5664e-05) (hash(x)=26484959) +653 train 8.125347 (lr=4.5734e-05) (hash(x)=29199854) +654 train 8.140368 (lr=4.5804e-05) (hash(x)=28369628) +655 train 8.058246 (lr=4.5874e-05) (hash(x)=24727764) +656 train 7.764702 (lr=4.5944e-05) (hash(x)=22610673) +657 train 7.673734 (lr=4.6014e-05) (hash(x)=22667179) +658 train 7.495795 (lr=4.6084e-05) (hash(x)=18477300) +659 train 7.913332 (lr=4.6154e-05) (hash(x)=23155773) +660 train 7.733016 (lr=4.6224e-05) (hash(x)=19461032) +661 train 7.987561 (lr=4.6294e-05) (hash(x)=23453788) +662 train 8.012786 (lr=4.6364e-05) (hash(x)=24543466) +663 train 7.896507 (lr=4.6434e-05) (hash(x)=21935931) +664 train 7.809489 (lr=4.6503e-05) (hash(x)=19910292) +665 train 7.949821 (lr=4.6573e-05) (hash(x)=24481079) +666 train 7.757785 (lr=4.6643e-05) (hash(x)=18922411) +667 train 7.770257 (lr=4.6713e-05) (hash(x)=20054917) +668 train 7.960350 (lr=4.6783e-05) (hash(x)=24850470) +669 train 8.046102 (lr=4.6853e-05) (hash(x)=25907741) +670 train 8.115245 (lr=4.6923e-05) (hash(x)=26873522) +671 train 8.119059 (lr=4.6993e-05) (hash(x)=27606073) +672 train 8.235764 (lr=4.7063e-05) (hash(x)=26209645) +673 train 8.066378 (lr=4.7133e-05) (hash(x)=25202001) +674 train 8.109986 (lr=4.7203e-05) (hash(x)=25569462) +675 train 8.071287 (lr=4.7273e-05) (hash(x)=26534487) +676 train 8.132545 (lr=4.7343e-05) (hash(x)=26455057) +677 train 7.995216 (lr=4.7413e-05) (hash(x)=24095850) +678 train 8.135344 (lr=4.7483e-05) (hash(x)=25287752) +679 train 7.661033 (lr=4.7552e-05) (hash(x)=22450341) +680 train 8.399800 (lr=4.7622e-05) (hash(x)=29004853) +681 train 8.074122 (lr=4.7692e-05) (hash(x)=27993763) +682 train 7.948694 (lr=4.7762e-05) (hash(x)=26382658) +683 train 8.029284 (lr=4.7832e-05) (hash(x)=25013073) +684 train 8.067512 (lr=4.7902e-05) (hash(x)=30595809) +685 train 8.154001 (lr=4.7972e-05) (hash(x)=30934371) +686 train 8.604256 (lr=4.8042e-05) (hash(x)=33060834) +687 train 8.067354 (lr=4.8112e-05) (hash(x)=25945859) +688 train 7.894383 (lr=4.8182e-05) (hash(x)=23375678) +689 train 7.945021 (lr=4.8252e-05) (hash(x)=25218689) +690 train 8.017615 (lr=4.8322e-05) (hash(x)=28127397) +691 train 8.006063 (lr=4.8392e-05) (hash(x)=24418091) +692 train 7.889371 (lr=4.8462e-05) (hash(x)=22761099) +693 train 7.940713 (lr=4.8531e-05) (hash(x)=24615466) +694 train 8.020497 (lr=4.8601e-05) (hash(x)=24699240) +695 train 7.924118 (lr=4.8671e-05) (hash(x)=21613707) +696 train 7.989163 (lr=4.8741e-05) (hash(x)=24977554) +697 train 7.948352 (lr=4.8811e-05) (hash(x)=24348175) +698 train 8.041857 (lr=4.8881e-05) (hash(x)=25102767) +699 train 8.035342 (lr=4.8951e-05) (hash(x)=26386157) +700 val loss 7.9775 +700 val perplexity 2914.7324 +700 train 8.032111 (lr=4.9021e-05) (hash(x)=26423460) +701 train 7.966982 (lr=4.9091e-05) (hash(x)=25771047) +702 train 7.963267 (lr=4.9161e-05) (hash(x)=26999875) +703 train 7.942808 (lr=4.9231e-05) (hash(x)=24396519) +704 train 7.971827 (lr=4.9301e-05) (hash(x)=22588122) +705 train 8.235239 (lr=4.9371e-05) (hash(x)=25142399) +706 train 7.914865 (lr=4.9441e-05) (hash(x)=20440214) +707 train 7.826618 (lr=4.9510e-05) (hash(x)=23265507) +708 train 7.922891 (lr=4.9580e-05) (hash(x)=24563470) +709 train 7.881802 (lr=4.9650e-05) (hash(x)=22514858) +710 train 8.170218 (lr=4.9720e-05) (hash(x)=26691212) +711 train 8.177080 (lr=4.9790e-05) (hash(x)=29138828) +712 train 8.154551 (lr=4.9860e-05) (hash(x)=28028528) +713 train 8.044320 (lr=4.9930e-05) (hash(x)=20531210) +714 train 7.898492 (lr=5.0000e-05) (hash(x)=25075352) +715 train 7.955347 (lr=5.0070e-05) (hash(x)=24265353) +716 train 8.063744 (lr=5.0140e-05) (hash(x)=24635726) +717 train 7.935947 (lr=5.0210e-05) (hash(x)=24999726) +718 train 8.136767 (lr=5.0280e-05) (hash(x)=27412910) +719 train 7.948442 (lr=5.0350e-05) (hash(x)=24685515) +720 train 7.989390 (lr=5.0420e-05) (hash(x)=23780329) +721 train 7.820396 (lr=5.0490e-05) (hash(x)=25071701) +722 train 7.948821 (lr=5.0559e-05) (hash(x)=23767130) +723 train 7.922784 (lr=5.0629e-05) (hash(x)=24876269) +724 train 8.010396 (lr=5.0699e-05) (hash(x)=26405773) +725 train 8.341125 (lr=5.0769e-05) (hash(x)=31733180) +726 train 7.670004 (lr=5.0839e-05) (hash(x)=21337509) +727 train 7.748898 (lr=5.0909e-05) (hash(x)=22825749) +728 train 8.083669 (lr=5.0979e-05) (hash(x)=28638695) +729 train 8.010269 (lr=5.1049e-05) (hash(x)=26393943) +730 train 8.132980 (lr=5.1119e-05) (hash(x)=27563583) +731 train 7.703439 (lr=5.1189e-05) (hash(x)=21239652) +732 train 7.830673 (lr=5.1259e-05) (hash(x)=23986428) +733 train 7.753836 (lr=5.1329e-05) (hash(x)=24943881) +734 train 8.185511 (lr=5.1399e-05) (hash(x)=29691448) +735 train 8.150530 (lr=5.1469e-05) (hash(x)=28767869) +736 train 7.929718 (lr=5.1538e-05) (hash(x)=23628188) +737 train 8.160108 (lr=5.1608e-05) (hash(x)=29341482) +738 train 8.014206 (lr=5.1678e-05) (hash(x)=30336570) +739 train 7.952652 (lr=5.1748e-05) (hash(x)=25614301) +740 train 7.886086 (lr=5.1818e-05) (hash(x)=24160500) +741 train 8.061432 (lr=5.1888e-05) (hash(x)=26030058) +742 train 8.341623 (lr=5.1958e-05) (hash(x)=29243936) +743 train 7.739198 (lr=5.2028e-05) (hash(x)=21159060) +744 train 7.829401 (lr=5.2098e-05) (hash(x)=23701853) +745 train 7.952498 (lr=5.2168e-05) (hash(x)=24629937) +746 train 7.915559 (lr=5.2238e-05) (hash(x)=25110108) +747 train 7.967239 (lr=5.2308e-05) (hash(x)=26751788) +748 train 7.998305 (lr=5.2378e-05) (hash(x)=26430427) +749 train 7.884861 (lr=5.2448e-05) (hash(x)=26012353) +750 val loss 7.9182 +750 val perplexity 2746.9441 +750 train 7.977761 (lr=5.2517e-05) (hash(x)=22735910) +751 train 7.787596 (lr=5.2587e-05) (hash(x)=25045397) +752 train 7.565936 (lr=5.2657e-05) (hash(x)=21554427) +753 train 7.631588 (lr=5.2727e-05) (hash(x)=23751143) +754 train 8.386518 (lr=5.2797e-05) (hash(x)=28602273) +755 train 8.413220 (lr=5.2867e-05) (hash(x)=29989709) +756 train 7.845114 (lr=5.2937e-05) (hash(x)=22331648) +757 train 8.216807 (lr=5.3007e-05) (hash(x)=31017246) +758 train 8.139812 (lr=5.3077e-05) (hash(x)=29709045) +759 train 8.226287 (lr=5.3147e-05) (hash(x)=25560928) +760 train 7.924768 (lr=5.3217e-05) (hash(x)=25075464) +761 train 8.034263 (lr=5.3287e-05) (hash(x)=27352253) +762 train 8.210927 (lr=5.3357e-05) (hash(x)=28187891) +763 train 8.056365 (lr=5.3427e-05) (hash(x)=26062687) +764 train 8.028152 (lr=5.3497e-05) (hash(x)=27427811) +765 train 8.119687 (lr=5.3566e-05) (hash(x)=27614522) +766 train 7.903881 (lr=5.3636e-05) (hash(x)=26129544) +767 train 8.352377 (lr=5.3706e-05) (hash(x)=28959222) +768 train 7.986194 (lr=5.3776e-05) (hash(x)=26860067) +769 train 7.793895 (lr=5.3846e-05) (hash(x)=25122598) +770 train 7.866271 (lr=5.3916e-05) (hash(x)=25245030) +771 train 7.884228 (lr=5.3986e-05) (hash(x)=25434884) +772 train 7.990996 (lr=5.4056e-05) (hash(x)=27732790) +773 train 7.923038 (lr=5.4126e-05) (hash(x)=27824438) +774 train 8.083838 (lr=5.4196e-05) (hash(x)=27201953) +775 train 7.864167 (lr=5.4266e-05) (hash(x)=21248405) +776 train 7.686079 (lr=5.4336e-05) (hash(x)=22805934) +777 train 7.933400 (lr=5.4406e-05) (hash(x)=26482588) +778 train 7.946062 (lr=5.4476e-05) (hash(x)=24153691) +779 train 8.048586 (lr=5.4545e-05) (hash(x)=25044192) +780 train 7.983455 (lr=5.4615e-05) (hash(x)=25910078) +781 train 7.985587 (lr=5.4685e-05) (hash(x)=28645524) +782 train 7.826103 (lr=5.4755e-05) (hash(x)=24368498) +783 train 7.907001 (lr=5.4825e-05) (hash(x)=25830182) +784 train 7.960712 (lr=5.4895e-05) (hash(x)=29181807) +785 train 7.905554 (lr=5.4965e-05) (hash(x)=25585137) +786 train 7.855505 (lr=5.5035e-05) (hash(x)=24798246) +787 train 7.920067 (lr=5.5105e-05) (hash(x)=26621419) +788 train 7.567250 (lr=5.5175e-05) (hash(x)=21446891) +789 train 7.490972 (lr=5.5245e-05) (hash(x)=22165286) +790 train 7.723611 (lr=5.5315e-05) (hash(x)=23477219) +791 train 8.022844 (lr=5.5385e-05) (hash(x)=25173113) +792 train 7.876415 (lr=5.5455e-05) (hash(x)=25853788) +793 train 7.965593 (lr=5.5524e-05) (hash(x)=27267091) +794 train 7.834192 (lr=5.5594e-05) (hash(x)=23743694) +795 train 7.795500 (lr=5.5664e-05) (hash(x)=24400133) +796 train 7.837193 (lr=5.5734e-05) (hash(x)=23663639) +797 train 7.724202 (lr=5.5804e-05) (hash(x)=23103223) +798 train 8.251511 (lr=5.5874e-05) (hash(x)=28748411) +799 train 7.593036 (lr=5.5944e-05) (hash(x)=23486277) +800 val loss 7.8629 +800 val perplexity 2598.9631 +800 train 7.805954 (lr=5.6014e-05) (hash(x)=25678518) +801 train 7.756560 (lr=5.6084e-05) (hash(x)=23421286) +802 train 7.914842 (lr=5.6154e-05) (hash(x)=26054104) +803 train 7.922350 (lr=5.6224e-05) (hash(x)=25978130) +804 train 7.955619 (lr=5.6294e-05) (hash(x)=26006525) +805 train 7.882534 (lr=5.6364e-05) (hash(x)=25769432) +806 train 7.681716 (lr=5.6434e-05) (hash(x)=22430795) +807 train 8.101932 (lr=5.6503e-05) (hash(x)=28916006) +808 train 7.851248 (lr=5.6573e-05) (hash(x)=25166800) +809 train 7.990370 (lr=5.6643e-05) (hash(x)=24226056) +810 train 7.799072 (lr=5.6713e-05) (hash(x)=25057934) +811 train 8.516942 (lr=5.6783e-05) (hash(x)=33195100) +812 train 8.008558 (lr=5.6853e-05) (hash(x)=26312888) +813 train 8.157557 (lr=5.6923e-05) (hash(x)=27730410) +814 train 8.025023 (lr=5.6993e-05) (hash(x)=27372474) +815 train 7.904026 (lr=5.7063e-05) (hash(x)=25556929) +816 train 7.946605 (lr=5.7133e-05) (hash(x)=26909985) +817 train 7.766621 (lr=5.7203e-05) (hash(x)=25991247) +818 train 7.956350 (lr=5.7273e-05) (hash(x)=27438141) +819 train 8.126765 (lr=5.7343e-05) (hash(x)=29536986) +820 train 7.882389 (lr=5.7413e-05) (hash(x)=24478391) +821 train 7.834686 (lr=5.7483e-05) (hash(x)=26125216) +822 train 7.870210 (lr=5.7552e-05) (hash(x)=26422130) +823 train 7.974974 (lr=5.7622e-05) (hash(x)=29648798) +824 train 7.771350 (lr=5.7692e-05) (hash(x)=21247770) +825 train 7.903155 (lr=5.7762e-05) (hash(x)=23195388) +826 train 7.842852 (lr=5.7832e-05) (hash(x)=25796725) +827 train 7.872902 (lr=5.7902e-05) (hash(x)=23124767) +828 train 7.878989 (lr=5.7972e-05) (hash(x)=25233464) +829 train 7.901389 (lr=5.8042e-05) (hash(x)=25713275) +830 train 7.799829 (lr=5.8112e-05) (hash(x)=25550167) +831 train 7.692333 (lr=5.8182e-05) (hash(x)=24976217) +832 train 8.017581 (lr=5.8252e-05) (hash(x)=28536827) +833 train 7.973631 (lr=5.8322e-05) (hash(x)=27500801) +834 train 7.745084 (lr=5.8392e-05) (hash(x)=25545765) +835 train 7.798102 (lr=5.8462e-05) (hash(x)=23632825) +836 train 7.814529 (lr=5.8531e-05) (hash(x)=25708009) +837 train 7.894954 (lr=5.8601e-05) (hash(x)=24456276) +838 train 7.948902 (lr=5.8671e-05) (hash(x)=29189855) +839 train 8.173480 (lr=5.8741e-05) (hash(x)=31019606) +840 train 8.072139 (lr=5.8811e-05) (hash(x)=26328013) +841 train 7.945664 (lr=5.8881e-05) (hash(x)=25027904) +842 train 7.767746 (lr=5.8951e-05) (hash(x)=23734189) +843 train 8.023991 (lr=5.9021e-05) (hash(x)=28236580) +844 train 7.833158 (lr=5.9091e-05) (hash(x)=26509780) +845 train 7.882763 (lr=5.9161e-05) (hash(x)=25386473) +846 train 7.856033 (lr=5.9231e-05) (hash(x)=24052671) +847 train 8.022127 (lr=5.9301e-05) (hash(x)=28269421) +848 train 7.441556 (lr=5.9371e-05) (hash(x)=22251724) +849 train 7.732103 (lr=5.9441e-05) (hash(x)=24308447) +850 val loss 7.8281 +850 val perplexity 2510.1155 +850 train 7.701881 (lr=5.9510e-05) (hash(x)=24242830) +851 train 7.877861 (lr=5.9580e-05) (hash(x)=25563279) +852 train 7.881621 (lr=5.9650e-05) (hash(x)=26354481) +853 train 7.982361 (lr=5.9720e-05) (hash(x)=26152637) +854 train 8.018649 (lr=5.9790e-05) (hash(x)=28051025) +855 train 7.836632 (lr=5.9860e-05) (hash(x)=24865358) +856 train 7.746289 (lr=5.9930e-05) (hash(x)=24288911) +857 train 7.660571 (lr=6.0000e-05) (hash(x)=22230964) +858 train 7.558389 (lr=6.0070e-05) (hash(x)=21303832) +859 train 7.687276 (lr=6.0140e-05) (hash(x)=22155546) +860 train 7.801235 (lr=6.0210e-05) (hash(x)=25296428) +861 train 7.982316 (lr=6.0280e-05) (hash(x)=29142319) +862 train 7.782876 (lr=6.0350e-05) (hash(x)=25545430) +863 train 7.592807 (lr=6.0420e-05) (hash(x)=26984272) +864 train 7.801058 (lr=6.0490e-05) (hash(x)=25429005) +865 train 7.867825 (lr=6.0559e-05) (hash(x)=27077032) +866 train 7.830287 (lr=6.0629e-05) (hash(x)=26494424) +867 train 7.805789 (lr=6.0699e-05) (hash(x)=23193673) +868 train 7.884441 (lr=6.0769e-05) (hash(x)=25075134) +869 train 7.895408 (lr=6.0839e-05) (hash(x)=27112558) +870 train 8.033248 (lr=6.0909e-05) (hash(x)=27436608) +871 train 7.762070 (lr=6.0979e-05) (hash(x)=24544116) +872 train 8.096791 (lr=6.1049e-05) (hash(x)=31632686) +873 train 7.760246 (lr=6.1119e-05) (hash(x)=25890184) +874 train 7.830308 (lr=6.1189e-05) (hash(x)=22887555) +875 train 7.781770 (lr=6.1259e-05) (hash(x)=24547533) +876 train 7.876429 (lr=6.1329e-05) (hash(x)=26553496) +877 train 7.931258 (lr=6.1399e-05) (hash(x)=27467688) +878 train 7.732944 (lr=6.1469e-05) (hash(x)=24766934) +879 train 7.644621 (lr=6.1538e-05) (hash(x)=22059850) +880 train 8.008822 (lr=6.1608e-05) (hash(x)=22871702) +881 train 7.818131 (lr=6.1678e-05) (hash(x)=23893130) +882 train 7.910497 (lr=6.1748e-05) (hash(x)=25125691) +883 train 7.827391 (lr=6.1818e-05) (hash(x)=25994573) +884 train 7.885223 (lr=6.1888e-05) (hash(x)=26076345) +885 train 7.824387 (lr=6.1958e-05) (hash(x)=26577783) +886 train 7.931816 (lr=6.2028e-05) (hash(x)=27395225) +887 train 7.734519 (lr=6.2098e-05) (hash(x)=23926632) +888 train 7.620015 (lr=6.2168e-05) (hash(x)=21737239) +889 train 7.856506 (lr=6.2238e-05) (hash(x)=23574207) +890 train 7.559768 (lr=6.2308e-05) (hash(x)=24365231) +891 train 7.739372 (lr=6.2378e-05) (hash(x)=27111369) +892 train 7.980888 (lr=6.2448e-05) (hash(x)=27290015) +893 train 7.760283 (lr=6.2517e-05) (hash(x)=23979820) +894 train 7.884521 (lr=6.2587e-05) (hash(x)=26450121) +895 train 7.791074 (lr=6.2657e-05) (hash(x)=27025333) +896 train 7.785667 (lr=6.2727e-05) (hash(x)=23624605) +897 train 7.602520 (lr=6.2797e-05) (hash(x)=22846386) +898 train 7.711951 (lr=6.2867e-05) (hash(x)=22970561) +899 train 7.506400 (lr=6.2937e-05) (hash(x)=16908068) +900 val loss 7.7783 +900 val perplexity 2388.1211 +900 train 7.738828 (lr=6.3007e-05) (hash(x)=24661446) +901 train 7.834022 (lr=6.3077e-05) (hash(x)=25664727) +902 train 7.793121 (lr=6.3147e-05) (hash(x)=25667011) +903 train 7.859830 (lr=6.3217e-05) (hash(x)=29120407) +904 train 7.890342 (lr=6.3287e-05) (hash(x)=23385735) +905 train 7.914644 (lr=6.3357e-05) (hash(x)=25564213) +906 train 7.962451 (lr=6.3427e-05) (hash(x)=25413898) +907 train 7.907856 (lr=6.3497e-05) (hash(x)=27092710) +908 train 7.716773 (lr=6.3566e-05) (hash(x)=25789923) +909 train 7.780805 (lr=6.3636e-05) (hash(x)=28533197) +910 train 7.669631 (lr=6.3706e-05) (hash(x)=22982996) +911 train 7.732990 (lr=6.3776e-05) (hash(x)=23827393) +912 train 7.463544 (lr=6.3846e-05) (hash(x)=21242640) +913 train 7.809579 (lr=6.3916e-05) (hash(x)=24154233) +914 train 7.808300 (lr=6.3986e-05) (hash(x)=24331967) +915 train 7.996433 (lr=6.4056e-05) (hash(x)=32812727) +916 train 7.714583 (lr=6.4126e-05) (hash(x)=23572994) +917 train 7.754520 (lr=6.4196e-05) (hash(x)=26305435) +918 train 7.788237 (lr=6.4266e-05) (hash(x)=26268355) +919 train 7.930555 (lr=6.4336e-05) (hash(x)=27230027) +920 train 7.754328 (lr=6.4406e-05) (hash(x)=23885377) +921 train 7.661673 (lr=6.4476e-05) (hash(x)=23532437) +922 train 7.765696 (lr=6.4545e-05) (hash(x)=25577034) +923 train 7.900760 (lr=6.4615e-05) (hash(x)=25703381) +924 train 7.874332 (lr=6.4685e-05) (hash(x)=27113866) +925 train 7.714868 (lr=6.4755e-05) (hash(x)=26961429) +926 train 7.530376 (lr=6.4825e-05) (hash(x)=21355372) +927 train 7.713244 (lr=6.4895e-05) (hash(x)=24968260) +928 train 7.697188 (lr=6.4965e-05) (hash(x)=25357517) +929 train 7.790793 (lr=6.5035e-05) (hash(x)=24854265) +930 train 7.542265 (lr=6.5105e-05) (hash(x)=21102770) +931 train 7.833665 (lr=6.5175e-05) (hash(x)=25676468) +932 train 7.760145 (lr=6.5245e-05) (hash(x)=22809869) +933 train 7.880684 (lr=6.5315e-05) (hash(x)=25503865) +934 train 7.741077 (lr=6.5385e-05) (hash(x)=24853995) +935 train 7.866751 (lr=6.5455e-05) (hash(x)=27544803) +936 train 7.897234 (lr=6.5524e-05) (hash(x)=25981933) +937 train 7.623727 (lr=6.5594e-05) (hash(x)=24658683) +938 train 7.816062 (lr=6.5664e-05) (hash(x)=23855201) +939 train 7.748947 (lr=6.5734e-05) (hash(x)=24331407) +940 train 7.953800 (lr=6.5804e-05) (hash(x)=29265551) +941 train 7.649426 (lr=6.5874e-05) (hash(x)=21892556) +942 train 7.682671 (lr=6.5944e-05) (hash(x)=27183405) +943 train 7.644789 (lr=6.6014e-05) (hash(x)=26540663) +944 train 7.579401 (lr=6.6084e-05) (hash(x)=25718393) +945 train 7.773842 (lr=6.6154e-05) (hash(x)=26819462) +946 train 7.803200 (lr=6.6224e-05) (hash(x)=27427540) +947 train 7.765273 (lr=6.6294e-05) (hash(x)=25532657) +948 train 7.989905 (lr=6.6364e-05) (hash(x)=27641372) +949 train 7.736608 (lr=6.6434e-05) (hash(x)=26515570) +950 val loss 7.7549 +950 val perplexity 2333.0427 +950 train 7.965173 (lr=6.6503e-05) (hash(x)=26911957) +951 train 8.067241 (lr=6.6573e-05) (hash(x)=25856625) +952 train 7.626445 (lr=6.6643e-05) (hash(x)=25219129) +953 train 7.611959 (lr=6.6713e-05) (hash(x)=25260471) +954 train 7.943676 (lr=6.6783e-05) (hash(x)=29373370) +955 train 7.530161 (lr=6.6853e-05) (hash(x)=23437426) +956 train 7.845940 (lr=6.6923e-05) (hash(x)=23769521) +957 train 7.884282 (lr=6.6993e-05) (hash(x)=25961833) +958 train 7.609067 (lr=6.7063e-05) (hash(x)=23582666) +959 train 7.680669 (lr=6.7133e-05) (hash(x)=23164356) +960 train 7.700919 (lr=6.7203e-05) (hash(x)=24443114) +961 train 7.702859 (lr=6.7273e-05) (hash(x)=25052665) +962 train 7.850937 (lr=6.7343e-05) (hash(x)=27802272) +963 train 7.732655 (lr=6.7413e-05) (hash(x)=25957896) +964 train 7.739980 (lr=6.7483e-05) (hash(x)=26737251) +965 train 7.852468 (lr=6.7552e-05) (hash(x)=24723263) +966 train 7.816308 (lr=6.7622e-05) (hash(x)=24707011) +967 train 7.793863 (lr=6.7692e-05) (hash(x)=25646282) +968 train 7.812010 (lr=6.7762e-05) (hash(x)=27544665) +969 train 7.736991 (lr=6.7832e-05) (hash(x)=25851993) +970 train 8.016932 (lr=6.7902e-05) (hash(x)=29059700) +971 train 7.705309 (lr=6.7972e-05) (hash(x)=21513584) +972 train 7.532838 (lr=6.8042e-05) (hash(x)=23151267) +973 train 7.744774 (lr=6.8112e-05) (hash(x)=26017176) +974 train 7.825635 (lr=6.8182e-05) (hash(x)=26979518) +975 train 7.813695 (lr=6.8252e-05) (hash(x)=23843233) +976 train 7.939095 (lr=6.8322e-05) (hash(x)=24193010) +977 train 7.704910 (lr=6.8392e-05) (hash(x)=21476847) +978 train 7.556543 (lr=6.8462e-05) (hash(x)=21366504) +979 train 7.645825 (lr=6.8531e-05) (hash(x)=23226697) +980 train 7.469772 (lr=6.8601e-05) (hash(x)=19961773) +981 train 7.329371 (lr=6.8671e-05) (hash(x)=19772969) +982 train 7.603461 (lr=6.8741e-05) (hash(x)=23110142) +983 train 7.857779 (lr=6.8811e-05) (hash(x)=24506028) +984 train 7.768296 (lr=6.8881e-05) (hash(x)=25480731) +985 train 7.570885 (lr=6.8951e-05) (hash(x)=21077417) +986 train 7.662778 (lr=6.9021e-05) (hash(x)=23686713) +987 train 7.776030 (lr=6.9091e-05) (hash(x)=26024321) +988 train 7.823163 (lr=6.9161e-05) (hash(x)=27424109) +989 train 7.884786 (lr=6.9231e-05) (hash(x)=27786174) +990 train 7.746999 (lr=6.9301e-05) (hash(x)=25232502) +991 train 7.754390 (lr=6.9371e-05) (hash(x)=22781277) +992 train 7.791809 (lr=6.9441e-05) (hash(x)=26184527) +993 train 7.800613 (lr=6.9510e-05) (hash(x)=24459895) +994 train 7.765071 (lr=6.9580e-05) (hash(x)=25244624) +995 train 7.871071 (lr=6.9650e-05) (hash(x)=24451843) +996 train 7.826175 (lr=6.9720e-05) (hash(x)=22129897) +997 train 7.678525 (lr=6.9790e-05) (hash(x)=21116390) +998 train 7.549222 (lr=6.9860e-05) (hash(x)=20650070) +999 train 7.856702 (lr=6.9930e-05) (hash(x)=24948650) +1000 val loss 7.7603 +1000 val perplexity 2345.6399 +1000 train 7.724970 (lr=7.0000e-05) (hash(x)=25444553) +1001 train 7.735434 (lr=7.0070e-05) (hash(x)=25617781) +1002 train 7.618886 (lr=7.0140e-05) (hash(x)=23862434) +1003 train 7.635397 (lr=7.0210e-05) (hash(x)=25559534) +1004 train 7.865026 (lr=7.0280e-05) (hash(x)=26577585) +1005 train 7.693472 (lr=7.0350e-05) (hash(x)=25546274) +1006 train 7.786810 (lr=7.0420e-05) (hash(x)=26284202) +1007 train 7.789339 (lr=7.0490e-05) (hash(x)=26373991) +1008 train 7.674046 (lr=7.0559e-05) (hash(x)=24612851) +1009 train 7.751946 (lr=7.0629e-05) (hash(x)=26410662) +1010 train 7.762634 (lr=7.0699e-05) (hash(x)=23824841) +1011 train 8.088248 (lr=7.0769e-05) (hash(x)=27756673) +1012 train 7.838677 (lr=7.0839e-05) (hash(x)=25427447) +1013 train 7.866074 (lr=7.0909e-05) (hash(x)=23661686) +1014 train 7.768099 (lr=7.0979e-05) (hash(x)=25129504) +1015 train 7.710646 (lr=7.1049e-05) (hash(x)=23402396) +1016 train 7.954428 (lr=7.1119e-05) (hash(x)=26145557) +1017 train 7.722658 (lr=7.1189e-05) (hash(x)=26547918) +1018 train 7.787627 (lr=7.1259e-05) (hash(x)=26653070) +1019 train 7.799064 (lr=7.1329e-05) (hash(x)=28250354) +1020 train 7.817101 (lr=7.1399e-05) (hash(x)=25437401) +1021 train 7.810413 (lr=7.1469e-05) (hash(x)=25598861) +1022 train 7.620878 (lr=7.1538e-05) (hash(x)=24572587) +1023 train 7.671915 (lr=7.1608e-05) (hash(x)=21562133) +1024 train 8.122222 (lr=7.1678e-05) (hash(x)=27718876) +1025 train 7.668527 (lr=7.1748e-05) (hash(x)=25312391) +1026 train 7.786267 (lr=7.1818e-05) (hash(x)=26579535) +1027 train 8.035489 (lr=7.1888e-05) (hash(x)=27253861) +1028 train 7.890021 (lr=7.1958e-05) (hash(x)=28451867) +1029 train 7.646950 (lr=7.2028e-05) (hash(x)=26795921) +1030 train 7.769313 (lr=7.2098e-05) (hash(x)=26147208) +1031 train 7.823601 (lr=7.2168e-05) (hash(x)=25009210) +1032 train 7.741508 (lr=7.2238e-05) (hash(x)=25213771) +1033 train 7.641292 (lr=7.2308e-05) (hash(x)=26254538) +1034 train 7.657427 (lr=7.2378e-05) (hash(x)=25565614) +1035 train 7.514269 (lr=7.2448e-05) (hash(x)=23052577) +1036 train 8.271474 (lr=7.2517e-05) (hash(x)=29630613) +1037 train 7.558994 (lr=7.2587e-05) (hash(x)=23667224) +1038 train 7.697736 (lr=7.2657e-05) (hash(x)=25740670) +1039 train 7.776024 (lr=7.2727e-05) (hash(x)=27161811) +1040 train 7.909841 (lr=7.2797e-05) (hash(x)=26385663) +1041 train 7.569968 (lr=7.2867e-05) (hash(x)=26313522) +1042 train 7.669928 (lr=7.2937e-05) (hash(x)=26814686) +1043 train 7.854439 (lr=7.3007e-05) (hash(x)=27302459) +1044 train 8.091805 (lr=7.3077e-05) (hash(x)=26758132) +1045 train 7.750108 (lr=7.3147e-05) (hash(x)=26837963) +1046 train 7.541519 (lr=7.3217e-05) (hash(x)=22089547) +1047 train 8.031597 (lr=7.3287e-05) (hash(x)=29515100) +1048 train 7.737901 (lr=7.3357e-05) (hash(x)=25471442) +1049 train 7.746735 (lr=7.3427e-05) (hash(x)=26674478) +1050 val loss 7.7217 +1050 val perplexity 2256.8030 +1050 train 7.675991 (lr=7.3497e-05) (hash(x)=25373386) +1051 train 7.697276 (lr=7.3566e-05) (hash(x)=25318001) +1052 train 7.839478 (lr=7.3636e-05) (hash(x)=27255021) +1053 train 7.829389 (lr=7.3706e-05) (hash(x)=25174043) +1054 train 7.551630 (lr=7.3776e-05) (hash(x)=23857597) +1055 train 7.783592 (lr=7.3846e-05) (hash(x)=25305929) +1056 train 7.853888 (lr=7.3916e-05) (hash(x)=27009246) +1057 train 7.897931 (lr=7.3986e-05) (hash(x)=26175477) +1058 train 7.638640 (lr=7.4056e-05) (hash(x)=22700025) +1059 train 7.669282 (lr=7.4126e-05) (hash(x)=24339043) +1060 train 7.515657 (lr=7.4196e-05) (hash(x)=22139900) +1061 train 8.268735 (lr=7.4266e-05) (hash(x)=25412772) +1062 train 7.764368 (lr=7.4336e-05) (hash(x)=27020849) +1063 train 7.622434 (lr=7.4406e-05) (hash(x)=26808543) +1064 train 7.490718 (lr=7.4476e-05) (hash(x)=23061527) +1065 train 7.637302 (lr=7.4545e-05) (hash(x)=24738650) +1066 train 7.551319 (lr=7.4615e-05) (hash(x)=24036715) +1067 train 7.608865 (lr=7.4685e-05) (hash(x)=25763991) +1068 train 7.837610 (lr=7.4755e-05) (hash(x)=27393753) +1069 train 7.965447 (lr=7.4825e-05) (hash(x)=28182190) +1070 train 7.599581 (lr=7.4895e-05) (hash(x)=23358569) +1071 train 7.805328 (lr=7.4965e-05) (hash(x)=25669509) +1072 train 7.896323 (lr=7.5035e-05) (hash(x)=29139024) +1073 train 7.802045 (lr=7.5105e-05) (hash(x)=25616522) +1074 train 7.719245 (lr=7.5175e-05) (hash(x)=25695789) +1075 train 7.907809 (lr=7.5245e-05) (hash(x)=27676869) +1076 train 7.756532 (lr=7.5315e-05) (hash(x)=25952695) +1077 train 7.757279 (lr=7.5385e-05) (hash(x)=26316170) +1078 train 7.660965 (lr=7.5455e-05) (hash(x)=24081867) +1079 train 7.885387 (lr=7.5524e-05) (hash(x)=28435805) +1080 train 7.724824 (lr=7.5594e-05) (hash(x)=23375063) +1081 train 7.743279 (lr=7.5664e-05) (hash(x)=26869022) +1082 train 7.645476 (lr=7.5734e-05) (hash(x)=25793007) +1083 train 7.630536 (lr=7.5804e-05) (hash(x)=23455211) +1084 train 7.601361 (lr=7.5874e-05) (hash(x)=20441501) +1085 train 7.980245 (lr=7.5944e-05) (hash(x)=29321187) +1086 train 8.137314 (lr=7.6014e-05) (hash(x)=32627505) +1087 train 7.637758 (lr=7.6084e-05) (hash(x)=26482758) +1088 train 7.486832 (lr=7.6154e-05) (hash(x)=21431511) +1089 train 7.739689 (lr=7.6224e-05) (hash(x)=26046639) +1090 train 7.822826 (lr=7.6294e-05) (hash(x)=27464841) +1091 train 7.677540 (lr=7.6364e-05) (hash(x)=27068280) +1092 train 7.556169 (lr=7.6434e-05) (hash(x)=23119133) +1093 train 7.746724 (lr=7.6503e-05) (hash(x)=26782091) +1094 train 7.757631 (lr=7.6573e-05) (hash(x)=26265326) +1095 train 7.781370 (lr=7.6643e-05) (hash(x)=24929929) +1096 train 7.670854 (lr=7.6713e-05) (hash(x)=23158628) +1097 train 7.765569 (lr=7.6783e-05) (hash(x)=25950541) +1098 train 7.569645 (lr=7.6853e-05) (hash(x)=22093912) +1099 train 7.680208 (lr=7.6923e-05) (hash(x)=25373676) +1100 val loss 7.6913 +1100 val perplexity 2189.2395 +1100 train 7.411321 (lr=7.6993e-05) (hash(x)=18986670) +1101 train 7.910885 (lr=7.7063e-05) (hash(x)=27283187) +1102 train 7.673476 (lr=7.7133e-05) (hash(x)=25474743) +1103 train 7.631413 (lr=7.7203e-05) (hash(x)=25043037) +1104 train 7.552835 (lr=7.7273e-05) (hash(x)=23156261) +1105 train 7.957338 (lr=7.7343e-05) (hash(x)=27027534) +1106 train 7.601126 (lr=7.7413e-05) (hash(x)=22733630) +1107 train 7.827056 (lr=7.7483e-05) (hash(x)=27906976) +1108 train 7.767021 (lr=7.7552e-05) (hash(x)=27848655) +1109 train 7.677806 (lr=7.7622e-05) (hash(x)=23889709) +1110 train 8.701029 (lr=7.7692e-05) (hash(x)=33189918) +1111 train 8.270568 (lr=7.7762e-05) (hash(x)=29151257) +1112 train 7.985045 (lr=7.7832e-05) (hash(x)=23881512) +1113 train 7.694586 (lr=7.7902e-05) (hash(x)=21307974) +1114 train 7.748064 (lr=7.7972e-05) (hash(x)=25264524) +1115 train 7.853532 (lr=7.8042e-05) (hash(x)=26405613) +1116 train 7.628790 (lr=7.8112e-05) (hash(x)=21918678) +1117 train 7.556639 (lr=7.8182e-05) (hash(x)=24233887) +1118 train 7.231820 (lr=7.8252e-05) (hash(x)=19490509) +1119 train 7.817255 (lr=7.8322e-05) (hash(x)=26400365) +1120 train 8.072845 (lr=7.8392e-05) (hash(x)=28572086) +1121 train 7.504819 (lr=7.8462e-05) (hash(x)=22293114) +1122 train 7.628548 (lr=7.8531e-05) (hash(x)=26845479) +1123 train 7.542142 (lr=7.8601e-05) (hash(x)=23971905) +1124 train 7.771909 (lr=7.8671e-05) (hash(x)=25639959) +1125 train 7.351790 (lr=7.8741e-05) (hash(x)=20076502) +1126 train 7.732255 (lr=7.8811e-05) (hash(x)=25089255) +1127 train 7.619716 (lr=7.8881e-05) (hash(x)=24098812) +1128 train 7.659267 (lr=7.8951e-05) (hash(x)=23493707) +1129 train 7.848596 (lr=7.9021e-05) (hash(x)=27610410) +1130 train 7.642006 (lr=7.9091e-05) (hash(x)=24540186) +1131 train 7.902016 (lr=7.9161e-05) (hash(x)=29402976) +1132 train 7.521301 (lr=7.9231e-05) (hash(x)=23776025) +1133 train 7.349211 (lr=7.9301e-05) (hash(x)=19032564) +1134 train 7.857601 (lr=7.9371e-05) (hash(x)=26921117) +1135 train 7.506359 (lr=7.9441e-05) (hash(x)=20967666) +1136 train 7.502602 (lr=7.9510e-05) (hash(x)=23394540) +1137 train 7.580247 (lr=7.9580e-05) (hash(x)=22666342) +1138 train 7.716850 (lr=7.9650e-05) (hash(x)=23482498) +1139 train 7.746026 (lr=7.9720e-05) (hash(x)=24287610) +1140 train 7.817502 (lr=7.9790e-05) (hash(x)=24512831) +1141 train 8.030296 (lr=7.9860e-05) (hash(x)=28637634) +1142 train 8.265096 (lr=7.9930e-05) (hash(x)=24107127) +1143 train 7.935025 (lr=8.0000e-05) (hash(x)=28667963) +1144 train 7.825990 (lr=8.0070e-05) (hash(x)=26302492) +1145 train 7.812433 (lr=8.0140e-05) (hash(x)=23621685) +1146 train 7.560300 (lr=8.0210e-05) (hash(x)=23997414) +1147 train 7.672646 (lr=8.0280e-05) (hash(x)=25974316) +1148 train 7.591832 (lr=8.0350e-05) (hash(x)=23464988) +1149 train 7.685136 (lr=8.0420e-05) (hash(x)=24487710) +1150 val loss 7.6811 +1150 val perplexity 2167.0981 +1150 train 7.926193 (lr=8.0490e-05) (hash(x)=29610350) +1151 train 7.974046 (lr=8.0559e-05) (hash(x)=27083417) +1152 train 7.408079 (lr=8.0629e-05) (hash(x)=20666288) +1153 train 7.503830 (lr=8.0699e-05) (hash(x)=22850633) +1154 train 7.673922 (lr=8.0769e-05) (hash(x)=24741872) +1155 train 8.009577 (lr=8.0839e-05) (hash(x)=28605205) +1156 train 7.497388 (lr=8.0909e-05) (hash(x)=22624463) +1157 train 7.720494 (lr=8.0979e-05) (hash(x)=24786468) +1158 train 7.509390 (lr=8.1049e-05) (hash(x)=21365399) +1159 train 7.656510 (lr=8.1119e-05) (hash(x)=23649001) +1160 train 7.725372 (lr=8.1189e-05) (hash(x)=28203982) +1161 train 7.659863 (lr=8.1259e-05) (hash(x)=26473994) +1162 train 7.340662 (lr=8.1329e-05) (hash(x)=19476441) +1163 train 7.629476 (lr=8.1399e-05) (hash(x)=25921700) +1164 train 7.444905 (lr=8.1469e-05) (hash(x)=23064343) +1165 train 7.600358 (lr=8.1538e-05) (hash(x)=24117626) +1166 train 7.488404 (lr=8.1608e-05) (hash(x)=21764556) +1167 train 8.338581 (lr=8.1678e-05) (hash(x)=31338300) +1168 train 7.863089 (lr=8.1748e-05) (hash(x)=27443187) +1169 train 7.277177 (lr=8.1818e-05) (hash(x)=21337692) +1170 train 7.793208 (lr=8.1888e-05) (hash(x)=27845383) +1171 train 7.631340 (lr=8.1958e-05) (hash(x)=23862328) +1172 train 7.755342 (lr=8.2028e-05) (hash(x)=23811014) +1173 train 7.735544 (lr=8.2098e-05) (hash(x)=24380098) +1174 train 7.497379 (lr=8.2168e-05) (hash(x)=22351136) +1175 train 7.718222 (lr=8.2238e-05) (hash(x)=30603174) +1176 train 7.752365 (lr=8.2308e-05) (hash(x)=27924596) +1177 train 8.085216 (lr=8.2378e-05) (hash(x)=30882548) +1178 train 7.574052 (lr=8.2448e-05) (hash(x)=22339464) +1179 train 7.399243 (lr=8.2517e-05) (hash(x)=23603806) +1180 train 7.787992 (lr=8.2587e-05) (hash(x)=24809041) +1181 train 7.606506 (lr=8.2657e-05) (hash(x)=24382442) +1182 train 7.582303 (lr=8.2727e-05) (hash(x)=23134077) +1183 train 7.575790 (lr=8.2797e-05) (hash(x)=24830965) +1184 train 7.687032 (lr=8.2867e-05) (hash(x)=25527259) +1185 train 7.717546 (lr=8.2937e-05) (hash(x)=25547480) +1186 train 7.584674 (lr=8.3007e-05) (hash(x)=24424314) +1187 train 7.956908 (lr=8.3077e-05) (hash(x)=32488729) +1188 train 7.887370 (lr=8.3147e-05) (hash(x)=31168462) +1189 train 8.121085 (lr=8.3217e-05) (hash(x)=31331643) +1190 train 7.792444 (lr=8.3287e-05) (hash(x)=28746633) +1191 train 7.774395 (lr=8.3357e-05) (hash(x)=27269893) +1192 train 7.632304 (lr=8.3427e-05) (hash(x)=23484031) +1193 train 7.621953 (lr=8.3497e-05) (hash(x)=23278725) +1194 train 7.736277 (lr=8.3566e-05) (hash(x)=25440745) +1195 train 7.754143 (lr=8.3636e-05) (hash(x)=25215077) +1196 train 7.790884 (lr=8.3706e-05) (hash(x)=28309266) +1197 train 7.512044 (lr=8.3776e-05) (hash(x)=22442404) +1198 train 7.547241 (lr=8.3846e-05) (hash(x)=20775262) +1199 train 7.624610 (lr=8.3916e-05) (hash(x)=24825041) +1200 val loss 7.6538 +1200 val perplexity 2108.6082 +1200 train 7.773851 (lr=8.3986e-05) (hash(x)=29016896) +1201 train 7.712793 (lr=8.4056e-05) (hash(x)=25590276) +1202 train 7.593689 (lr=8.4126e-05) (hash(x)=22816384) +1203 train 7.715631 (lr=8.4196e-05) (hash(x)=25893804) +1204 train 7.608298 (lr=8.4266e-05) (hash(x)=23983816) +1205 train 7.512746 (lr=8.4336e-05) (hash(x)=22222468) +1206 train 7.540434 (lr=8.4406e-05) (hash(x)=23039141) +1207 train 7.523247 (lr=8.4476e-05) (hash(x)=22724871) +1208 train 7.540944 (lr=8.4545e-05) (hash(x)=25253062) +1209 train 7.570007 (lr=8.4615e-05) (hash(x)=25140744) +1210 train 7.601460 (lr=8.4685e-05) (hash(x)=24717218) +1211 train 7.725622 (lr=8.4755e-05) (hash(x)=27317554) +1212 train 7.391031 (lr=8.4825e-05) (hash(x)=22013236) +1213 train 7.912396 (lr=8.4895e-05) (hash(x)=26692343) +1214 train 7.386497 (lr=8.4965e-05) (hash(x)=19859225) +1215 train 7.392780 (lr=8.5035e-05) (hash(x)=24683717) +1216 train 7.442928 (lr=8.5105e-05) (hash(x)=21932013) +1217 train 7.691833 (lr=8.5175e-05) (hash(x)=26849303) +1218 train 7.776963 (lr=8.5245e-05) (hash(x)=26458000) +1219 train 7.523682 (lr=8.5315e-05) (hash(x)=21584083) +1220 train 7.889732 (lr=8.5385e-05) (hash(x)=23598625) +1221 train 7.635664 (lr=8.5455e-05) (hash(x)=26059939) +1222 train 7.847499 (lr=8.5524e-05) (hash(x)=25481982) +1223 train 7.759632 (lr=8.5594e-05) (hash(x)=26190337) +1224 train 7.944954 (lr=8.5664e-05) (hash(x)=28767755) +1225 train 7.575881 (lr=8.5734e-05) (hash(x)=23663918) +1226 train 7.647916 (lr=8.5804e-05) (hash(x)=21293227) +1227 train 7.660882 (lr=8.5874e-05) (hash(x)=22249019) +1228 train 7.774898 (lr=8.5944e-05) (hash(x)=26886529) +1229 train 7.585140 (lr=8.6014e-05) (hash(x)=25779849) +1230 train 7.698213 (lr=8.6084e-05) (hash(x)=26228964) +1231 train 7.607533 (lr=8.6154e-05) (hash(x)=23086289) +1232 train 7.717332 (lr=8.6224e-05) (hash(x)=23198922) +1233 train 7.766889 (lr=8.6294e-05) (hash(x)=27523941) +1234 train 7.542465 (lr=8.6364e-05) (hash(x)=24293992) +1235 train 8.293038 (lr=8.6434e-05) (hash(x)=28047044) +1236 train 7.726960 (lr=8.6503e-05) (hash(x)=23688671) +1237 train 7.594000 (lr=8.6573e-05) (hash(x)=25125498) +1238 train 7.513489 (lr=8.6643e-05) (hash(x)=21977292) +1239 train 7.602165 (lr=8.6713e-05) (hash(x)=23593875) +1240 train 7.498254 (lr=8.6783e-05) (hash(x)=22659030) +1241 train 7.636603 (lr=8.6853e-05) (hash(x)=25117733) +1242 train 7.582280 (lr=8.6923e-05) (hash(x)=22322808) +1243 train 7.656497 (lr=8.6993e-05) (hash(x)=26059735) +1244 train 7.596968 (lr=8.7063e-05) (hash(x)=22485526) +1245 train 7.499175 (lr=8.7133e-05) (hash(x)=23028679) +1246 train 7.509893 (lr=8.7203e-05) (hash(x)=22906035) +1247 train 7.415217 (lr=8.7273e-05) (hash(x)=22414190) +1248 train 7.700216 (lr=8.7343e-05) (hash(x)=26229624) +1249 train 7.466747 (lr=8.7413e-05) (hash(x)=22223137) +1250 val loss 7.6283 +1250 val perplexity 2055.4727 +1250 train 7.735762 (lr=8.7483e-05) (hash(x)=24911520) +1251 train 7.941397 (lr=8.7552e-05) (hash(x)=24204591) +1252 train 7.520742 (lr=8.7622e-05) (hash(x)=24379601) +1253 train 7.458228 (lr=8.7692e-05) (hash(x)=22922475) +1254 train 7.499607 (lr=8.7762e-05) (hash(x)=23426249) +1255 train 7.765358 (lr=8.7832e-05) (hash(x)=26758114) +1256 train 7.450566 (lr=8.7902e-05) (hash(x)=24027111) +1257 train 7.610456 (lr=8.7972e-05) (hash(x)=25358064) +1258 train 7.517433 (lr=8.8042e-05) (hash(x)=22571285) +1259 train 7.880438 (lr=8.8112e-05) (hash(x)=20084233) +1260 train 7.680524 (lr=8.8182e-05) (hash(x)=18786581) +1261 train 7.612664 (lr=8.8252e-05) (hash(x)=26395104) +1262 train 7.521901 (lr=8.8322e-05) (hash(x)=24212567) +1263 train 7.369564 (lr=8.8392e-05) (hash(x)=21563184) +1264 train 7.646481 (lr=8.8462e-05) (hash(x)=26490150) +1265 train 7.714450 (lr=8.8531e-05) (hash(x)=25207694) +1266 train 7.541973 (lr=8.8601e-05) (hash(x)=23914544) +1267 train 7.555626 (lr=8.8671e-05) (hash(x)=23861489) +1268 train 7.962837 (lr=8.8741e-05) (hash(x)=30714540) +1269 train 7.513237 (lr=8.8811e-05) (hash(x)=23471007) +1270 train 7.526311 (lr=8.8881e-05) (hash(x)=23244293) +1271 train 7.467156 (lr=8.8951e-05) (hash(x)=19218470) +1272 train 7.754834 (lr=8.9021e-05) (hash(x)=26965136) +1273 train 7.490944 (lr=8.9091e-05) (hash(x)=22944035) +1274 train 7.524467 (lr=8.9161e-05) (hash(x)=22002714) +1275 train 7.828475 (lr=8.9231e-05) (hash(x)=28469562) +1276 train 7.868680 (lr=8.9301e-05) (hash(x)=26889992) +1277 train 7.899649 (lr=8.9371e-05) (hash(x)=26452814) +1278 train 7.717763 (lr=8.9441e-05) (hash(x)=28397488) +1279 train 7.784276 (lr=8.9510e-05) (hash(x)=25588469) +1280 train 7.657163 (lr=8.9580e-05) (hash(x)=24833139) +1281 train 7.532075 (lr=8.9650e-05) (hash(x)=24788298) +1282 train 7.786645 (lr=8.9720e-05) (hash(x)=24979383) +1283 train 7.754496 (lr=8.9790e-05) (hash(x)=25236367) +1284 train 7.586683 (lr=8.9860e-05) (hash(x)=22638257) +1285 train 7.451813 (lr=8.9930e-05) (hash(x)=23069067) +1286 train 7.627491 (lr=9.0000e-05) (hash(x)=25133239) +1287 train 8.189127 (lr=9.0070e-05) (hash(x)=30433767) +1288 train 8.200941 (lr=9.0140e-05) (hash(x)=34319079) +1289 train 8.037804 (lr=9.0210e-05) (hash(x)=29268881) +1290 train 7.663255 (lr=9.0280e-05) (hash(x)=24528336) +1291 train 7.862807 (lr=9.0350e-05) (hash(x)=26302626) +1292 train 7.856649 (lr=9.0420e-05) (hash(x)=25479111) +1293 train 7.983995 (lr=9.0490e-05) (hash(x)=24749682) +1294 train 7.542015 (lr=9.0559e-05) (hash(x)=24111393) +1295 train 7.316991 (lr=9.0629e-05) (hash(x)=17851621) +1296 train 7.601911 (lr=9.0699e-05) (hash(x)=26463070) +1297 train 7.618654 (lr=9.0769e-05) (hash(x)=25620741) +1298 train 8.245809 (lr=9.0839e-05) (hash(x)=28225676) +1299 train 8.041636 (lr=9.0909e-05) (hash(x)=27028191) +1300 val loss 7.6198 +1300 val perplexity 2038.0818 +1300 train 7.704319 (lr=9.0979e-05) (hash(x)=29006516) +1301 train 7.798656 (lr=9.1049e-05) (hash(x)=27590299) +1302 train 7.927667 (lr=9.1119e-05) (hash(x)=28678983) +1303 train 7.761888 (lr=9.1189e-05) (hash(x)=25183690) +1304 train 7.342271 (lr=9.1259e-05) (hash(x)=19918097) +1305 train 8.104841 (lr=9.1329e-05) (hash(x)=31114252) +1306 train 8.091505 (lr=9.1399e-05) (hash(x)=30913255) +1307 train 7.647157 (lr=9.1469e-05) (hash(x)=26182243) +1308 train 7.858234 (lr=9.1538e-05) (hash(x)=27420668) +1309 train 8.155184 (lr=9.1608e-05) (hash(x)=30419908) +1310 train 8.039784 (lr=9.1678e-05) (hash(x)=29002281) +1311 train 7.725760 (lr=9.1748e-05) (hash(x)=27040642) +1312 train 7.604611 (lr=9.1818e-05) (hash(x)=26929300) +1313 train 7.700959 (lr=9.1888e-05) (hash(x)=26240761) +1314 train 7.728531 (lr=9.1958e-05) (hash(x)=27161876) +1315 train 7.552768 (lr=9.2028e-05) (hash(x)=24489607) +1316 train 7.960321 (lr=9.2098e-05) (hash(x)=27040115) +1317 train 7.625279 (lr=9.2168e-05) (hash(x)=25012872) +1318 train 7.260036 (lr=9.2238e-05) (hash(x)=20894720) +1319 train 7.395163 (lr=9.2308e-05) (hash(x)=22183303) +1320 train 7.616780 (lr=9.2378e-05) (hash(x)=26291778) +1321 train 7.697935 (lr=9.2448e-05) (hash(x)=27682633) +1322 train 7.529243 (lr=9.2517e-05) (hash(x)=26490892) +1323 train 7.956995 (lr=9.2587e-05) (hash(x)=28844646) +1324 train 8.262079 (lr=9.2657e-05) (hash(x)=29545304) +1325 train 8.384376 (lr=9.2727e-05) (hash(x)=31082070) +1326 train 8.013751 (lr=9.2797e-05) (hash(x)=27486316) +1327 train 7.975816 (lr=9.2867e-05) (hash(x)=27537063) +1328 train 7.713930 (lr=9.2937e-05) (hash(x)=26955557) +1329 train 7.717659 (lr=9.3007e-05) (hash(x)=26125988) +1330 train 7.715825 (lr=9.3077e-05) (hash(x)=22800125) +1331 train 7.867137 (lr=9.3147e-05) (hash(x)=25446686) +1332 train 7.910416 (lr=9.3217e-05) (hash(x)=28743746) +1333 train 7.617290 (lr=9.3287e-05) (hash(x)=19819857) +1334 train 7.401163 (lr=9.3357e-05) (hash(x)=23518628) +1335 train 7.343490 (lr=9.3427e-05) (hash(x)=19492832) +1336 train 7.668746 (lr=9.3497e-05) (hash(x)=24627720) +1337 train 7.557425 (lr=9.3566e-05) (hash(x)=23741214) +1338 train 7.613309 (lr=9.3636e-05) (hash(x)=25837914) +1339 train 7.529362 (lr=9.3706e-05) (hash(x)=25484958) +1340 train 7.497659 (lr=9.3776e-05) (hash(x)=23671284) +1341 train 7.594093 (lr=9.3846e-05) (hash(x)=25525370) +1342 train 7.695169 (lr=9.3916e-05) (hash(x)=26585300) +1343 train 7.739574 (lr=9.3986e-05) (hash(x)=25951629) +1344 train 7.920334 (lr=9.4056e-05) (hash(x)=28743135) +1345 train 8.059464 (lr=9.4126e-05) (hash(x)=28557663) +1346 train 7.469379 (lr=9.4196e-05) (hash(x)=22642751) +1347 train 7.386016 (lr=9.4266e-05) (hash(x)=23462798) +1348 train 7.276106 (lr=9.4336e-05) (hash(x)=24292328) +1349 train 7.626187 (lr=9.4406e-05) (hash(x)=27320280) +1350 val loss 7.6472 +1350 val perplexity 2094.8062 +1350 train 7.823181 (lr=9.4476e-05) (hash(x)=27352812) +1351 train 7.683807 (lr=9.4545e-05) (hash(x)=22408682) +1352 train 7.581374 (lr=9.4615e-05) (hash(x)=23144732) +1353 train 7.448056 (lr=9.4685e-05) (hash(x)=22230799) +1354 train 7.822244 (lr=9.4755e-05) (hash(x)=29747687) +1355 train 8.027953 (lr=9.4825e-05) (hash(x)=31317970) +1356 train 7.284126 (lr=9.4895e-05) (hash(x)=20131758) +1357 train 7.632356 (lr=9.4965e-05) (hash(x)=24020983) +1358 train 7.481984 (lr=9.5035e-05) (hash(x)=23998051) +1359 train 7.579682 (lr=9.5105e-05) (hash(x)=27633457) +1360 train 7.297615 (lr=9.5175e-05) (hash(x)=20155247) +1361 train 7.557321 (lr=9.5245e-05) (hash(x)=23766987) +1362 train 7.446182 (lr=9.5315e-05) (hash(x)=25960383) +1363 train 7.737021 (lr=9.5385e-05) (hash(x)=23729283) +1364 train 7.855870 (lr=9.5455e-05) (hash(x)=27775445) +1365 train 7.700654 (lr=9.5524e-05) (hash(x)=25975834) +1366 train 7.533186 (lr=9.5594e-05) (hash(x)=22765259) +1367 train 7.794721 (lr=9.5664e-05) (hash(x)=27635080) +1368 train 7.547934 (lr=9.5734e-05) (hash(x)=23848542) +1369 train 7.687129 (lr=9.5804e-05) (hash(x)=27181156) +1370 train 7.820779 (lr=9.5874e-05) (hash(x)=28321340) +1371 train 7.564061 (lr=9.5944e-05) (hash(x)=25918780) +1372 train 7.570645 (lr=9.6014e-05) (hash(x)=23338297) +1373 train 7.709507 (lr=9.6084e-05) (hash(x)=22370417) +1374 train 7.644927 (lr=9.6154e-05) (hash(x)=24272668) +1375 train 7.305396 (lr=9.6224e-05) (hash(x)=22287596) +1376 train 7.504327 (lr=9.6294e-05) (hash(x)=25257403) +1377 train 7.435921 (lr=9.6364e-05) (hash(x)=21584419) +1378 train 7.573711 (lr=9.6434e-05) (hash(x)=25318823) +1379 train 7.388754 (lr=9.6503e-05) (hash(x)=22694623) +1380 train 7.513053 (lr=9.6573e-05) (hash(x)=23743406) +1381 train 7.742075 (lr=9.6643e-05) (hash(x)=30820846) +1382 train 8.256877 (lr=9.6713e-05) (hash(x)=34639557) +1383 train 8.138252 (lr=9.6783e-05) (hash(x)=35895440) +1384 train 7.639295 (lr=9.6853e-05) (hash(x)=26304839) +1385 train 7.804806 (lr=9.6923e-05) (hash(x)=27058657) +1386 train 7.635779 (lr=9.6993e-05) (hash(x)=25209529) +1387 train 7.540990 (lr=9.7063e-05) (hash(x)=24298886) +1388 train 7.683206 (lr=9.7133e-05) (hash(x)=26200200) +1389 train 7.568798 (lr=9.7203e-05) (hash(x)=27303061) +1390 train 7.649774 (lr=9.7273e-05) (hash(x)=26531628) +1391 train 7.661313 (lr=9.7343e-05) (hash(x)=25888847) +1392 train 7.761017 (lr=9.7413e-05) (hash(x)=28924067) +1393 train 7.255843 (lr=9.7483e-05) (hash(x)=21267641) +1394 train 7.848943 (lr=9.7552e-05) (hash(x)=29419156) +1395 train 8.109614 (lr=9.7622e-05) (hash(x)=30860646) +1396 train 7.624811 (lr=9.7692e-05) (hash(x)=25744434) +1397 train 7.614799 (lr=9.7762e-05) (hash(x)=26881837) +1398 train 7.617313 (lr=9.7832e-05) (hash(x)=26676176) +1399 train 7.767561 (lr=9.7902e-05) (hash(x)=26518800) +1400 val loss 7.6003 +1400 val perplexity 1998.7760 +1400 train 7.542076 (lr=9.7972e-05) (hash(x)=25043238) +1401 train 7.802737 (lr=9.8042e-05) (hash(x)=25863277) +1402 train 7.450890 (lr=9.8112e-05) (hash(x)=24073623) +1403 train 7.490213 (lr=9.8182e-05) (hash(x)=25385523) +1404 train 7.573586 (lr=9.8252e-05) (hash(x)=24958112) +1405 train 7.438422 (lr=9.8322e-05) (hash(x)=23362519) +1406 train 7.722353 (lr=9.8392e-05) (hash(x)=29262616) +1407 train 8.091835 (lr=9.8462e-05) (hash(x)=37519283) +1408 train 8.435130 (lr=9.8531e-05) (hash(x)=33716930) +1409 train 7.594713 (lr=9.8601e-05) (hash(x)=23392584) +1410 train 8.010777 (lr=9.8671e-05) (hash(x)=22877779) +1411 train 8.304646 (lr=9.8741e-05) (hash(x)=20564397) +1412 train 7.839003 (lr=9.8811e-05) (hash(x)=24366235) +1413 train 7.756907 (lr=9.8881e-05) (hash(x)=27065499) +1414 train 7.597601 (lr=9.8951e-05) (hash(x)=26844114) +1415 train 7.689362 (lr=9.9021e-05) (hash(x)=25141945) +1416 train 7.904518 (lr=9.9091e-05) (hash(x)=28813116) +1417 train 7.622396 (lr=9.9161e-05) (hash(x)=25466598) +1418 train 7.509842 (lr=9.9231e-05) (hash(x)=22800032) +1419 train 7.580604 (lr=9.9301e-05) (hash(x)=22717866) +1420 train 8.063341 (lr=9.9371e-05) (hash(x)=28040763) +1421 train 8.154731 (lr=9.9441e-05) (hash(x)=29648992) +1422 train 8.141720 (lr=9.9510e-05) (hash(x)=31747228) +1423 train 7.613905 (lr=9.9580e-05) (hash(x)=28527939) +1424 train 7.552922 (lr=9.9650e-05) (hash(x)=21563992) +1425 train 7.490391 (lr=9.9720e-05) (hash(x)=25134784) +1426 train 7.714632 (lr=9.9790e-05) (hash(x)=28442823) +1427 train 8.265360 (lr=9.9860e-05) (hash(x)=32757059) +1428 train 7.485407 (lr=9.9930e-05) (hash(x)=24110500) +1429 train 7.562804 (lr=1.0000e-04) (hash(x)=24145729) +1430 train 7.592943 (lr=1.0000e-04) (hash(x)=23541086) +1431 train 7.442477 (lr=1.0000e-04) (hash(x)=21942471) +1432 train 7.519547 (lr=1.0000e-04) (hash(x)=24736836) +1433 train 7.673421 (lr=1.0000e-04) (hash(x)=25325444) +1434 train 7.671552 (lr=1.0000e-04) (hash(x)=25188954) +1435 train 8.214477 (lr=1.0000e-04) (hash(x)=24247339) +1436 train 7.665534 (lr=9.9999e-05) (hash(x)=23773363) +1437 train 7.418392 (lr=9.9999e-05) (hash(x)=24142989) +1438 train 7.413645 (lr=9.9999e-05) (hash(x)=24226952) +1439 train 7.674069 (lr=9.9999e-05) (hash(x)=24955630) +1440 train 7.586534 (lr=9.9998e-05) (hash(x)=24563233) +1441 train 7.722664 (lr=9.9998e-05) (hash(x)=25491335) +1442 train 8.062204 (lr=9.9997e-05) (hash(x)=33253763) +1443 train 7.459095 (lr=9.9997e-05) (hash(x)=21368780) +1444 train 7.532956 (lr=9.9997e-05) (hash(x)=26615500) +1445 train 7.772788 (lr=9.9996e-05) (hash(x)=27146278) +1446 train 7.605585 (lr=9.9996e-05) (hash(x)=25904861) +1447 train 7.464867 (lr=9.9995e-05) (hash(x)=25541230) +1448 train 7.589569 (lr=9.9994e-05) (hash(x)=25434227) +1449 train 7.574108 (lr=9.9994e-05) (hash(x)=25375355) +1450 val loss 7.5715 +1450 val perplexity 1942.1119 +1450 train 7.394762 (lr=9.9993e-05) (hash(x)=21921129) +1451 train 7.395784 (lr=9.9992e-05) (hash(x)=23098806) +1452 train 7.435196 (lr=9.9992e-05) (hash(x)=22000544) +1453 train 7.370130 (lr=9.9991e-05) (hash(x)=22061174) +1454 train 7.429468 (lr=9.9990e-05) (hash(x)=24326286) +1455 train 7.461661 (lr=9.9989e-05) (hash(x)=23501481) +1456 train 7.652351 (lr=9.9988e-05) (hash(x)=26397938) +1457 train 7.652698 (lr=9.9987e-05) (hash(x)=24656430) +1458 train 7.360956 (lr=9.9986e-05) (hash(x)=23494971) +1459 train 7.445696 (lr=9.9985e-05) (hash(x)=23802681) +1460 train 7.417461 (lr=9.9984e-05) (hash(x)=21990153) +1461 train 7.455377 (lr=9.9983e-05) (hash(x)=23496118) +1462 train 7.454205 (lr=9.9982e-05) (hash(x)=24233822) +1463 train 7.780473 (lr=9.9981e-05) (hash(x)=22754988) +1464 train 7.484998 (lr=9.9980e-05) (hash(x)=23116635) +1465 train 7.230609 (lr=9.9979e-05) (hash(x)=21461650) +1466 train 7.355899 (lr=9.9977e-05) (hash(x)=22274473) +1467 train 7.372632 (lr=9.9976e-05) (hash(x)=22183009) +1468 train 7.618997 (lr=9.9975e-05) (hash(x)=24972441) +1469 train 7.428972 (lr=9.9974e-05) (hash(x)=22300616) +1470 train 7.201539 (lr=9.9972e-05) (hash(x)=21443060) +1471 train 7.410271 (lr=9.9971e-05) (hash(x)=23475070) +1472 train 7.358217 (lr=9.9969e-05) (hash(x)=22316810) +1473 train 7.793060 (lr=9.9968e-05) (hash(x)=24508407) +1474 train 7.768698 (lr=9.9966e-05) (hash(x)=24603557) +1475 train 7.456150 (lr=9.9965e-05) (hash(x)=23359061) +1476 train 7.494702 (lr=9.9963e-05) (hash(x)=22950844) +1477 train 7.535951 (lr=9.9962e-05) (hash(x)=22588667) +1478 train 7.668327 (lr=9.9960e-05) (hash(x)=26083526) +1479 train 7.553586 (lr=9.9958e-05) (hash(x)=23609959) +1480 train 7.585758 (lr=9.9956e-05) (hash(x)=24088171) +1481 train 7.576770 (lr=9.9955e-05) (hash(x)=25394852) +1482 train 7.512492 (lr=9.9953e-05) (hash(x)=24503040) +1483 train 7.294722 (lr=9.9951e-05) (hash(x)=22408449) +1484 train 7.503948 (lr=9.9949e-05) (hash(x)=25069325) +1485 train 7.558415 (lr=9.9947e-05) (hash(x)=26947398) +1486 train 7.024287 (lr=9.9945e-05) (hash(x)=17527161) +1487 train 7.435582 (lr=9.9943e-05) (hash(x)=23441847) +1488 train 7.455894 (lr=9.9941e-05) (hash(x)=25592861) +1489 train 7.379799 (lr=9.9939e-05) (hash(x)=23101350) +1490 train 7.368329 (lr=9.9937e-05) (hash(x)=24201380) +1491 train 7.455991 (lr=9.9935e-05) (hash(x)=23676365) +1492 train 7.563512 (lr=9.9933e-05) (hash(x)=26668088) +1493 train 7.698401 (lr=9.9931e-05) (hash(x)=26488811) +1494 train 7.665294 (lr=9.9929e-05) (hash(x)=27248109) +1495 train 7.705422 (lr=9.9926e-05) (hash(x)=23096292) +1496 train 7.602151 (lr=9.9924e-05) (hash(x)=22101981) +1497 train 7.782796 (lr=9.9922e-05) (hash(x)=24512380) +1498 train 7.579436 (lr=9.9919e-05) (hash(x)=25367738) +1499 train 7.570287 (lr=9.9917e-05) (hash(x)=27706294) +1500 val loss 7.5564 +1500 val perplexity 1912.9572 +1500 train 7.668346 (lr=9.9915e-05) (hash(x)=24154026) +1501 train 7.403558 (lr=9.9912e-05) (hash(x)=21892472) +1502 train 7.453605 (lr=9.9910e-05) (hash(x)=23662543) +1503 train 7.499188 (lr=9.9907e-05) (hash(x)=26171093) +1504 train 7.530446 (lr=9.9905e-05) (hash(x)=25974292) +1505 train 7.406452 (lr=9.9902e-05) (hash(x)=23191101) +1506 train 7.654873 (lr=9.9899e-05) (hash(x)=26498861) +1507 train 8.131579 (lr=9.9897e-05) (hash(x)=34946941) +1508 train 7.786778 (lr=9.9894e-05) (hash(x)=25442719) +1509 train 7.602220 (lr=9.9891e-05) (hash(x)=25569942) +1510 train 7.331902 (lr=9.9889e-05) (hash(x)=21265828) +1511 train 7.237501 (lr=9.9886e-05) (hash(x)=20060838) +1512 train 7.405521 (lr=9.9883e-05) (hash(x)=22588251) +1513 train 7.364694 (lr=9.9880e-05) (hash(x)=24581020) +1514 train 7.354810 (lr=9.9877e-05) (hash(x)=21882493) +1515 train 7.339589 (lr=9.9874e-05) (hash(x)=21591702) +1516 train 7.287219 (lr=9.9871e-05) (hash(x)=19813285) +1517 train 7.375370 (lr=9.9868e-05) (hash(x)=21870012) +1518 train 7.456922 (lr=9.9865e-05) (hash(x)=26895498) +1519 train 7.512613 (lr=9.9862e-05) (hash(x)=25451055) +1520 train 7.570896 (lr=9.9859e-05) (hash(x)=25395865) +1521 train 7.038536 (lr=9.9856e-05) (hash(x)=18989695) +1522 train 6.915082 (lr=9.9853e-05) (hash(x)=17040678) +1523 train 6.975852 (lr=9.9849e-05) (hash(x)=18691455) +1524 train 7.119104 (lr=9.9846e-05) (hash(x)=19017167) +1525 train 7.443802 (lr=9.9843e-05) (hash(x)=22406503) +1526 train 7.605214 (lr=9.9840e-05) (hash(x)=23036138) +1527 train 7.476691 (lr=9.9836e-05) (hash(x)=24934792) +1528 train 7.487691 (lr=9.9833e-05) (hash(x)=22843127) +1529 train 7.424181 (lr=9.9829e-05) (hash(x)=24249677) +1530 train 7.293639 (lr=9.9826e-05) (hash(x)=23318555) +1531 train 7.347257 (lr=9.9822e-05) (hash(x)=23864361) +1532 train 7.265583 (lr=9.9819e-05) (hash(x)=20242060) +1533 train 7.395837 (lr=9.9815e-05) (hash(x)=21549554) +1534 train 7.265296 (lr=9.9812e-05) (hash(x)=21642024) +1535 train 7.727150 (lr=9.9808e-05) (hash(x)=25367597) +1536 train 7.938468 (lr=9.9804e-05) (hash(x)=27224144) +1537 train 7.423300 (lr=9.9801e-05) (hash(x)=24409290) +1538 train 7.471480 (lr=9.9797e-05) (hash(x)=24987180) +1539 train 7.403322 (lr=9.9793e-05) (hash(x)=27016702) +1540 train 7.631844 (lr=9.9789e-05) (hash(x)=25819636) +1541 train 7.614645 (lr=9.9785e-05) (hash(x)=25520453) +1542 train 7.355336 (lr=9.9782e-05) (hash(x)=23580496) +1543 train 7.587131 (lr=9.9778e-05) (hash(x)=25022148) +1544 train 7.589864 (lr=9.9774e-05) (hash(x)=25447327) +1545 train 7.557675 (lr=9.9770e-05) (hash(x)=25010319) +1546 train 7.489712 (lr=9.9766e-05) (hash(x)=25511777) +1547 train 7.457152 (lr=9.9762e-05) (hash(x)=24459012) +1548 train 7.518682 (lr=9.9758e-05) (hash(x)=25082785) +1549 train 7.584249 (lr=9.9753e-05) (hash(x)=26528670) +1550 val loss 7.5220 +1550 val perplexity 1848.2748 +1550 train 7.519648 (lr=9.9749e-05) (hash(x)=26684367) +1551 train 7.513700 (lr=9.9745e-05) (hash(x)=25431365) +1552 train 7.463858 (lr=9.9741e-05) (hash(x)=24802747) +1553 train 7.260620 (lr=9.9737e-05) (hash(x)=24229522) +1554 train 7.516990 (lr=9.9732e-05) (hash(x)=24757176) +1555 train 7.621021 (lr=9.9728e-05) (hash(x)=25958785) +1556 train 7.649517 (lr=9.9724e-05) (hash(x)=26810735) +1557 train 7.291135 (lr=9.9719e-05) (hash(x)=22882640) +1558 train 7.772582 (lr=9.9715e-05) (hash(x)=27220057) +1559 train 8.036844 (lr=9.9710e-05) (hash(x)=29307788) +1560 train 7.481160 (lr=9.9706e-05) (hash(x)=25214030) +1561 train 7.319656 (lr=9.9701e-05) (hash(x)=23167825) +1562 train 7.405079 (lr=9.9697e-05) (hash(x)=24658511) +1563 train 7.547817 (lr=9.9692e-05) (hash(x)=24965435) +1564 train 7.305961 (lr=9.9687e-05) (hash(x)=23620579) +1565 train 7.263647 (lr=9.9683e-05) (hash(x)=23772949) +1566 train 7.461912 (lr=9.9678e-05) (hash(x)=23807939) +1567 train 7.658962 (lr=9.9673e-05) (hash(x)=25651929) +1568 train 7.590435 (lr=9.9669e-05) (hash(x)=25549933) +1569 train 7.319429 (lr=9.9664e-05) (hash(x)=23146724) +1570 train 7.395033 (lr=9.9659e-05) (hash(x)=24099275) +1571 train 7.605850 (lr=9.9654e-05) (hash(x)=28451031) +1572 train 7.667609 (lr=9.9649e-05) (hash(x)=25488511) +1573 train 7.453511 (lr=9.9644e-05) (hash(x)=23796771) +1574 train 7.508954 (lr=9.9639e-05) (hash(x)=22642764) +1575 train 7.578377 (lr=9.9634e-05) (hash(x)=26312387) +1576 train 7.399590 (lr=9.9629e-05) (hash(x)=22486223) +1577 train 7.401503 (lr=9.9624e-05) (hash(x)=21257377) +1578 train 7.535518 (lr=9.9619e-05) (hash(x)=24328365) +1579 train 7.595758 (lr=9.9614e-05) (hash(x)=25326650) +1580 train 7.581200 (lr=9.9609e-05) (hash(x)=26484837) +1581 train 7.356983 (lr=9.9603e-05) (hash(x)=24605603) +1582 train 7.428238 (lr=9.9598e-05) (hash(x)=24668537) +1583 train 7.349536 (lr=9.9593e-05) (hash(x)=23804913) +1584 train 7.644853 (lr=9.9587e-05) (hash(x)=23615391) +1585 train 7.571862 (lr=9.9582e-05) (hash(x)=24322926) +1586 train 7.337522 (lr=9.9577e-05) (hash(x)=19753104) +1587 train 7.798651 (lr=9.9571e-05) (hash(x)=25537529) +1588 train 7.217848 (lr=9.9566e-05) (hash(x)=22835476) +1589 train 7.349454 (lr=9.9560e-05) (hash(x)=25707197) +1590 train 7.370522 (lr=9.9555e-05) (hash(x)=24191203) +1591 train 7.635532 (lr=9.9549e-05) (hash(x)=26115519) +1592 train 7.510044 (lr=9.9544e-05) (hash(x)=25781547) +1593 train 7.345926 (lr=9.9538e-05) (hash(x)=24850654) +1594 train 7.226909 (lr=9.9532e-05) (hash(x)=23300928) +1595 train 7.489104 (lr=9.9526e-05) (hash(x)=25494804) +1596 train 7.505783 (lr=9.9521e-05) (hash(x)=28169410) +1597 train 7.260895 (lr=9.9515e-05) (hash(x)=21972022) +1598 train 7.827859 (lr=9.9509e-05) (hash(x)=27687290) +1599 train 7.654065 (lr=9.9503e-05) (hash(x)=23210747) +1600 val loss 7.4951 +1600 val perplexity 1799.1815 +1600 train 7.689946 (lr=9.9497e-05) (hash(x)=20362758) +1601 train 7.473335 (lr=9.9491e-05) (hash(x)=17064773) +1602 train 7.456367 (lr=9.9486e-05) (hash(x)=17173694) +1603 train 7.527927 (lr=9.9480e-05) (hash(x)=15717069) +1604 train 7.663166 (lr=9.9474e-05) (hash(x)=15117973) +1605 train 7.416817 (lr=9.9467e-05) (hash(x)=16189636) +1606 train 7.376255 (lr=9.9461e-05) (hash(x)=16552095) +1607 train 7.233268 (lr=9.9455e-05) (hash(x)=18463712) +1608 train 7.410152 (lr=9.9449e-05) (hash(x)=17572155) +1609 train 7.394718 (lr=9.9443e-05) (hash(x)=19970072) +1610 train 7.417041 (lr=9.9437e-05) (hash(x)=20463871) +1611 train 7.492772 (lr=9.9430e-05) (hash(x)=20705573) +1612 train 7.411780 (lr=9.9424e-05) (hash(x)=24441646) +1613 train 7.540515 (lr=9.9418e-05) (hash(x)=22913147) +1614 train 7.691865 (lr=9.9411e-05) (hash(x)=23081598) +1615 train 7.425433 (lr=9.9405e-05) (hash(x)=23245699) +1616 train 7.372193 (lr=9.9399e-05) (hash(x)=23003072) +1617 train 7.664133 (lr=9.9392e-05) (hash(x)=27121904) +1618 train 7.409372 (lr=9.9386e-05) (hash(x)=25092305) +1619 train 7.456995 (lr=9.9379e-05) (hash(x)=23444521) +1620 train 7.448396 (lr=9.9372e-05) (hash(x)=22130531) +1621 train 7.182889 (lr=9.9366e-05) (hash(x)=20917937) +1622 train 7.348384 (lr=9.9359e-05) (hash(x)=22526838) +1623 train 7.456064 (lr=9.9353e-05) (hash(x)=21770300) +1624 train 8.596474 (lr=9.9346e-05) (hash(x)=22333537) +1625 train 8.610916 (lr=9.9339e-05) (hash(x)=24642519) +1626 train 7.765912 (lr=9.9332e-05) (hash(x)=25199038) +1627 train 7.546754 (lr=9.9325e-05) (hash(x)=23334569) +1628 train 7.453106 (lr=9.9319e-05) (hash(x)=23785360) +1629 train 7.118863 (lr=9.9312e-05) (hash(x)=21796200) +1630 train 7.178386 (lr=9.9305e-05) (hash(x)=22389081) +1631 train 7.449071 (lr=9.9298e-05) (hash(x)=25387532) +1632 train 6.995853 (lr=9.9291e-05) (hash(x)=17247578) +1633 train 7.357841 (lr=9.9284e-05) (hash(x)=22203733) +1634 train 7.553280 (lr=9.9277e-05) (hash(x)=24387455) +1635 train 8.081560 (lr=9.9270e-05) (hash(x)=29466743) +1636 train 7.397768 (lr=9.9263e-05) (hash(x)=25354152) +1637 train 7.512306 (lr=9.9255e-05) (hash(x)=21756102) +1638 train 7.436822 (lr=9.9248e-05) (hash(x)=23544029) +1639 train 7.578954 (lr=9.9241e-05) (hash(x)=27718703) +1640 train 7.532594 (lr=9.9234e-05) (hash(x)=25697138) +1641 train 7.370145 (lr=9.9226e-05) (hash(x)=22978681) +1642 train 7.908510 (lr=9.9219e-05) (hash(x)=29527067) +1643 train 7.002521 (lr=9.9212e-05) (hash(x)=17631973) +1644 train 7.437129 (lr=9.9204e-05) (hash(x)=24860172) +1645 train 7.764694 (lr=9.9197e-05) (hash(x)=27947891) +1646 train 7.516241 (lr=9.9190e-05) (hash(x)=23819556) +1647 train 7.514245 (lr=9.9182e-05) (hash(x)=27661052) +1648 train 7.314153 (lr=9.9174e-05) (hash(x)=23014209) +1649 train 7.245010 (lr=9.9167e-05) (hash(x)=23061452) +1650 val loss 7.4759 +1650 val perplexity 1764.9318 +1650 train 7.376585 (lr=9.9159e-05) (hash(x)=21949051) +1651 train 7.392902 (lr=9.9152e-05) (hash(x)=22244096) +1652 train 7.347905 (lr=9.9144e-05) (hash(x)=25997585) +1653 train 7.447517 (lr=9.9136e-05) (hash(x)=25389713) +1654 train 7.394194 (lr=9.9129e-05) (hash(x)=24390520) +1655 train 7.637126 (lr=9.9121e-05) (hash(x)=26538928) +1656 train 7.531452 (lr=9.9113e-05) (hash(x)=28708088) +1657 train 7.691043 (lr=9.9105e-05) (hash(x)=25685569) +1658 train 7.207916 (lr=9.9097e-05) (hash(x)=22163531) +1659 train 7.362077 (lr=9.9089e-05) (hash(x)=26256802) +1660 train 7.798995 (lr=9.9081e-05) (hash(x)=30016026) +1661 train 7.379456 (lr=9.9073e-05) (hash(x)=24412323) +1662 train 7.422559 (lr=9.9065e-05) (hash(x)=24722307) +1663 train 7.316232 (lr=9.9057e-05) (hash(x)=21772654) +1664 train 7.254829 (lr=9.9049e-05) (hash(x)=24984527) +1665 train 7.420322 (lr=9.9041e-05) (hash(x)=25456825) +1666 train 7.738033 (lr=9.9033e-05) (hash(x)=24383976) +1667 train 7.656590 (lr=9.9025e-05) (hash(x)=25026277) +1668 train 7.578587 (lr=9.9017e-05) (hash(x)=28121715) +1669 train 7.565839 (lr=9.9008e-05) (hash(x)=26855439) +1670 train 7.680259 (lr=9.9000e-05) (hash(x)=33370924) +1671 train 7.558134 (lr=9.8992e-05) (hash(x)=26263254) +1672 train 7.958613 (lr=9.8983e-05) (hash(x)=29958158) +1673 train 7.253134 (lr=9.8975e-05) (hash(x)=21917396) +1674 train 7.438924 (lr=9.8967e-05) (hash(x)=24196295) +1675 train 7.441872 (lr=9.8958e-05) (hash(x)=24726314) +1676 train 7.210462 (lr=9.8950e-05) (hash(x)=22137742) +1677 train 7.348825 (lr=9.8941e-05) (hash(x)=24375100) +1678 train 7.300235 (lr=9.8933e-05) (hash(x)=23965039) +1679 train 7.370009 (lr=9.8924e-05) (hash(x)=23552356) +1680 train 7.344107 (lr=9.8915e-05) (hash(x)=26136969) +1681 train 7.583508 (lr=9.8907e-05) (hash(x)=25343112) +1682 train 7.246088 (lr=9.8898e-05) (hash(x)=22831508) +1683 train 7.538913 (lr=9.8889e-05) (hash(x)=26699819) +1684 train 7.645973 (lr=9.8881e-05) (hash(x)=25435504) +1685 train 7.844914 (lr=9.8872e-05) (hash(x)=25218858) +1686 train 8.463086 (lr=9.8863e-05) (hash(x)=25664448) +1687 train 7.488420 (lr=9.8854e-05) (hash(x)=22707141) +1688 train 7.659462 (lr=9.8845e-05) (hash(x)=28001383) +1689 train 7.842801 (lr=9.8836e-05) (hash(x)=29168269) +1690 train 7.798914 (lr=9.8827e-05) (hash(x)=29637522) +1691 train 7.813694 (lr=9.8818e-05) (hash(x)=25676149) +1692 train 7.260183 (lr=9.8809e-05) (hash(x)=20919831) +1693 train 7.487841 (lr=9.8800e-05) (hash(x)=24324401) +1694 train 7.547260 (lr=9.8791e-05) (hash(x)=26862625) +1695 train 7.925104 (lr=9.8782e-05) (hash(x)=34234481) +1696 train 7.485803 (lr=9.8773e-05) (hash(x)=27415195) +1697 train 7.325102 (lr=9.8764e-05) (hash(x)=24511386) +1698 train 7.477888 (lr=9.8754e-05) (hash(x)=26904299) +1699 train 7.324034 (lr=9.8745e-05) (hash(x)=25401624) +1700 val loss 7.4523 +1700 val perplexity 1723.8466 +1700 train 7.374481 (lr=9.8736e-05) (hash(x)=26498489) +1701 train 7.391296 (lr=9.8726e-05) (hash(x)=22340685) +1702 train 7.453912 (lr=9.8717e-05) (hash(x)=26396757) +1703 train 8.022030 (lr=9.8708e-05) (hash(x)=35008670) +1704 train 7.802600 (lr=9.8698e-05) (hash(x)=31782020) +1705 train 7.708256 (lr=9.8689e-05) (hash(x)=29662286) +1706 train 7.859245 (lr=9.8679e-05) (hash(x)=34215782) +1707 train 7.382083 (lr=9.8670e-05) (hash(x)=25682280) +1708 train 7.567661 (lr=9.8660e-05) (hash(x)=27109048) +1709 train 7.622838 (lr=9.8651e-05) (hash(x)=27686498) +1710 train 7.409604 (lr=9.8641e-05) (hash(x)=24247565) +1711 train 7.455441 (lr=9.8631e-05) (hash(x)=25891543) +1712 train 7.553524 (lr=9.8621e-05) (hash(x)=26436778) +1713 train 7.203092 (lr=9.8612e-05) (hash(x)=22538881) +1714 train 7.156044 (lr=9.8602e-05) (hash(x)=21993512) +1715 train 7.686321 (lr=9.8592e-05) (hash(x)=25962407) +1716 train 7.475731 (lr=9.8582e-05) (hash(x)=24130284) +1717 train 7.313895 (lr=9.8572e-05) (hash(x)=24819073) +1718 train 7.182270 (lr=9.8563e-05) (hash(x)=23496648) +1719 train 7.240640 (lr=9.8553e-05) (hash(x)=21971224) +1720 train 7.132576 (lr=9.8543e-05) (hash(x)=21498081) +1721 train 7.210300 (lr=9.8533e-05) (hash(x)=20951317) +1722 train 7.687034 (lr=9.8523e-05) (hash(x)=28848134) +1723 train 7.732970 (lr=9.8512e-05) (hash(x)=30838142) +1724 train 7.683999 (lr=9.8502e-05) (hash(x)=28844392) +1725 train 7.329654 (lr=9.8492e-05) (hash(x)=23102419) +1726 train 7.363141 (lr=9.8482e-05) (hash(x)=22374479) +1727 train 7.640989 (lr=9.8472e-05) (hash(x)=27312186) +1728 train 7.954645 (lr=9.8462e-05) (hash(x)=34362559) +1729 train 7.858129 (lr=9.8451e-05) (hash(x)=30920030) +1730 train 7.243946 (lr=9.8441e-05) (hash(x)=23684126) +1731 train 7.469177 (lr=9.8431e-05) (hash(x)=23657081) +1732 train 7.642815 (lr=9.8420e-05) (hash(x)=28463299) +1733 train 7.933242 (lr=9.8410e-05) (hash(x)=35351214) +1734 train 7.458425 (lr=9.8399e-05) (hash(x)=28855662) +1735 train 7.008958 (lr=9.8389e-05) (hash(x)=22163749) +1736 train 7.054298 (lr=9.8378e-05) (hash(x)=22024585) +1737 train 7.262231 (lr=9.8368e-05) (hash(x)=24629160) +1738 train 7.359699 (lr=9.8357e-05) (hash(x)=25220941) +1739 train 7.296997 (lr=9.8347e-05) (hash(x)=24829818) +1740 train 7.645015 (lr=9.8336e-05) (hash(x)=28453898) +1741 train 7.709255 (lr=9.8325e-05) (hash(x)=25424550) +1742 train 7.356044 (lr=9.8315e-05) (hash(x)=23437814) +1743 train 7.393402 (lr=9.8304e-05) (hash(x)=25942888) +1744 train 7.399914 (lr=9.8293e-05) (hash(x)=24503801) +1745 train 7.663328 (lr=9.8282e-05) (hash(x)=26418501) +1746 train 7.560948 (lr=9.8271e-05) (hash(x)=27177691) +1747 train 7.285450 (lr=9.8260e-05) (hash(x)=23785671) +1748 train 7.711374 (lr=9.8249e-05) (hash(x)=27362772) +1749 train 7.453773 (lr=9.8239e-05) (hash(x)=25097859) +1750 val loss 7.4318 +1750 val perplexity 1688.9089 +1750 train 7.397357 (lr=9.8228e-05) (hash(x)=24662466) +1751 train 7.318053 (lr=9.8217e-05) (hash(x)=25493916) +1752 train 7.420856 (lr=9.8205e-05) (hash(x)=24655868) +1753 train 7.669025 (lr=9.8194e-05) (hash(x)=19819210) +1754 train 7.265428 (lr=9.8183e-05) (hash(x)=21377155) +1755 train 8.097730 (lr=9.8172e-05) (hash(x)=28618702) +1756 train 8.025474 (lr=9.8161e-05) (hash(x)=27324953) +1757 train 7.719892 (lr=9.8150e-05) (hash(x)=29707907) +1758 train 7.479365 (lr=9.8138e-05) (hash(x)=24485921) +1759 train 7.603380 (lr=9.8127e-05) (hash(x)=24289951) +1760 train 7.324706 (lr=9.8116e-05) (hash(x)=22496716) +1761 train 7.459314 (lr=9.8104e-05) (hash(x)=25147026) +1762 train 7.517076 (lr=9.8093e-05) (hash(x)=26851828) +1763 train 7.486136 (lr=9.8082e-05) (hash(x)=26331486) +1764 train 7.317941 (lr=9.8070e-05) (hash(x)=24383054) +1765 train 7.565468 (lr=9.8059e-05) (hash(x)=25885126) +1766 train 7.462944 (lr=9.8047e-05) (hash(x)=25848470) +1767 train 7.294460 (lr=9.8036e-05) (hash(x)=23648671) +1768 train 7.250833 (lr=9.8024e-05) (hash(x)=23168674) +1769 train 7.119879 (lr=9.8012e-05) (hash(x)=20252079) +1770 train 7.386022 (lr=9.8001e-05) (hash(x)=23914287) +1771 train 7.656206 (lr=9.7989e-05) (hash(x)=27292797) +1772 train 6.810091 (lr=9.7977e-05) (hash(x)=16175151) +1773 train 6.987397 (lr=9.7966e-05) (hash(x)=18317379) +1774 train 7.382342 (lr=9.7954e-05) (hash(x)=24464271) +1775 train 7.301078 (lr=9.7942e-05) (hash(x)=24992055) +1776 train 7.991748 (lr=9.7930e-05) (hash(x)=26032451) +1777 train 7.718616 (lr=9.7918e-05) (hash(x)=24734221) +1778 train 7.725537 (lr=9.7906e-05) (hash(x)=25413430) +1779 train 7.556351 (lr=9.7894e-05) (hash(x)=24398330) +1780 train 7.391904 (lr=9.7882e-05) (hash(x)=24568049) +1781 train 7.298171 (lr=9.7870e-05) (hash(x)=23573984) +1782 train 7.522724 (lr=9.7858e-05) (hash(x)=27338410) +1783 train 7.491463 (lr=9.7846e-05) (hash(x)=26005549) +1784 train 7.361574 (lr=9.7834e-05) (hash(x)=24332331) +1785 train 7.219684 (lr=9.7822e-05) (hash(x)=22583878) +1786 train 7.363845 (lr=9.7810e-05) (hash(x)=24599113) +1787 train 7.798728 (lr=9.7798e-05) (hash(x)=30259737) +1788 train 7.559614 (lr=9.7785e-05) (hash(x)=26504237) +1789 train 7.421225 (lr=9.7773e-05) (hash(x)=25196470) +1790 train 7.328633 (lr=9.7761e-05) (hash(x)=23607871) +1791 train 7.251710 (lr=9.7748e-05) (hash(x)=21046554) +1792 train 7.501821 (lr=9.7736e-05) (hash(x)=27285635) +1793 train 7.482577 (lr=9.7724e-05) (hash(x)=25454371) +1794 train 7.526433 (lr=9.7711e-05) (hash(x)=26486575) +1795 train 7.011604 (lr=9.7699e-05) (hash(x)=18773877) +1796 train 7.155341 (lr=9.7686e-05) (hash(x)=22506761) +1797 train 7.445928 (lr=9.7674e-05) (hash(x)=24645168) +1798 train 7.503385 (lr=9.7661e-05) (hash(x)=25046236) +1799 train 7.593579 (lr=9.7648e-05) (hash(x)=26321539) +1800 val loss 7.4121 +1800 val perplexity 1655.8232 +1800 train 7.339212 (lr=9.7636e-05) (hash(x)=24602494) +1801 train 7.520759 (lr=9.7623e-05) (hash(x)=25722713) +1802 train 7.248544 (lr=9.7610e-05) (hash(x)=23711219) +1803 train 7.395931 (lr=9.7598e-05) (hash(x)=22850804) +1804 train 7.697293 (lr=9.7585e-05) (hash(x)=25829388) +1805 train 7.220232 (lr=9.7572e-05) (hash(x)=22503524) +1806 train 7.498116 (lr=9.7559e-05) (hash(x)=26669453) +1807 train 7.416278 (lr=9.7546e-05) (hash(x)=27807872) +1808 train 7.454011 (lr=9.7533e-05) (hash(x)=23543560) +1809 train 7.582186 (lr=9.7520e-05) (hash(x)=25845590) +1810 train 7.365791 (lr=9.7507e-05) (hash(x)=23026635) +1811 train 7.316777 (lr=9.7494e-05) (hash(x)=25545137) +1812 train 7.828792 (lr=9.7481e-05) (hash(x)=27746841) +1813 train 7.203731 (lr=9.7468e-05) (hash(x)=25471231) +1814 train 7.357221 (lr=9.7455e-05) (hash(x)=24333204) +1815 train 7.172542 (lr=9.7442e-05) (hash(x)=21555364) +1816 train 7.429884 (lr=9.7429e-05) (hash(x)=26317977) +1817 train 7.491275 (lr=9.7416e-05) (hash(x)=24474988) +1818 train 7.156835 (lr=9.7402e-05) (hash(x)=21975953) +1819 train 7.756032 (lr=9.7389e-05) (hash(x)=27243798) +1820 train 7.364816 (lr=9.7376e-05) (hash(x)=25097367) +1821 train 7.310440 (lr=9.7362e-05) (hash(x)=24419085) +1822 train 7.239017 (lr=9.7349e-05) (hash(x)=23058837) +1823 train 7.396731 (lr=9.7336e-05) (hash(x)=26325324) +1824 train 7.120374 (lr=9.7322e-05) (hash(x)=20581023) +1825 train 7.464490 (lr=9.7309e-05) (hash(x)=24822111) +1826 train 7.210276 (lr=9.7295e-05) (hash(x)=24336304) +1827 train 7.353508 (lr=9.7282e-05) (hash(x)=26228728) +1828 train 7.465117 (lr=9.7268e-05) (hash(x)=26445781) +1829 train 7.553165 (lr=9.7254e-05) (hash(x)=24707042) +1830 train 7.840407 (lr=9.7241e-05) (hash(x)=27882744) +1831 train 7.344106 (lr=9.7227e-05) (hash(x)=24956294) +1832 train 7.131429 (lr=9.7213e-05) (hash(x)=20984728) +1833 train 7.192122 (lr=9.7200e-05) (hash(x)=23424737) +1834 train 7.526016 (lr=9.7186e-05) (hash(x)=26207120) +1835 train 7.599092 (lr=9.7172e-05) (hash(x)=25592289) +1836 train 7.267522 (lr=9.7158e-05) (hash(x)=24326649) +1837 train 7.428262 (lr=9.7144e-05) (hash(x)=26826109) +1838 train 7.369808 (lr=9.7131e-05) (hash(x)=24759294) +1839 train 7.384630 (lr=9.7117e-05) (hash(x)=24429389) +1840 train 7.329772 (lr=9.7103e-05) (hash(x)=25537519) +1841 train 7.304237 (lr=9.7089e-05) (hash(x)=24747421) +1842 train 7.199068 (lr=9.7075e-05) (hash(x)=23079065) +1843 train 7.624504 (lr=9.7061e-05) (hash(x)=28733708) +1844 train 7.362938 (lr=9.7046e-05) (hash(x)=23937742) +1845 train 7.625499 (lr=9.7032e-05) (hash(x)=29704803) +1846 train 7.814999 (lr=9.7018e-05) (hash(x)=34617155) +1847 train 7.522012 (lr=9.7004e-05) (hash(x)=27929846) +1848 train 7.900806 (lr=9.6990e-05) (hash(x)=28280878) +1849 train 6.928714 (lr=9.6976e-05) (hash(x)=18961171) +1850 val loss 7.4217 +1850 val perplexity 1671.9331 +1850 train 7.509269 (lr=9.6961e-05) (hash(x)=27146015) +1851 train 7.292832 (lr=9.6947e-05) (hash(x)=22417476) +1852 train 7.425663 (lr=9.6933e-05) (hash(x)=24583152) +1853 train 7.461938 (lr=9.6918e-05) (hash(x)=26364120) +1854 train 7.634904 (lr=9.6904e-05) (hash(x)=25946767) +1855 train 7.460590 (lr=9.6889e-05) (hash(x)=25282897) +1856 train 7.406744 (lr=9.6875e-05) (hash(x)=25154557) +1857 train 7.126847 (lr=9.6860e-05) (hash(x)=22082503) +1858 train 7.168303 (lr=9.6846e-05) (hash(x)=23974606) +1859 train 7.302906 (lr=9.6831e-05) (hash(x)=22278062) +1860 train 7.223392 (lr=9.6817e-05) (hash(x)=19509639) +1861 train 7.500202 (lr=9.6802e-05) (hash(x)=24271468) +1862 train 7.095600 (lr=9.6787e-05) (hash(x)=21943809) +1863 train 7.289443 (lr=9.6773e-05) (hash(x)=26802508) +1864 train 7.899676 (lr=9.6758e-05) (hash(x)=34178409) +1865 train 8.009926 (lr=9.6743e-05) (hash(x)=33468379) +1866 train 7.205641 (lr=9.6728e-05) (hash(x)=22109262) +1867 train 6.969067 (lr=9.6713e-05) (hash(x)=22094832) +1868 train 7.214456 (lr=9.6699e-05) (hash(x)=24016953) +1869 train 7.542691 (lr=9.6684e-05) (hash(x)=26759850) +1870 train 7.348718 (lr=9.6669e-05) (hash(x)=23570779) +1871 train 7.776452 (lr=9.6654e-05) (hash(x)=28390416) +1872 train 7.783852 (lr=9.6639e-05) (hash(x)=26215770) +1873 train 7.625124 (lr=9.6624e-05) (hash(x)=22727956) +1874 train 7.422798 (lr=9.6609e-05) (hash(x)=21304587) +1875 train 7.717017 (lr=9.6593e-05) (hash(x)=26379331) +1876 train 7.791904 (lr=9.6578e-05) (hash(x)=25252419) +1877 train 7.628366 (lr=9.6563e-05) (hash(x)=25048158) +1878 train 7.577814 (lr=9.6548e-05) (hash(x)=23588991) +1879 train 7.587068 (lr=9.6533e-05) (hash(x)=26292451) +1880 train 7.463929 (lr=9.6518e-05) (hash(x)=23617086) +1881 train 7.346846 (lr=9.6502e-05) (hash(x)=23336031) +1882 train 7.383061 (lr=9.6487e-05) (hash(x)=19198742) +1883 train 8.011502 (lr=9.6472e-05) (hash(x)=26301866) +1884 train 7.935305 (lr=9.6456e-05) (hash(x)=30114703) +1885 train 7.520323 (lr=9.6441e-05) (hash(x)=26687040) +1886 train 7.381042 (lr=9.6425e-05) (hash(x)=25810717) +1887 train 7.205831 (lr=9.6410e-05) (hash(x)=22915344) +1888 train 7.516150 (lr=9.6394e-05) (hash(x)=27046189) +1889 train 7.122968 (lr=9.6379e-05) (hash(x)=19831900) +1890 train 7.526109 (lr=9.6363e-05) (hash(x)=27786987) +1891 train 7.393745 (lr=9.6348e-05) (hash(x)=25448318) +1892 train 7.404613 (lr=9.6332e-05) (hash(x)=25166953) +1893 train 7.356683 (lr=9.6316e-05) (hash(x)=24993116) +1894 train 7.454364 (lr=9.6301e-05) (hash(x)=25748002) +1895 train 7.641526 (lr=9.6285e-05) (hash(x)=24744383) +1896 train 7.405171 (lr=9.6269e-05) (hash(x)=25560120) +1897 train 7.234173 (lr=9.6253e-05) (hash(x)=23731849) +1898 train 7.236158 (lr=9.6237e-05) (hash(x)=24115851) +1899 train 7.218469 (lr=9.6222e-05) (hash(x)=22835201) +1900 val loss 7.3832 +1900 val perplexity 1608.7281 +1900 train 7.040901 (lr=9.6206e-05) (hash(x)=21927896) +1901 train 7.433208 (lr=9.6190e-05) (hash(x)=24652361) +1902 train 7.567661 (lr=9.6174e-05) (hash(x)=27332405) +1903 train 7.407279 (lr=9.6158e-05) (hash(x)=26284678) +1904 train 7.329398 (lr=9.6142e-05) (hash(x)=23441305) +1905 train 7.438139 (lr=9.6126e-05) (hash(x)=27522881) +1906 train 7.491512 (lr=9.6110e-05) (hash(x)=25521191) +1907 train 7.301385 (lr=9.6093e-05) (hash(x)=24745936) +1908 train 7.178315 (lr=9.6077e-05) (hash(x)=21653364) +1909 train 7.261212 (lr=9.6061e-05) (hash(x)=21973969) +1910 train 7.252117 (lr=9.6045e-05) (hash(x)=24318192) +1911 train 7.180370 (lr=9.6029e-05) (hash(x)=21654269) +1912 train 7.248740 (lr=9.6012e-05) (hash(x)=24142904) +1913 train 7.130932 (lr=9.5996e-05) (hash(x)=21708739) +1914 train 7.340265 (lr=9.5980e-05) (hash(x)=22937923) +1915 train 7.928859 (lr=9.5963e-05) (hash(x)=32387999) +1916 train 8.086902 (lr=9.5947e-05) (hash(x)=28958671) +1917 train 8.137359 (lr=9.5930e-05) (hash(x)=32662682) +1918 train 8.047401 (lr=9.5914e-05) (hash(x)=31364539) +1919 train 8.100623 (lr=9.5897e-05) (hash(x)=29466268) +1920 train 8.083808 (lr=9.5881e-05) (hash(x)=31407564) +1921 train 7.924318 (lr=9.5864e-05) (hash(x)=28372973) +1922 train 8.041694 (lr=9.5848e-05) (hash(x)=28620993) +1923 train 8.089282 (lr=9.5831e-05) (hash(x)=30736727) +1924 train 7.982526 (lr=9.5814e-05) (hash(x)=30370374) +1925 train 7.926750 (lr=9.5798e-05) (hash(x)=29935562) +1926 train 7.908166 (lr=9.5781e-05) (hash(x)=30528627) +1927 train 7.960012 (lr=9.5764e-05) (hash(x)=32616762) +1928 train 7.776181 (lr=9.5748e-05) (hash(x)=29150044) +1929 train 7.979130 (lr=9.5731e-05) (hash(x)=32861403) +1930 train 7.923763 (lr=9.5714e-05) (hash(x)=31053918) +1931 train 7.823977 (lr=9.5697e-05) (hash(x)=29358578) +1932 train 7.933630 (lr=9.5680e-05) (hash(x)=31521292) +1933 train 7.845188 (lr=9.5663e-05) (hash(x)=31218966) +1934 train 7.873199 (lr=9.5646e-05) (hash(x)=31811872) +1935 train 8.043457 (lr=9.5629e-05) (hash(x)=32201138) +1936 train 7.798697 (lr=9.5612e-05) (hash(x)=28631348) +1937 train 7.889997 (lr=9.5595e-05) (hash(x)=30545133) +1938 train 7.937959 (lr=9.5578e-05) (hash(x)=32136080) +1939 train 8.018390 (lr=9.5561e-05) (hash(x)=30041621) +1940 train 7.799721 (lr=9.5544e-05) (hash(x)=30537181) +1941 train 7.819769 (lr=9.5526e-05) (hash(x)=30371023) +1942 train 7.961944 (lr=9.5509e-05) (hash(x)=30734634) +1943 train 7.884132 (lr=9.5492e-05) (hash(x)=33683468) +1944 train 7.920615 (lr=9.5475e-05) (hash(x)=30472451) +1945 train 7.773091 (lr=9.5457e-05) (hash(x)=29809830) +1946 train 7.584156 (lr=9.5440e-05) (hash(x)=26077593) +1947 train 7.535529 (lr=9.5423e-05) (hash(x)=26837755) +1948 train 7.509357 (lr=9.5405e-05) (hash(x)=23910920) +1949 train 7.494641 (lr=9.5388e-05) (hash(x)=26084089) +1950 val loss 7.4765 +1950 val perplexity 1765.9840 +1950 train 7.669034 (lr=9.5370e-05) (hash(x)=26963533) +1951 train 7.545027 (lr=9.5353e-05) (hash(x)=27498125) +1952 train 7.688615 (lr=9.5335e-05) (hash(x)=29512508) +1953 train 7.933879 (lr=9.5318e-05) (hash(x)=34478395) +1954 train 7.623395 (lr=9.5300e-05) (hash(x)=25357046) +1955 train 7.398530 (lr=9.5282e-05) (hash(x)=22372507) +1956 train 7.384389 (lr=9.5265e-05) (hash(x)=24501779) +1957 train 7.432466 (lr=9.5247e-05) (hash(x)=25638879) +1958 train 7.263442 (lr=9.5229e-05) (hash(x)=24243109) +1959 train 7.200738 (lr=9.5211e-05) (hash(x)=25164318) +1960 train 7.364195 (lr=9.5194e-05) (hash(x)=24139533) +1961 train 7.415610 (lr=9.5176e-05) (hash(x)=27271900) +1962 train 7.262756 (lr=9.5158e-05) (hash(x)=24869232) +1963 train 7.456609 (lr=9.5140e-05) (hash(x)=26562947) +1964 train 7.354466 (lr=9.5122e-05) (hash(x)=26477326) +1965 train 7.439659 (lr=9.5104e-05) (hash(x)=24917192) +1966 train 7.210030 (lr=9.5086e-05) (hash(x)=23110147) +1967 train 7.270374 (lr=9.5068e-05) (hash(x)=25690221) +1968 train 7.778417 (lr=9.5050e-05) (hash(x)=26999273) +1969 train 7.366109 (lr=9.5032e-05) (hash(x)=24807841) +1970 train 7.293334 (lr=9.5014e-05) (hash(x)=23918831) +1971 train 7.224725 (lr=9.4996e-05) (hash(x)=21947305) +1972 train 7.323404 (lr=9.4978e-05) (hash(x)=22874486) +1973 train 7.331963 (lr=9.4960e-05) (hash(x)=22195089) +1974 train 7.364048 (lr=9.4941e-05) (hash(x)=25345359) +1975 train 7.496216 (lr=9.4923e-05) (hash(x)=29031550) +1976 train 7.463796 (lr=9.4905e-05) (hash(x)=29947423) +1977 train 7.613786 (lr=9.4886e-05) (hash(x)=29395823) +1978 train 7.414834 (lr=9.4868e-05) (hash(x)=26968216) +1979 train 7.475563 (lr=9.4850e-05) (hash(x)=26551589) +1980 train 7.451082 (lr=9.4831e-05) (hash(x)=25657210) +1981 train 7.357472 (lr=9.4813e-05) (hash(x)=23689487) +1982 train 7.479733 (lr=9.4794e-05) (hash(x)=25744240) +1983 train 7.438456 (lr=9.4776e-05) (hash(x)=24094093) +1984 train 7.160108 (lr=9.4757e-05) (hash(x)=21724872) +1985 train 7.182761 (lr=9.4739e-05) (hash(x)=24106453) +1986 train 7.269586 (lr=9.4720e-05) (hash(x)=25004577) +1987 train 7.311450 (lr=9.4702e-05) (hash(x)=23639076) +1988 train 7.602857 (lr=9.4683e-05) (hash(x)=29408797) +1989 train 7.256337 (lr=9.4664e-05) (hash(x)=25107314) +1990 train 9.968402 (lr=9.4646e-05) (hash(x)=49896019) +1991 train 11.583695 (lr=9.4627e-05) (hash(x)=61455960) +1992 train 11.433439 (lr=9.4608e-05) (hash(x)=63788199) +1993 train 11.550307 (lr=9.4589e-05) (hash(x)=63899424) +1994 train 11.160883 (lr=9.4570e-05) (hash(x)=66412689) +1995 train 10.736119 (lr=9.4551e-05) (hash(x)=65636572) +1996 train 10.876654 (lr=9.4533e-05) (hash(x)=69649789) +1997 train 10.605784 (lr=9.4514e-05) (hash(x)=71578682) +1998 train 9.696266 (lr=9.4495e-05) (hash(x)=58341730) +1999 train 9.661384 (lr=9.4476e-05) (hash(x)=61104710) +2000 val loss 8.1768 +2000 val perplexity 3557.6147 +2000 train 9.200585 (lr=9.4457e-05) (hash(x)=52865322) +2001 train 8.379687 (lr=9.4438e-05) (hash(x)=23633693) +2002 train 8.400035 (lr=9.4419e-05) (hash(x)=25297571) +2003 train 8.583264 (lr=9.4399e-05) (hash(x)=24123821) +2004 train 8.018343 (lr=9.4380e-05) (hash(x)=20161517) +2005 train 7.816702 (lr=9.4361e-05) (hash(x)=19919984) +2006 train 7.683692 (lr=9.4342e-05) (hash(x)=18626507) +2007 train 7.778310 (lr=9.4323e-05) (hash(x)=20881126) +2008 train 7.823384 (lr=9.4303e-05) (hash(x)=26261448) +2009 train 7.838355 (lr=9.4284e-05) (hash(x)=27528050) +2010 train 7.838785 (lr=9.4265e-05) (hash(x)=26692097) +2011 train 7.549336 (lr=9.4245e-05) (hash(x)=23209969) +2012 train 7.502820 (lr=9.4226e-05) (hash(x)=26083446) +2013 train 7.699161 (lr=9.4207e-05) (hash(x)=28426467) +2014 train 7.485112 (lr=9.4187e-05) (hash(x)=26158154) +2015 train 7.582832 (lr=9.4168e-05) (hash(x)=26920243) +2016 train 7.301827 (lr=9.4148e-05) (hash(x)=21365321) +2017 train 7.436649 (lr=9.4129e-05) (hash(x)=25730699) +2018 train 7.492280 (lr=9.4109e-05) (hash(x)=25177106) +2019 train 7.405663 (lr=9.4089e-05) (hash(x)=26127756) +2020 train 6.960647 (lr=9.4070e-05) (hash(x)=19770037) +2021 train 7.406251 (lr=9.4050e-05) (hash(x)=26479346) +2022 train 7.452372 (lr=9.4030e-05) (hash(x)=25967643) +2023 train 7.341243 (lr=9.4011e-05) (hash(x)=21970343) +2024 train 7.546413 (lr=9.3991e-05) (hash(x)=26449648) +2025 train 7.498183 (lr=9.3971e-05) (hash(x)=24874094) +2026 train 7.117273 (lr=9.3951e-05) (hash(x)=21399697) +2027 train 7.337845 (lr=9.3931e-05) (hash(x)=24097897) +2028 train 7.395458 (lr=9.3912e-05) (hash(x)=24453548) +2029 train 7.459747 (lr=9.3892e-05) (hash(x)=26692093) +2030 train 7.312388 (lr=9.3872e-05) (hash(x)=27217002) +2031 train 7.676645 (lr=9.3852e-05) (hash(x)=31676352) +2032 train 7.367687 (lr=9.3832e-05) (hash(x)=23396350) +2033 train 7.354585 (lr=9.3812e-05) (hash(x)=26245173) +2034 train 7.403970 (lr=9.3792e-05) (hash(x)=24821033) +2035 train 7.450092 (lr=9.3772e-05) (hash(x)=23908053) +2036 train 7.226610 (lr=9.3752e-05) (hash(x)=23469373) +2037 train 7.268276 (lr=9.3731e-05) (hash(x)=24102198) +2038 train 7.312931 (lr=9.3711e-05) (hash(x)=24712135) +2039 train 7.508435 (lr=9.3691e-05) (hash(x)=25600562) +2040 train 7.437677 (lr=9.3671e-05) (hash(x)=23193393) +2041 train 7.425218 (lr=9.3650e-05) (hash(x)=24776954) +2042 train 7.531919 (lr=9.3630e-05) (hash(x)=28066546) +2043 train 7.148987 (lr=9.3610e-05) (hash(x)=23549168) +2044 train 7.211742 (lr=9.3590e-05) (hash(x)=22681487) +2045 train 7.361938 (lr=9.3569e-05) (hash(x)=26663184) +2046 train 7.360723 (lr=9.3549e-05) (hash(x)=23320809) +2047 train 7.235884 (lr=9.3528e-05) (hash(x)=22022924) +2048 train 7.527880 (lr=9.3508e-05) (hash(x)=27960930) +2049 train 7.321806 (lr=9.3487e-05) (hash(x)=24899178) +2050 val loss 7.3571 +2050 val perplexity 1567.3103 +2050 train 7.238761 (lr=9.3467e-05) (hash(x)=24450711) +2051 train 7.212597 (lr=9.3446e-05) (hash(x)=23294980) +2052 train 7.115702 (lr=9.3426e-05) (hash(x)=23243665) +2053 train 6.979260 (lr=9.3405e-05) (hash(x)=21004461) +2054 train 7.307242 (lr=9.3384e-05) (hash(x)=24493583) +2055 train 7.237287 (lr=9.3364e-05) (hash(x)=22777085) +2056 train 7.186096 (lr=9.3343e-05) (hash(x)=25169889) +2057 train 7.810291 (lr=9.3322e-05) (hash(x)=28395880) +2058 train 7.709615 (lr=9.3301e-05) (hash(x)=29603726) +2059 train 7.401039 (lr=9.3281e-05) (hash(x)=26271115) +2060 train 7.388737 (lr=9.3260e-05) (hash(x)=25616212) +2061 train 7.479687 (lr=9.3239e-05) (hash(x)=26398325) +2062 train 7.202235 (lr=9.3218e-05) (hash(x)=23836586) +2063 train 7.119380 (lr=9.3197e-05) (hash(x)=21727744) +2064 train 7.322962 (lr=9.3176e-05) (hash(x)=25183195) +2065 train 7.463408 (lr=9.3155e-05) (hash(x)=27108132) +2066 train 7.161251 (lr=9.3134e-05) (hash(x)=20987812) +2067 train 7.462093 (lr=9.3113e-05) (hash(x)=22729318) +2068 train 7.309678 (lr=9.3092e-05) (hash(x)=23129709) +2069 train 7.778791 (lr=9.3071e-05) (hash(x)=32820084) +2070 train 7.839276 (lr=9.3050e-05) (hash(x)=33763489) +2071 train 7.306186 (lr=9.3029e-05) (hash(x)=20701998) +2072 train 7.539376 (lr=9.3007e-05) (hash(x)=27765988) +2073 train 7.316176 (lr=9.2986e-05) (hash(x)=24157446) +2074 train 7.248422 (lr=9.2965e-05) (hash(x)=22014978) +2075 train 7.719910 (lr=9.2944e-05) (hash(x)=27928398) +2076 train 7.562911 (lr=9.2922e-05) (hash(x)=27880142) +2077 train 7.812881 (lr=9.2901e-05) (hash(x)=34991795) +2078 train 7.460542 (lr=9.2880e-05) (hash(x)=25944128) +2079 train 7.167021 (lr=9.2858e-05) (hash(x)=20863982) +2080 train 7.598068 (lr=9.2837e-05) (hash(x)=28036097) +2081 train 7.613956 (lr=9.2815e-05) (hash(x)=25813615) +2082 train 7.109401 (lr=9.2794e-05) (hash(x)=22862316) +2083 train 7.147624 (lr=9.2772e-05) (hash(x)=22827054) +2084 train 7.234077 (lr=9.2751e-05) (hash(x)=23996531) +2085 train 7.351546 (lr=9.2729e-05) (hash(x)=25756087) +2086 train 7.363837 (lr=9.2708e-05) (hash(x)=23165889) +2087 train 7.548309 (lr=9.2686e-05) (hash(x)=25084926) +2088 train 7.384036 (lr=9.2665e-05) (hash(x)=26063862) +2089 train 7.423720 (lr=9.2643e-05) (hash(x)=27843638) +2090 train 7.708993 (lr=9.2621e-05) (hash(x)=27375554) +2091 train 7.448667 (lr=9.2599e-05) (hash(x)=25540961) +2092 train 7.212790 (lr=9.2578e-05) (hash(x)=22933785) +2093 train 7.376614 (lr=9.2556e-05) (hash(x)=23996956) +2094 train 7.062139 (lr=9.2534e-05) (hash(x)=22915854) +2095 train 7.337296 (lr=9.2512e-05) (hash(x)=24412897) +2096 train 7.352556 (lr=9.2490e-05) (hash(x)=25152336) +2097 train 7.663269 (lr=9.2468e-05) (hash(x)=29525589) +2098 train 7.477965 (lr=9.2446e-05) (hash(x)=26435656) +2099 train 7.395745 (lr=9.2424e-05) (hash(x)=26269869) +2100 val loss 7.3460 +2100 val perplexity 1550.0273 +2100 train 7.169369 (lr=9.2402e-05) (hash(x)=23856783) +2101 train 7.420522 (lr=9.2380e-05) (hash(x)=26039611) +2102 train 7.180470 (lr=9.2358e-05) (hash(x)=25048861) +2103 train 7.295809 (lr=9.2336e-05) (hash(x)=25434913) +2104 train 7.440258 (lr=9.2314e-05) (hash(x)=24203891) +2105 train 7.329838 (lr=9.2292e-05) (hash(x)=26016998) +2106 train 7.428583 (lr=9.2270e-05) (hash(x)=23986767) +2107 train 7.357130 (lr=9.2248e-05) (hash(x)=25157653) +2108 train 7.483462 (lr=9.2225e-05) (hash(x)=30193751) +2109 train 7.365497 (lr=9.2203e-05) (hash(x)=22630574) +2110 train 7.243353 (lr=9.2181e-05) (hash(x)=23475467) +2111 train 7.520359 (lr=9.2158e-05) (hash(x)=26302544) +2112 train 7.304993 (lr=9.2136e-05) (hash(x)=21276592) +2113 train 7.565195 (lr=9.2114e-05) (hash(x)=27566393) +2114 train 7.294739 (lr=9.2091e-05) (hash(x)=25028015) +2115 train 7.061958 (lr=9.2069e-05) (hash(x)=22010703) +2116 train 7.400566 (lr=9.2046e-05) (hash(x)=23711709) +2117 train 7.447844 (lr=9.2024e-05) (hash(x)=26105026) +2118 train 7.795824 (lr=9.2001e-05) (hash(x)=34433894) +2119 train 7.875904 (lr=9.1979e-05) (hash(x)=34976197) +2120 train 7.380187 (lr=9.1956e-05) (hash(x)=27690727) +2121 train 7.236113 (lr=9.1934e-05) (hash(x)=24368234) +2122 train 7.206772 (lr=9.1911e-05) (hash(x)=25095726) +2123 train 7.403834 (lr=9.1888e-05) (hash(x)=28248301) +2124 train 7.168137 (lr=9.1866e-05) (hash(x)=23322302) +2125 train 7.623239 (lr=9.1843e-05) (hash(x)=26416200) +2126 train 7.282564 (lr=9.1820e-05) (hash(x)=26577567) +2127 train 7.332838 (lr=9.1797e-05) (hash(x)=23870805) +2128 train 7.258214 (lr=9.1775e-05) (hash(x)=25440544) +2129 train 7.388047 (lr=9.1752e-05) (hash(x)=25795021) +2130 train 7.221292 (lr=9.1729e-05) (hash(x)=20896402) +2131 train 7.240280 (lr=9.1706e-05) (hash(x)=24457252) +2132 train 7.353273 (lr=9.1683e-05) (hash(x)=25926760) +2133 train 7.213721 (lr=9.1660e-05) (hash(x)=23503725) +2134 train 7.767136 (lr=9.1637e-05) (hash(x)=28728828) +2135 train 7.269607 (lr=9.1614e-05) (hash(x)=25041103) +2136 train 7.300962 (lr=9.1591e-05) (hash(x)=22863770) +2137 train 7.175138 (lr=9.1568e-05) (hash(x)=23037755) +2138 train 7.379213 (lr=9.1545e-05) (hash(x)=25848413) +2139 train 7.428613 (lr=9.1522e-05) (hash(x)=25998487) +2140 train 7.288810 (lr=9.1499e-05) (hash(x)=22754440) +2141 train 7.517872 (lr=9.1475e-05) (hash(x)=27705382) +2142 train 7.563870 (lr=9.1452e-05) (hash(x)=27629095) +2143 train 7.406896 (lr=9.1429e-05) (hash(x)=26041745) +2144 train 7.212018 (lr=9.1406e-05) (hash(x)=21909712) +2145 train 7.390607 (lr=9.1382e-05) (hash(x)=24353905) +2146 train 7.305933 (lr=9.1359e-05) (hash(x)=24482587) +2147 train 7.429465 (lr=9.1336e-05) (hash(x)=27249810) +2148 train 7.554241 (lr=9.1312e-05) (hash(x)=26709938) +2149 train 7.210660 (lr=9.1289e-05) (hash(x)=23831457) +2150 val loss 7.3263 +2150 val perplexity 1519.8181 +2150 train 7.549266 (lr=9.1266e-05) (hash(x)=29776243) +2151 train 7.081358 (lr=9.1242e-05) (hash(x)=24068619) +2152 train 7.283151 (lr=9.1219e-05) (hash(x)=22208671) +2153 train 7.449821 (lr=9.1195e-05) (hash(x)=26680905) +2154 train 7.296283 (lr=9.1172e-05) (hash(x)=23567808) +2155 train 7.555337 (lr=9.1148e-05) (hash(x)=26359528) +2156 train 7.369514 (lr=9.1124e-05) (hash(x)=23787652) +2157 train 7.622348 (lr=9.1101e-05) (hash(x)=28347177) +2158 train 7.293718 (lr=9.1077e-05) (hash(x)=25266519) +2159 train 7.196327 (lr=9.1053e-05) (hash(x)=25441262) +2160 train 7.157899 (lr=9.1030e-05) (hash(x)=23959943) +2161 train 7.408196 (lr=9.1006e-05) (hash(x)=27888093) +2162 train 7.303717 (lr=9.0982e-05) (hash(x)=25547833) +2163 train 7.256354 (lr=9.0958e-05) (hash(x)=24413659) +2164 train 8.741388 (lr=9.0935e-05) (hash(x)=34397626) +2165 train 7.180147 (lr=9.0911e-05) (hash(x)=21159323) +2166 train 7.403095 (lr=9.0887e-05) (hash(x)=25360269) +2167 train 7.442857 (lr=9.0863e-05) (hash(x)=29181867) +2168 train 7.231674 (lr=9.0839e-05) (hash(x)=22501613) +2169 train 7.312149 (lr=9.0815e-05) (hash(x)=26469077) +2170 train 7.287474 (lr=9.0791e-05) (hash(x)=26665118) +2171 train 7.967572 (lr=9.0767e-05) (hash(x)=31551575) +2172 train 7.256455 (lr=9.0743e-05) (hash(x)=24803935) +2173 train 7.134781 (lr=9.0719e-05) (hash(x)=20896465) +2174 train 7.654171 (lr=9.0695e-05) (hash(x)=25702284) +2175 train 7.596988 (lr=9.0671e-05) (hash(x)=27093757) +2176 train 7.368248 (lr=9.0647e-05) (hash(x)=26024255) +2177 train 7.489920 (lr=9.0622e-05) (hash(x)=26443521) +2178 train 7.445979 (lr=9.0598e-05) (hash(x)=25478467) +2179 train 7.315368 (lr=9.0574e-05) (hash(x)=23624298) +2180 train 7.390514 (lr=9.0550e-05) (hash(x)=27304178) +2181 train 7.122838 (lr=9.0525e-05) (hash(x)=23016570) +2182 train 7.123189 (lr=9.0501e-05) (hash(x)=21073756) +2183 train 7.219768 (lr=9.0477e-05) (hash(x)=25150275) +2184 train 7.028125 (lr=9.0452e-05) (hash(x)=21004187) +2185 train 7.268645 (lr=9.0428e-05) (hash(x)=25876062) +2186 train 7.211702 (lr=9.0404e-05) (hash(x)=24221275) +2187 train 7.475940 (lr=9.0379e-05) (hash(x)=26239886) +2188 train 7.201730 (lr=9.0355e-05) (hash(x)=23299261) +2189 train 7.627392 (lr=9.0330e-05) (hash(x)=31024703) +2190 train 7.775284 (lr=9.0306e-05) (hash(x)=30084774) +2191 train 8.040596 (lr=9.0281e-05) (hash(x)=33457102) +2192 train 7.241947 (lr=9.0256e-05) (hash(x)=22423723) +2193 train 7.257112 (lr=9.0232e-05) (hash(x)=21989055) +2194 train 7.281559 (lr=9.0207e-05) (hash(x)=23286499) +2195 train 7.250037 (lr=9.0182e-05) (hash(x)=17499738) +2196 train 7.275844 (lr=9.0158e-05) (hash(x)=25329557) +2197 train 7.150320 (lr=9.0133e-05) (hash(x)=24195578) +2198 train 7.409891 (lr=9.0108e-05) (hash(x)=26646383) +2199 train 7.275305 (lr=9.0083e-05) (hash(x)=25755322) +2200 val loss 7.3030 +2200 val perplexity 1484.7085 +2200 train 7.347435 (lr=9.0059e-05) (hash(x)=27592223) +2201 train 7.531307 (lr=9.0034e-05) (hash(x)=26164625) +2202 train 7.387149 (lr=9.0009e-05) (hash(x)=21856341) +2203 train 7.263204 (lr=8.9984e-05) (hash(x)=23722795) +2204 train 7.345616 (lr=8.9959e-05) (hash(x)=25409645) +2205 train 7.276019 (lr=8.9934e-05) (hash(x)=23415339) +2206 train 7.258400 (lr=8.9909e-05) (hash(x)=24147928) +2207 train 7.167024 (lr=8.9884e-05) (hash(x)=23630794) +2208 train 7.276780 (lr=8.9859e-05) (hash(x)=27361452) +2209 train 7.285574 (lr=8.9834e-05) (hash(x)=25632158) +2210 train 7.112037 (lr=8.9809e-05) (hash(x)=21159789) +2211 train 7.249116 (lr=8.9784e-05) (hash(x)=23374168) +2212 train 7.284759 (lr=8.9759e-05) (hash(x)=24844739) +2213 train 7.180048 (lr=8.9734e-05) (hash(x)=23461285) +2214 train 7.237035 (lr=8.9708e-05) (hash(x)=27958481) +2215 train 7.154205 (lr=8.9683e-05) (hash(x)=25167987) +2216 train 7.330347 (lr=8.9658e-05) (hash(x)=22873204) +2217 train 7.952194 (lr=8.9633e-05) (hash(x)=31038116) +2218 train 7.396835 (lr=8.9607e-05) (hash(x)=28883155) +2219 train 7.299251 (lr=8.9582e-05) (hash(x)=30941010) +2220 train 7.276727 (lr=8.9557e-05) (hash(x)=24947521) +2221 train 7.347504 (lr=8.9531e-05) (hash(x)=22703293) +2222 train 7.272521 (lr=8.9506e-05) (hash(x)=23976007) +2223 train 7.226344 (lr=8.9480e-05) (hash(x)=24043224) +2224 train 7.138952 (lr=8.9455e-05) (hash(x)=23981093) +2225 train 7.272443 (lr=8.9430e-05) (hash(x)=26445994) +2226 train 7.585788 (lr=8.9404e-05) (hash(x)=27252393) +2227 train 7.538344 (lr=8.9378e-05) (hash(x)=29736627) +2228 train 7.466464 (lr=8.9353e-05) (hash(x)=24698933) +2229 train 7.132633 (lr=8.9327e-05) (hash(x)=24357840) +2230 train 7.270620 (lr=8.9302e-05) (hash(x)=25384498) +2231 train 7.431575 (lr=8.9276e-05) (hash(x)=24665411) +2232 train 7.287443 (lr=8.9250e-05) (hash(x)=24646352) +2233 train 7.259429 (lr=8.9225e-05) (hash(x)=25670741) +2234 train 7.299839 (lr=8.9199e-05) (hash(x)=26648242) +2235 train 7.572075 (lr=8.9173e-05) (hash(x)=27916043) +2236 train 7.292144 (lr=8.9147e-05) (hash(x)=25963100) +2237 train 7.362732 (lr=8.9122e-05) (hash(x)=27357379) +2238 train 7.151688 (lr=8.9096e-05) (hash(x)=21852360) +2239 train 7.061471 (lr=8.9070e-05) (hash(x)=17321657) +2240 train 7.000966 (lr=8.9044e-05) (hash(x)=18446645) +2241 train 6.841232 (lr=8.9018e-05) (hash(x)=17550988) +2242 train 7.284041 (lr=8.8992e-05) (hash(x)=27052347) +2243 train 7.136199 (lr=8.8966e-05) (hash(x)=23829833) +2244 train 7.377961 (lr=8.8940e-05) (hash(x)=27267264) +2245 train 7.574502 (lr=8.8914e-05) (hash(x)=24673611) +2246 train 7.510265 (lr=8.8888e-05) (hash(x)=25248507) +2247 train 7.752446 (lr=8.8862e-05) (hash(x)=27932591) +2248 train 7.572406 (lr=8.8836e-05) (hash(x)=26078877) +2249 train 7.640331 (lr=8.8810e-05) (hash(x)=26067367) +2250 val loss 7.3095 +2250 val perplexity 1494.3724 +2250 train 7.629164 (lr=8.8784e-05) (hash(x)=29143527) +2251 train 7.630521 (lr=8.8758e-05) (hash(x)=28206079) +2252 train 8.166834 (lr=8.8731e-05) (hash(x)=28894494) +2253 train 7.706875 (lr=8.8705e-05) (hash(x)=27977422) +2254 train 7.370323 (lr=8.8679e-05) (hash(x)=26446420) +2255 train 7.534102 (lr=8.8653e-05) (hash(x)=29447954) +2256 train 7.416091 (lr=8.8626e-05) (hash(x)=22181789) +2257 train 7.379810 (lr=8.8600e-05) (hash(x)=24976337) +2258 train 7.341047 (lr=8.8574e-05) (hash(x)=23277532) +2259 train 7.478186 (lr=8.8547e-05) (hash(x)=25935364) +2260 train 7.598431 (lr=8.8521e-05) (hash(x)=26988889) +2261 train 7.365674 (lr=8.8494e-05) (hash(x)=26887303) +2262 train 7.313022 (lr=8.8468e-05) (hash(x)=25021426) +2263 train 7.258947 (lr=8.8442e-05) (hash(x)=24621816) +2264 train 7.131543 (lr=8.8415e-05) (hash(x)=22132007) +2265 train 7.042737 (lr=8.8388e-05) (hash(x)=22648602) +2266 train 7.336933 (lr=8.8362e-05) (hash(x)=23132242) +2267 train 7.381040 (lr=8.8335e-05) (hash(x)=24070405) +2268 train 6.994016 (lr=8.8309e-05) (hash(x)=21412906) +2269 train 7.731239 (lr=8.8282e-05) (hash(x)=27547292) +2270 train 7.480199 (lr=8.8255e-05) (hash(x)=27740500) +2271 train 7.187518 (lr=8.8229e-05) (hash(x)=24682294) +2272 train 7.639990 (lr=8.8202e-05) (hash(x)=27969424) +2273 train 7.311761 (lr=8.8175e-05) (hash(x)=22172182) +2274 train 7.300608 (lr=8.8148e-05) (hash(x)=26485905) +2275 train 7.182308 (lr=8.8122e-05) (hash(x)=24050209) +2276 train 7.372203 (lr=8.8095e-05) (hash(x)=28802650) +2277 train 7.107923 (lr=8.8068e-05) (hash(x)=23644616) +2278 train 7.310755 (lr=8.8041e-05) (hash(x)=25409768) +2279 train 7.495898 (lr=8.8014e-05) (hash(x)=28057095) +2280 train 7.962677 (lr=8.7987e-05) (hash(x)=31689723) +2281 train 7.112563 (lr=8.7960e-05) (hash(x)=22252427) +2282 train 7.355461 (lr=8.7933e-05) (hash(x)=24142092) +2283 train 7.305022 (lr=8.7906e-05) (hash(x)=22523232) +2284 train 7.478622 (lr=8.7879e-05) (hash(x)=26017294) +2285 train 7.360403 (lr=8.7852e-05) (hash(x)=25025388) +2286 train 7.119000 (lr=8.7825e-05) (hash(x)=23819479) +2287 train 7.294262 (lr=8.7798e-05) (hash(x)=24547536) +2288 train 7.058488 (lr=8.7771e-05) (hash(x)=22622789) +2289 train 7.032804 (lr=8.7744e-05) (hash(x)=23874051) +2290 train 7.389180 (lr=8.7717e-05) (hash(x)=25015641) +2291 train 7.264043 (lr=8.7690e-05) (hash(x)=24978712) +2292 train 7.339063 (lr=8.7662e-05) (hash(x)=25311986) +2293 train 7.105177 (lr=8.7635e-05) (hash(x)=24298295) +2294 train 7.201923 (lr=8.7608e-05) (hash(x)=26481527) +2295 train 6.911346 (lr=8.7580e-05) (hash(x)=18987545) +2296 train 7.171516 (lr=8.7553e-05) (hash(x)=24617990) +2297 train 7.171642 (lr=8.7526e-05) (hash(x)=23903200) +2298 train 7.496759 (lr=8.7498e-05) (hash(x)=26278697) +2299 train 7.273841 (lr=8.7471e-05) (hash(x)=24092784) +2300 val loss 7.2777 +2300 val perplexity 1447.7188 +2300 train 7.211025 (lr=8.7444e-05) (hash(x)=22894919) +2301 train 7.276067 (lr=8.7416e-05) (hash(x)=24253964) +2302 train 7.213390 (lr=8.7389e-05) (hash(x)=23750610) +2303 train 7.249958 (lr=8.7361e-05) (hash(x)=26745063) +2304 train 7.056579 (lr=8.7334e-05) (hash(x)=21407001) +2305 train 7.464346 (lr=8.7306e-05) (hash(x)=26680082) +2306 train 7.371277 (lr=8.7278e-05) (hash(x)=26722122) +2307 train 7.202259 (lr=8.7251e-05) (hash(x)=22539112) +2308 train 6.983199 (lr=8.7223e-05) (hash(x)=19927356) +2309 train 7.099267 (lr=8.7196e-05) (hash(x)=21431267) +2310 train 7.015253 (lr=8.7168e-05) (hash(x)=21073487) +2311 train 7.039517 (lr=8.7140e-05) (hash(x)=21447406) +2312 train 7.012456 (lr=8.7112e-05) (hash(x)=22667253) +2313 train 6.994792 (lr=8.7085e-05) (hash(x)=20849089) +2314 train 7.001114 (lr=8.7057e-05) (hash(x)=19168351) +2315 train 7.009834 (lr=8.7029e-05) (hash(x)=21082139) +2316 train 7.003282 (lr=8.7001e-05) (hash(x)=21493530) +2317 train 6.944051 (lr=8.6973e-05) (hash(x)=19506447) +2318 train 7.075522 (lr=8.6946e-05) (hash(x)=23128797) +2319 train 7.177702 (lr=8.6918e-05) (hash(x)=24650655) +2320 train 6.958718 (lr=8.6890e-05) (hash(x)=21833080) +2321 train 7.491633 (lr=8.6862e-05) (hash(x)=26355512) +2322 train 7.637177 (lr=8.6834e-05) (hash(x)=26746363) +2323 train 7.117847 (lr=8.6806e-05) (hash(x)=22130721) +2324 train 7.463762 (lr=8.6778e-05) (hash(x)=28301752) +2325 train 7.309616 (lr=8.6750e-05) (hash(x)=26444359) +2326 train 7.644962 (lr=8.6722e-05) (hash(x)=24836130) +2327 train 8.112872 (lr=8.6694e-05) (hash(x)=26519976) +2328 train 9.683517 (lr=8.6665e-05) (hash(x)=35558906) +2329 train 7.673827 (lr=8.6637e-05) (hash(x)=30877729) +2330 train 7.532681 (lr=8.6609e-05) (hash(x)=28028485) +2331 train 7.656726 (lr=8.6581e-05) (hash(x)=25582440) +2332 train 7.995494 (lr=8.6553e-05) (hash(x)=29402491) +2333 train 7.308908 (lr=8.6524e-05) (hash(x)=25200284) +2334 train 7.319424 (lr=8.6496e-05) (hash(x)=26288480) +2335 train 7.081914 (lr=8.6468e-05) (hash(x)=20106514) +2336 train 7.091234 (lr=8.6440e-05) (hash(x)=22522123) +2337 train 7.108397 (lr=8.6411e-05) (hash(x)=23362041) +2338 train 7.220696 (lr=8.6383e-05) (hash(x)=26003099) +2339 train 7.241889 (lr=8.6354e-05) (hash(x)=25695510) +2340 train 7.260509 (lr=8.6326e-05) (hash(x)=27225904) +2341 train 6.999607 (lr=8.6298e-05) (hash(x)=21573008) +2342 train 7.459043 (lr=8.6269e-05) (hash(x)=21386628) +2343 train 7.221634 (lr=8.6241e-05) (hash(x)=20117808) +2344 train 7.342771 (lr=8.6212e-05) (hash(x)=21592790) +2345 train 7.262313 (lr=8.6184e-05) (hash(x)=19909192) +2346 train 7.386932 (lr=8.6155e-05) (hash(x)=22529262) +2347 train 7.430618 (lr=8.6126e-05) (hash(x)=24501900) +2348 train 7.231268 (lr=8.6098e-05) (hash(x)=25912171) +2349 train 7.339563 (lr=8.6069e-05) (hash(x)=25606665) +2350 val loss 7.2873 +2350 val perplexity 1461.5613 +2350 train 7.243436 (lr=8.6041e-05) (hash(x)=24487351) +2351 train 7.485913 (lr=8.6012e-05) (hash(x)=25510334) +2352 train 7.382000 (lr=8.5983e-05) (hash(x)=25357989) +2353 train 7.022101 (lr=8.5954e-05) (hash(x)=24656801) +2354 train 7.109513 (lr=8.5926e-05) (hash(x)=23312772) +2355 train 6.963347 (lr=8.5897e-05) (hash(x)=22099158) +2356 train 7.040122 (lr=8.5868e-05) (hash(x)=26507898) +2357 train 7.377231 (lr=8.5839e-05) (hash(x)=28351614) +2358 train 7.368436 (lr=8.5810e-05) (hash(x)=27489567) +2359 train 7.374716 (lr=8.5782e-05) (hash(x)=25749120) +2360 train 7.699848 (lr=8.5753e-05) (hash(x)=31711338) +2361 train 7.832639 (lr=8.5724e-05) (hash(x)=29645018) +2362 train 7.800963 (lr=8.5695e-05) (hash(x)=29713268) +2363 train 6.976130 (lr=8.5666e-05) (hash(x)=21720691) +2364 train 7.109052 (lr=8.5637e-05) (hash(x)=24316633) +2365 train 7.028809 (lr=8.5608e-05) (hash(x)=21597124) +2366 train 7.058042 (lr=8.5579e-05) (hash(x)=22520345) +2367 train 7.091152 (lr=8.5550e-05) (hash(x)=24357241) +2368 train 7.219082 (lr=8.5521e-05) (hash(x)=24085450) +2369 train 7.147810 (lr=8.5491e-05) (hash(x)=25136495) +2370 train 7.634660 (lr=8.5462e-05) (hash(x)=26073986) +2371 train 7.539937 (lr=8.5433e-05) (hash(x)=28911272) +2372 train 7.340642 (lr=8.5404e-05) (hash(x)=26667356) +2373 train 7.171861 (lr=8.5375e-05) (hash(x)=25225894) +2374 train 7.200359 (lr=8.5346e-05) (hash(x)=24404081) +2375 train 7.249054 (lr=8.5316e-05) (hash(x)=25584945) +2376 train 7.102266 (lr=8.5287e-05) (hash(x)=23831571) +2377 train 7.143669 (lr=8.5258e-05) (hash(x)=23521916) +2378 train 7.150081 (lr=8.5228e-05) (hash(x)=25318634) +2379 train 6.970850 (lr=8.5199e-05) (hash(x)=21847287) +2380 train 7.365528 (lr=8.5170e-05) (hash(x)=23877060) +2381 train 7.148109 (lr=8.5140e-05) (hash(x)=24069020) +2382 train 6.925205 (lr=8.5111e-05) (hash(x)=21724290) +2383 train 7.207216 (lr=8.5081e-05) (hash(x)=25198897) +2384 train 7.092941 (lr=8.5052e-05) (hash(x)=24109958) +2385 train 6.933299 (lr=8.5022e-05) (hash(x)=20122390) +2386 train 7.226129 (lr=8.4993e-05) (hash(x)=24062305) +2387 train 6.997215 (lr=8.4963e-05) (hash(x)=22436833) +2388 train 7.286058 (lr=8.4934e-05) (hash(x)=26013214) +2389 train 7.655356 (lr=8.4904e-05) (hash(x)=27691436) +2390 train 7.814809 (lr=8.4875e-05) (hash(x)=30802878) +2391 train 6.942753 (lr=8.4845e-05) (hash(x)=23475891) +2392 train 6.955529 (lr=8.4815e-05) (hash(x)=23118133) +2393 train 6.868847 (lr=8.4786e-05) (hash(x)=21469159) +2394 train 7.242414 (lr=8.4756e-05) (hash(x)=26444484) +2395 train 7.087527 (lr=8.4726e-05) (hash(x)=25083992) +2396 train 7.459487 (lr=8.4697e-05) (hash(x)=23461229) +2397 train 7.355222 (lr=8.4667e-05) (hash(x)=20441653) +2398 train 7.400091 (lr=8.4637e-05) (hash(x)=28024211) +2399 train 7.220272 (lr=8.4607e-05) (hash(x)=23644804) +2400 val loss 7.2571 +2400 val perplexity 1418.1428 +2400 train 7.043389 (lr=8.4577e-05) (hash(x)=26685301) +2401 train 6.910322 (lr=8.4548e-05) (hash(x)=20820913) +2402 train 7.055347 (lr=8.4518e-05) (hash(x)=22178190) +2403 train 7.665170 (lr=8.4488e-05) (hash(x)=31377168) +2404 train 7.859192 (lr=8.4458e-05) (hash(x)=33795307) +2405 train 7.963831 (lr=8.4428e-05) (hash(x)=34450341) +2406 train 7.168924 (lr=8.4398e-05) (hash(x)=25834183) +2407 train 7.428725 (lr=8.4368e-05) (hash(x)=25629584) +2408 train 7.185726 (lr=8.4338e-05) (hash(x)=25080123) +2409 train 7.079300 (lr=8.4308e-05) (hash(x)=21975628) +2410 train 7.632606 (lr=8.4278e-05) (hash(x)=27430197) +2411 train 7.798501 (lr=8.4248e-05) (hash(x)=29285135) +2412 train 7.512384 (lr=8.4218e-05) (hash(x)=24640105) +2413 train 7.588512 (lr=8.4188e-05) (hash(x)=29628864) +2414 train 7.804480 (lr=8.4157e-05) (hash(x)=30096444) +2415 train 7.627733 (lr=8.4127e-05) (hash(x)=29797280) +2416 train 6.964795 (lr=8.4097e-05) (hash(x)=22686143) +2417 train 7.600655 (lr=8.4067e-05) (hash(x)=28346842) +2418 train 7.576963 (lr=8.4037e-05) (hash(x)=28167937) +2419 train 7.792889 (lr=8.4006e-05) (hash(x)=33122326) +2420 train 7.846228 (lr=8.3976e-05) (hash(x)=33044913) +2421 train 7.626894 (lr=8.3946e-05) (hash(x)=31250981) +2422 train 7.877117 (lr=8.3915e-05) (hash(x)=29827111) +2423 train 7.799427 (lr=8.3885e-05) (hash(x)=30026394) +2424 train 7.963005 (lr=8.3855e-05) (hash(x)=26998238) +2425 train 7.922716 (lr=8.3824e-05) (hash(x)=24850684) +2426 train 8.102103 (lr=8.3794e-05) (hash(x)=36659853) +2427 train 8.003306 (lr=8.3763e-05) (hash(x)=34353164) +2428 train 7.292330 (lr=8.3733e-05) (hash(x)=23630644) +2429 train 7.235127 (lr=8.3702e-05) (hash(x)=24528186) +2430 train 7.147475 (lr=8.3672e-05) (hash(x)=22665222) +2431 train 7.288540 (lr=8.3641e-05) (hash(x)=26594177) +2432 train 7.610065 (lr=8.3611e-05) (hash(x)=29300546) +2433 train 7.041495 (lr=8.3580e-05) (hash(x)=21331715) +2434 train 7.311594 (lr=8.3550e-05) (hash(x)=26290885) +2435 train 7.232109 (lr=8.3519e-05) (hash(x)=25554738) +2436 train 7.512748 (lr=8.3488e-05) (hash(x)=26744311) +2437 train 7.440485 (lr=8.3458e-05) (hash(x)=26872344) +2438 train 7.452415 (lr=8.3427e-05) (hash(x)=27636081) +2439 train 7.262796 (lr=8.3396e-05) (hash(x)=23766256) +2440 train 7.382935 (lr=8.3366e-05) (hash(x)=24434438) +2441 train 7.169082 (lr=8.3335e-05) (hash(x)=22992618) +2442 train 7.061765 (lr=8.3304e-05) (hash(x)=22393467) +2443 train 7.355365 (lr=8.3273e-05) (hash(x)=26853444) +2444 train 7.250920 (lr=8.3242e-05) (hash(x)=25101020) +2445 train 7.152129 (lr=8.3212e-05) (hash(x)=24705456) +2446 train 7.482802 (lr=8.3181e-05) (hash(x)=26798611) +2447 train 7.138916 (lr=8.3150e-05) (hash(x)=24250150) +2448 train 7.205715 (lr=8.3119e-05) (hash(x)=24494331) +2449 train 7.217046 (lr=8.3088e-05) (hash(x)=27579257) +2450 val loss 7.2633 +2450 val perplexity 1426.9698 +2450 train 6.990164 (lr=8.3057e-05) (hash(x)=22377407) +2451 train 7.293854 (lr=8.3026e-05) (hash(x)=26289588) +2452 train 7.170987 (lr=8.2995e-05) (hash(x)=25871900) +2453 train 7.080434 (lr=8.2964e-05) (hash(x)=23437197) +2454 train 7.370845 (lr=8.2933e-05) (hash(x)=23557786) +2455 train 7.266783 (lr=8.2902e-05) (hash(x)=26108817) +2456 train 7.180434 (lr=8.2871e-05) (hash(x)=26440482) +2457 train 7.176221 (lr=8.2840e-05) (hash(x)=24583191) +2458 train 7.190712 (lr=8.2809e-05) (hash(x)=23756440) +2459 train 7.052144 (lr=8.2778e-05) (hash(x)=23814987) +2460 train 7.448923 (lr=8.2746e-05) (hash(x)=28508433) +2461 train 7.086175 (lr=8.2715e-05) (hash(x)=25692442) +2462 train 7.067592 (lr=8.2684e-05) (hash(x)=24699197) +2463 train 6.761191 (lr=8.2653e-05) (hash(x)=18582688) +2464 train 7.089777 (lr=8.2621e-05) (hash(x)=23266625) +2465 train 7.452682 (lr=8.2590e-05) (hash(x)=26565489) +2466 train 6.923781 (lr=8.2559e-05) (hash(x)=21686599) +2467 train 7.176549 (lr=8.2528e-05) (hash(x)=25558792) +2468 train 6.989615 (lr=8.2496e-05) (hash(x)=25110035) +2469 train 7.351989 (lr=8.2465e-05) (hash(x)=26263661) +2470 train 7.077378 (lr=8.2434e-05) (hash(x)=22282189) +2471 train 7.076295 (lr=8.2402e-05) (hash(x)=23272705) +2472 train 7.177516 (lr=8.2371e-05) (hash(x)=25300067) +2473 train 7.375316 (lr=8.2339e-05) (hash(x)=26802369) +2474 train 7.026335 (lr=8.2308e-05) (hash(x)=24646471) +2475 train 7.030842 (lr=8.2276e-05) (hash(x)=24709241) +2476 train 7.123580 (lr=8.2245e-05) (hash(x)=26747197) +2477 train 7.185779 (lr=8.2213e-05) (hash(x)=25201108) +2478 train 7.228471 (lr=8.2182e-05) (hash(x)=24962427) +2479 train 7.076988 (lr=8.2150e-05) (hash(x)=24793412) +2480 train 7.167375 (lr=8.2119e-05) (hash(x)=24452301) +2481 train 7.174242 (lr=8.2087e-05) (hash(x)=25177251) +2482 train 7.081955 (lr=8.2055e-05) (hash(x)=25801499) +2483 train 7.273290 (lr=8.2024e-05) (hash(x)=27256707) +2484 train 7.532939 (lr=8.1992e-05) (hash(x)=25303237) +2485 train 7.147523 (lr=8.1960e-05) (hash(x)=21641481) +2486 train 7.091980 (lr=8.1929e-05) (hash(x)=23818831) +2487 train 6.876251 (lr=8.1897e-05) (hash(x)=19280989) +2488 train 7.217847 (lr=8.1865e-05) (hash(x)=24075167) +2489 train 7.248451 (lr=8.1833e-05) (hash(x)=26651546) +2490 train 7.180351 (lr=8.1801e-05) (hash(x)=25367186) +2491 train 7.132442 (lr=8.1770e-05) (hash(x)=26508642) +2492 train 7.236092 (lr=8.1738e-05) (hash(x)=25294182) +2493 train 7.098199 (lr=8.1706e-05) (hash(x)=23916886) +2494 train 7.013870 (lr=8.1674e-05) (hash(x)=21189910) +2495 train 7.103362 (lr=8.1642e-05) (hash(x)=22751150) +2496 train 7.529450 (lr=8.1610e-05) (hash(x)=26608502) +2497 train 7.955255 (lr=8.1578e-05) (hash(x)=25372010) +2498 train 7.186715 (lr=8.1546e-05) (hash(x)=22006251) +2499 train 7.130632 (lr=8.1514e-05) (hash(x)=23880160) +2500 val loss 7.2456 +2500 val perplexity 1401.9304 +2500 train 7.046248 (lr=8.1482e-05) (hash(x)=23225337) +2501 train 7.194190 (lr=8.1450e-05) (hash(x)=24932950) +2502 train 6.943300 (lr=8.1418e-05) (hash(x)=20022340) +2503 train 7.316518 (lr=8.1386e-05) (hash(x)=23537942) +2504 train 7.220870 (lr=8.1354e-05) (hash(x)=24884288) +2505 train 6.873021 (lr=8.1322e-05) (hash(x)=21296580) +2506 train 7.120688 (lr=8.1290e-05) (hash(x)=23001455) +2507 train 7.408484 (lr=8.1258e-05) (hash(x)=26975313) +2508 train 7.394467 (lr=8.1226e-05) (hash(x)=26029962) +2509 train 7.115604 (lr=8.1193e-05) (hash(x)=24302204) +2510 train 6.820881 (lr=8.1161e-05) (hash(x)=22997203) +2511 train 6.947347 (lr=8.1129e-05) (hash(x)=23748375) +2512 train 7.173843 (lr=8.1097e-05) (hash(x)=24453191) +2513 train 6.857778 (lr=8.1064e-05) (hash(x)=22026776) +2514 train 6.933522 (lr=8.1032e-05) (hash(x)=19934168) +2515 train 7.268282 (lr=8.1000e-05) (hash(x)=25541754) +2516 train 7.603858 (lr=8.0967e-05) (hash(x)=26604471) +2517 train 7.582002 (lr=8.0935e-05) (hash(x)=27900386) +2518 train 7.539437 (lr=8.0903e-05) (hash(x)=26403431) +2519 train 7.559876 (lr=8.0870e-05) (hash(x)=27413825) +2520 train 7.624435 (lr=8.0838e-05) (hash(x)=28332637) +2521 train 7.473042 (lr=8.0806e-05) (hash(x)=27223027) +2522 train 7.429119 (lr=8.0773e-05) (hash(x)=23843387) +2523 train 7.430352 (lr=8.0741e-05) (hash(x)=27075951) +2524 train 7.589894 (lr=8.0708e-05) (hash(x)=29300154) +2525 train 7.273842 (lr=8.0676e-05) (hash(x)=28100582) +2526 train 7.408080 (lr=8.0643e-05) (hash(x)=28051084) +2527 train 7.123979 (lr=8.0611e-05) (hash(x)=21682445) +2528 train 7.313963 (lr=8.0578e-05) (hash(x)=24062589) +2529 train 7.498386 (lr=8.0545e-05) (hash(x)=29616079) +2530 train 7.418300 (lr=8.0513e-05) (hash(x)=25170523) +2531 train 7.026035 (lr=8.0480e-05) (hash(x)=23361504) +2532 train 7.198094 (lr=8.0447e-05) (hash(x)=24444462) +2533 train 7.186713 (lr=8.0415e-05) (hash(x)=24035993) +2534 train 7.177400 (lr=8.0382e-05) (hash(x)=24696651) +2535 train 7.169126 (lr=8.0349e-05) (hash(x)=22040184) +2536 train 7.059067 (lr=8.0317e-05) (hash(x)=27400103) +2537 train 7.402420 (lr=8.0284e-05) (hash(x)=27383080) +2538 train 7.201631 (lr=8.0251e-05) (hash(x)=24212212) +2539 train 7.034242 (lr=8.0218e-05) (hash(x)=23727731) +2540 train 7.187125 (lr=8.0186e-05) (hash(x)=24149487) +2541 train 6.966671 (lr=8.0153e-05) (hash(x)=23794649) +2542 train 7.146671 (lr=8.0120e-05) (hash(x)=26147774) +2543 train 7.305170 (lr=8.0087e-05) (hash(x)=24463229) +2544 train 7.337552 (lr=8.0054e-05) (hash(x)=26361238) +2545 train 7.012348 (lr=8.0021e-05) (hash(x)=18891545) +2546 train 7.524085 (lr=7.9988e-05) (hash(x)=30380438) +2547 train 7.754784 (lr=7.9955e-05) (hash(x)=32663792) +2548 train 7.129684 (lr=7.9922e-05) (hash(x)=25175499) +2549 train 7.291333 (lr=7.9889e-05) (hash(x)=26702407) +2550 val loss 7.2411 +2550 val perplexity 1395.5609 +2550 train 7.176040 (lr=7.9856e-05) (hash(x)=24578061) +2551 train 7.189266 (lr=7.9823e-05) (hash(x)=24091954) +2552 train 7.211392 (lr=7.9790e-05) (hash(x)=23041778) +2553 train 6.971749 (lr=7.9757e-05) (hash(x)=23686239) +2554 train 7.071661 (lr=7.9724e-05) (hash(x)=22745355) +2555 train 7.159893 (lr=7.9691e-05) (hash(x)=23599013) +2556 train 7.065262 (lr=7.9658e-05) (hash(x)=26033088) +2557 train 7.152458 (lr=7.9625e-05) (hash(x)=21634218) +2558 train 7.058867 (lr=7.9592e-05) (hash(x)=20985281) +2559 train 7.329015 (lr=7.9559e-05) (hash(x)=26670219) +2560 train 7.095412 (lr=7.9525e-05) (hash(x)=26499936) +2561 train 7.174282 (lr=7.9492e-05) (hash(x)=23547908) +2562 train 7.058046 (lr=7.9459e-05) (hash(x)=22306373) +2563 train 7.200162 (lr=7.9426e-05) (hash(x)=24380893) +2564 train 7.091991 (lr=7.9392e-05) (hash(x)=23726190) +2565 train 7.159463 (lr=7.9359e-05) (hash(x)=26967512) +2566 train 7.222157 (lr=7.9326e-05) (hash(x)=23414576) +2567 train 7.471991 (lr=7.9292e-05) (hash(x)=25558986) +2568 train 7.352828 (lr=7.9259e-05) (hash(x)=27057505) +2569 train 7.313040 (lr=7.9226e-05) (hash(x)=26048135) +2570 train 7.277523 (lr=7.9192e-05) (hash(x)=26991032) +2571 train 7.319695 (lr=7.9159e-05) (hash(x)=25729492) +2572 train 6.875146 (lr=7.9126e-05) (hash(x)=20611723) +2573 train 7.002118 (lr=7.9092e-05) (hash(x)=24563606) +2574 train 7.075395 (lr=7.9059e-05) (hash(x)=23330043) +2575 train 7.107999 (lr=7.9025e-05) (hash(x)=19218943) +2576 train 7.473648 (lr=7.8992e-05) (hash(x)=20985122) +2577 train 7.108492 (lr=7.8958e-05) (hash(x)=24133609) +2578 train 7.429964 (lr=7.8925e-05) (hash(x)=28368610) +2579 train 7.115589 (lr=7.8891e-05) (hash(x)=23952206) +2580 train 7.052817 (lr=7.8858e-05) (hash(x)=23068957) +2581 train 7.143063 (lr=7.8824e-05) (hash(x)=25365277) +2582 train 7.497603 (lr=7.8790e-05) (hash(x)=24721184) +2583 train 7.208568 (lr=7.8757e-05) (hash(x)=24551402) +2584 train 6.925717 (lr=7.8723e-05) (hash(x)=20469327) +2585 train 7.335097 (lr=7.8689e-05) (hash(x)=24966478) +2586 train 7.072318 (lr=7.8656e-05) (hash(x)=18626184) +2587 train 7.086159 (lr=7.8622e-05) (hash(x)=24007642) +2588 train 7.043004 (lr=7.8588e-05) (hash(x)=23521875) +2589 train 7.275438 (lr=7.8555e-05) (hash(x)=25204207) +2590 train 7.051706 (lr=7.8521e-05) (hash(x)=25449801) +2591 train 7.248460 (lr=7.8487e-05) (hash(x)=25229281) +2592 train 7.107719 (lr=7.8453e-05) (hash(x)=23202696) +2593 train 6.961912 (lr=7.8420e-05) (hash(x)=22435944) +2594 train 6.986125 (lr=7.8386e-05) (hash(x)=20787439) +2595 train 6.523028 (lr=7.8352e-05) (hash(x)=18214283) +2596 train 6.739177 (lr=7.8318e-05) (hash(x)=20851477) +2597 train 6.729547 (lr=7.8284e-05) (hash(x)=20609675) +2598 train 6.850606 (lr=7.8250e-05) (hash(x)=20061218) +2599 train 6.889063 (lr=7.8216e-05) (hash(x)=21251127) +2600 val loss 7.2290 +2600 val perplexity 1378.8595 +2600 train 7.449707 (lr=7.8182e-05) (hash(x)=30948038) +2601 train 7.677385 (lr=7.8148e-05) (hash(x)=32279160) +2602 train 7.311376 (lr=7.8114e-05) (hash(x)=26607151) +2603 train 7.204645 (lr=7.8080e-05) (hash(x)=25097619) +2604 train 6.763173 (lr=7.8046e-05) (hash(x)=20892421) +2605 train 6.972365 (lr=7.8012e-05) (hash(x)=22212821) +2606 train 7.288909 (lr=7.7978e-05) (hash(x)=24720588) +2607 train 7.259151 (lr=7.7944e-05) (hash(x)=25800857) +2608 train 7.069077 (lr=7.7910e-05) (hash(x)=22901279) +2609 train 6.971006 (lr=7.7876e-05) (hash(x)=20921910) +2610 train 7.177587 (lr=7.7842e-05) (hash(x)=24846267) +2611 train 7.043622 (lr=7.7808e-05) (hash(x)=22918428) +2612 train 6.986376 (lr=7.7774e-05) (hash(x)=22805901) +2613 train 7.198064 (lr=7.7740e-05) (hash(x)=24345816) +2614 train 7.018367 (lr=7.7705e-05) (hash(x)=22962012) +2615 train 7.278886 (lr=7.7671e-05) (hash(x)=25836189) +2616 train 7.307697 (lr=7.7637e-05) (hash(x)=27922916) +2617 train 7.052021 (lr=7.7603e-05) (hash(x)=21697866) +2618 train 7.048131 (lr=7.7569e-05) (hash(x)=24283369) +2619 train 6.949728 (lr=7.7534e-05) (hash(x)=24504567) +2620 train 7.067414 (lr=7.7500e-05) (hash(x)=25557725) +2621 train 7.120831 (lr=7.7466e-05) (hash(x)=23135849) +2622 train 7.052707 (lr=7.7431e-05) (hash(x)=22888908) +2623 train 7.237929 (lr=7.7397e-05) (hash(x)=25999255) +2624 train 7.097707 (lr=7.7363e-05) (hash(x)=24446851) +2625 train 6.832132 (lr=7.7328e-05) (hash(x)=21137520) +2626 train 7.155792 (lr=7.7294e-05) (hash(x)=26245754) +2627 train 7.511257 (lr=7.7260e-05) (hash(x)=27308968) +2628 train 7.269405 (lr=7.7225e-05) (hash(x)=23961169) +2629 train 7.203412 (lr=7.7191e-05) (hash(x)=25924731) +2630 train 7.257740 (lr=7.7156e-05) (hash(x)=25782315) +2631 train 7.285024 (lr=7.7122e-05) (hash(x)=20149394) +2632 train 7.370693 (lr=7.7087e-05) (hash(x)=23801981) +2633 train 7.133825 (lr=7.7053e-05) (hash(x)=23830286) +2634 train 7.095954 (lr=7.7018e-05) (hash(x)=25325236) +2635 train 7.083118 (lr=7.6984e-05) (hash(x)=24498556) +2636 train 7.061827 (lr=7.6949e-05) (hash(x)=23693078) +2637 train 7.223608 (lr=7.6914e-05) (hash(x)=25484922) +2638 train 6.880971 (lr=7.6880e-05) (hash(x)=22645025) +2639 train 6.874373 (lr=7.6845e-05) (hash(x)=21999338) +2640 train 7.102464 (lr=7.6811e-05) (hash(x)=21758019) +2641 train 7.051405 (lr=7.6776e-05) (hash(x)=24064168) +2642 train 7.080467 (lr=7.6741e-05) (hash(x)=26847292) +2643 train 6.932977 (lr=7.6707e-05) (hash(x)=23280568) +2644 train 6.941515 (lr=7.6672e-05) (hash(x)=21749161) +2645 train 7.610134 (lr=7.6637e-05) (hash(x)=30082352) +2646 train 7.453617 (lr=7.6603e-05) (hash(x)=28334297) +2647 train 7.602986 (lr=7.6568e-05) (hash(x)=27611302) +2648 train 8.030151 (lr=7.6533e-05) (hash(x)=31007436) +2649 train 6.873607 (lr=7.6498e-05) (hash(x)=22356183) +2650 val loss 7.2351 +2650 val perplexity 1387.2290 +2650 train 6.951745 (lr=7.6463e-05) (hash(x)=23071731) +2651 train 6.953683 (lr=7.6429e-05) (hash(x)=23982308) +2652 train 7.315399 (lr=7.6394e-05) (hash(x)=25673823) +2653 train 7.084527 (lr=7.6359e-05) (hash(x)=22973788) +2654 train 7.253745 (lr=7.6324e-05) (hash(x)=25386647) +2655 train 6.976453 (lr=7.6289e-05) (hash(x)=22778356) +2656 train 7.244457 (lr=7.6254e-05) (hash(x)=26669130) +2657 train 6.912775 (lr=7.6219e-05) (hash(x)=23542930) +2658 train 7.061801 (lr=7.6184e-05) (hash(x)=23307871) +2659 train 7.029367 (lr=7.6150e-05) (hash(x)=23467046) +2660 train 7.178328 (lr=7.6115e-05) (hash(x)=24728872) +2661 train 7.762254 (lr=7.6080e-05) (hash(x)=29719902) +2662 train 7.084755 (lr=7.6045e-05) (hash(x)=25114165) +2663 train 7.008303 (lr=7.6010e-05) (hash(x)=24195959) +2664 train 7.210104 (lr=7.5975e-05) (hash(x)=26938509) +2665 train 7.402573 (lr=7.5940e-05) (hash(x)=27168434) +2666 train 7.567108 (lr=7.5904e-05) (hash(x)=27488221) +2667 train 8.289969 (lr=7.5869e-05) (hash(x)=32710438) +2668 train 7.357002 (lr=7.5834e-05) (hash(x)=25073185) +2669 train 7.351825 (lr=7.5799e-05) (hash(x)=26951664) +2670 train 7.493211 (lr=7.5764e-05) (hash(x)=24886228) +2671 train 6.973970 (lr=7.5729e-05) (hash(x)=19127465) +2672 train 7.229761 (lr=7.5694e-05) (hash(x)=27134917) +2673 train 7.208239 (lr=7.5659e-05) (hash(x)=25673955) +2674 train 7.709810 (lr=7.5623e-05) (hash(x)=27111776) +2675 train 7.629849 (lr=7.5588e-05) (hash(x)=28962580) +2676 train 7.169705 (lr=7.5553e-05) (hash(x)=25593381) +2677 train 7.221689 (lr=7.5518e-05) (hash(x)=25238916) +2678 train 7.092689 (lr=7.5482e-05) (hash(x)=27453574) +2679 train 7.076344 (lr=7.5447e-05) (hash(x)=22426274) +2680 train 7.092131 (lr=7.5412e-05) (hash(x)=22974780) +2681 train 7.102254 (lr=7.5377e-05) (hash(x)=24668644) +2682 train 7.113407 (lr=7.5341e-05) (hash(x)=26182084) +2683 train 7.322803 (lr=7.5306e-05) (hash(x)=25606512) +2684 train 7.146583 (lr=7.5271e-05) (hash(x)=24885252) +2685 train 6.933522 (lr=7.5235e-05) (hash(x)=21290254) +2686 train 6.847473 (lr=7.5200e-05) (hash(x)=21367078) +2687 train 7.068842 (lr=7.5165e-05) (hash(x)=23785205) +2688 train 6.968710 (lr=7.5129e-05) (hash(x)=24640056) +2689 train 7.428986 (lr=7.5094e-05) (hash(x)=27083886) +2690 train 7.101662 (lr=7.5058e-05) (hash(x)=23603571) +2691 train 7.190720 (lr=7.5023e-05) (hash(x)=24779414) +2692 train 6.878998 (lr=7.4987e-05) (hash(x)=22200693) +2693 train 7.164819 (lr=7.4952e-05) (hash(x)=26907868) +2694 train 7.575682 (lr=7.4916e-05) (hash(x)=32034827) +2695 train 7.422646 (lr=7.4881e-05) (hash(x)=28505676) +2696 train 7.032067 (lr=7.4845e-05) (hash(x)=23805750) +2697 train 7.378057 (lr=7.4810e-05) (hash(x)=29804750) +2698 train 7.669556 (lr=7.4774e-05) (hash(x)=28443583) +2699 train 7.551099 (lr=7.4739e-05) (hash(x)=29156288) +2700 val loss 7.2362 +2700 val perplexity 1388.8546 +2700 train 7.229923 (lr=7.4703e-05) (hash(x)=25895743) +2701 train 6.868848 (lr=7.4667e-05) (hash(x)=21173795) +2702 train 6.781389 (lr=7.4632e-05) (hash(x)=20790866) +2703 train 7.371957 (lr=7.4596e-05) (hash(x)=27706477) +2704 train 7.480898 (lr=7.4560e-05) (hash(x)=30358985) +2705 train 7.058275 (lr=7.4525e-05) (hash(x)=23548492) +2706 train 7.184417 (lr=7.4489e-05) (hash(x)=25879696) +2707 train 7.056418 (lr=7.4453e-05) (hash(x)=23711800) +2708 train 7.579518 (lr=7.4418e-05) (hash(x)=28763123) +2709 train 7.212767 (lr=7.4382e-05) (hash(x)=23327642) +2710 train 7.265865 (lr=7.4346e-05) (hash(x)=25634166) +2711 train 7.189331 (lr=7.4310e-05) (hash(x)=28684175) +2712 train 7.270860 (lr=7.4275e-05) (hash(x)=23996278) +2713 train 6.866451 (lr=7.4239e-05) (hash(x)=21795980) +2714 train 7.226157 (lr=7.4203e-05) (hash(x)=24840769) +2715 train 7.182115 (lr=7.4167e-05) (hash(x)=25225466) +2716 train 7.468156 (lr=7.4131e-05) (hash(x)=27500471) +2717 train 7.122303 (lr=7.4096e-05) (hash(x)=24703036) +2718 train 7.274582 (lr=7.4060e-05) (hash(x)=24294293) +2719 train 7.251173 (lr=7.4024e-05) (hash(x)=28003600) +2720 train 6.933806 (lr=7.3988e-05) (hash(x)=22822962) +2721 train 6.788012 (lr=7.3952e-05) (hash(x)=24189246) +2722 train 6.934772 (lr=7.3916e-05) (hash(x)=22608951) +2723 train 7.635660 (lr=7.3880e-05) (hash(x)=27989890) +2724 train 7.344147 (lr=7.3844e-05) (hash(x)=24175838) +2725 train 7.187057 (lr=7.3808e-05) (hash(x)=24781792) +2726 train 6.987957 (lr=7.3772e-05) (hash(x)=23413276) +2727 train 7.390488 (lr=7.3736e-05) (hash(x)=27586845) +2728 train 7.196514 (lr=7.3700e-05) (hash(x)=27336264) +2729 train 7.292687 (lr=7.3664e-05) (hash(x)=26808464) +2730 train 7.084236 (lr=7.3628e-05) (hash(x)=22312009) +2731 train 7.128381 (lr=7.3592e-05) (hash(x)=22373927) +2732 train 7.065298 (lr=7.3556e-05) (hash(x)=23428834) +2733 train 7.116901 (lr=7.3520e-05) (hash(x)=25304441) +2734 train 7.136591 (lr=7.3484e-05) (hash(x)=24798164) +2735 train 6.902412 (lr=7.3448e-05) (hash(x)=21176405) +2736 train 7.016788 (lr=7.3412e-05) (hash(x)=22343075) +2737 train 7.075347 (lr=7.3375e-05) (hash(x)=23825332) +2738 train 7.136215 (lr=7.3339e-05) (hash(x)=24191865) +2739 train 6.932880 (lr=7.3303e-05) (hash(x)=23806052) +2740 train 6.963048 (lr=7.3267e-05) (hash(x)=21764591) +2741 train 7.143097 (lr=7.3231e-05) (hash(x)=25548695) +2742 train 7.377651 (lr=7.3195e-05) (hash(x)=26847535) +2743 train 7.041770 (lr=7.3158e-05) (hash(x)=25888433) +2744 train 7.015508 (lr=7.3122e-05) (hash(x)=24327454) +2745 train 6.919673 (lr=7.3086e-05) (hash(x)=22543301) +2746 train 7.376377 (lr=7.3050e-05) (hash(x)=24593022) +2747 train 8.021897 (lr=7.3013e-05) (hash(x)=27797727) +2748 train 7.411527 (lr=7.2977e-05) (hash(x)=28067682) +2749 train 7.031240 (lr=7.2941e-05) (hash(x)=25278538) +2750 val loss 7.2179 +2750 val perplexity 1363.6040 +2750 train 6.987408 (lr=7.2904e-05) (hash(x)=23875731) +2751 train 7.209880 (lr=7.2868e-05) (hash(x)=27916982) +2752 train 7.165582 (lr=7.2832e-05) (hash(x)=25726799) +2753 train 6.996352 (lr=7.2795e-05) (hash(x)=25227141) +2754 train 7.277334 (lr=7.2759e-05) (hash(x)=27679212) +2755 train 6.966829 (lr=7.2723e-05) (hash(x)=24621793) +2756 train 6.882265 (lr=7.2686e-05) (hash(x)=21962296) +2757 train 7.237183 (lr=7.2650e-05) (hash(x)=24899679) +2758 train 6.920803 (lr=7.2613e-05) (hash(x)=21452158) +2759 train 7.040957 (lr=7.2577e-05) (hash(x)=24334708) +2760 train 7.305443 (lr=7.2540e-05) (hash(x)=25523041) +2761 train 7.399784 (lr=7.2504e-05) (hash(x)=30389813) +2762 train 6.942527 (lr=7.2467e-05) (hash(x)=22426014) +2763 train 7.050287 (lr=7.2431e-05) (hash(x)=24419143) +2764 train 7.129070 (lr=7.2394e-05) (hash(x)=24850536) +2765 train 7.189841 (lr=7.2358e-05) (hash(x)=24181393) +2766 train 6.642366 (lr=7.2321e-05) (hash(x)=18882503) +2767 train 7.171815 (lr=7.2285e-05) (hash(x)=25617709) +2768 train 7.124564 (lr=7.2248e-05) (hash(x)=24076662) +2769 train 7.036266 (lr=7.2212e-05) (hash(x)=21656802) +2770 train 6.966382 (lr=7.2175e-05) (hash(x)=21014265) +2771 train 7.140977 (lr=7.2138e-05) (hash(x)=24556034) +2772 train 6.871316 (lr=7.2102e-05) (hash(x)=22046665) +2773 train 7.178439 (lr=7.2065e-05) (hash(x)=26761579) +2774 train 8.625687 (lr=7.2028e-05) (hash(x)=41414315) +2775 train 7.065683 (lr=7.1992e-05) (hash(x)=25152362) +2776 train 7.274761 (lr=7.1955e-05) (hash(x)=25567641) +2777 train 7.173348 (lr=7.1918e-05) (hash(x)=25427935) +2778 train 7.228363 (lr=7.1882e-05) (hash(x)=25824457) +2779 train 7.163246 (lr=7.1845e-05) (hash(x)=24326376) +2780 train 7.193741 (lr=7.1808e-05) (hash(x)=27447230) +2781 train 7.032738 (lr=7.1772e-05) (hash(x)=24003710) +2782 train 6.951207 (lr=7.1735e-05) (hash(x)=24157390) +2783 train 7.069984 (lr=7.1698e-05) (hash(x)=24276512) +2784 train 6.888892 (lr=7.1661e-05) (hash(x)=21503752) +2785 train 6.856857 (lr=7.1624e-05) (hash(x)=20031488) +2786 train 6.866115 (lr=7.1588e-05) (hash(x)=21788715) +2787 train 7.054446 (lr=7.1551e-05) (hash(x)=24344695) +2788 train 7.110061 (lr=7.1514e-05) (hash(x)=22927763) +2789 train 6.975429 (lr=7.1477e-05) (hash(x)=23710755) +2790 train 7.234476 (lr=7.1440e-05) (hash(x)=26924620) +2791 train 7.529736 (lr=7.1403e-05) (hash(x)=26776133) +2792 train 6.987967 (lr=7.1367e-05) (hash(x)=19936770) +2793 train 7.158672 (lr=7.1330e-05) (hash(x)=25440959) +2794 train 7.107743 (lr=7.1293e-05) (hash(x)=25146097) +2795 train 6.912386 (lr=7.1256e-05) (hash(x)=21847282) +2796 train 7.118247 (lr=7.1219e-05) (hash(x)=25639784) +2797 train 6.885759 (lr=7.1182e-05) (hash(x)=21199921) +2798 train 7.087149 (lr=7.1145e-05) (hash(x)=22360806) +2799 train 6.573804 (lr=7.1108e-05) (hash(x)=20254159) +2800 val loss 7.2018 +2800 val perplexity 1341.8789 +2800 train 6.723239 (lr=7.1071e-05) (hash(x)=23348345) +2801 train 7.330130 (lr=7.1034e-05) (hash(x)=24908033) +2802 train 7.038005 (lr=7.0997e-05) (hash(x)=23350309) +2803 train 7.119995 (lr=7.0960e-05) (hash(x)=25044762) +2804 train 7.004907 (lr=7.0923e-05) (hash(x)=24071026) +2805 train 6.801010 (lr=7.0886e-05) (hash(x)=22169363) +2806 train 7.083452 (lr=7.0849e-05) (hash(x)=23757564) +2807 train 7.503932 (lr=7.0812e-05) (hash(x)=27873855) +2808 train 7.267971 (lr=7.0775e-05) (hash(x)=26577893) +2809 train 7.347413 (lr=7.0738e-05) (hash(x)=27001634) +2810 train 7.117549 (lr=7.0701e-05) (hash(x)=24796541) +2811 train 7.016591 (lr=7.0663e-05) (hash(x)=22575615) +2812 train 7.109993 (lr=7.0626e-05) (hash(x)=25876475) +2813 train 7.100484 (lr=7.0589e-05) (hash(x)=24765155) +2814 train 7.051296 (lr=7.0552e-05) (hash(x)=25785699) +2815 train 7.237129 (lr=7.0515e-05) (hash(x)=25113614) +2816 train 7.117232 (lr=7.0478e-05) (hash(x)=24415748) +2817 train 7.210429 (lr=7.0441e-05) (hash(x)=25140622) +2818 train 7.096807 (lr=7.0403e-05) (hash(x)=24845866) +2819 train 7.572482 (lr=7.0366e-05) (hash(x)=28062905) +2820 train 7.079957 (lr=7.0329e-05) (hash(x)=22041086) +2821 train 7.226446 (lr=7.0292e-05) (hash(x)=24957184) +2822 train 7.112862 (lr=7.0254e-05) (hash(x)=24360380) +2823 train 7.257249 (lr=7.0217e-05) (hash(x)=26192886) +2824 train 7.130089 (lr=7.0180e-05) (hash(x)=25001858) +2825 train 7.097934 (lr=7.0143e-05) (hash(x)=24721193) +2826 train 7.168826 (lr=7.0105e-05) (hash(x)=26186227) +2827 train 7.115407 (lr=7.0068e-05) (hash(x)=25770338) +2828 train 7.196857 (lr=7.0031e-05) (hash(x)=25920767) +2829 train 7.112911 (lr=6.9993e-05) (hash(x)=25060684) +2830 train 6.804474 (lr=6.9956e-05) (hash(x)=22933946) +2831 train 6.963117 (lr=6.9919e-05) (hash(x)=24614912) +2832 train 6.710889 (lr=6.9881e-05) (hash(x)=19955522) +2833 train 6.769231 (lr=6.9844e-05) (hash(x)=21111215) +2834 train 7.637467 (lr=6.9806e-05) (hash(x)=28817924) +2835 train 7.209808 (lr=6.9769e-05) (hash(x)=26934071) +2836 train 7.108380 (lr=6.9732e-05) (hash(x)=24768851) +2837 train 7.078125 (lr=6.9694e-05) (hash(x)=25706447) +2838 train 6.845582 (lr=6.9657e-05) (hash(x)=19579834) +2839 train 7.089358 (lr=6.9619e-05) (hash(x)=25397093) +2840 train 7.548527 (lr=6.9582e-05) (hash(x)=27902141) +2841 train 7.195232 (lr=6.9544e-05) (hash(x)=25383069) +2842 train 6.967842 (lr=6.9507e-05) (hash(x)=22007373) +2843 train 7.053309 (lr=6.9469e-05) (hash(x)=25925963) +2844 train 7.119252 (lr=6.9432e-05) (hash(x)=25711128) +2845 train 6.800800 (lr=6.9394e-05) (hash(x)=21881216) +2846 train 6.999874 (lr=6.9357e-05) (hash(x)=20277075) +2847 train 7.068250 (lr=6.9319e-05) (hash(x)=19811802) +2848 train 6.960330 (lr=6.9282e-05) (hash(x)=23878906) +2849 train 7.230841 (lr=6.9244e-05) (hash(x)=25034966) +2850 val loss 7.2006 +2850 val perplexity 1340.2343 +2850 train 7.238771 (lr=6.9207e-05) (hash(x)=24359507) +2851 train 6.974811 (lr=6.9169e-05) (hash(x)=23248423) +2852 train 6.996830 (lr=6.9132e-05) (hash(x)=21782773) +2853 train 7.129562 (lr=6.9094e-05) (hash(x)=23804418) +2854 train 7.187891 (lr=6.9056e-05) (hash(x)=22525078) +2855 train 7.165097 (lr=6.9019e-05) (hash(x)=25579655) +2856 train 7.285513 (lr=6.8981e-05) (hash(x)=27048876) +2857 train 7.381214 (lr=6.8943e-05) (hash(x)=26468479) +2858 train 7.051609 (lr=6.8906e-05) (hash(x)=23854933) +2859 train 7.430383 (lr=6.8868e-05) (hash(x)=25537603) +2860 train 6.843930 (lr=6.8830e-05) (hash(x)=20979252) +2861 train 7.413319 (lr=6.8793e-05) (hash(x)=26504374) +2862 train 7.240139 (lr=6.8755e-05) (hash(x)=27561842) +2863 train 7.233803 (lr=6.8717e-05) (hash(x)=26096514) +2864 train 7.247566 (lr=6.8680e-05) (hash(x)=25926899) +2865 train 7.263680 (lr=6.8642e-05) (hash(x)=26058348) +2866 train 7.262163 (lr=6.8604e-05) (hash(x)=29802259) +2867 train 7.191299 (lr=6.8566e-05) (hash(x)=24132888) +2868 train 6.879841 (lr=6.8529e-05) (hash(x)=23369410) +2869 train 7.018146 (lr=6.8491e-05) (hash(x)=25387506) +2870 train 7.244428 (lr=6.8453e-05) (hash(x)=27375344) +2871 train 7.008622 (lr=6.8415e-05) (hash(x)=22589633) +2872 train 7.157390 (lr=6.8377e-05) (hash(x)=23250237) +2873 train 7.046779 (lr=6.8340e-05) (hash(x)=25511322) +2874 train 6.702127 (lr=6.8302e-05) (hash(x)=18356418) +2875 train 7.134651 (lr=6.8264e-05) (hash(x)=27781566) +2876 train 7.020293 (lr=6.8226e-05) (hash(x)=24878173) +2877 train 7.510081 (lr=6.8188e-05) (hash(x)=30018637) +2878 train 7.357207 (lr=6.8150e-05) (hash(x)=27168416) +2879 train 7.325697 (lr=6.8113e-05) (hash(x)=26757147) +2880 train 7.354921 (lr=6.8075e-05) (hash(x)=26637081) +2881 train 7.236104 (lr=6.8037e-05) (hash(x)=24795024) +2882 train 7.476753 (lr=6.7999e-05) (hash(x)=29787745) +2883 train 7.333497 (lr=6.7961e-05) (hash(x)=26649864) +2884 train 7.179771 (lr=6.7923e-05) (hash(x)=27306612) +2885 train 7.254550 (lr=6.7885e-05) (hash(x)=27568311) +2886 train 7.272128 (lr=6.7847e-05) (hash(x)=27440150) +2887 train 7.008849 (lr=6.7809e-05) (hash(x)=24963730) +2888 train 7.019795 (lr=6.7771e-05) (hash(x)=23619807) +2889 train 7.500165 (lr=6.7733e-05) (hash(x)=29447356) +2890 train 7.017523 (lr=6.7695e-05) (hash(x)=25144675) +2891 train 6.952178 (lr=6.7657e-05) (hash(x)=25249959) +2892 train 6.973180 (lr=6.7619e-05) (hash(x)=26608712) +2893 train 6.986906 (lr=6.7581e-05) (hash(x)=26333258) +2894 train 6.792217 (lr=6.7543e-05) (hash(x)=20682182) +2895 train 7.240668 (lr=6.7505e-05) (hash(x)=27703124) +2896 train 7.010001 (lr=6.7467e-05) (hash(x)=23228180) +2897 train 6.915221 (lr=6.7429e-05) (hash(x)=25252411) +2898 train 6.892532 (lr=6.7391e-05) (hash(x)=22879178) +2899 train 7.193981 (lr=6.7353e-05) (hash(x)=26459082) +2900 val loss 7.1939 +2900 val perplexity 1331.3291 +2900 train 7.006777 (lr=6.7315e-05) (hash(x)=24569501) +2901 train 6.800600 (lr=6.7277e-05) (hash(x)=19803884) +2902 train 6.827096 (lr=6.7239e-05) (hash(x)=18799747) +2903 train 7.155840 (lr=6.7201e-05) (hash(x)=24781713) +2904 train 7.306390 (lr=6.7162e-05) (hash(x)=25016590) +2905 train 7.511495 (lr=6.7124e-05) (hash(x)=29006906) +2906 train 7.236108 (lr=6.7086e-05) (hash(x)=24069959) +2907 train 7.376032 (lr=6.7048e-05) (hash(x)=26597693) +2908 train 7.009996 (lr=6.7010e-05) (hash(x)=25014146) +2909 train 7.248057 (lr=6.6972e-05) (hash(x)=24943747) +2910 train 7.160687 (lr=6.6933e-05) (hash(x)=27847542) +2911 train 7.071071 (lr=6.6895e-05) (hash(x)=24720476) +2912 train 6.923473 (lr=6.6857e-05) (hash(x)=24388804) +2913 train 7.055753 (lr=6.6819e-05) (hash(x)=23567535) +2914 train 7.366176 (lr=6.6781e-05) (hash(x)=29673625) +2915 train 7.069814 (lr=6.6742e-05) (hash(x)=23691295) +2916 train 7.437544 (lr=6.6704e-05) (hash(x)=26572819) +2917 train 7.077970 (lr=6.6666e-05) (hash(x)=23237812) +2918 train 7.351524 (lr=6.6628e-05) (hash(x)=26531016) +2919 train 6.865723 (lr=6.6589e-05) (hash(x)=23481301) +2920 train 7.171569 (lr=6.6551e-05) (hash(x)=24839184) +2921 train 7.043506 (lr=6.6513e-05) (hash(x)=23327755) +2922 train 7.308557 (lr=6.6475e-05) (hash(x)=26347114) +2923 train 6.935979 (lr=6.6436e-05) (hash(x)=23295676) +2924 train 7.004292 (lr=6.6398e-05) (hash(x)=24557178) +2925 train 7.077360 (lr=6.6360e-05) (hash(x)=26067788) +2926 train 7.039259 (lr=6.6321e-05) (hash(x)=25694982) +2927 train 7.121198 (lr=6.6283e-05) (hash(x)=25641033) +2928 train 7.153839 (lr=6.6245e-05) (hash(x)=24906422) +2929 train 7.348268 (lr=6.6206e-05) (hash(x)=27803515) +2930 train 7.287197 (lr=6.6168e-05) (hash(x)=26208803) +2931 train 6.794353 (lr=6.6130e-05) (hash(x)=22441379) +2932 train 7.070145 (lr=6.6091e-05) (hash(x)=24741626) +2933 train 6.971687 (lr=6.6053e-05) (hash(x)=24595257) +2934 train 7.019661 (lr=6.6015e-05) (hash(x)=23939167) +2935 train 7.288353 (lr=6.5976e-05) (hash(x)=27369437) +2936 train 6.924839 (lr=6.5938e-05) (hash(x)=21409783) +2937 train 7.178783 (lr=6.5899e-05) (hash(x)=25923735) +2938 train 7.194887 (lr=6.5861e-05) (hash(x)=29559511) +2939 train 7.088407 (lr=6.5822e-05) (hash(x)=24482272) +2940 train 7.073501 (lr=6.5784e-05) (hash(x)=24767658) +2941 train 7.261295 (lr=6.5746e-05) (hash(x)=26425020) +2942 train 7.617923 (lr=6.5707e-05) (hash(x)=27444868) +2943 train 7.055211 (lr=6.5669e-05) (hash(x)=24760900) +2944 train 7.046614 (lr=6.5630e-05) (hash(x)=25605407) +2945 train 6.962229 (lr=6.5592e-05) (hash(x)=22886951) +2946 train 7.313763 (lr=6.5553e-05) (hash(x)=26112205) +2947 train 7.113897 (lr=6.5515e-05) (hash(x)=23919156) +2948 train 7.102212 (lr=6.5476e-05) (hash(x)=23729312) +2949 train 7.402309 (lr=6.5438e-05) (hash(x)=30440878) +2950 val loss 7.1905 +2950 val perplexity 1326.8287 +2950 train 6.786554 (lr=6.5399e-05) (hash(x)=20004041) +2951 train 6.803770 (lr=6.5361e-05) (hash(x)=21692546) +2952 train 6.860165 (lr=6.5322e-05) (hash(x)=23021681) +2953 train 7.223380 (lr=6.5283e-05) (hash(x)=26663597) +2954 train 7.104939 (lr=6.5245e-05) (hash(x)=23727385) +2955 train 7.070703 (lr=6.5206e-05) (hash(x)=27692087) +2956 train 7.102132 (lr=6.5168e-05) (hash(x)=24003378) +2957 train 7.763047 (lr=6.5129e-05) (hash(x)=29534673) +2958 train 6.986273 (lr=6.5091e-05) (hash(x)=22875068) +2959 train 6.945974 (lr=6.5052e-05) (hash(x)=22720391) +2960 train 6.752948 (lr=6.5013e-05) (hash(x)=17997400) +2961 train 6.981091 (lr=6.4975e-05) (hash(x)=22853822) +2962 train 7.042998 (lr=6.4936e-05) (hash(x)=25238004) +2963 train 7.189340 (lr=6.4898e-05) (hash(x)=26146560) +2964 train 7.307939 (lr=6.4859e-05) (hash(x)=21894867) +2965 train 7.282150 (lr=6.4820e-05) (hash(x)=23001150) +2966 train 6.975122 (lr=6.4782e-05) (hash(x)=23392923) +2967 train 7.033990 (lr=6.4743e-05) (hash(x)=24376979) +2968 train 7.001326 (lr=6.4704e-05) (hash(x)=23781449) +2969 train 7.170909 (lr=6.4666e-05) (hash(x)=25315495) +2970 train 7.294919 (lr=6.4627e-05) (hash(x)=27165470) +2971 train 7.108132 (lr=6.4588e-05) (hash(x)=22917712) +2972 train 7.454242 (lr=6.4550e-05) (hash(x)=27928456) +2973 train 6.835503 (lr=6.4511e-05) (hash(x)=19890855) +2974 train 6.807533 (lr=6.4472e-05) (hash(x)=21318134) +2975 train 6.964107 (lr=6.4433e-05) (hash(x)=22244509) +2976 train 6.903629 (lr=6.4395e-05) (hash(x)=21293137) +2977 train 6.933931 (lr=6.4356e-05) (hash(x)=23465789) +2978 train 6.943202 (lr=6.4317e-05) (hash(x)=21169753) +2979 train 7.321872 (lr=6.4279e-05) (hash(x)=25243385) +2980 train 7.378124 (lr=6.4240e-05) (hash(x)=27465812) +2981 train 7.076969 (lr=6.4201e-05) (hash(x)=24615492) +2982 train 6.995056 (lr=6.4162e-05) (hash(x)=23081307) +2983 train 6.796424 (lr=6.4123e-05) (hash(x)=21831960) +2984 train 6.900626 (lr=6.4085e-05) (hash(x)=23242850) +2985 train 7.017429 (lr=6.4046e-05) (hash(x)=24308188) +2986 train 7.205235 (lr=6.4007e-05) (hash(x)=28541601) +2987 train 7.083720 (lr=6.3968e-05) (hash(x)=24842373) +2988 train 6.819007 (lr=6.3930e-05) (hash(x)=21967126) +2989 train 7.035549 (lr=6.3891e-05) (hash(x)=22951616) +2990 train 7.131406 (lr=6.3852e-05) (hash(x)=24325714) +2991 train 6.926776 (lr=6.3813e-05) (hash(x)=24921535) +2992 train 7.168899 (lr=6.3774e-05) (hash(x)=25937112) +2993 train 6.815470 (lr=6.3735e-05) (hash(x)=20716218) +2994 train 7.129852 (lr=6.3697e-05) (hash(x)=25450724) +2995 train 7.065860 (lr=6.3658e-05) (hash(x)=24344615) +2996 train 6.793522 (lr=6.3619e-05) (hash(x)=20299058) +2997 train 7.052524 (lr=6.3580e-05) (hash(x)=23859426) +2998 train 7.015225 (lr=6.3541e-05) (hash(x)=23094397) +2999 train 7.355964 (lr=6.3502e-05) (hash(x)=25381251) +3000 val loss 7.1821 +3000 val perplexity 1315.6536 +3000 train 7.076856 (lr=6.3463e-05) (hash(x)=23586527) +3001 train 6.964966 (lr=6.3424e-05) (hash(x)=24220410) +3002 train 6.840761 (lr=6.3385e-05) (hash(x)=20597347) +3003 train 6.916656 (lr=6.3347e-05) (hash(x)=22887303) +3004 train 7.268612 (lr=6.3308e-05) (hash(x)=25869462) +3005 train 6.954668 (lr=6.3269e-05) (hash(x)=22098530) +3006 train 7.284526 (lr=6.3230e-05) (hash(x)=26246291) +3007 train 7.199028 (lr=6.3191e-05) (hash(x)=25687352) +3008 train 6.955804 (lr=6.3152e-05) (hash(x)=25425646) +3009 train 7.145828 (lr=6.3113e-05) (hash(x)=26021124) +3010 train 7.191001 (lr=6.3074e-05) (hash(x)=25392057) +3011 train 7.258545 (lr=6.3035e-05) (hash(x)=27791412) +3012 train 7.063430 (lr=6.2996e-05) (hash(x)=23181098) +3013 train 7.092586 (lr=6.2957e-05) (hash(x)=25521889) +3014 train 6.909080 (lr=6.2918e-05) (hash(x)=21685795) +3015 train 7.092331 (lr=6.2879e-05) (hash(x)=25221654) +3016 train 7.241386 (lr=6.2840e-05) (hash(x)=24888744) +3017 train 7.123539 (lr=6.2801e-05) (hash(x)=24200150) +3018 train 7.073767 (lr=6.2762e-05) (hash(x)=26943942) +3019 train 7.038803 (lr=6.2723e-05) (hash(x)=23243731) +3020 train 6.892597 (lr=6.2684e-05) (hash(x)=21068284) +3021 train 7.054150 (lr=6.2645e-05) (hash(x)=23876902) +3022 train 7.204466 (lr=6.2606e-05) (hash(x)=25337639) +3023 train 7.132018 (lr=6.2567e-05) (hash(x)=24469863) +3024 train 7.565323 (lr=6.2528e-05) (hash(x)=27850876) +3025 train 7.437714 (lr=6.2489e-05) (hash(x)=20515778) +3026 train 7.208425 (lr=6.2450e-05) (hash(x)=29019173) +3027 train 6.828850 (lr=6.2411e-05) (hash(x)=22484936) +3028 train 6.977558 (lr=6.2372e-05) (hash(x)=24639400) +3029 train 7.165406 (lr=6.2333e-05) (hash(x)=26835174) +3030 train 7.317525 (lr=6.2294e-05) (hash(x)=29843763) +3031 train 7.024087 (lr=6.2255e-05) (hash(x)=25291413) +3032 train 6.963004 (lr=6.2216e-05) (hash(x)=24590244) +3033 train 7.201188 (lr=6.2176e-05) (hash(x)=28880142) +3034 train 6.959767 (lr=6.2137e-05) (hash(x)=23372199) +3035 train 6.924915 (lr=6.2098e-05) (hash(x)=23952225) +3036 train 7.093061 (lr=6.2059e-05) (hash(x)=24589186) +3037 train 7.027373 (lr=6.2020e-05) (hash(x)=23260323) +3038 train 7.181679 (lr=6.1981e-05) (hash(x)=25824498) +3039 train 7.144939 (lr=6.1942e-05) (hash(x)=25744274) +3040 train 7.102704 (lr=6.1903e-05) (hash(x)=21610247) +3041 train 7.243455 (lr=6.1863e-05) (hash(x)=25079786) +3042 train 6.872775 (lr=6.1824e-05) (hash(x)=23219195) +3043 train 6.798146 (lr=6.1785e-05) (hash(x)=22616739) +3044 train 7.099998 (lr=6.1746e-05) (hash(x)=24908480) +3045 train 6.977353 (lr=6.1707e-05) (hash(x)=22293489) +3046 train 6.981655 (lr=6.1668e-05) (hash(x)=23557651) +3047 train 7.034400 (lr=6.1629e-05) (hash(x)=24246963) +3048 train 7.121018 (lr=6.1589e-05) (hash(x)=24490083) +3049 train 7.117502 (lr=6.1550e-05) (hash(x)=22372895) +3050 val loss 7.1767 +3050 val perplexity 1308.5961 +3050 train 6.827045 (lr=6.1511e-05) (hash(x)=21759470) +3051 train 6.726995 (lr=6.1472e-05) (hash(x)=19407094) +3052 train 7.113690 (lr=6.1433e-05) (hash(x)=23957047) +3053 train 7.211717 (lr=6.1393e-05) (hash(x)=24719318) +3054 train 6.988748 (lr=6.1354e-05) (hash(x)=20719314) +3055 train 6.942288 (lr=6.1315e-05) (hash(x)=19724058) +3056 train 6.744185 (lr=6.1276e-05) (hash(x)=14407266) +3057 train 6.621927 (lr=6.1237e-05) (hash(x)=12468292) +3058 train 6.904540 (lr=6.1197e-05) (hash(x)=16098279) +3059 train 7.000754 (lr=6.1158e-05) (hash(x)=18836491) +3060 train 6.827541 (lr=6.1119e-05) (hash(x)=19132277) +3061 train 6.974889 (lr=6.1080e-05) (hash(x)=22814208) +3062 train 7.014987 (lr=6.1040e-05) (hash(x)=24838508) +3063 train 6.880541 (lr=6.1001e-05) (hash(x)=20705649) +3064 train 7.920250 (lr=6.0962e-05) (hash(x)=29416914) +3065 train 7.372309 (lr=6.0923e-05) (hash(x)=25972430) +3066 train 6.768861 (lr=6.0883e-05) (hash(x)=23705805) +3067 train 6.838080 (lr=6.0844e-05) (hash(x)=21325875) +3068 train 7.048010 (lr=6.0805e-05) (hash(x)=23526506) +3069 train 7.494702 (lr=6.0766e-05) (hash(x)=27282337) +3070 train 7.372543 (lr=6.0726e-05) (hash(x)=27968043) +3071 train 7.189350 (lr=6.0687e-05) (hash(x)=24938685) +3072 train 7.369475 (lr=6.0648e-05) (hash(x)=26942737) +3073 train 7.307905 (lr=6.0609e-05) (hash(x)=23506879) +3074 train 6.952847 (lr=6.0569e-05) (hash(x)=23589913) +3075 train 7.164884 (lr=6.0530e-05) (hash(x)=25152403) +3076 train 7.271792 (lr=6.0491e-05) (hash(x)=23425868) +3077 train 7.462520 (lr=6.0451e-05) (hash(x)=23966181) +3078 train 7.512804 (lr=6.0412e-05) (hash(x)=27312570) +3079 train 7.111295 (lr=6.0373e-05) (hash(x)=21707000) +3080 train 7.031447 (lr=6.0333e-05) (hash(x)=25600427) +3081 train 7.141860 (lr=6.0294e-05) (hash(x)=24270631) +3082 train 7.282323 (lr=6.0255e-05) (hash(x)=25199537) +3083 train 6.481702 (lr=6.0215e-05) (hash(x)=17952018) +3084 train 6.607629 (lr=6.0176e-05) (hash(x)=18733143) +3085 train 7.301732 (lr=6.0137e-05) (hash(x)=26946100) +3086 train 7.090919 (lr=6.0097e-05) (hash(x)=25547515) +3087 train 7.072492 (lr=6.0058e-05) (hash(x)=24948980) +3088 train 8.306003 (lr=6.0019e-05) (hash(x)=35461645) +3089 train 7.308891 (lr=5.9979e-05) (hash(x)=28330877) +3090 train 7.221870 (lr=5.9940e-05) (hash(x)=27687861) +3091 train 7.349576 (lr=5.9901e-05) (hash(x)=28012110) +3092 train 7.202691 (lr=5.9861e-05) (hash(x)=24684480) +3093 train 7.162090 (lr=5.9822e-05) (hash(x)=26225786) +3094 train 6.838156 (lr=5.9783e-05) (hash(x)=23098156) +3095 train 7.403228 (lr=5.9743e-05) (hash(x)=30773958) +3096 train 7.722194 (lr=5.9704e-05) (hash(x)=28640406) +3097 train 7.642578 (lr=5.9664e-05) (hash(x)=28201086) +3098 train 7.950781 (lr=5.9625e-05) (hash(x)=35002344) +3099 train 7.495586 (lr=5.9586e-05) (hash(x)=29481068) +3100 val loss 7.2053 +3100 val perplexity 1346.5709 +3100 train 7.082394 (lr=5.9546e-05) (hash(x)=26374528) +3101 train 7.081879 (lr=5.9507e-05) (hash(x)=24153602) +3102 train 7.117868 (lr=5.9467e-05) (hash(x)=25478746) +3103 train 7.409488 (lr=5.9428e-05) (hash(x)=26769046) +3104 train 6.989508 (lr=5.9389e-05) (hash(x)=21841970) +3105 train 7.287090 (lr=5.9349e-05) (hash(x)=27693052) +3106 train 6.767949 (lr=5.9310e-05) (hash(x)=20689448) +3107 train 7.108919 (lr=5.9270e-05) (hash(x)=26755048) +3108 train 7.145564 (lr=5.9231e-05) (hash(x)=24431904) +3109 train 6.998395 (lr=5.9192e-05) (hash(x)=21009792) +3110 train 7.087413 (lr=5.9152e-05) (hash(x)=21909003) +3111 train 7.157713 (lr=5.9113e-05) (hash(x)=18849656) +3112 train 7.235143 (lr=5.9073e-05) (hash(x)=22223376) +3113 train 7.502052 (lr=5.9034e-05) (hash(x)=25652491) +3114 train 7.418718 (lr=5.8994e-05) (hash(x)=23521434) +3115 train 7.483254 (lr=5.8955e-05) (hash(x)=25449800) +3116 train 7.883206 (lr=5.8915e-05) (hash(x)=27655847) +3117 train 7.972101 (lr=5.8876e-05) (hash(x)=29878248) +3118 train 7.951712 (lr=5.8837e-05) (hash(x)=30444094) +3119 train 7.571568 (lr=5.8797e-05) (hash(x)=24624950) +3120 train 6.878465 (lr=5.8758e-05) (hash(x)=20798511) +3121 train 7.250591 (lr=5.8718e-05) (hash(x)=26581679) +3122 train 7.164769 (lr=5.8679e-05) (hash(x)=25333422) +3123 train 7.213751 (lr=5.8639e-05) (hash(x)=26174069) +3124 train 7.265864 (lr=5.8600e-05) (hash(x)=25219475) +3125 train 7.167471 (lr=5.8560e-05) (hash(x)=20919061) +3126 train 7.105676 (lr=5.8521e-05) (hash(x)=23828688) +3127 train 7.657790 (lr=5.8481e-05) (hash(x)=27299605) +3128 train 6.982613 (lr=5.8442e-05) (hash(x)=23797514) +3129 train 7.219584 (lr=5.8402e-05) (hash(x)=23601883) +3130 train 7.452859 (lr=5.8363e-05) (hash(x)=31003964) +3131 train 7.186853 (lr=5.8323e-05) (hash(x)=24777273) +3132 train 7.044397 (lr=5.8284e-05) (hash(x)=25403249) +3133 train 7.266519 (lr=5.8244e-05) (hash(x)=28913150) +3134 train 7.211750 (lr=5.8205e-05) (hash(x)=26541508) +3135 train 7.168379 (lr=5.8165e-05) (hash(x)=24113445) +3136 train 6.960460 (lr=5.8126e-05) (hash(x)=25464565) +3137 train 7.218002 (lr=5.8086e-05) (hash(x)=26581432) +3138 train 7.076044 (lr=5.8047e-05) (hash(x)=23074513) +3139 train 6.945391 (lr=5.8007e-05) (hash(x)=23970384) +3140 train 7.177320 (lr=5.7968e-05) (hash(x)=26694495) +3141 train 7.152896 (lr=5.7928e-05) (hash(x)=26883445) +3142 train 7.293770 (lr=5.7889e-05) (hash(x)=28632211) +3143 train 7.729378 (lr=5.7849e-05) (hash(x)=32644465) +3144 train 7.466313 (lr=5.7810e-05) (hash(x)=27490443) +3145 train 7.002845 (lr=5.7770e-05) (hash(x)=23814853) +3146 train 7.460741 (lr=5.7731e-05) (hash(x)=29664236) +3147 train 7.783699 (lr=5.7691e-05) (hash(x)=29951548) +3148 train 7.541490 (lr=5.7652e-05) (hash(x)=28426503) +3149 train 6.918369 (lr=5.7612e-05) (hash(x)=23727657) +3150 val loss 7.1884 +3150 val perplexity 1323.9266 +3150 train 7.065353 (lr=5.7573e-05) (hash(x)=21430659) +3151 train 7.126821 (lr=5.7533e-05) (hash(x)=25829219) +3152 train 7.260050 (lr=5.7494e-05) (hash(x)=29735208) +3153 train 7.316164 (lr=5.7454e-05) (hash(x)=28173447) +3154 train 6.996086 (lr=5.7414e-05) (hash(x)=22909641) +3155 train 7.182899 (lr=5.7375e-05) (hash(x)=20556094) +3156 train 6.923070 (lr=5.7335e-05) (hash(x)=24013769) +3157 train 6.940440 (lr=5.7296e-05) (hash(x)=22525971) +3158 train 7.042087 (lr=5.7256e-05) (hash(x)=25492728) +3159 train 7.091775 (lr=5.7217e-05) (hash(x)=25194550) +3160 train 7.188159 (lr=5.7177e-05) (hash(x)=25610603) +3161 train 7.153368 (lr=5.7138e-05) (hash(x)=23848640) +3162 train 6.945510 (lr=5.7098e-05) (hash(x)=24082226) +3163 train 7.331679 (lr=5.7058e-05) (hash(x)=28482186) +3164 train 7.244294 (lr=5.7019e-05) (hash(x)=27542978) +3165 train 6.998170 (lr=5.6979e-05) (hash(x)=22540954) +3166 train 7.131061 (lr=5.6940e-05) (hash(x)=26103641) +3167 train 7.092690 (lr=5.6900e-05) (hash(x)=25941804) +3168 train 7.124884 (lr=5.6861e-05) (hash(x)=25965921) +3169 train 7.363469 (lr=5.6821e-05) (hash(x)=25631269) +3170 train 6.960805 (lr=5.6782e-05) (hash(x)=23471525) +3171 train 7.185703 (lr=5.6742e-05) (hash(x)=27049208) +3172 train 7.221294 (lr=5.6702e-05) (hash(x)=27074992) +3173 train 7.128050 (lr=5.6663e-05) (hash(x)=25712617) +3174 train 7.064292 (lr=5.6623e-05) (hash(x)=25884917) +3175 train 7.133052 (lr=5.6584e-05) (hash(x)=24075727) +3176 train 6.970638 (lr=5.6544e-05) (hash(x)=23681759) +3177 train 7.279997 (lr=5.6505e-05) (hash(x)=25786577) +3178 train 7.229699 (lr=5.6465e-05) (hash(x)=27307614) +3179 train 7.304723 (lr=5.6425e-05) (hash(x)=25082806) +3180 train 7.254166 (lr=5.6386e-05) (hash(x)=26098308) +3181 train 7.021703 (lr=5.6346e-05) (hash(x)=24080140) +3182 train 7.251948 (lr=5.6307e-05) (hash(x)=26399395) +3183 train 7.293254 (lr=5.6267e-05) (hash(x)=23104539) +3184 train 6.914632 (lr=5.6227e-05) (hash(x)=23356930) +3185 train 7.157646 (lr=5.6188e-05) (hash(x)=27972420) +3186 train 6.858898 (lr=5.6148e-05) (hash(x)=21338924) +3187 train 7.312344 (lr=5.6109e-05) (hash(x)=25351113) +3188 train 7.234123 (lr=5.6069e-05) (hash(x)=26019439) +3189 train 7.316402 (lr=5.6030e-05) (hash(x)=30149312) +3190 train 6.964044 (lr=5.5990e-05) (hash(x)=23028152) +3191 train 7.343313 (lr=5.5950e-05) (hash(x)=23018983) +3192 train 6.986101 (lr=5.5911e-05) (hash(x)=23190787) +3193 train 7.442594 (lr=5.5871e-05) (hash(x)=27798543) +3194 train 7.183992 (lr=5.5832e-05) (hash(x)=25193663) +3195 train 6.953703 (lr=5.5792e-05) (hash(x)=25302106) +3196 train 7.127880 (lr=5.5752e-05) (hash(x)=24325364) +3197 train 7.125920 (lr=5.5713e-05) (hash(x)=25399101) +3198 train 6.976474 (lr=5.5673e-05) (hash(x)=23606439) +3199 train 7.036001 (lr=5.5634e-05) (hash(x)=24422929) +3200 val loss 7.1673 +3200 val perplexity 1296.3066 +3200 train 7.212708 (lr=5.5594e-05) (hash(x)=24760381) +3201 train 6.851112 (lr=5.5554e-05) (hash(x)=23278576) +3202 train 7.079858 (lr=5.5515e-05) (hash(x)=24897511) +3203 train 7.406600 (lr=5.5475e-05) (hash(x)=29052117) +3204 train 7.132778 (lr=5.5436e-05) (hash(x)=25772923) +3205 train 7.294305 (lr=5.5396e-05) (hash(x)=25885977) +3206 train 7.099472 (lr=5.5356e-05) (hash(x)=21985272) +3207 train 7.001196 (lr=5.5317e-05) (hash(x)=23389696) +3208 train 6.937285 (lr=5.5277e-05) (hash(x)=25299042) +3209 train 7.178825 (lr=5.5238e-05) (hash(x)=23703987) +3210 train 7.054483 (lr=5.5198e-05) (hash(x)=23362342) +3211 train 7.121007 (lr=5.5158e-05) (hash(x)=23962503) +3212 train 7.038999 (lr=5.5119e-05) (hash(x)=21216023) +3213 train 7.107913 (lr=5.5079e-05) (hash(x)=25841931) +3214 train 6.977215 (lr=5.5040e-05) (hash(x)=23631428) +3215 train 7.394379 (lr=5.5000e-05) (hash(x)=29102969) +3216 train 7.134840 (lr=5.4960e-05) (hash(x)=25782766) +3217 train 7.397995 (lr=5.4921e-05) (hash(x)=28825867) +3218 train 7.359859 (lr=5.4881e-05) (hash(x)=24609499) +3219 train 7.273381 (lr=5.4842e-05) (hash(x)=24948166) +3220 train 7.339865 (lr=5.4802e-05) (hash(x)=26919841) +3221 train 7.185152 (lr=5.4762e-05) (hash(x)=27236198) +3222 train 6.957768 (lr=5.4723e-05) (hash(x)=24029305) +3223 train 7.522686 (lr=5.4683e-05) (hash(x)=28359859) +3224 train 7.289096 (lr=5.4644e-05) (hash(x)=24886008) +3225 train 7.143851 (lr=5.4604e-05) (hash(x)=27159867) +3226 train 7.398267 (lr=5.4564e-05) (hash(x)=20672023) +3227 train 7.088409 (lr=5.4525e-05) (hash(x)=22360298) +3228 train 7.526853 (lr=5.4485e-05) (hash(x)=27478658) +3229 train 7.334272 (lr=5.4446e-05) (hash(x)=26575886) +3230 train 7.505825 (lr=5.4406e-05) (hash(x)=26890615) +3231 train 7.128051 (lr=5.4366e-05) (hash(x)=24630955) +3232 train 7.416794 (lr=5.4327e-05) (hash(x)=27016054) +3233 train 7.574304 (lr=5.4287e-05) (hash(x)=28444407) +3234 train 6.989623 (lr=5.4248e-05) (hash(x)=24053336) +3235 train 7.316509 (lr=5.4208e-05) (hash(x)=26897402) +3236 train 7.442090 (lr=5.4168e-05) (hash(x)=29451214) +3237 train 7.252037 (lr=5.4129e-05) (hash(x)=27268677) +3238 train 7.375387 (lr=5.4089e-05) (hash(x)=27494000) +3239 train 6.995770 (lr=5.4050e-05) (hash(x)=22969113) +3240 train 6.965786 (lr=5.4010e-05) (hash(x)=21944576) +3241 train 7.186940 (lr=5.3970e-05) (hash(x)=21671079) +3242 train 7.069255 (lr=5.3931e-05) (hash(x)=23912980) +3243 train 7.040962 (lr=5.3891e-05) (hash(x)=25205781) +3244 train 7.035944 (lr=5.3852e-05) (hash(x)=25654244) +3245 train 6.970091 (lr=5.3812e-05) (hash(x)=23335929) +3246 train 7.373597 (lr=5.3773e-05) (hash(x)=27953926) +3247 train 7.153877 (lr=5.3733e-05) (hash(x)=27004415) +3248 train 6.781514 (lr=5.3693e-05) (hash(x)=20471566) +3249 train 7.011041 (lr=5.3654e-05) (hash(x)=25797941) +3250 val loss 7.1657 +3250 val perplexity 1294.2141 +3250 train 6.918749 (lr=5.3614e-05) (hash(x)=21787064) +3251 train 6.900497 (lr=5.3575e-05) (hash(x)=22974875) +3252 train 7.178724 (lr=5.3535e-05) (hash(x)=28431267) +3253 train 7.084133 (lr=5.3495e-05) (hash(x)=25584910) +3254 train 6.872852 (lr=5.3456e-05) (hash(x)=23888922) +3255 train 7.099912 (lr=5.3416e-05) (hash(x)=22265063) +3256 train 6.670624 (lr=5.3377e-05) (hash(x)=21926624) +3257 train 7.017261 (lr=5.3337e-05) (hash(x)=23073191) +3258 train 7.003231 (lr=5.3298e-05) (hash(x)=24409183) +3259 train 7.102806 (lr=5.3258e-05) (hash(x)=23312114) +3260 train 6.969154 (lr=5.3218e-05) (hash(x)=21001289) +3261 train 7.191983 (lr=5.3179e-05) (hash(x)=25514824) +3262 train 6.943002 (lr=5.3139e-05) (hash(x)=22526800) +3263 train 7.383806 (lr=5.3100e-05) (hash(x)=26905990) +3264 train 7.045146 (lr=5.3060e-05) (hash(x)=24469631) +3265 train 6.882955 (lr=5.3021e-05) (hash(x)=21149081) +3266 train 7.099418 (lr=5.2981e-05) (hash(x)=24696215) +3267 train 7.413184 (lr=5.2942e-05) (hash(x)=27089280) +3268 train 6.963094 (lr=5.2902e-05) (hash(x)=23100446) +3269 train 7.171128 (lr=5.2862e-05) (hash(x)=25061229) +3270 train 7.079191 (lr=5.2823e-05) (hash(x)=24337543) +3271 train 7.141380 (lr=5.2783e-05) (hash(x)=24047679) +3272 train 7.222412 (lr=5.2744e-05) (hash(x)=27616773) +3273 train 7.117217 (lr=5.2704e-05) (hash(x)=25315110) +3274 train 7.173608 (lr=5.2665e-05) (hash(x)=28354645) +3275 train 7.040140 (lr=5.2625e-05) (hash(x)=25034684) +3276 train 7.080457 (lr=5.2586e-05) (hash(x)=23550342) +3277 train 7.766521 (lr=5.2546e-05) (hash(x)=28661487) +3278 train 7.312929 (lr=5.2506e-05) (hash(x)=24724622) +3279 train 7.254720 (lr=5.2467e-05) (hash(x)=26905582) +3280 train 7.365082 (lr=5.2427e-05) (hash(x)=26838818) +3281 train 7.046571 (lr=5.2388e-05) (hash(x)=23949017) +3282 train 6.552548 (lr=5.2348e-05) (hash(x)=18846300) +3283 train 6.925761 (lr=5.2309e-05) (hash(x)=21406950) +3284 train 6.761380 (lr=5.2269e-05) (hash(x)=21157696) +3285 train 6.859032 (lr=5.2230e-05) (hash(x)=21440152) +3286 train 7.036348 (lr=5.2190e-05) (hash(x)=26749182) +3287 train 7.239441 (lr=5.2151e-05) (hash(x)=29018970) +3288 train 7.208063 (lr=5.2111e-05) (hash(x)=27577517) +3289 train 6.803941 (lr=5.2072e-05) (hash(x)=19190537) +3290 train 6.848770 (lr=5.2032e-05) (hash(x)=21957991) +3291 train 6.873558 (lr=5.1993e-05) (hash(x)=20853530) +3292 train 6.795363 (lr=5.1953e-05) (hash(x)=22291731) +3293 train 6.996900 (lr=5.1914e-05) (hash(x)=23786853) +3294 train 7.152802 (lr=5.1874e-05) (hash(x)=25740147) +3295 train 7.264665 (lr=5.1835e-05) (hash(x)=24503315) +3296 train 7.018249 (lr=5.1795e-05) (hash(x)=22541728) +3297 train 7.323743 (lr=5.1756e-05) (hash(x)=27067328) +3298 train 6.971559 (lr=5.1716e-05) (hash(x)=22600715) +3299 train 6.971979 (lr=5.1677e-05) (hash(x)=23080074) +3300 val loss 7.1609 +3300 val perplexity 1288.0336 +3300 train 6.766130 (lr=5.1637e-05) (hash(x)=22097758) +3301 train 6.959410 (lr=5.1598e-05) (hash(x)=24105430) +3302 train 6.848013 (lr=5.1558e-05) (hash(x)=23343775) +3303 train 7.085985 (lr=5.1519e-05) (hash(x)=22607537) +3304 train 7.146168 (lr=5.1479e-05) (hash(x)=26501182) +3305 train 7.419655 (lr=5.1440e-05) (hash(x)=26063650) +3306 train 7.008843 (lr=5.1400e-05) (hash(x)=23486602) +3307 train 7.983051 (lr=5.1361e-05) (hash(x)=32179773) +3308 train 11.254981 (lr=5.1321e-05) (hash(x)=66155855) +3309 train 8.455606 (lr=5.1282e-05) (hash(x)=37724427) +3310 train 7.525533 (lr=5.1242e-05) (hash(x)=28861610) +3311 train 7.481259 (lr=5.1203e-05) (hash(x)=26690225) +3312 train 7.038710 (lr=5.1163e-05) (hash(x)=24136450) +3313 train 7.194191 (lr=5.1124e-05) (hash(x)=23702010) +3314 train 7.426018 (lr=5.1085e-05) (hash(x)=28761762) +3315 train 6.770142 (lr=5.1045e-05) (hash(x)=22109609) +3316 train 7.165321 (lr=5.1006e-05) (hash(x)=25168631) +3317 train 7.094397 (lr=5.0966e-05) (hash(x)=24503786) +3318 train 7.064327 (lr=5.0927e-05) (hash(x)=23698606) +3319 train 7.139474 (lr=5.0887e-05) (hash(x)=24226255) +3320 train 7.705260 (lr=5.0848e-05) (hash(x)=31110577) +3321 train 7.072329 (lr=5.0808e-05) (hash(x)=24752754) +3322 train 6.921070 (lr=5.0769e-05) (hash(x)=21135610) +3323 train 6.880546 (lr=5.0730e-05) (hash(x)=23013573) +3324 train 6.607651 (lr=5.0690e-05) (hash(x)=20289715) +3325 train 6.911069 (lr=5.0651e-05) (hash(x)=22700287) +3326 train 6.976628 (lr=5.0611e-05) (hash(x)=21320362) +3327 train 7.126300 (lr=5.0572e-05) (hash(x)=23622702) +3328 train 7.351221 (lr=5.0533e-05) (hash(x)=27435461) +3329 train 7.122192 (lr=5.0493e-05) (hash(x)=25435452) +3330 train 7.140485 (lr=5.0454e-05) (hash(x)=27952557) +3331 train 6.790493 (lr=5.0414e-05) (hash(x)=21517429) +3332 train 6.916715 (lr=5.0375e-05) (hash(x)=24288985) +3333 train 7.094319 (lr=5.0336e-05) (hash(x)=23374788) +3334 train 6.905548 (lr=5.0296e-05) (hash(x)=22042499) +3335 train 7.171392 (lr=5.0257e-05) (hash(x)=23910425) +3336 train 7.489471 (lr=5.0217e-05) (hash(x)=28118508) +3337 train 7.280733 (lr=5.0178e-05) (hash(x)=26737440) +3338 train 7.053440 (lr=5.0139e-05) (hash(x)=24472271) +3339 train 6.985376 (lr=5.0099e-05) (hash(x)=24407484) +3340 train 7.561083 (lr=5.0060e-05) (hash(x)=27908937) +3341 train 7.687016 (lr=5.0021e-05) (hash(x)=29038937) +3342 train 7.425869 (lr=4.9981e-05) (hash(x)=24802580) +3343 train 7.446274 (lr=4.9942e-05) (hash(x)=27213318) +3344 train 7.485359 (lr=4.9903e-05) (hash(x)=28693458) +3345 train 6.761752 (lr=4.9863e-05) (hash(x)=20332324) +3346 train 7.174021 (lr=4.9824e-05) (hash(x)=26726007) +3347 train 7.066182 (lr=4.9785e-05) (hash(x)=25524191) +3348 train 7.150161 (lr=4.9745e-05) (hash(x)=25553293) +3349 train 7.058458 (lr=4.9706e-05) (hash(x)=25614848) +3350 val loss 7.1559 +3350 val perplexity 1281.6002 +3350 train 7.178411 (lr=4.9667e-05) (hash(x)=25747903) +3351 train 7.136533 (lr=4.9627e-05) (hash(x)=26701577) +3352 train 6.869873 (lr=4.9588e-05) (hash(x)=21964135) +3353 train 7.028427 (lr=4.9549e-05) (hash(x)=24461007) +3354 train 7.044485 (lr=4.9509e-05) (hash(x)=25818495) +3355 train 6.859325 (lr=4.9470e-05) (hash(x)=22091266) +3356 train 6.890969 (lr=4.9431e-05) (hash(x)=24476213) +3357 train 7.272299 (lr=4.9391e-05) (hash(x)=24500423) +3358 train 7.003636 (lr=4.9352e-05) (hash(x)=21754841) +3359 train 7.350554 (lr=4.9313e-05) (hash(x)=26216794) +3360 train 6.813680 (lr=4.9274e-05) (hash(x)=24267249) +3361 train 7.167957 (lr=4.9234e-05) (hash(x)=23143515) +3362 train 7.044198 (lr=4.9195e-05) (hash(x)=24120302) +3363 train 7.169624 (lr=4.9156e-05) (hash(x)=20817340) +3364 train 7.176620 (lr=4.9117e-05) (hash(x)=22285847) +3365 train 7.461348 (lr=4.9077e-05) (hash(x)=28151597) +3366 train 7.858064 (lr=4.9038e-05) (hash(x)=31593285) +3367 train 7.483630 (lr=4.8999e-05) (hash(x)=27579623) +3368 train 7.167889 (lr=4.8960e-05) (hash(x)=24995988) +3369 train 6.801226 (lr=4.8920e-05) (hash(x)=22166810) +3370 train 7.074440 (lr=4.8881e-05) (hash(x)=23948298) +3371 train 6.981334 (lr=4.8842e-05) (hash(x)=21532187) +3372 train 7.046064 (lr=4.8803e-05) (hash(x)=23571652) +3373 train 7.409064 (lr=4.8763e-05) (hash(x)=26911513) +3374 train 7.354423 (lr=4.8724e-05) (hash(x)=24011329) +3375 train 7.532451 (lr=4.8685e-05) (hash(x)=26086198) +3376 train 7.107624 (lr=4.8646e-05) (hash(x)=22844402) +3377 train 7.042275 (lr=4.8607e-05) (hash(x)=21817762) +3378 train 7.109140 (lr=4.8567e-05) (hash(x)=23903232) +3379 train 7.085977 (lr=4.8528e-05) (hash(x)=23911729) +3380 train 7.051967 (lr=4.8489e-05) (hash(x)=24485288) +3381 train 7.249861 (lr=4.8450e-05) (hash(x)=27955492) +3382 train 6.944435 (lr=4.8411e-05) (hash(x)=25884586) +3383 train 7.171678 (lr=4.8371e-05) (hash(x)=24863441) +3384 train 7.480363 (lr=4.8332e-05) (hash(x)=22045992) +3385 train 7.577587 (lr=4.8293e-05) (hash(x)=29174796) +3386 train 7.844823 (lr=4.8254e-05) (hash(x)=32589942) +3387 train 7.447412 (lr=4.8215e-05) (hash(x)=28856978) +3388 train 6.925507 (lr=4.8176e-05) (hash(x)=21667904) +3389 train 6.922204 (lr=4.8137e-05) (hash(x)=23431801) +3390 train 6.714769 (lr=4.8097e-05) (hash(x)=20877285) +3391 train 6.998856 (lr=4.8058e-05) (hash(x)=25236385) +3392 train 7.253060 (lr=4.8019e-05) (hash(x)=25373071) +3393 train 7.378212 (lr=4.7980e-05) (hash(x)=25713464) +3394 train 7.335614 (lr=4.7941e-05) (hash(x)=25713475) +3395 train 7.225235 (lr=4.7902e-05) (hash(x)=24278687) +3396 train 7.320177 (lr=4.7863e-05) (hash(x)=27491349) +3397 train 7.207424 (lr=4.7824e-05) (hash(x)=24513692) +3398 train 7.334812 (lr=4.7784e-05) (hash(x)=26853415) +3399 train 7.399760 (lr=4.7745e-05) (hash(x)=25330803) +3400 val loss 7.1535 +3400 val perplexity 1278.5873 +3400 train 7.370831 (lr=4.7706e-05) (hash(x)=26578066) +3401 train 7.389366 (lr=4.7667e-05) (hash(x)=26811522) +3402 train 7.064907 (lr=4.7628e-05) (hash(x)=25611092) +3403 train 6.859709 (lr=4.7589e-05) (hash(x)=21568545) +3404 train 6.891487 (lr=4.7550e-05) (hash(x)=22756484) +3405 train 7.149481 (lr=4.7511e-05) (hash(x)=27927608) +3406 train 7.189945 (lr=4.7472e-05) (hash(x)=27497018) +3407 train 6.993824 (lr=4.7433e-05) (hash(x)=22508532) +3408 train 7.442372 (lr=4.7394e-05) (hash(x)=26673287) +3409 train 7.092665 (lr=4.7355e-05) (hash(x)=23675869) +3410 train 7.024217 (lr=4.7316e-05) (hash(x)=25496948) +3411 train 6.987905 (lr=4.7277e-05) (hash(x)=24850662) +3412 train 7.256757 (lr=4.7238e-05) (hash(x)=29790167) +3413 train 6.911361 (lr=4.7199e-05) (hash(x)=24193434) +3414 train 7.303030 (lr=4.7160e-05) (hash(x)=25310919) +3415 train 6.975216 (lr=4.7121e-05) (hash(x)=21799261) +3416 train 7.268846 (lr=4.7082e-05) (hash(x)=26620074) +3417 train 7.213312 (lr=4.7043e-05) (hash(x)=26719309) +3418 train 7.584724 (lr=4.7004e-05) (hash(x)=23190530) +3419 train 7.170166 (lr=4.6965e-05) (hash(x)=24884891) +3420 train 7.176807 (lr=4.6926e-05) (hash(x)=25545849) +3421 train 7.123625 (lr=4.6887e-05) (hash(x)=26021405) +3422 train 7.061736 (lr=4.6848e-05) (hash(x)=23887343) +3423 train 7.155437 (lr=4.6809e-05) (hash(x)=26311168) +3424 train 6.791521 (lr=4.6770e-05) (hash(x)=21051541) +3425 train 7.200824 (lr=4.6731e-05) (hash(x)=23553179) +3426 train 7.032512 (lr=4.6692e-05) (hash(x)=24345540) +3427 train 7.513115 (lr=4.6653e-05) (hash(x)=27549895) +3428 train 6.844220 (lr=4.6615e-05) (hash(x)=22559753) +3429 train 6.809780 (lr=4.6576e-05) (hash(x)=21647642) +3430 train 6.700476 (lr=4.6537e-05) (hash(x)=20130901) +3431 train 6.847688 (lr=4.6498e-05) (hash(x)=20977430) +3432 train 6.862245 (lr=4.6459e-05) (hash(x)=21356429) +3433 train 6.865416 (lr=4.6420e-05) (hash(x)=23494380) +3434 train 7.084756 (lr=4.6381e-05) (hash(x)=23805501) +3435 train 7.084999 (lr=4.6342e-05) (hash(x)=23448855) +3436 train 7.426790 (lr=4.6303e-05) (hash(x)=26000319) +3437 train 6.909041 (lr=4.6265e-05) (hash(x)=21760032) +3438 train 7.028069 (lr=4.6226e-05) (hash(x)=24424886) +3439 train 7.414480 (lr=4.6187e-05) (hash(x)=26941617) +3440 train 7.443843 (lr=4.6148e-05) (hash(x)=26798528) +3441 train 7.458059 (lr=4.6109e-05) (hash(x)=27464193) +3442 train 7.369335 (lr=4.6070e-05) (hash(x)=25649118) +3443 train 7.358450 (lr=4.6032e-05) (hash(x)=26953192) +3444 train 7.237504 (lr=4.5993e-05) (hash(x)=22224958) +3445 train 7.022991 (lr=4.5954e-05) (hash(x)=24044587) +3446 train 7.486331 (lr=4.5915e-05) (hash(x)=29584466) +3447 train 7.861309 (lr=4.5877e-05) (hash(x)=30008957) +3448 train 7.714694 (lr=4.5838e-05) (hash(x)=26059290) +3449 train 6.700504 (lr=4.5799e-05) (hash(x)=19733965) +3450 val loss 7.1697 +3450 val perplexity 1299.4655 +3450 train 7.182146 (lr=4.5760e-05) (hash(x)=23960200) +3451 train 7.400932 (lr=4.5721e-05) (hash(x)=27069893) +3452 train 7.022536 (lr=4.5683e-05) (hash(x)=23947772) +3453 train 7.108341 (lr=4.5644e-05) (hash(x)=22707406) +3454 train 7.292567 (lr=4.5605e-05) (hash(x)=27832550) +3455 train 7.154397 (lr=4.5567e-05) (hash(x)=27125962) +3456 train 7.020888 (lr=4.5528e-05) (hash(x)=24510254) +3457 train 6.813281 (lr=4.5489e-05) (hash(x)=23545652) +3458 train 6.873003 (lr=4.5450e-05) (hash(x)=23554751) +3459 train 7.027353 (lr=4.5412e-05) (hash(x)=23341415) +3460 train 7.181516 (lr=4.5373e-05) (hash(x)=21784583) +3461 train 6.975412 (lr=4.5334e-05) (hash(x)=22214769) +3462 train 7.063587 (lr=4.5296e-05) (hash(x)=24206922) +3463 train 7.157049 (lr=4.5257e-05) (hash(x)=25888358) +3464 train 6.976776 (lr=4.5218e-05) (hash(x)=22689666) +3465 train 7.081431 (lr=4.5180e-05) (hash(x)=24918697) +3466 train 7.392087 (lr=4.5141e-05) (hash(x)=28237214) +3467 train 7.481596 (lr=4.5102e-05) (hash(x)=26761645) +3468 train 7.145650 (lr=4.5064e-05) (hash(x)=26979307) +3469 train 7.047006 (lr=4.5025e-05) (hash(x)=23553754) +3470 train 7.205006 (lr=4.4987e-05) (hash(x)=25256849) +3471 train 7.017419 (lr=4.4948e-05) (hash(x)=21725719) +3472 train 7.135771 (lr=4.4909e-05) (hash(x)=24897801) +3473 train 7.073413 (lr=4.4871e-05) (hash(x)=26175307) +3474 train 6.907539 (lr=4.4832e-05) (hash(x)=23309218) +3475 train 6.973886 (lr=4.4794e-05) (hash(x)=25746493) +3476 train 7.297223 (lr=4.4755e-05) (hash(x)=27169613) +3477 train 6.989899 (lr=4.4717e-05) (hash(x)=22937341) +3478 train 7.090474 (lr=4.4678e-05) (hash(x)=24250636) +3479 train 6.901933 (lr=4.4639e-05) (hash(x)=21669704) +3480 train 6.899553 (lr=4.4601e-05) (hash(x)=24431839) +3481 train 6.981943 (lr=4.4562e-05) (hash(x)=22763387) +3482 train 6.920833 (lr=4.4524e-05) (hash(x)=20489446) +3483 train 6.932116 (lr=4.4485e-05) (hash(x)=21167493) +3484 train 6.919730 (lr=4.4447e-05) (hash(x)=23465087) +3485 train 7.163336 (lr=4.4408e-05) (hash(x)=26175023) +3486 train 7.254633 (lr=4.4370e-05) (hash(x)=24986207) +3487 train 6.815897 (lr=4.4331e-05) (hash(x)=23166993) +3488 train 7.109806 (lr=4.4293e-05) (hash(x)=25281216) +3489 train 6.907752 (lr=4.4254e-05) (hash(x)=21824285) +3490 train 6.926468 (lr=4.4216e-05) (hash(x)=22352750) +3491 train 7.128725 (lr=4.4178e-05) (hash(x)=23947208) +3492 train 7.203909 (lr=4.4139e-05) (hash(x)=26257363) +3493 train 7.079601 (lr=4.4101e-05) (hash(x)=25103214) +3494 train 7.134792 (lr=4.4062e-05) (hash(x)=25267583) +3495 train 7.197777 (lr=4.4024e-05) (hash(x)=26235974) +3496 train 7.369438 (lr=4.3985e-05) (hash(x)=26430769) +3497 train 7.760746 (lr=4.3947e-05) (hash(x)=28282027) +3498 train 7.634902 (lr=4.3909e-05) (hash(x)=28386462) +3499 train 7.283718 (lr=4.3870e-05) (hash(x)=29822604) +3500 val loss 7.1465 +3500 val perplexity 1269.6151 +3500 train 7.204989 (lr=4.3832e-05) (hash(x)=29225386) +3501 train 7.063200 (lr=4.3794e-05) (hash(x)=25249294) +3502 train 6.789040 (lr=4.3755e-05) (hash(x)=20020741) +3503 train 6.992849 (lr=4.3717e-05) (hash(x)=25426430) +3504 train 6.943071 (lr=4.3679e-05) (hash(x)=25720411) +3505 train 7.004997 (lr=4.3640e-05) (hash(x)=25602639) +3506 train 7.107967 (lr=4.3602e-05) (hash(x)=26724388) +3507 train 7.003287 (lr=4.3564e-05) (hash(x)=26043735) +3508 train 6.948297 (lr=4.3525e-05) (hash(x)=24955163) +3509 train 6.942870 (lr=4.3487e-05) (hash(x)=20936107) +3510 train 6.934468 (lr=4.3449e-05) (hash(x)=20317378) +3511 train 6.933589 (lr=4.3411e-05) (hash(x)=22966314) +3512 train 7.302487 (lr=4.3372e-05) (hash(x)=25870930) +3513 train 7.116292 (lr=4.3334e-05) (hash(x)=24656635) +3514 train 7.414349 (lr=4.3296e-05) (hash(x)=28576810) +3515 train 7.320477 (lr=4.3258e-05) (hash(x)=27944619) +3516 train 7.134233 (lr=4.3219e-05) (hash(x)=27421509) +3517 train 6.864111 (lr=4.3181e-05) (hash(x)=20844620) +3518 train 7.098914 (lr=4.3143e-05) (hash(x)=28569406) +3519 train 6.959816 (lr=4.3105e-05) (hash(x)=23448505) +3520 train 7.147099 (lr=4.3067e-05) (hash(x)=24852577) +3521 train 7.037481 (lr=4.3028e-05) (hash(x)=23963103) +3522 train 6.906695 (lr=4.2990e-05) (hash(x)=24816516) +3523 train 7.127808 (lr=4.2952e-05) (hash(x)=24205942) +3524 train 6.693325 (lr=4.2914e-05) (hash(x)=20988660) +3525 train 6.775380 (lr=4.2876e-05) (hash(x)=21631366) +3526 train 7.000646 (lr=4.2838e-05) (hash(x)=23499370) +3527 train 7.142966 (lr=4.2799e-05) (hash(x)=26330693) +3528 train 6.778508 (lr=4.2761e-05) (hash(x)=23937176) +3529 train 7.060754 (lr=4.2723e-05) (hash(x)=27345885) +3530 train 6.743794 (lr=4.2685e-05) (hash(x)=21104610) +3531 train 7.158582 (lr=4.2647e-05) (hash(x)=24844466) +3532 train 6.436285 (lr=4.2609e-05) (hash(x)=21055483) +3533 train 6.842092 (lr=4.2571e-05) (hash(x)=23229414) +3534 train 7.137909 (lr=4.2533e-05) (hash(x)=26676920) +3535 train 7.113358 (lr=4.2495e-05) (hash(x)=29550596) +3536 train 6.855545 (lr=4.2457e-05) (hash(x)=22231942) +3537 train 7.042648 (lr=4.2419e-05) (hash(x)=25843852) +3538 train 7.195062 (lr=4.2381e-05) (hash(x)=27110533) +3539 train 6.713787 (lr=4.2343e-05) (hash(x)=20506540) +3540 train 6.839575 (lr=4.2305e-05) (hash(x)=21599346) +3541 train 7.080832 (lr=4.2267e-05) (hash(x)=26395519) +3542 train 7.055472 (lr=4.2229e-05) (hash(x)=25892512) +3543 train 7.074159 (lr=4.2191e-05) (hash(x)=22124892) +3544 train 6.976161 (lr=4.2153e-05) (hash(x)=21882567) +3545 train 7.052577 (lr=4.2115e-05) (hash(x)=24316212) +3546 train 6.987598 (lr=4.2077e-05) (hash(x)=24296310) +3547 train 7.079109 (lr=4.2039e-05) (hash(x)=24867036) +3548 train 7.032906 (lr=4.2001e-05) (hash(x)=23351896) +3549 train 7.005128 (lr=4.1963e-05) (hash(x)=21576408) +3550 val loss 7.1371 +3550 val perplexity 1257.7465 +3550 train 7.153156 (lr=4.1925e-05) (hash(x)=26377338) +3551 train 6.964626 (lr=4.1887e-05) (hash(x)=25607640) +3552 train 7.294925 (lr=4.1850e-05) (hash(x)=27619776) +3553 train 6.794110 (lr=4.1812e-05) (hash(x)=23454533) +3554 train 6.991329 (lr=4.1774e-05) (hash(x)=22542519) +3555 train 7.065126 (lr=4.1736e-05) (hash(x)=26176930) +3556 train 6.825369 (lr=4.1698e-05) (hash(x)=22815181) +3557 train 6.838085 (lr=4.1660e-05) (hash(x)=21821757) +3558 train 6.876188 (lr=4.1623e-05) (hash(x)=23988293) +3559 train 6.801759 (lr=4.1585e-05) (hash(x)=23795894) +3560 train 6.734798 (lr=4.1547e-05) (hash(x)=22898969) +3561 train 6.756094 (lr=4.1509e-05) (hash(x)=21510825) +3562 train 6.690776 (lr=4.1471e-05) (hash(x)=22499317) +3563 train 6.721694 (lr=4.1434e-05) (hash(x)=23756298) +3564 train 6.756469 (lr=4.1396e-05) (hash(x)=23964512) +3565 train 6.853859 (lr=4.1358e-05) (hash(x)=23262803) +3566 train 7.070596 (lr=4.1320e-05) (hash(x)=23347279) +3567 train 6.968491 (lr=4.1283e-05) (hash(x)=24165449) +3568 train 7.080394 (lr=4.1245e-05) (hash(x)=25503946) +3569 train 7.049026 (lr=4.1207e-05) (hash(x)=26532839) +3570 train 6.703461 (lr=4.1170e-05) (hash(x)=21889816) +3571 train 6.986960 (lr=4.1132e-05) (hash(x)=26643739) +3572 train 7.220114 (lr=4.1094e-05) (hash(x)=26826130) +3573 train 7.219539 (lr=4.1057e-05) (hash(x)=25810624) +3574 train 7.064491 (lr=4.1019e-05) (hash(x)=23080331) +3575 train 7.215478 (lr=4.0981e-05) (hash(x)=24697756) +3576 train 7.083433 (lr=4.0944e-05) (hash(x)=25158900) +3577 train 7.226175 (lr=4.0906e-05) (hash(x)=25793633) +3578 train 6.772457 (lr=4.0868e-05) (hash(x)=21468493) +3579 train 7.092026 (lr=4.0831e-05) (hash(x)=24431101) +3580 train 6.968700 (lr=4.0793e-05) (hash(x)=27314357) +3581 train 7.178342 (lr=4.0756e-05) (hash(x)=26286249) +3582 train 7.410492 (lr=4.0718e-05) (hash(x)=25954856) +3583 train 7.302507 (lr=4.0681e-05) (hash(x)=27218899) +3584 train 7.061196 (lr=4.0643e-05) (hash(x)=24249114) +3585 train 6.945038 (lr=4.0606e-05) (hash(x)=23659934) +3586 train 6.954710 (lr=4.0568e-05) (hash(x)=25995600) +3587 train 6.950931 (lr=4.0531e-05) (hash(x)=29462219) +3588 train 7.070975 (lr=4.0493e-05) (hash(x)=23346714) +3589 train 7.194385 (lr=4.0456e-05) (hash(x)=27168432) +3590 train 6.964287 (lr=4.0418e-05) (hash(x)=23954240) +3591 train 6.937036 (lr=4.0381e-05) (hash(x)=24748522) +3592 train 7.135034 (lr=4.0343e-05) (hash(x)=24887007) +3593 train 6.880814 (lr=4.0306e-05) (hash(x)=25539383) +3594 train 6.823798 (lr=4.0268e-05) (hash(x)=20104613) +3595 train 7.316921 (lr=4.0231e-05) (hash(x)=24843486) +3596 train 7.334237 (lr=4.0194e-05) (hash(x)=24357864) +3597 train 7.003714 (lr=4.0156e-05) (hash(x)=23873745) +3598 train 7.193416 (lr=4.0119e-05) (hash(x)=25142829) +3599 train 7.243416 (lr=4.0081e-05) (hash(x)=24965317) +3600 val loss 7.1343 +3600 val perplexity 1254.2966 +3600 train 6.695977 (lr=4.0044e-05) (hash(x)=18505205) +3601 train 6.753592 (lr=4.0007e-05) (hash(x)=23632877) +3602 train 6.977284 (lr=3.9969e-05) (hash(x)=23704554) +3603 train 7.147740 (lr=3.9932e-05) (hash(x)=26584754) +3604 train 6.743688 (lr=3.9895e-05) (hash(x)=20667709) +3605 train 6.661757 (lr=3.9857e-05) (hash(x)=20573248) +3606 train 6.820621 (lr=3.9820e-05) (hash(x)=23998997) +3607 train 6.987638 (lr=3.9783e-05) (hash(x)=22031210) +3608 train 7.034643 (lr=3.9746e-05) (hash(x)=24124536) +3609 train 6.940462 (lr=3.9708e-05) (hash(x)=22650144) +3610 train 7.014401 (lr=3.9671e-05) (hash(x)=23796998) +3611 train 7.077527 (lr=3.9634e-05) (hash(x)=24860582) +3612 train 6.561630 (lr=3.9597e-05) (hash(x)=20591300) +3613 train 7.018953 (lr=3.9559e-05) (hash(x)=23447130) +3614 train 7.017313 (lr=3.9522e-05) (hash(x)=26237963) +3615 train 7.142828 (lr=3.9485e-05) (hash(x)=25877990) +3616 train 6.933193 (lr=3.9448e-05) (hash(x)=24808003) +3617 train 7.123529 (lr=3.9411e-05) (hash(x)=24103543) +3618 train 7.053784 (lr=3.9374e-05) (hash(x)=24877184) +3619 train 7.121736 (lr=3.9337e-05) (hash(x)=24970646) +3620 train 7.092340 (lr=3.9299e-05) (hash(x)=25764524) +3621 train 7.209274 (lr=3.9262e-05) (hash(x)=25313591) +3622 train 7.097543 (lr=3.9225e-05) (hash(x)=23260940) +3623 train 7.015538 (lr=3.9188e-05) (hash(x)=24382381) +3624 train 6.945402 (lr=3.9151e-05) (hash(x)=24618902) +3625 train 7.136990 (lr=3.9114e-05) (hash(x)=25074871) +3626 train 6.861184 (lr=3.9077e-05) (hash(x)=24472251) +3627 train 6.997707 (lr=3.9040e-05) (hash(x)=25221746) +3628 train 7.081108 (lr=3.9003e-05) (hash(x)=27448790) +3629 train 7.059134 (lr=3.8966e-05) (hash(x)=25221431) +3630 train 6.614772 (lr=3.8929e-05) (hash(x)=22034366) +3631 train 7.185193 (lr=3.8892e-05) (hash(x)=24551999) +3632 train 6.904369 (lr=3.8855e-05) (hash(x)=24330217) +3633 train 6.995605 (lr=3.8818e-05) (hash(x)=22792380) +3634 train 6.814212 (lr=3.8781e-05) (hash(x)=22393767) +3635 train 7.129939 (lr=3.8744e-05) (hash(x)=28151378) +3636 train 7.149781 (lr=3.8707e-05) (hash(x)=26999341) +3637 train 7.171254 (lr=3.8670e-05) (hash(x)=27251870) +3638 train 7.075058 (lr=3.8633e-05) (hash(x)=23439462) +3639 train 7.173140 (lr=3.8597e-05) (hash(x)=25765516) +3640 train 7.052122 (lr=3.8560e-05) (hash(x)=24720171) +3641 train 7.247197 (lr=3.8523e-05) (hash(x)=23927187) +3642 train 7.022046 (lr=3.8486e-05) (hash(x)=23879561) +3643 train 7.130441 (lr=3.8449e-05) (hash(x)=25630696) +3644 train 6.729268 (lr=3.8412e-05) (hash(x)=22030016) +3645 train 7.200371 (lr=3.8376e-05) (hash(x)=28781600) +3646 train 7.230927 (lr=3.8339e-05) (hash(x)=26668019) +3647 train 7.258426 (lr=3.8302e-05) (hash(x)=25204247) +3648 train 7.439731 (lr=3.8265e-05) (hash(x)=31261394) +3649 train 7.247179 (lr=3.8228e-05) (hash(x)=26193103) +3650 val loss 7.1354 +3650 val perplexity 1255.6940 +3650 train 7.073248 (lr=3.8192e-05) (hash(x)=23872456) +3651 train 7.000774 (lr=3.8155e-05) (hash(x)=26326447) +3652 train 6.954245 (lr=3.8118e-05) (hash(x)=26449631) +3653 train 7.258951 (lr=3.8082e-05) (hash(x)=26373461) +3654 train 7.092443 (lr=3.8045e-05) (hash(x)=24882768) +3655 train 7.165485 (lr=3.8008e-05) (hash(x)=26321813) +3656 train 7.181929 (lr=3.7972e-05) (hash(x)=27056428) +3657 train 7.125481 (lr=3.7935e-05) (hash(x)=24583976) +3658 train 6.847803 (lr=3.7898e-05) (hash(x)=22259624) +3659 train 7.025688 (lr=3.7862e-05) (hash(x)=25400396) +3660 train 6.880936 (lr=3.7825e-05) (hash(x)=21095507) +3661 train 7.121005 (lr=3.7788e-05) (hash(x)=27231042) +3662 train 6.881444 (lr=3.7752e-05) (hash(x)=27292771) +3663 train 7.286573 (lr=3.7715e-05) (hash(x)=25528323) +3664 train 7.080335 (lr=3.7679e-05) (hash(x)=24374502) +3665 train 6.857071 (lr=3.7642e-05) (hash(x)=22463800) +3666 train 7.157429 (lr=3.7606e-05) (hash(x)=25413960) +3667 train 7.067559 (lr=3.7569e-05) (hash(x)=24035353) +3668 train 6.981021 (lr=3.7533e-05) (hash(x)=24815852) +3669 train 6.877489 (lr=3.7496e-05) (hash(x)=22995856) +3670 train 7.153368 (lr=3.7460e-05) (hash(x)=28128238) +3671 train 7.168497 (lr=3.7423e-05) (hash(x)=25114729) +3672 train 6.888383 (lr=3.7387e-05) (hash(x)=19337726) +3673 train 7.360645 (lr=3.7350e-05) (hash(x)=26674420) +3674 train 6.849414 (lr=3.7314e-05) (hash(x)=22553270) +3675 train 6.683236 (lr=3.7277e-05) (hash(x)=21634962) +3676 train 6.877352 (lr=3.7241e-05) (hash(x)=23362669) +3677 train 7.088217 (lr=3.7205e-05) (hash(x)=24781824) +3678 train 6.535100 (lr=3.7168e-05) (hash(x)=17909688) +3679 train 7.730559 (lr=3.7132e-05) (hash(x)=31341964) +3680 train 7.307890 (lr=3.7096e-05) (hash(x)=29071335) +3681 train 6.734783 (lr=3.7059e-05) (hash(x)=19486640) +3682 train 6.896248 (lr=3.7023e-05) (hash(x)=24301133) +3683 train 7.131004 (lr=3.6987e-05) (hash(x)=29172813) +3684 train 7.640782 (lr=3.6950e-05) (hash(x)=31501337) +3685 train 7.251473 (lr=3.6914e-05) (hash(x)=27377840) +3686 train 7.021501 (lr=3.6878e-05) (hash(x)=24499761) +3687 train 7.031301 (lr=3.6842e-05) (hash(x)=26326024) +3688 train 6.967888 (lr=3.6805e-05) (hash(x)=23179996) +3689 train 6.657029 (lr=3.6769e-05) (hash(x)=20963675) +3690 train 6.984338 (lr=3.6733e-05) (hash(x)=26650521) +3691 train 6.700220 (lr=3.6697e-05) (hash(x)=20140071) +3692 train 6.693928 (lr=3.6661e-05) (hash(x)=21734340) +3693 train 7.015608 (lr=3.6625e-05) (hash(x)=23848422) +3694 train 7.073050 (lr=3.6588e-05) (hash(x)=27499953) +3695 train 7.317773 (lr=3.6552e-05) (hash(x)=27273311) +3696 train 7.246073 (lr=3.6516e-05) (hash(x)=25741091) +3697 train 6.973986 (lr=3.6480e-05) (hash(x)=22010794) +3698 train 7.074765 (lr=3.6444e-05) (hash(x)=24616138) +3699 train 7.431591 (lr=3.6408e-05) (hash(x)=31276487) +3700 val loss 7.1347 +3700 val perplexity 1254.7520 +3700 train 7.070241 (lr=3.6372e-05) (hash(x)=24042922) +3701 train 6.848796 (lr=3.6336e-05) (hash(x)=21985431) +3702 train 6.699677 (lr=3.6300e-05) (hash(x)=21336316) +3703 train 6.517236 (lr=3.6264e-05) (hash(x)=17819313) +3704 train 7.202779 (lr=3.6228e-05) (hash(x)=27033851) +3705 train 7.228539 (lr=3.6192e-05) (hash(x)=27260043) +3706 train 7.306301 (lr=3.6156e-05) (hash(x)=26847649) +3707 train 7.258765 (lr=3.6120e-05) (hash(x)=25843618) +3708 train 7.256042 (lr=3.6084e-05) (hash(x)=25828009) +3709 train 7.236429 (lr=3.6048e-05) (hash(x)=24960960) +3710 train 7.347453 (lr=3.6012e-05) (hash(x)=24852741) +3711 train 6.802457 (lr=3.5976e-05) (hash(x)=23769243) +3712 train 7.031156 (lr=3.5940e-05) (hash(x)=27110690) +3713 train 7.002872 (lr=3.5904e-05) (hash(x)=22817285) +3714 train 6.722854 (lr=3.5869e-05) (hash(x)=19618355) +3715 train 7.290656 (lr=3.5833e-05) (hash(x)=28731298) +3716 train 7.005032 (lr=3.5797e-05) (hash(x)=23091196) +3717 train 7.571858 (lr=3.5761e-05) (hash(x)=28825233) +3718 train 7.090446 (lr=3.5725e-05) (hash(x)=25778506) +3719 train 7.049296 (lr=3.5690e-05) (hash(x)=23788738) +3720 train 6.332336 (lr=3.5654e-05) (hash(x)=16684794) +3721 train 6.913268 (lr=3.5618e-05) (hash(x)=24755102) +3722 train 7.221091 (lr=3.5582e-05) (hash(x)=26839238) +3723 train 7.222126 (lr=3.5547e-05) (hash(x)=26599031) +3724 train 7.085629 (lr=3.5511e-05) (hash(x)=25945650) +3725 train 7.288311 (lr=3.5475e-05) (hash(x)=27434751) +3726 train 6.990199 (lr=3.5440e-05) (hash(x)=24814591) +3727 train 6.972614 (lr=3.5404e-05) (hash(x)=24818744) +3728 train 7.056462 (lr=3.5368e-05) (hash(x)=25649817) +3729 train 6.963872 (lr=3.5333e-05) (hash(x)=24987021) +3730 train 6.895769 (lr=3.5297e-05) (hash(x)=24667779) +3731 train 6.885812 (lr=3.5261e-05) (hash(x)=23053871) +3732 train 6.572399 (lr=3.5226e-05) (hash(x)=19264856) +3733 train 7.193758 (lr=3.5190e-05) (hash(x)=23718117) +3734 train 6.871974 (lr=3.5155e-05) (hash(x)=21904779) +3735 train 7.080991 (lr=3.5119e-05) (hash(x)=23472795) +3736 train 7.322123 (lr=3.5084e-05) (hash(x)=24650440) +3737 train 7.407407 (lr=3.5048e-05) (hash(x)=25243911) +3738 train 7.838086 (lr=3.5013e-05) (hash(x)=30423616) +3739 train 7.830652 (lr=3.4977e-05) (hash(x)=29748225) +3740 train 7.167532 (lr=3.4942e-05) (hash(x)=25180684) +3741 train 7.189909 (lr=3.4906e-05) (hash(x)=25619065) +3742 train 7.537383 (lr=3.4871e-05) (hash(x)=31847002) +3743 train 7.113905 (lr=3.4835e-05) (hash(x)=24991832) +3744 train 7.024286 (lr=3.4800e-05) (hash(x)=23836263) +3745 train 6.935663 (lr=3.4765e-05) (hash(x)=24651902) +3746 train 7.455006 (lr=3.4729e-05) (hash(x)=22936538) +3747 train 7.437267 (lr=3.4694e-05) (hash(x)=23681545) +3748 train 6.866568 (lr=3.4659e-05) (hash(x)=21140825) +3749 train 7.061965 (lr=3.4623e-05) (hash(x)=24932453) +3750 val loss 7.1384 +3750 val perplexity 1259.3529 +3750 train 7.260777 (lr=3.4588e-05) (hash(x)=25919062) +3751 train 6.985515 (lr=3.4553e-05) (hash(x)=22424066) +3752 train 7.073425 (lr=3.4518e-05) (hash(x)=23542210) +3753 train 6.948923 (lr=3.4482e-05) (hash(x)=22113561) +3754 train 6.821170 (lr=3.4447e-05) (hash(x)=24892794) +3755 train 7.306448 (lr=3.4412e-05) (hash(x)=25262748) +3756 train 7.082793 (lr=3.4377e-05) (hash(x)=24477975) +3757 train 6.855741 (lr=3.4341e-05) (hash(x)=24681189) +3758 train 6.916286 (lr=3.4306e-05) (hash(x)=24052603) +3759 train 7.166149 (lr=3.4271e-05) (hash(x)=26474878) +3760 train 7.694734 (lr=3.4236e-05) (hash(x)=28228836) +3761 train 7.202746 (lr=3.4201e-05) (hash(x)=23832522) +3762 train 7.185278 (lr=3.4166e-05) (hash(x)=24416789) +3763 train 6.928669 (lr=3.4131e-05) (hash(x)=23930593) +3764 train 6.996229 (lr=3.4096e-05) (hash(x)=23895092) +3765 train 6.979225 (lr=3.4060e-05) (hash(x)=26865287) +3766 train 6.948952 (lr=3.4025e-05) (hash(x)=21330722) +3767 train 7.027794 (lr=3.3990e-05) (hash(x)=22704349) +3768 train 7.181102 (lr=3.3955e-05) (hash(x)=27740886) +3769 train 7.165552 (lr=3.3920e-05) (hash(x)=24935936) +3770 train 6.992636 (lr=3.3885e-05) (hash(x)=23497487) +3771 train 7.237686 (lr=3.3850e-05) (hash(x)=24801048) +3772 train 6.982893 (lr=3.3816e-05) (hash(x)=25490486) +3773 train 6.968751 (lr=3.3781e-05) (hash(x)=21166466) +3774 train 7.150920 (lr=3.3746e-05) (hash(x)=23225244) +3775 train 6.987882 (lr=3.3711e-05) (hash(x)=22293673) +3776 train 7.287956 (lr=3.3676e-05) (hash(x)=25700016) +3777 train 6.796963 (lr=3.3641e-05) (hash(x)=22370207) +3778 train 7.165889 (lr=3.3606e-05) (hash(x)=25224849) +3779 train 7.086677 (lr=3.3571e-05) (hash(x)=23311934) +3780 train 6.776362 (lr=3.3537e-05) (hash(x)=19627124) +3781 train 7.295051 (lr=3.3502e-05) (hash(x)=27132838) +3782 train 7.267979 (lr=3.3467e-05) (hash(x)=27242104) +3783 train 6.753025 (lr=3.3432e-05) (hash(x)=21785487) +3784 train 7.091585 (lr=3.3397e-05) (hash(x)=25798262) +3785 train 6.988492 (lr=3.3363e-05) (hash(x)=24806937) +3786 train 6.803957 (lr=3.3328e-05) (hash(x)=24098756) +3787 train 6.812099 (lr=3.3293e-05) (hash(x)=22981456) +3788 train 7.279775 (lr=3.3259e-05) (hash(x)=22441908) +3789 train 7.171987 (lr=3.3224e-05) (hash(x)=25867804) +3790 train 7.067308 (lr=3.3189e-05) (hash(x)=22835586) +3791 train 7.246681 (lr=3.3155e-05) (hash(x)=25251063) +3792 train 7.143736 (lr=3.3120e-05) (hash(x)=27059729) +3793 train 7.108888 (lr=3.3086e-05) (hash(x)=23819311) +3794 train 6.793153 (lr=3.3051e-05) (hash(x)=21345757) +3795 train 7.039379 (lr=3.3016e-05) (hash(x)=25796422) +3796 train 6.749095 (lr=3.2982e-05) (hash(x)=21414971) +3797 train 7.048190 (lr=3.2947e-05) (hash(x)=26120920) +3798 train 6.947441 (lr=3.2913e-05) (hash(x)=22008247) +3799 train 7.034019 (lr=3.2878e-05) (hash(x)=22722211) +3800 val loss 7.1216 +3800 val perplexity 1238.4312 +3800 train 6.787002 (lr=3.2844e-05) (hash(x)=24484513) +3801 train 7.116556 (lr=3.2809e-05) (hash(x)=24463866) +3802 train 7.123451 (lr=3.2775e-05) (hash(x)=26470775) +3803 train 7.110019 (lr=3.2740e-05) (hash(x)=24296755) +3804 train 7.120426 (lr=3.2706e-05) (hash(x)=24381309) +3805 train 7.327460 (lr=3.2672e-05) (hash(x)=26781262) +3806 train 6.813284 (lr=3.2637e-05) (hash(x)=23563137) +3807 train 7.016725 (lr=3.2603e-05) (hash(x)=24522269) +3808 train 6.828580 (lr=3.2569e-05) (hash(x)=22871995) +3809 train 7.194257 (lr=3.2534e-05) (hash(x)=24751946) +3810 train 7.018553 (lr=3.2500e-05) (hash(x)=19879741) +3811 train 7.069273 (lr=3.2466e-05) (hash(x)=25617184) +3812 train 6.739600 (lr=3.2431e-05) (hash(x)=21776722) +3813 train 6.870236 (lr=3.2397e-05) (hash(x)=22663402) +3814 train 7.222604 (lr=3.2363e-05) (hash(x)=26072046) +3815 train 6.878938 (lr=3.2329e-05) (hash(x)=23329475) +3816 train 6.956517 (lr=3.2295e-05) (hash(x)=25519031) +3817 train 6.944304 (lr=3.2260e-05) (hash(x)=22846270) +3818 train 6.942779 (lr=3.2226e-05) (hash(x)=20299429) +3819 train 7.398857 (lr=3.2192e-05) (hash(x)=30652062) +3820 train 6.681805 (lr=3.2158e-05) (hash(x)=19824665) +3821 train 7.273590 (lr=3.2124e-05) (hash(x)=26698904) +3822 train 7.108531 (lr=3.2090e-05) (hash(x)=27612163) +3823 train 6.927314 (lr=3.2056e-05) (hash(x)=24735165) +3824 train 6.633111 (lr=3.2022e-05) (hash(x)=19965890) +3825 train 6.819928 (lr=3.1988e-05) (hash(x)=23518594) +3826 train 6.803623 (lr=3.1954e-05) (hash(x)=22388460) +3827 train 6.872812 (lr=3.1920e-05) (hash(x)=23795686) +3828 train 6.771307 (lr=3.1886e-05) (hash(x)=24470150) +3829 train 6.445783 (lr=3.1852e-05) (hash(x)=19483392) +3830 train 6.876035 (lr=3.1818e-05) (hash(x)=23304516) +3831 train 7.214910 (lr=3.1784e-05) (hash(x)=27002892) +3832 train 6.953500 (lr=3.1750e-05) (hash(x)=22114813) +3833 train 7.115218 (lr=3.1716e-05) (hash(x)=26221916) +3834 train 6.657477 (lr=3.1682e-05) (hash(x)=27261960) +3835 train 6.928489 (lr=3.1648e-05) (hash(x)=21189101) +3836 train 6.610512 (lr=3.1614e-05) (hash(x)=20638173) +3837 train 7.067635 (lr=3.1580e-05) (hash(x)=25497439) +3838 train 6.532077 (lr=3.1547e-05) (hash(x)=20460499) +3839 train 6.973387 (lr=3.1513e-05) (hash(x)=23499349) +3840 train 7.864839 (lr=3.1479e-05) (hash(x)=22671939) +3841 train 7.800055 (lr=3.1445e-05) (hash(x)=26809295) +3842 train 7.093402 (lr=3.1412e-05) (hash(x)=28094504) +3843 train 7.040216 (lr=3.1378e-05) (hash(x)=26807896) +3844 train 7.138612 (lr=3.1344e-05) (hash(x)=24749334) +3845 train 7.059986 (lr=3.1311e-05) (hash(x)=25031330) +3846 train 6.932657 (lr=3.1277e-05) (hash(x)=23008126) +3847 train 6.917378 (lr=3.1243e-05) (hash(x)=22461589) +3848 train 7.165001 (lr=3.1210e-05) (hash(x)=24959391) +3849 train 7.064467 (lr=3.1176e-05) (hash(x)=24239512) +3850 val loss 7.1232 +3850 val perplexity 1240.4039 +3850 train 6.930219 (lr=3.1142e-05) (hash(x)=24760422) +3851 train 7.394743 (lr=3.1109e-05) (hash(x)=26904123) +3852 train 6.490754 (lr=3.1075e-05) (hash(x)=17986444) +3853 train 6.930872 (lr=3.1042e-05) (hash(x)=21618533) +3854 train 6.967258 (lr=3.1008e-05) (hash(x)=27107027) +3855 train 7.224290 (lr=3.0975e-05) (hash(x)=26415040) +3856 train 7.741684 (lr=3.0941e-05) (hash(x)=28682703) +3857 train 6.914844 (lr=3.0908e-05) (hash(x)=22824767) +3858 train 7.092441 (lr=3.0874e-05) (hash(x)=24540450) +3859 train 7.039645 (lr=3.0841e-05) (hash(x)=24463181) +3860 train 6.960654 (lr=3.0808e-05) (hash(x)=22832558) +3861 train 7.168118 (lr=3.0774e-05) (hash(x)=26582384) +3862 train 7.868812 (lr=3.0741e-05) (hash(x)=32327364) +3863 train 7.195433 (lr=3.0708e-05) (hash(x)=26349465) +3864 train 6.950583 (lr=3.0674e-05) (hash(x)=23079414) +3865 train 6.985291 (lr=3.0641e-05) (hash(x)=23464639) +3866 train 6.804447 (lr=3.0608e-05) (hash(x)=21406620) +3867 train 6.633623 (lr=3.0574e-05) (hash(x)=21205988) +3868 train 6.712148 (lr=3.0541e-05) (hash(x)=22742634) +3869 train 6.761690 (lr=3.0508e-05) (hash(x)=24868938) +3870 train 7.173701 (lr=3.0475e-05) (hash(x)=28095283) +3871 train 6.854703 (lr=3.0441e-05) (hash(x)=21596677) +3872 train 7.049161 (lr=3.0408e-05) (hash(x)=26884381) +3873 train 7.143625 (lr=3.0375e-05) (hash(x)=26410272) +3874 train 6.948999 (lr=3.0342e-05) (hash(x)=22915785) +3875 train 6.919699 (lr=3.0309e-05) (hash(x)=23575666) +3876 train 6.904463 (lr=3.0276e-05) (hash(x)=25313223) +3877 train 6.297148 (lr=3.0243e-05) (hash(x)=16319719) +3878 train 7.026267 (lr=3.0210e-05) (hash(x)=23227579) +3879 train 6.921570 (lr=3.0177e-05) (hash(x)=24117012) +3880 train 7.022704 (lr=3.0144e-05) (hash(x)=24681517) +3881 train 6.939816 (lr=3.0111e-05) (hash(x)=23186527) +3882 train 6.923233 (lr=3.0078e-05) (hash(x)=23472784) +3883 train 6.918868 (lr=3.0045e-05) (hash(x)=26013014) +3884 train 7.074748 (lr=3.0012e-05) (hash(x)=25952206) +3885 train 7.266810 (lr=2.9979e-05) (hash(x)=23897834) +3886 train 6.971779 (lr=2.9946e-05) (hash(x)=26350364) +3887 train 7.013419 (lr=2.9913e-05) (hash(x)=24105761) +3888 train 7.093251 (lr=2.9880e-05) (hash(x)=22801707) +3889 train 6.941818 (lr=2.9847e-05) (hash(x)=21821937) +3890 train 6.885367 (lr=2.9814e-05) (hash(x)=24264640) +3891 train 6.816034 (lr=2.9782e-05) (hash(x)=20369133) +3892 train 6.790411 (lr=2.9749e-05) (hash(x)=24313506) +3893 train 6.835435 (lr=2.9716e-05) (hash(x)=22104086) +3894 train 7.049918 (lr=2.9683e-05) (hash(x)=25312602) +3895 train 7.126865 (lr=2.9651e-05) (hash(x)=25725049) +3896 train 6.942673 (lr=2.9618e-05) (hash(x)=22981231) +3897 train 6.779183 (lr=2.9585e-05) (hash(x)=18021467) +3898 train 6.746675 (lr=2.9553e-05) (hash(x)=17960254) +3899 train 6.943507 (lr=2.9520e-05) (hash(x)=19808118) +3900 val loss 7.1178 +3900 val perplexity 1233.7488 +3900 train 6.707670 (lr=2.9487e-05) (hash(x)=21022829) +3901 train 6.878623 (lr=2.9455e-05) (hash(x)=22434663) +3902 train 6.622908 (lr=2.9422e-05) (hash(x)=20208091) +3903 train 6.775033 (lr=2.9389e-05) (hash(x)=22892776) +3904 train 6.890543 (lr=2.9357e-05) (hash(x)=21554367) +3905 train 7.012418 (lr=2.9324e-05) (hash(x)=23704875) +3906 train 7.011228 (lr=2.9292e-05) (hash(x)=21690340) +3907 train 6.912842 (lr=2.9259e-05) (hash(x)=23736780) +3908 train 6.777201 (lr=2.9227e-05) (hash(x)=21060920) +3909 train 6.734700 (lr=2.9194e-05) (hash(x)=20091559) +3910 train 6.997702 (lr=2.9162e-05) (hash(x)=22147974) +3911 train 6.950674 (lr=2.9130e-05) (hash(x)=21630383) +3912 train 7.240246 (lr=2.9097e-05) (hash(x)=28339385) +3913 train 7.002183 (lr=2.9065e-05) (hash(x)=25355505) +3914 train 6.855289 (lr=2.9033e-05) (hash(x)=20843914) +3915 train 7.352769 (lr=2.9000e-05) (hash(x)=25397467) +3916 train 7.071580 (lr=2.8968e-05) (hash(x)=23587501) +3917 train 6.647397 (lr=2.8936e-05) (hash(x)=19036533) +3918 train 6.888074 (lr=2.8903e-05) (hash(x)=29749389) +3919 train 6.785631 (lr=2.8871e-05) (hash(x)=24727094) +3920 train 6.786265 (lr=2.8839e-05) (hash(x)=22723450) +3921 train 6.985675 (lr=2.8807e-05) (hash(x)=24424680) +3922 train 7.104455 (lr=2.8774e-05) (hash(x)=25817917) +3923 train 6.885776 (lr=2.8742e-05) (hash(x)=23951182) +3924 train 6.925546 (lr=2.8710e-05) (hash(x)=21177944) +3925 train 6.736981 (lr=2.8678e-05) (hash(x)=23533768) +3926 train 6.994064 (lr=2.8646e-05) (hash(x)=24263615) +3927 train 6.784451 (lr=2.8614e-05) (hash(x)=22835000) +3928 train 7.027159 (lr=2.8582e-05) (hash(x)=26076156) +3929 train 6.966483 (lr=2.8550e-05) (hash(x)=25171508) +3930 train 7.002641 (lr=2.8518e-05) (hash(x)=22021396) +3931 train 7.169370 (lr=2.8486e-05) (hash(x)=28767849) +3932 train 7.151038 (lr=2.8454e-05) (hash(x)=29497606) +3933 train 6.849379 (lr=2.8422e-05) (hash(x)=22723124) +3934 train 7.119727 (lr=2.8390e-05) (hash(x)=27106616) +3935 train 7.010452 (lr=2.8358e-05) (hash(x)=22839049) +3936 train 6.987648 (lr=2.8326e-05) (hash(x)=25101923) +3937 train 6.999134 (lr=2.8294e-05) (hash(x)=25945975) +3938 train 7.126518 (lr=2.8262e-05) (hash(x)=25382013) +3939 train 6.633171 (lr=2.8230e-05) (hash(x)=19930900) +3940 train 6.808693 (lr=2.8199e-05) (hash(x)=22202373) +3941 train 7.003555 (lr=2.8167e-05) (hash(x)=24592992) +3942 train 6.906811 (lr=2.8135e-05) (hash(x)=25002271) +3943 train 6.740229 (lr=2.8103e-05) (hash(x)=20654136) +3944 train 6.827472 (lr=2.8071e-05) (hash(x)=20061590) +3945 train 6.750586 (lr=2.8040e-05) (hash(x)=21441361) +3946 train 6.965801 (lr=2.8008e-05) (hash(x)=20055468) +3947 train 7.639375 (lr=2.7976e-05) (hash(x)=28495621) +3948 train 7.087349 (lr=2.7945e-05) (hash(x)=25959236) +3949 train 7.385490 (lr=2.7913e-05) (hash(x)=26750193) +3950 val loss 7.1206 +3950 val perplexity 1237.1515 +3950 train 7.222060 (lr=2.7881e-05) (hash(x)=25882605) +3951 train 7.300110 (lr=2.7850e-05) (hash(x)=26776000) +3952 train 6.859282 (lr=2.7818e-05) (hash(x)=24155107) +3953 train 6.976541 (lr=2.7787e-05) (hash(x)=23441845) +3954 train 6.917934 (lr=2.7755e-05) (hash(x)=22860915) +3955 train 6.646356 (lr=2.7724e-05) (hash(x)=21584429) +3956 train 6.245481 (lr=2.7692e-05) (hash(x)=16535556) +3957 train 6.353455 (lr=2.7661e-05) (hash(x)=17946180) +3958 train 6.937276 (lr=2.7629e-05) (hash(x)=25367610) +3959 train 6.800485 (lr=2.7598e-05) (hash(x)=22560658) +3960 train 7.066949 (lr=2.7566e-05) (hash(x)=23809585) +3961 train 7.296007 (lr=2.7535e-05) (hash(x)=20438213) +3962 train 7.664642 (lr=2.7504e-05) (hash(x)=30520037) +3963 train 7.341022 (lr=2.7472e-05) (hash(x)=25276565) +3964 train 7.052654 (lr=2.7441e-05) (hash(x)=26796532) +3965 train 6.807517 (lr=2.7410e-05) (hash(x)=22850475) +3966 train 7.347946 (lr=2.7379e-05) (hash(x)=25983698) +3967 train 7.197177 (lr=2.7347e-05) (hash(x)=25995933) +3968 train 7.431790 (lr=2.7316e-05) (hash(x)=25319339) +3969 train 7.051843 (lr=2.7285e-05) (hash(x)=25066892) +3970 train 7.246583 (lr=2.7254e-05) (hash(x)=26931819) +3971 train 7.170333 (lr=2.7222e-05) (hash(x)=24163910) +3972 train 7.101772 (lr=2.7191e-05) (hash(x)=25359634) +3973 train 6.979788 (lr=2.7160e-05) (hash(x)=24323444) +3974 train 7.151429 (lr=2.7129e-05) (hash(x)=26529231) +3975 train 7.171805 (lr=2.7098e-05) (hash(x)=24635394) +3976 train 7.476318 (lr=2.7067e-05) (hash(x)=24783093) +3977 train 7.576387 (lr=2.7036e-05) (hash(x)=26710509) +3978 train 6.994949 (lr=2.7005e-05) (hash(x)=25396630) +3979 train 6.895425 (lr=2.6974e-05) (hash(x)=22556381) +3980 train 7.216133 (lr=2.6943e-05) (hash(x)=26912161) +3981 train 6.757588 (lr=2.6912e-05) (hash(x)=22268078) +3982 train 7.809175 (lr=2.6881e-05) (hash(x)=30430328) +3983 train 7.451788 (lr=2.6850e-05) (hash(x)=27537228) +3984 train 6.835459 (lr=2.6819e-05) (hash(x)=24468603) +3985 train 7.169216 (lr=2.6788e-05) (hash(x)=27006663) +3986 train 7.412668 (lr=2.6758e-05) (hash(x)=27014728) +3987 train 6.846756 (lr=2.6727e-05) (hash(x)=20883633) +3988 train 6.969495 (lr=2.6696e-05) (hash(x)=23361791) +3989 train 7.064998 (lr=2.6665e-05) (hash(x)=26775925) +3990 train 7.622212 (lr=2.6634e-05) (hash(x)=30648934) +3991 train 7.124698 (lr=2.6604e-05) (hash(x)=26496730) +3992 train 6.958568 (lr=2.6573e-05) (hash(x)=25942897) +3993 train 6.975277 (lr=2.6542e-05) (hash(x)=24887111) +3994 train 6.879897 (lr=2.6512e-05) (hash(x)=22908550) +3995 train 6.591222 (lr=2.6481e-05) (hash(x)=20342150) +3996 train 6.855712 (lr=2.6450e-05) (hash(x)=22261760) +3997 train 6.936772 (lr=2.6420e-05) (hash(x)=22731641) +3998 train 6.807312 (lr=2.6389e-05) (hash(x)=20669749) +3999 train 6.693205 (lr=2.6359e-05) (hash(x)=16533310) +4000 val loss 7.1130 +4000 val perplexity 1227.8810 +4000 train 6.956467 (lr=2.6328e-05) (hash(x)=23661341) +4001 train 6.940834 (lr=2.6298e-05) (hash(x)=24644301) +4002 train 6.780399 (lr=2.6267e-05) (hash(x)=22938438) +4003 train 6.855608 (lr=2.6237e-05) (hash(x)=24315862) +4004 train 7.073081 (lr=2.6206e-05) (hash(x)=25169315) +4005 train 7.048657 (lr=2.6176e-05) (hash(x)=24752796) +4006 train 7.001415 (lr=2.6145e-05) (hash(x)=23103706) +4007 train 7.118254 (lr=2.6115e-05) (hash(x)=24881176) +4008 train 6.989354 (lr=2.6085e-05) (hash(x)=23971947) +4009 train 7.316092 (lr=2.6054e-05) (hash(x)=27741054) +4010 train 7.696841 (lr=2.6024e-05) (hash(x)=30956251) +4011 train 7.024237 (lr=2.5994e-05) (hash(x)=23649686) +4012 train 6.899214 (lr=2.5963e-05) (hash(x)=23344798) +4013 train 7.536523 (lr=2.5933e-05) (hash(x)=29529498) +4014 train 7.048038 (lr=2.5903e-05) (hash(x)=24688359) +4015 train 7.015501 (lr=2.5873e-05) (hash(x)=25593613) +4016 train 7.133725 (lr=2.5843e-05) (hash(x)=25674488) +4017 train 6.569929 (lr=2.5812e-05) (hash(x)=21345346) +4018 train 6.896854 (lr=2.5782e-05) (hash(x)=21978324) +4019 train 6.919792 (lr=2.5752e-05) (hash(x)=23669244) +4020 train 6.798806 (lr=2.5722e-05) (hash(x)=22479613) +4021 train 6.808807 (lr=2.5692e-05) (hash(x)=22855256) +4022 train 7.188725 (lr=2.5662e-05) (hash(x)=19759826) +4023 train 7.097862 (lr=2.5632e-05) (hash(x)=22886646) +4024 train 7.031093 (lr=2.5602e-05) (hash(x)=25553008) +4025 train 6.934070 (lr=2.5572e-05) (hash(x)=25487028) +4026 train 7.502660 (lr=2.5542e-05) (hash(x)=26799246) +4027 train 7.754510 (lr=2.5512e-05) (hash(x)=30728540) +4028 train 7.234760 (lr=2.5482e-05) (hash(x)=23966676) +4029 train 6.909357 (lr=2.5452e-05) (hash(x)=22118783) +4030 train 7.029565 (lr=2.5423e-05) (hash(x)=24744703) +4031 train 7.049985 (lr=2.5393e-05) (hash(x)=21407676) +4032 train 6.967624 (lr=2.5363e-05) (hash(x)=20623349) +4033 train 6.763423 (lr=2.5333e-05) (hash(x)=24723788) +4034 train 7.086251 (lr=2.5303e-05) (hash(x)=25030709) +4035 train 7.118169 (lr=2.5274e-05) (hash(x)=26326164) +4036 train 6.989428 (lr=2.5244e-05) (hash(x)=23754475) +4037 train 7.596120 (lr=2.5214e-05) (hash(x)=30112933) +4038 train 7.326912 (lr=2.5185e-05) (hash(x)=27474299) +4039 train 6.828002 (lr=2.5155e-05) (hash(x)=21720304) +4040 train 7.225290 (lr=2.5125e-05) (hash(x)=25142674) +4041 train 7.492235 (lr=2.5096e-05) (hash(x)=25284552) +4042 train 7.364039 (lr=2.5066e-05) (hash(x)=24554942) +4043 train 7.126592 (lr=2.5037e-05) (hash(x)=23773870) +4044 train 6.874338 (lr=2.5007e-05) (hash(x)=23896338) +4045 train 7.652104 (lr=2.4978e-05) (hash(x)=34984911) +4046 train 6.933669 (lr=2.4948e-05) (hash(x)=23854263) +4047 train 7.266080 (lr=2.4919e-05) (hash(x)=27263416) +4048 train 6.939867 (lr=2.4889e-05) (hash(x)=24989642) +4049 train 6.949967 (lr=2.4860e-05) (hash(x)=24492055) +4050 val loss 7.1164 +4050 val perplexity 1231.9552 +4050 train 6.866966 (lr=2.4830e-05) (hash(x)=21579916) +4051 train 7.094913 (lr=2.4801e-05) (hash(x)=25274710) +4052 train 6.970107 (lr=2.4772e-05) (hash(x)=24701947) +4053 train 6.951900 (lr=2.4742e-05) (hash(x)=25477340) +4054 train 6.878278 (lr=2.4713e-05) (hash(x)=23774195) +4055 train 7.132710 (lr=2.4684e-05) (hash(x)=25840801) +4056 train 7.303440 (lr=2.4654e-05) (hash(x)=27972529) +4057 train 7.128435 (lr=2.4625e-05) (hash(x)=26952458) +4058 train 6.586481 (lr=2.4596e-05) (hash(x)=22683653) +4059 train 6.651990 (lr=2.4567e-05) (hash(x)=20984129) +4060 train 6.848738 (lr=2.4538e-05) (hash(x)=22816482) +4061 train 7.159888 (lr=2.4509e-05) (hash(x)=24285302) +4062 train 7.565282 (lr=2.4479e-05) (hash(x)=31517950) +4063 train 7.733249 (lr=2.4450e-05) (hash(x)=31424568) +4064 train 7.378619 (lr=2.4421e-05) (hash(x)=29497876) +4065 train 7.316209 (lr=2.4392e-05) (hash(x)=27277376) +4066 train 7.084900 (lr=2.4363e-05) (hash(x)=26832588) +4067 train 6.913115 (lr=2.4334e-05) (hash(x)=25149712) +4068 train 6.935953 (lr=2.4305e-05) (hash(x)=23728457) +4069 train 6.829392 (lr=2.4276e-05) (hash(x)=25265136) +4070 train 7.353373 (lr=2.4247e-05) (hash(x)=25241681) +4071 train 7.032249 (lr=2.4218e-05) (hash(x)=23403065) +4072 train 7.009370 (lr=2.4190e-05) (hash(x)=25808207) +4073 train 6.935869 (lr=2.4161e-05) (hash(x)=23904844) +4074 train 6.577974 (lr=2.4132e-05) (hash(x)=18865309) +4075 train 7.084338 (lr=2.4103e-05) (hash(x)=23531744) +4076 train 7.048118 (lr=2.4074e-05) (hash(x)=25784275) +4077 train 6.846191 (lr=2.4046e-05) (hash(x)=22417529) +4078 train 6.817352 (lr=2.4017e-05) (hash(x)=23095491) +4079 train 6.962112 (lr=2.3988e-05) (hash(x)=22656033) +4080 train 6.983415 (lr=2.3959e-05) (hash(x)=25865435) +4081 train 7.105186 (lr=2.3931e-05) (hash(x)=25699377) +4082 train 7.122478 (lr=2.3902e-05) (hash(x)=20854084) +4083 train 6.628908 (lr=2.3874e-05) (hash(x)=18950799) +4084 train 6.897038 (lr=2.3845e-05) (hash(x)=22633739) +4085 train 7.678629 (lr=2.3816e-05) (hash(x)=34054446) +4086 train 7.256126 (lr=2.3788e-05) (hash(x)=27599387) +4087 train 7.078924 (lr=2.3759e-05) (hash(x)=26869295) +4088 train 7.052718 (lr=2.3731e-05) (hash(x)=24075139) +4089 train 7.473450 (lr=2.3702e-05) (hash(x)=29784110) +4090 train 7.824329 (lr=2.3674e-05) (hash(x)=34273918) +4091 train 8.047860 (lr=2.3646e-05) (hash(x)=34472685) +4092 train 7.476111 (lr=2.3617e-05) (hash(x)=30113791) +4093 train 6.796131 (lr=2.3589e-05) (hash(x)=22366381) +4094 train 7.038492 (lr=2.3560e-05) (hash(x)=24922935) +4095 train 7.255333 (lr=2.3532e-05) (hash(x)=25504151) +4096 train 7.184505 (lr=2.3504e-05) (hash(x)=24517375) +4097 train 7.853765 (lr=2.3476e-05) (hash(x)=25871651) +4098 train 6.915700 (lr=2.3447e-05) (hash(x)=23480225) +4099 train 6.805564 (lr=2.3419e-05) (hash(x)=22559978) +4100 val loss 7.1186 +4100 val perplexity 1234.7823 +4100 train 7.229079 (lr=2.3391e-05) (hash(x)=25795272) +4101 train 7.191655 (lr=2.3363e-05) (hash(x)=25440399) +4102 train 6.826233 (lr=2.3335e-05) (hash(x)=21581806) +4103 train 6.925743 (lr=2.3306e-05) (hash(x)=25781518) +4104 train 7.020848 (lr=2.3278e-05) (hash(x)=24682372) +4105 train 6.842964 (lr=2.3250e-05) (hash(x)=22440094) +4106 train 7.016873 (lr=2.3222e-05) (hash(x)=23661032) +4107 train 7.248802 (lr=2.3194e-05) (hash(x)=26966012) +4108 train 7.306997 (lr=2.3166e-05) (hash(x)=26232227) +4109 train 6.944251 (lr=2.3138e-05) (hash(x)=24110656) +4110 train 7.201070 (lr=2.3110e-05) (hash(x)=25938621) +4111 train 7.049236 (lr=2.3082e-05) (hash(x)=26432850) +4112 train 7.044616 (lr=2.3054e-05) (hash(x)=25387672) +4113 train 6.787262 (lr=2.3027e-05) (hash(x)=22740017) +4114 train 7.194937 (lr=2.2999e-05) (hash(x)=26384190) +4115 train 6.870177 (lr=2.2971e-05) (hash(x)=24725583) +4116 train 7.039085 (lr=2.2943e-05) (hash(x)=23986700) +4117 train 6.986946 (lr=2.2915e-05) (hash(x)=18529900) +4118 train 7.041190 (lr=2.2888e-05) (hash(x)=22236257) +4119 train 6.688338 (lr=2.2860e-05) (hash(x)=20155894) +4120 train 6.461432 (lr=2.2832e-05) (hash(x)=17423813) +4121 train 6.430839 (lr=2.2804e-05) (hash(x)=18905183) +4122 train 6.827074 (lr=2.2777e-05) (hash(x)=22534398) +4123 train 7.486656 (lr=2.2749e-05) (hash(x)=25247868) +4124 train 7.009796 (lr=2.2722e-05) (hash(x)=23994188) +4125 train 6.898708 (lr=2.2694e-05) (hash(x)=22929754) +4126 train 6.777982 (lr=2.2666e-05) (hash(x)=22485897) +4127 train 6.808177 (lr=2.2639e-05) (hash(x)=22270169) +4128 train 6.789535 (lr=2.2611e-05) (hash(x)=23638027) +4129 train 7.106621 (lr=2.2584e-05) (hash(x)=23821210) +4130 train 6.976544 (lr=2.2556e-05) (hash(x)=25021512) +4131 train 7.038673 (lr=2.2529e-05) (hash(x)=25240141) +4132 train 7.001752 (lr=2.2502e-05) (hash(x)=22833160) +4133 train 6.925098 (lr=2.2474e-05) (hash(x)=22909944) +4134 train 7.175041 (lr=2.2447e-05) (hash(x)=26163558) +4135 train 6.891644 (lr=2.2420e-05) (hash(x)=22108461) +4136 train 6.851529 (lr=2.2392e-05) (hash(x)=22549232) +4137 train 7.047470 (lr=2.2365e-05) (hash(x)=24701302) +4138 train 7.136223 (lr=2.2338e-05) (hash(x)=25206013) +4139 train 7.148471 (lr=2.2310e-05) (hash(x)=27896130) +4140 train 6.871216 (lr=2.2283e-05) (hash(x)=24106243) +4141 train 7.474809 (lr=2.2256e-05) (hash(x)=27158651) +4142 train 6.994752 (lr=2.2229e-05) (hash(x)=23841147) +4143 train 6.995917 (lr=2.2202e-05) (hash(x)=24802848) +4144 train 7.273572 (lr=2.2175e-05) (hash(x)=24911295) +4145 train 7.083026 (lr=2.2148e-05) (hash(x)=26473900) +4146 train 7.172719 (lr=2.2121e-05) (hash(x)=26785092) +4147 train 7.473383 (lr=2.2094e-05) (hash(x)=30188532) +4148 train 6.972543 (lr=2.2067e-05) (hash(x)=25010649) +4149 train 6.941202 (lr=2.2040e-05) (hash(x)=22409016) +4150 val loss 7.1116 +4150 val perplexity 1226.0796 +4150 train 7.683386 (lr=2.2013e-05) (hash(x)=31675024) +4151 train 6.979326 (lr=2.1986e-05) (hash(x)=25086604) +4152 train 6.984966 (lr=2.1959e-05) (hash(x)=24429343) +4153 train 7.165264 (lr=2.1932e-05) (hash(x)=25014232) +4154 train 7.057404 (lr=2.1905e-05) (hash(x)=25366275) +4155 train 7.482812 (lr=2.1878e-05) (hash(x)=24031473) +4156 train 7.065683 (lr=2.1852e-05) (hash(x)=26651059) +4157 train 7.151743 (lr=2.1825e-05) (hash(x)=26069721) +4158 train 7.301620 (lr=2.1798e-05) (hash(x)=28114382) +4159 train 7.287978 (lr=2.1771e-05) (hash(x)=26983186) +4160 train 6.595932 (lr=2.1745e-05) (hash(x)=21944670) +4161 train 7.393857 (lr=2.1718e-05) (hash(x)=28155702) +4162 train 6.825052 (lr=2.1691e-05) (hash(x)=24765002) +4163 train 7.059619 (lr=2.1665e-05) (hash(x)=26492636) +4164 train 7.026535 (lr=2.1638e-05) (hash(x)=24063705) +4165 train 7.328267 (lr=2.1612e-05) (hash(x)=27079573) +4166 train 6.981730 (lr=2.1585e-05) (hash(x)=24912201) +4167 train 7.083774 (lr=2.1558e-05) (hash(x)=27208507) +4168 train 6.963474 (lr=2.1532e-05) (hash(x)=25824320) +4169 train 7.515057 (lr=2.1506e-05) (hash(x)=29641677) +4170 train 7.264709 (lr=2.1479e-05) (hash(x)=26275614) +4171 train 7.077083 (lr=2.1453e-05) (hash(x)=25227725) +4172 train 7.205072 (lr=2.1426e-05) (hash(x)=27417375) +4173 train 7.367180 (lr=2.1400e-05) (hash(x)=25581973) +4174 train 7.526299 (lr=2.1374e-05) (hash(x)=30360417) +4175 train 6.886801 (lr=2.1347e-05) (hash(x)=23862845) +4176 train 6.985076 (lr=2.1321e-05) (hash(x)=25415130) +4177 train 6.987051 (lr=2.1295e-05) (hash(x)=23111123) +4178 train 6.930514 (lr=2.1269e-05) (hash(x)=24022804) +4179 train 6.958898 (lr=2.1242e-05) (hash(x)=25148490) +4180 train 7.177494 (lr=2.1216e-05) (hash(x)=22792092) +4181 train 7.262455 (lr=2.1190e-05) (hash(x)=24779698) +4182 train 7.161405 (lr=2.1164e-05) (hash(x)=24870844) +4183 train 6.859567 (lr=2.1138e-05) (hash(x)=22664494) +4184 train 6.915431 (lr=2.1112e-05) (hash(x)=22599729) +4185 train 7.149596 (lr=2.1086e-05) (hash(x)=24707078) +4186 train 6.922101 (lr=2.1060e-05) (hash(x)=23823945) +4187 train 6.604365 (lr=2.1034e-05) (hash(x)=22219856) +4188 train 7.326782 (lr=2.1008e-05) (hash(x)=27061401) +4189 train 7.050564 (lr=2.0982e-05) (hash(x)=23398766) +4190 train 7.155566 (lr=2.0956e-05) (hash(x)=27916730) +4191 train 7.029538 (lr=2.0930e-05) (hash(x)=24092927) +4192 train 7.064705 (lr=2.0904e-05) (hash(x)=24723657) +4193 train 7.111931 (lr=2.0878e-05) (hash(x)=24676155) +4194 train 6.975658 (lr=2.0853e-05) (hash(x)=23455369) +4195 train 6.908817 (lr=2.0827e-05) (hash(x)=21999890) +4196 train 6.840187 (lr=2.0801e-05) (hash(x)=23385567) +4197 train 7.064030 (lr=2.0775e-05) (hash(x)=25120814) +4198 train 6.767467 (lr=2.0750e-05) (hash(x)=21308113) +4199 train 7.111178 (lr=2.0724e-05) (hash(x)=27213812) +4200 val loss 7.1033 +4200 val perplexity 1215.9142 +4200 train 6.628310 (lr=2.0698e-05) (hash(x)=19675382) +4201 train 6.964005 (lr=2.0673e-05) (hash(x)=23882161) +4202 train 6.939094 (lr=2.0647e-05) (hash(x)=24338567) +4203 train 7.235091 (lr=2.0622e-05) (hash(x)=27649723) +4204 train 7.037454 (lr=2.0596e-05) (hash(x)=27563514) +4205 train 7.011948 (lr=2.0570e-05) (hash(x)=23128552) +4206 train 6.942943 (lr=2.0545e-05) (hash(x)=26203283) +4207 train 6.958184 (lr=2.0520e-05) (hash(x)=23929955) +4208 train 6.627049 (lr=2.0494e-05) (hash(x)=20978691) +4209 train 6.971202 (lr=2.0469e-05) (hash(x)=21875178) +4210 train 7.028824 (lr=2.0443e-05) (hash(x)=23563293) +4211 train 7.191700 (lr=2.0418e-05) (hash(x)=25538503) +4212 train 7.228526 (lr=2.0393e-05) (hash(x)=24171014) +4213 train 7.038465 (lr=2.0367e-05) (hash(x)=22306665) +4214 train 6.977544 (lr=2.0342e-05) (hash(x)=26082318) +4215 train 6.754302 (lr=2.0317e-05) (hash(x)=23025790) +4216 train 6.839692 (lr=2.0292e-05) (hash(x)=21146597) +4217 train 7.211431 (lr=2.0266e-05) (hash(x)=27470230) +4218 train 6.945869 (lr=2.0241e-05) (hash(x)=22691005) +4219 train 6.744386 (lr=2.0216e-05) (hash(x)=21550313) +4220 train 6.795108 (lr=2.0191e-05) (hash(x)=20618443) +4221 train 6.945331 (lr=2.0166e-05) (hash(x)=25260787) +4222 train 7.041317 (lr=2.0141e-05) (hash(x)=25249873) +4223 train 6.607742 (lr=2.0116e-05) (hash(x)=20452272) +4224 train 6.922502 (lr=2.0091e-05) (hash(x)=25649764) +4225 train 6.768842 (lr=2.0066e-05) (hash(x)=19589460) +4226 train 7.233301 (lr=2.0041e-05) (hash(x)=26477595) +4227 train 7.381035 (lr=2.0016e-05) (hash(x)=27585442) +4228 train 7.242433 (lr=1.9991e-05) (hash(x)=25821343) +4229 train 7.139218 (lr=1.9966e-05) (hash(x)=24549919) +4230 train 7.051530 (lr=1.9941e-05) (hash(x)=26124522) +4231 train 7.344734 (lr=1.9917e-05) (hash(x)=26473464) +4232 train 7.349886 (lr=1.9892e-05) (hash(x)=28883028) +4233 train 7.296960 (lr=1.9867e-05) (hash(x)=29611296) +4234 train 7.177600 (lr=1.9842e-05) (hash(x)=29059941) +4235 train 7.042607 (lr=1.9818e-05) (hash(x)=26368203) +4236 train 7.085766 (lr=1.9793e-05) (hash(x)=27021360) +4237 train 6.984057 (lr=1.9768e-05) (hash(x)=26135379) +4238 train 6.782108 (lr=1.9744e-05) (hash(x)=25862549) +4239 train 7.194730 (lr=1.9719e-05) (hash(x)=28276603) +4240 train 6.747451 (lr=1.9694e-05) (hash(x)=22170090) +4241 train 7.103270 (lr=1.9670e-05) (hash(x)=22625589) +4242 train 7.172184 (lr=1.9645e-05) (hash(x)=25751475) +4243 train 7.029750 (lr=1.9621e-05) (hash(x)=25836838) +4244 train 6.973560 (lr=1.9596e-05) (hash(x)=23938214) +4245 train 6.921146 (lr=1.9572e-05) (hash(x)=22759365) +4246 train 6.881105 (lr=1.9548e-05) (hash(x)=24964628) +4247 train 6.576833 (lr=1.9523e-05) (hash(x)=21480367) +4248 train 7.104682 (lr=1.9499e-05) (hash(x)=25974694) +4249 train 7.434238 (lr=1.9475e-05) (hash(x)=29830546) +4250 val loss 7.1013 +4250 val perplexity 1213.5712 +4250 train 7.141304 (lr=1.9450e-05) (hash(x)=26283200) +4251 train 7.170385 (lr=1.9426e-05) (hash(x)=25605672) +4252 train 6.813120 (lr=1.9402e-05) (hash(x)=21439107) +4253 train 6.732586 (lr=1.9378e-05) (hash(x)=22626883) +4254 train 7.126801 (lr=1.9353e-05) (hash(x)=25627150) +4255 train 7.274863 (lr=1.9329e-05) (hash(x)=24658642) +4256 train 7.308109 (lr=1.9305e-05) (hash(x)=29755505) +4257 train 7.033446 (lr=1.9281e-05) (hash(x)=22750846) +4258 train 6.969226 (lr=1.9257e-05) (hash(x)=21892651) +4259 train 7.026051 (lr=1.9233e-05) (hash(x)=22487960) +4260 train 7.073902 (lr=1.9209e-05) (hash(x)=24059869) +4261 train 6.852515 (lr=1.9185e-05) (hash(x)=21090180) +4262 train 6.961793 (lr=1.9161e-05) (hash(x)=22716452) +4263 train 7.125350 (lr=1.9137e-05) (hash(x)=26854801) +4264 train 7.009674 (lr=1.9113e-05) (hash(x)=23815428) +4265 train 6.852380 (lr=1.9089e-05) (hash(x)=23368704) +4266 train 6.923054 (lr=1.9065e-05) (hash(x)=24301098) +4267 train 7.171653 (lr=1.9042e-05) (hash(x)=25025039) +4268 train 6.892658 (lr=1.9018e-05) (hash(x)=25425736) +4269 train 7.088333 (lr=1.8994e-05) (hash(x)=27439380) +4270 train 6.503526 (lr=1.8970e-05) (hash(x)=18682756) +4271 train 6.686102 (lr=1.8947e-05) (hash(x)=17862226) +4272 train 7.291107 (lr=1.8923e-05) (hash(x)=29946491) +4273 train 6.540887 (lr=1.8899e-05) (hash(x)=21392062) +4274 train 7.116943 (lr=1.8876e-05) (hash(x)=25195556) +4275 train 7.094360 (lr=1.8852e-05) (hash(x)=26682036) +4276 train 7.024802 (lr=1.8828e-05) (hash(x)=21235260) +4277 train 6.799823 (lr=1.8805e-05) (hash(x)=22118984) +4278 train 6.849181 (lr=1.8781e-05) (hash(x)=24094510) +4279 train 7.396651 (lr=1.8758e-05) (hash(x)=28519182) +4280 train 7.070971 (lr=1.8734e-05) (hash(x)=26652859) +4281 train 6.946276 (lr=1.8711e-05) (hash(x)=24463139) +4282 train 6.919365 (lr=1.8688e-05) (hash(x)=23281870) +4283 train 7.158379 (lr=1.8664e-05) (hash(x)=29181174) +4284 train 6.838312 (lr=1.8641e-05) (hash(x)=24797417) +4285 train 7.204206 (lr=1.8618e-05) (hash(x)=29026537) +4286 train 6.953696 (lr=1.8594e-05) (hash(x)=23045165) +4287 train 6.889179 (lr=1.8571e-05) (hash(x)=25193694) +4288 train 6.928756 (lr=1.8548e-05) (hash(x)=23475407) +4289 train 7.090600 (lr=1.8525e-05) (hash(x)=24875410) +4290 train 7.010337 (lr=1.8501e-05) (hash(x)=26328101) +4291 train 7.248637 (lr=1.8478e-05) (hash(x)=26273661) +4292 train 7.008438 (lr=1.8455e-05) (hash(x)=23271891) +4293 train 6.951200 (lr=1.8432e-05) (hash(x)=23300732) +4294 train 7.047371 (lr=1.8409e-05) (hash(x)=24243693) +4295 train 7.158835 (lr=1.8386e-05) (hash(x)=25642620) +4296 train 7.115497 (lr=1.8363e-05) (hash(x)=27730411) +4297 train 6.904631 (lr=1.8340e-05) (hash(x)=25485335) +4298 train 6.776999 (lr=1.8317e-05) (hash(x)=25268789) +4299 train 7.265495 (lr=1.8294e-05) (hash(x)=28917143) +4300 val loss 7.1051 +4300 val perplexity 1218.1920 +4300 train 7.400025 (lr=1.8271e-05) (hash(x)=28987991) +4301 train 7.167047 (lr=1.8248e-05) (hash(x)=25989151) +4302 train 7.031513 (lr=1.8225e-05) (hash(x)=25658195) +4303 train 7.004003 (lr=1.8203e-05) (hash(x)=25765909) +4304 train 6.996198 (lr=1.8180e-05) (hash(x)=25704261) +4305 train 7.006896 (lr=1.8157e-05) (hash(x)=24438198) +4306 train 6.791645 (lr=1.8134e-05) (hash(x)=22871710) +4307 train 6.628737 (lr=1.8112e-05) (hash(x)=20160896) +4308 train 7.201484 (lr=1.8089e-05) (hash(x)=24218641) +4309 train 6.613863 (lr=1.8066e-05) (hash(x)=22073751) +4310 train 6.990598 (lr=1.8044e-05) (hash(x)=26434959) +4311 train 6.666770 (lr=1.8021e-05) (hash(x)=20750531) +4312 train 6.795331 (lr=1.7999e-05) (hash(x)=22232293) +4313 train 7.091185 (lr=1.7976e-05) (hash(x)=27324521) +4314 train 6.755219 (lr=1.7954e-05) (hash(x)=22217862) +4315 train 7.220911 (lr=1.7931e-05) (hash(x)=25741958) +4316 train 6.968910 (lr=1.7909e-05) (hash(x)=22738456) +4317 train 7.014500 (lr=1.7886e-05) (hash(x)=25387302) +4318 train 6.964660 (lr=1.7864e-05) (hash(x)=24669014) +4319 train 7.098552 (lr=1.7842e-05) (hash(x)=24917098) +4320 train 7.031719 (lr=1.7819e-05) (hash(x)=26698227) +4321 train 6.843967 (lr=1.7797e-05) (hash(x)=23518293) +4322 train 6.767742 (lr=1.7775e-05) (hash(x)=23643971) +4323 train 6.981382 (lr=1.7752e-05) (hash(x)=25659505) +4324 train 6.753648 (lr=1.7730e-05) (hash(x)=22697720) +4325 train 7.258354 (lr=1.7708e-05) (hash(x)=25082178) +4326 train 6.809711 (lr=1.7686e-05) (hash(x)=24166546) +4327 train 6.984670 (lr=1.7664e-05) (hash(x)=24499766) +4328 train 7.044811 (lr=1.7642e-05) (hash(x)=24338607) +4329 train 6.865884 (lr=1.7620e-05) (hash(x)=23225420) +4330 train 7.032399 (lr=1.7598e-05) (hash(x)=25907032) +4331 train 6.825396 (lr=1.7576e-05) (hash(x)=24634979) +4332 train 6.909925 (lr=1.7554e-05) (hash(x)=22161377) +4333 train 7.070257 (lr=1.7532e-05) (hash(x)=22559939) +4334 train 6.832530 (lr=1.7510e-05) (hash(x)=20840022) +4335 train 7.150864 (lr=1.7488e-05) (hash(x)=25067358) +4336 train 6.810643 (lr=1.7466e-05) (hash(x)=23432626) +4337 train 6.960062 (lr=1.7444e-05) (hash(x)=23820385) +4338 train 7.689847 (lr=1.7422e-05) (hash(x)=31594930) +4339 train 7.177345 (lr=1.7401e-05) (hash(x)=27138750) +4340 train 7.374126 (lr=1.7379e-05) (hash(x)=30031341) +4341 train 6.904373 (lr=1.7357e-05) (hash(x)=24602807) +4342 train 6.690157 (lr=1.7335e-05) (hash(x)=21584976) +4343 train 7.138640 (lr=1.7314e-05) (hash(x)=27479796) +4344 train 6.768027 (lr=1.7292e-05) (hash(x)=22746241) +4345 train 6.975423 (lr=1.7271e-05) (hash(x)=19728452) +4346 train 6.779113 (lr=1.7249e-05) (hash(x)=24502020) +4347 train 7.263031 (lr=1.7228e-05) (hash(x)=28225954) +4348 train 6.893173 (lr=1.7206e-05) (hash(x)=23893447) +4349 train 7.243659 (lr=1.7185e-05) (hash(x)=25654586) +4350 val loss 7.0983 +4350 val perplexity 1209.9489 +4350 train 7.046176 (lr=1.7163e-05) (hash(x)=23856469) +4351 train 6.960130 (lr=1.7142e-05) (hash(x)=23136080) +4352 train 7.076477 (lr=1.7120e-05) (hash(x)=26532918) +4353 train 7.002841 (lr=1.7099e-05) (hash(x)=25461947) +4354 train 7.022457 (lr=1.7078e-05) (hash(x)=26590231) +4355 train 6.711968 (lr=1.7056e-05) (hash(x)=21441985) +4356 train 7.038139 (lr=1.7035e-05) (hash(x)=26507941) +4357 train 7.312367 (lr=1.7014e-05) (hash(x)=26245238) +4358 train 7.093636 (lr=1.6993e-05) (hash(x)=24879059) +4359 train 7.369892 (lr=1.6971e-05) (hash(x)=29810074) +4360 train 6.790264 (lr=1.6950e-05) (hash(x)=24258069) +4361 train 6.892333 (lr=1.6929e-05) (hash(x)=25229360) +4362 train 7.079349 (lr=1.6908e-05) (hash(x)=25440206) +4363 train 6.981412 (lr=1.6887e-05) (hash(x)=23222125) +4364 train 6.801941 (lr=1.6866e-05) (hash(x)=23353186) +4365 train 7.044431 (lr=1.6845e-05) (hash(x)=26995240) +4366 train 6.965198 (lr=1.6824e-05) (hash(x)=24135899) +4367 train 7.010820 (lr=1.6803e-05) (hash(x)=24765539) +4368 train 7.045510 (lr=1.6782e-05) (hash(x)=26051004) +4369 train 6.764864 (lr=1.6761e-05) (hash(x)=22559142) +4370 train 6.679128 (lr=1.6740e-05) (hash(x)=20364388) +4371 train 7.190889 (lr=1.6719e-05) (hash(x)=25938817) +4372 train 7.219393 (lr=1.6699e-05) (hash(x)=26060945) +4373 train 7.148701 (lr=1.6678e-05) (hash(x)=27866714) +4374 train 7.060311 (lr=1.6657e-05) (hash(x)=27104972) +4375 train 6.743577 (lr=1.6636e-05) (hash(x)=22216309) +4376 train 6.763860 (lr=1.6616e-05) (hash(x)=20781533) +4377 train 6.712322 (lr=1.6595e-05) (hash(x)=18784350) +4378 train 6.833623 (lr=1.6574e-05) (hash(x)=21102897) +4379 train 7.140400 (lr=1.6554e-05) (hash(x)=25647489) +4380 train 6.913792 (lr=1.6533e-05) (hash(x)=24486462) +4381 train 7.179599 (lr=1.6513e-05) (hash(x)=26539114) +4382 train 6.780683 (lr=1.6492e-05) (hash(x)=20026045) +4383 train 7.074321 (lr=1.6472e-05) (hash(x)=20613861) +4384 train 6.786656 (lr=1.6451e-05) (hash(x)=20676237) +4385 train 7.014400 (lr=1.6431e-05) (hash(x)=24893163) +4386 train 6.541601 (lr=1.6410e-05) (hash(x)=17299395) +4387 train 6.717485 (lr=1.6390e-05) (hash(x)=19580191) +4388 train 6.942542 (lr=1.6370e-05) (hash(x)=25588218) +4389 train 7.068130 (lr=1.6350e-05) (hash(x)=26433063) +4390 train 7.159954 (lr=1.6329e-05) (hash(x)=24917693) +4391 train 6.818077 (lr=1.6309e-05) (hash(x)=23462447) +4392 train 7.040278 (lr=1.6289e-05) (hash(x)=27185416) +4393 train 7.166673 (lr=1.6269e-05) (hash(x)=24109010) +4394 train 6.921016 (lr=1.6248e-05) (hash(x)=21486000) +4395 train 6.812726 (lr=1.6228e-05) (hash(x)=22230006) +4396 train 7.255578 (lr=1.6208e-05) (hash(x)=26092311) +4397 train 6.959388 (lr=1.6188e-05) (hash(x)=24112426) +4398 train 6.796140 (lr=1.6168e-05) (hash(x)=21881373) +4399 train 6.953893 (lr=1.6148e-05) (hash(x)=26739455) +4400 val loss 7.0972 +4400 val perplexity 1208.5800 +4400 train 6.807819 (lr=1.6128e-05) (hash(x)=22873602) +4401 train 6.923546 (lr=1.6108e-05) (hash(x)=26748712) +4402 train 7.092526 (lr=1.6088e-05) (hash(x)=26306618) +4403 train 7.263973 (lr=1.6069e-05) (hash(x)=26898808) +4404 train 6.976615 (lr=1.6049e-05) (hash(x)=25067751) +4405 train 7.026517 (lr=1.6029e-05) (hash(x)=25397145) +4406 train 7.187680 (lr=1.6009e-05) (hash(x)=24796962) +4407 train 6.986690 (lr=1.5989e-05) (hash(x)=23222996) +4408 train 6.938432 (lr=1.5970e-05) (hash(x)=24820189) +4409 train 7.351451 (lr=1.5950e-05) (hash(x)=27669038) +4410 train 6.951462 (lr=1.5930e-05) (hash(x)=24283976) +4411 train 7.165775 (lr=1.5911e-05) (hash(x)=25018789) +4412 train 7.052809 (lr=1.5891e-05) (hash(x)=26247064) +4413 train 7.117778 (lr=1.5871e-05) (hash(x)=22942904) +4414 train 6.974518 (lr=1.5852e-05) (hash(x)=23918746) +4415 train 7.087386 (lr=1.5832e-05) (hash(x)=26489285) +4416 train 6.035558 (lr=1.5813e-05) (hash(x)=14942495) +4417 train 6.838605 (lr=1.5793e-05) (hash(x)=23908505) +4418 train 7.086286 (lr=1.5774e-05) (hash(x)=25854036) +4419 train 7.010619 (lr=1.5755e-05) (hash(x)=27522868) +4420 train 6.890639 (lr=1.5735e-05) (hash(x)=26549205) +4421 train 6.768083 (lr=1.5716e-05) (hash(x)=24565522) +4422 train 7.126428 (lr=1.5697e-05) (hash(x)=23919123) +4423 train 6.979373 (lr=1.5677e-05) (hash(x)=25185942) +4424 train 6.975517 (lr=1.5658e-05) (hash(x)=24818969) +4425 train 7.093617 (lr=1.5639e-05) (hash(x)=26750372) +4426 train 7.090957 (lr=1.5620e-05) (hash(x)=25621536) +4427 train 7.530828 (lr=1.5601e-05) (hash(x)=28037060) +4428 train 7.499798 (lr=1.5581e-05) (hash(x)=30829517) +4429 train 7.112058 (lr=1.5562e-05) (hash(x)=28728766) +4430 train 7.074931 (lr=1.5543e-05) (hash(x)=25936895) +4431 train 7.212723 (lr=1.5524e-05) (hash(x)=27476158) +4432 train 6.958673 (lr=1.5505e-05) (hash(x)=23297921) +4433 train 6.913663 (lr=1.5486e-05) (hash(x)=23201299) +4434 train 6.827579 (lr=1.5467e-05) (hash(x)=22681766) +4435 train 6.855939 (lr=1.5449e-05) (hash(x)=23217512) +4436 train 7.333196 (lr=1.5430e-05) (hash(x)=29322443) +4437 train 6.892830 (lr=1.5411e-05) (hash(x)=23502072) +4438 train 7.006314 (lr=1.5392e-05) (hash(x)=28873527) +4439 train 7.043706 (lr=1.5373e-05) (hash(x)=23653175) +4440 train 6.841694 (lr=1.5354e-05) (hash(x)=21635879) +4441 train 6.862329 (lr=1.5336e-05) (hash(x)=22201854) +4442 train 6.784439 (lr=1.5317e-05) (hash(x)=23101164) +4443 train 7.231406 (lr=1.5298e-05) (hash(x)=25475122) +4444 train 6.946392 (lr=1.5280e-05) (hash(x)=25124825) +4445 train 7.104573 (lr=1.5261e-05) (hash(x)=26883852) +4446 train 6.869002 (lr=1.5243e-05) (hash(x)=24731829) +4447 train 6.833882 (lr=1.5224e-05) (hash(x)=22405076) +4448 train 7.052345 (lr=1.5206e-05) (hash(x)=27633869) +4449 train 7.093553 (lr=1.5187e-05) (hash(x)=25162594) +4450 val loss 7.0932 +4450 val perplexity 1203.7068 +4450 train 7.068309 (lr=1.5169e-05) (hash(x)=26438149) +4451 train 7.098373 (lr=1.5150e-05) (hash(x)=26748800) +4452 train 6.842219 (lr=1.5132e-05) (hash(x)=22971620) +4453 train 6.949512 (lr=1.5114e-05) (hash(x)=25886430) +4454 train 6.746194 (lr=1.5095e-05) (hash(x)=21084137) +4455 train 6.925636 (lr=1.5077e-05) (hash(x)=25673545) +4456 train 7.590150 (lr=1.5059e-05) (hash(x)=29389002) +4457 train 6.664068 (lr=1.5040e-05) (hash(x)=21676076) +4458 train 6.747885 (lr=1.5022e-05) (hash(x)=22616647) +4459 train 7.157440 (lr=1.5004e-05) (hash(x)=22771197) +4460 train 7.097187 (lr=1.4986e-05) (hash(x)=26393514) +4461 train 7.294613 (lr=1.4968e-05) (hash(x)=24996433) +4462 train 6.916074 (lr=1.4950e-05) (hash(x)=19594028) +4463 train 7.104534 (lr=1.4932e-05) (hash(x)=22675428) +4464 train 7.074461 (lr=1.4914e-05) (hash(x)=26566551) +4465 train 7.061786 (lr=1.4896e-05) (hash(x)=22469290) +4466 train 7.590714 (lr=1.4878e-05) (hash(x)=29821654) +4467 train 7.092782 (lr=1.4860e-05) (hash(x)=26305388) +4468 train 6.903243 (lr=1.4842e-05) (hash(x)=21998506) +4469 train 7.379979 (lr=1.4824e-05) (hash(x)=23953315) +4470 train 6.946317 (lr=1.4806e-05) (hash(x)=23985456) +4471 train 7.371722 (lr=1.4789e-05) (hash(x)=28168456) +4472 train 7.006649 (lr=1.4771e-05) (hash(x)=25126411) +4473 train 6.808835 (lr=1.4753e-05) (hash(x)=24619336) +4474 train 7.000342 (lr=1.4735e-05) (hash(x)=24467798) +4475 train 7.827411 (lr=1.4718e-05) (hash(x)=31673254) +4476 train 7.601554 (lr=1.4700e-05) (hash(x)=29929610) +4477 train 7.384850 (lr=1.4682e-05) (hash(x)=29412572) +4478 train 7.556397 (lr=1.4665e-05) (hash(x)=31910006) +4479 train 7.157993 (lr=1.4647e-05) (hash(x)=26072586) +4480 train 7.123860 (lr=1.4630e-05) (hash(x)=25782825) +4481 train 6.943635 (lr=1.4612e-05) (hash(x)=21131363) +4482 train 7.048269 (lr=1.4595e-05) (hash(x)=25071223) +4483 train 7.642678 (lr=1.4577e-05) (hash(x)=32249577) +4484 train 6.883214 (lr=1.4560e-05) (hash(x)=24752808) +4485 train 6.950164 (lr=1.4543e-05) (hash(x)=24970539) +4486 train 6.880367 (lr=1.4525e-05) (hash(x)=24191005) +4487 train 7.113439 (lr=1.4508e-05) (hash(x)=24974331) +4488 train 7.257430 (lr=1.4491e-05) (hash(x)=27043409) +4489 train 6.737814 (lr=1.4474e-05) (hash(x)=11320385) +4490 train 6.780952 (lr=1.4456e-05) (hash(x)=11919565) +4491 train 6.816203 (lr=1.4439e-05) (hash(x)=10404694) +4492 train 6.858163 (lr=1.4422e-05) (hash(x)=12393159) +4493 train 6.772747 (lr=1.4405e-05) (hash(x)=11843609) +4494 train 6.788728 (lr=1.4388e-05) (hash(x)=12632729) +4495 train 6.961488 (lr=1.4371e-05) (hash(x)=21951984) +4496 train 7.643718 (lr=1.4354e-05) (hash(x)=19411544) +4497 train 7.562191 (lr=1.4337e-05) (hash(x)=21000228) +4498 train 7.190759 (lr=1.4320e-05) (hash(x)=26018207) +4499 train 7.211633 (lr=1.4303e-05) (hash(x)=24659058) +4500 val loss 7.0964 +4500 val perplexity 1207.5690 +4500 train 7.388783 (lr=1.4286e-05) (hash(x)=27919597) +4501 train 6.960556 (lr=1.4269e-05) (hash(x)=26232596) +4502 train 7.104497 (lr=1.4252e-05) (hash(x)=26248912) +4503 train 6.956741 (lr=1.4236e-05) (hash(x)=25403751) +4504 train 6.895400 (lr=1.4219e-05) (hash(x)=21096637) +4505 train 7.050279 (lr=1.4202e-05) (hash(x)=26560941) +4506 train 7.041679 (lr=1.4186e-05) (hash(x)=24942406) +4507 train 7.119974 (lr=1.4169e-05) (hash(x)=24405748) +4508 train 7.022792 (lr=1.4152e-05) (hash(x)=22975455) +4509 train 6.951202 (lr=1.4136e-05) (hash(x)=26358820) +4510 train 6.951820 (lr=1.4119e-05) (hash(x)=24211938) +4511 train 7.128498 (lr=1.4103e-05) (hash(x)=26396012) +4512 train 6.778832 (lr=1.4086e-05) (hash(x)=22534410) +4513 train 6.914022 (lr=1.4070e-05) (hash(x)=23855025) +4514 train 6.790264 (lr=1.4053e-05) (hash(x)=22722345) +4515 train 6.778295 (lr=1.4037e-05) (hash(x)=22779251) +4516 train 7.087291 (lr=1.4020e-05) (hash(x)=23973078) +4517 train 6.898941 (lr=1.4004e-05) (hash(x)=19886228) +4518 train 7.013783 (lr=1.3988e-05) (hash(x)=23849694) +4519 train 7.422998 (lr=1.3971e-05) (hash(x)=24827190) +4520 train 6.988333 (lr=1.3955e-05) (hash(x)=25111498) +4521 train 7.829704 (lr=1.3939e-05) (hash(x)=29752556) +4522 train 7.251663 (lr=1.3923e-05) (hash(x)=25606805) +4523 train 7.023266 (lr=1.3907e-05) (hash(x)=22209714) +4524 train 6.765357 (lr=1.3890e-05) (hash(x)=24991834) +4525 train 7.043352 (lr=1.3874e-05) (hash(x)=27808158) +4526 train 6.968431 (lr=1.3858e-05) (hash(x)=23041199) +4527 train 7.028699 (lr=1.3842e-05) (hash(x)=24847458) +4528 train 6.971292 (lr=1.3826e-05) (hash(x)=25091787) +4529 train 7.911080 (lr=1.3810e-05) (hash(x)=29745551) +4530 train 6.653679 (lr=1.3794e-05) (hash(x)=20447167) +4531 train 6.881450 (lr=1.3778e-05) (hash(x)=20720911) +4532 train 7.054593 (lr=1.3763e-05) (hash(x)=24803353) +4533 train 7.102252 (lr=1.3747e-05) (hash(x)=23780724) +4534 train 7.131336 (lr=1.3731e-05) (hash(x)=23423120) +4535 train 6.767944 (lr=1.3715e-05) (hash(x)=22159088) +4536 train 6.991149 (lr=1.3699e-05) (hash(x)=25820304) +4537 train 6.785881 (lr=1.3684e-05) (hash(x)=22813612) +4538 train 7.111928 (lr=1.3668e-05) (hash(x)=27827979) +4539 train 7.099751 (lr=1.3652e-05) (hash(x)=25737179) +4540 train 7.286355 (lr=1.3637e-05) (hash(x)=23401504) +4541 train 6.961981 (lr=1.3621e-05) (hash(x)=25071988) +4542 train 7.004028 (lr=1.3606e-05) (hash(x)=22844541) +4543 train 6.756504 (lr=1.3590e-05) (hash(x)=22140034) +4544 train 7.020656 (lr=1.3575e-05) (hash(x)=26522091) +4545 train 7.067778 (lr=1.3559e-05) (hash(x)=24099725) +4546 train 6.636528 (lr=1.3544e-05) (hash(x)=19127182) +4547 train 6.757005 (lr=1.3528e-05) (hash(x)=18992693) +4548 train 7.762558 (lr=1.3513e-05) (hash(x)=26723015) +4549 train 7.517518 (lr=1.3498e-05) (hash(x)=30389969) +4550 val loss 7.0913 +4550 val perplexity 1201.5226 +4550 train 6.889426 (lr=1.3482e-05) (hash(x)=24065654) +4551 train 6.644254 (lr=1.3467e-05) (hash(x)=19044797) +4552 train 7.138043 (lr=1.3452e-05) (hash(x)=24919665) +4553 train 7.100670 (lr=1.3437e-05) (hash(x)=22780968) +4554 train 6.893739 (lr=1.3422e-05) (hash(x)=24549699) +4555 train 6.780965 (lr=1.3407e-05) (hash(x)=21374811) +4556 train 6.904799 (lr=1.3391e-05) (hash(x)=25225950) +4557 train 7.052687 (lr=1.3376e-05) (hash(x)=25691882) +4558 train 6.946235 (lr=1.3361e-05) (hash(x)=24685235) +4559 train 6.775463 (lr=1.3346e-05) (hash(x)=23932794) +4560 train 7.415143 (lr=1.3331e-05) (hash(x)=28152043) +4561 train 6.851534 (lr=1.3316e-05) (hash(x)=23417051) +4562 train 6.949960 (lr=1.3301e-05) (hash(x)=26250211) +4563 train 7.192236 (lr=1.3287e-05) (hash(x)=25428813) +4564 train 7.319800 (lr=1.3272e-05) (hash(x)=27477379) +4565 train 7.058763 (lr=1.3257e-05) (hash(x)=23015212) +4566 train 6.828859 (lr=1.3242e-05) (hash(x)=22837608) +4567 train 6.929012 (lr=1.3227e-05) (hash(x)=25256890) +4568 train 6.824346 (lr=1.3213e-05) (hash(x)=22742827) +4569 train 7.256679 (lr=1.3198e-05) (hash(x)=30167922) +4570 train 6.938115 (lr=1.3183e-05) (hash(x)=24540265) +4571 train 7.232423 (lr=1.3169e-05) (hash(x)=26752941) +4572 train 7.055402 (lr=1.3154e-05) (hash(x)=25094026) +4573 train 7.697778 (lr=1.3140e-05) (hash(x)=28508785) +4574 train 7.145086 (lr=1.3125e-05) (hash(x)=26501871) +4575 train 6.920610 (lr=1.3111e-05) (hash(x)=24161711) +4576 train 6.867337 (lr=1.3096e-05) (hash(x)=24313695) +4577 train 7.284462 (lr=1.3082e-05) (hash(x)=28248933) +4578 train 7.417217 (lr=1.3067e-05) (hash(x)=28445722) +4579 train 7.063791 (lr=1.3053e-05) (hash(x)=24589015) +4580 train 7.217794 (lr=1.3039e-05) (hash(x)=26192193) +4581 train 6.858341 (lr=1.3024e-05) (hash(x)=25131316) +4582 train 6.960042 (lr=1.3010e-05) (hash(x)=26631504) +4583 train 6.784709 (lr=1.2996e-05) (hash(x)=22036817) +4584 train 7.407726 (lr=1.2982e-05) (hash(x)=28361254) +4585 train 7.050708 (lr=1.2968e-05) (hash(x)=24828340) +4586 train 6.707524 (lr=1.2954e-05) (hash(x)=24067304) +4587 train 6.473747 (lr=1.2939e-05) (hash(x)=20733289) +4588 train 6.397799 (lr=1.2925e-05) (hash(x)=19526622) +4589 train 6.797368 (lr=1.2911e-05) (hash(x)=22148688) +4590 train 7.048625 (lr=1.2897e-05) (hash(x)=24141800) +4591 train 7.084527 (lr=1.2883e-05) (hash(x)=26663208) +4592 train 6.731121 (lr=1.2869e-05) (hash(x)=22536305) +4593 train 6.980722 (lr=1.2856e-05) (hash(x)=23608185) +4594 train 6.868320 (lr=1.2842e-05) (hash(x)=23348495) +4595 train 7.060974 (lr=1.2828e-05) (hash(x)=25409759) +4596 train 7.032508 (lr=1.2814e-05) (hash(x)=25572131) +4597 train 7.011698 (lr=1.2800e-05) (hash(x)=21782039) +4598 train 6.975694 (lr=1.2787e-05) (hash(x)=24643923) +4599 train 6.918044 (lr=1.2773e-05) (hash(x)=24072213) +4600 val loss 7.0903 +4600 val perplexity 1200.3235 +4600 train 6.876495 (lr=1.2759e-05) (hash(x)=23925612) +4601 train 6.956270 (lr=1.2746e-05) (hash(x)=23315415) +4602 train 6.937702 (lr=1.2732e-05) (hash(x)=21793800) +4603 train 6.886436 (lr=1.2718e-05) (hash(x)=24921200) +4604 train 7.170299 (lr=1.2705e-05) (hash(x)=27226113) +4605 train 6.942295 (lr=1.2691e-05) (hash(x)=22920960) +4606 train 6.881690 (lr=1.2678e-05) (hash(x)=21947750) +4607 train 6.922460 (lr=1.2664e-05) (hash(x)=22766044) +4608 train 7.326093 (lr=1.2651e-05) (hash(x)=28237005) +4609 train 6.804798 (lr=1.2638e-05) (hash(x)=24922621) +4610 train 7.016792 (lr=1.2624e-05) (hash(x)=24899830) +4611 train 7.395681 (lr=1.2611e-05) (hash(x)=32920298) +4612 train 6.845113 (lr=1.2598e-05) (hash(x)=25083835) +4613 train 6.907353 (lr=1.2584e-05) (hash(x)=22863054) +4614 train 6.947271 (lr=1.2571e-05) (hash(x)=24841464) +4615 train 7.267007 (lr=1.2558e-05) (hash(x)=27871153) +4616 train 7.200563 (lr=1.2545e-05) (hash(x)=28025163) +4617 train 6.892261 (lr=1.2532e-05) (hash(x)=24659561) +4618 train 7.028543 (lr=1.2519e-05) (hash(x)=25067194) +4619 train 6.997411 (lr=1.2506e-05) (hash(x)=22731460) +4620 train 6.934418 (lr=1.2493e-05) (hash(x)=20445873) +4621 train 7.030559 (lr=1.2480e-05) (hash(x)=26033948) +4622 train 6.879930 (lr=1.2467e-05) (hash(x)=22473213) +4623 train 7.439482 (lr=1.2454e-05) (hash(x)=24037280) +4624 train 7.892189 (lr=1.2441e-05) (hash(x)=25624131) +4625 train 7.548648 (lr=1.2428e-05) (hash(x)=26799867) +4626 train 7.039856 (lr=1.2415e-05) (hash(x)=27187602) +4627 train 6.985469 (lr=1.2402e-05) (hash(x)=23277695) +4628 train 6.996015 (lr=1.2390e-05) (hash(x)=24748234) +4629 train 7.103099 (lr=1.2377e-05) (hash(x)=26103104) +4630 train 7.013176 (lr=1.2364e-05) (hash(x)=24327389) +4631 train 7.126393 (lr=1.2352e-05) (hash(x)=24121850) +4632 train 6.977039 (lr=1.2339e-05) (hash(x)=23714590) +4633 train 7.010002 (lr=1.2326e-05) (hash(x)=22379412) +4634 train 7.270399 (lr=1.2314e-05) (hash(x)=24454713) +4635 train 6.918402 (lr=1.2301e-05) (hash(x)=22966977) +4636 train 6.913132 (lr=1.2289e-05) (hash(x)=23764884) +4637 train 6.769634 (lr=1.2276e-05) (hash(x)=23827429) +4638 train 6.987321 (lr=1.2264e-05) (hash(x)=24088592) +4639 train 7.003129 (lr=1.2252e-05) (hash(x)=24380031) +4640 train 7.089194 (lr=1.2239e-05) (hash(x)=26065050) +4641 train 6.976621 (lr=1.2227e-05) (hash(x)=24442902) +4642 train 6.535799 (lr=1.2215e-05) (hash(x)=18548782) +4643 train 7.090964 (lr=1.2202e-05) (hash(x)=26957303) +4644 train 7.077011 (lr=1.2190e-05) (hash(x)=25032727) +4645 train 6.956608 (lr=1.2178e-05) (hash(x)=27224706) +4646 train 7.112770 (lr=1.2166e-05) (hash(x)=27508476) +4647 train 6.819920 (lr=1.2154e-05) (hash(x)=23055215) +4648 train 6.952229 (lr=1.2142e-05) (hash(x)=24496194) +4649 train 8.308723 (lr=1.2130e-05) (hash(x)=13982941) +4650 val loss 7.0902 +4650 val perplexity 1200.1466 +4650 train 7.545433 (lr=1.2118e-05) (hash(x)=16721547) +4651 train 6.967191 (lr=1.2106e-05) (hash(x)=22929154) +4652 train 6.908184 (lr=1.2094e-05) (hash(x)=23323994) +4653 train 7.259391 (lr=1.2082e-05) (hash(x)=24877951) +4654 train 7.087210 (lr=1.2070e-05) (hash(x)=24096183) +4655 train 6.913729 (lr=1.2058e-05) (hash(x)=25329724) +4656 train 6.876972 (lr=1.2046e-05) (hash(x)=23877337) +4657 train 6.517696 (lr=1.2034e-05) (hash(x)=20923083) +4658 train 6.845137 (lr=1.2023e-05) (hash(x)=23807996) +4659 train 6.943208 (lr=1.2011e-05) (hash(x)=24370475) +4660 train 7.336542 (lr=1.1999e-05) (hash(x)=28202255) +4661 train 7.002159 (lr=1.1988e-05) (hash(x)=26142119) +4662 train 6.836768 (lr=1.1976e-05) (hash(x)=21387743) +4663 train 6.968919 (lr=1.1964e-05) (hash(x)=25662408) +4664 train 7.011909 (lr=1.1953e-05) (hash(x)=23962815) +4665 train 6.914903 (lr=1.1941e-05) (hash(x)=23987677) +4666 train 7.226171 (lr=1.1930e-05) (hash(x)=26554284) +4667 train 7.277901 (lr=1.1918e-05) (hash(x)=25991817) +4668 train 6.987844 (lr=1.1907e-05) (hash(x)=24256966) +4669 train 6.753883 (lr=1.1896e-05) (hash(x)=22187158) +4670 train 7.051125 (lr=1.1884e-05) (hash(x)=26295320) +4671 train 7.069325 (lr=1.1873e-05) (hash(x)=26346814) +4672 train 7.283455 (lr=1.1862e-05) (hash(x)=26594196) +4673 train 7.113834 (lr=1.1850e-05) (hash(x)=24322101) +4674 train 7.197891 (lr=1.1839e-05) (hash(x)=27274566) +4675 train 6.997515 (lr=1.1828e-05) (hash(x)=24505725) +4676 train 7.173940 (lr=1.1817e-05) (hash(x)=26167371) +4677 train 7.256233 (lr=1.1806e-05) (hash(x)=28062311) +4678 train 6.983968 (lr=1.1795e-05) (hash(x)=23476009) +4679 train 7.096643 (lr=1.1783e-05) (hash(x)=25283256) +4680 train 6.800355 (lr=1.1772e-05) (hash(x)=22033246) +4681 train 6.846190 (lr=1.1761e-05) (hash(x)=22716214) +4682 train 6.996624 (lr=1.1751e-05) (hash(x)=25672672) +4683 train 6.869849 (lr=1.1740e-05) (hash(x)=22979072) +4684 train 7.101758 (lr=1.1729e-05) (hash(x)=27439204) +4685 train 6.990166 (lr=1.1718e-05) (hash(x)=24857737) +4686 train 7.282285 (lr=1.1707e-05) (hash(x)=29615897) +4687 train 6.839374 (lr=1.1696e-05) (hash(x)=24021771) +4688 train 6.980030 (lr=1.1685e-05) (hash(x)=27410807) +4689 train 6.778539 (lr=1.1675e-05) (hash(x)=22850411) +4690 train 7.069856 (lr=1.1664e-05) (hash(x)=24949696) +4691 train 6.887985 (lr=1.1653e-05) (hash(x)=22956381) +4692 train 7.331995 (lr=1.1643e-05) (hash(x)=28193458) +4693 train 6.911501 (lr=1.1632e-05) (hash(x)=25596844) +4694 train 6.856194 (lr=1.1622e-05) (hash(x)=22101377) +4695 train 6.795256 (lr=1.1611e-05) (hash(x)=23576840) +4696 train 6.758906 (lr=1.1601e-05) (hash(x)=21849758) +4697 train 6.988976 (lr=1.1590e-05) (hash(x)=26431349) +4698 train 7.102832 (lr=1.1580e-05) (hash(x)=22960758) +4699 train 6.997495 (lr=1.1569e-05) (hash(x)=23243097) +4700 val loss 7.0905 +4700 val perplexity 1200.5370 +4700 train 6.902458 (lr=1.1559e-05) (hash(x)=23715370) +4701 train 7.538031 (lr=1.1549e-05) (hash(x)=30678293) +4702 train 7.583252 (lr=1.1538e-05) (hash(x)=32481620) +4703 train 7.175531 (lr=1.1528e-05) (hash(x)=26414858) +4704 train 7.051473 (lr=1.1518e-05) (hash(x)=24768691) +4705 train 6.672046 (lr=1.1508e-05) (hash(x)=21627762) +4706 train 6.795448 (lr=1.1498e-05) (hash(x)=21024917) +4707 train 6.763872 (lr=1.1488e-05) (hash(x)=23570951) +4708 train 6.893025 (lr=1.1477e-05) (hash(x)=23729185) +4709 train 7.242049 (lr=1.1467e-05) (hash(x)=25933754) +4710 train 6.697395 (lr=1.1457e-05) (hash(x)=23091014) +4711 train 6.794242 (lr=1.1447e-05) (hash(x)=20099261) +4712 train 6.982205 (lr=1.1437e-05) (hash(x)=26807297) +4713 train 6.870405 (lr=1.1428e-05) (hash(x)=25332115) +4714 train 6.876316 (lr=1.1418e-05) (hash(x)=23247605) +4715 train 6.732117 (lr=1.1408e-05) (hash(x)=23786549) +4716 train 6.842529 (lr=1.1398e-05) (hash(x)=23981166) +4717 train 7.034042 (lr=1.1388e-05) (hash(x)=25967754) +4718 train 6.886543 (lr=1.1379e-05) (hash(x)=23659116) +4719 train 6.939319 (lr=1.1369e-05) (hash(x)=22453718) +4720 train 6.891037 (lr=1.1359e-05) (hash(x)=22597951) +4721 train 7.082169 (lr=1.1349e-05) (hash(x)=25284885) +4722 train 7.048584 (lr=1.1340e-05) (hash(x)=24748569) +4723 train 6.631489 (lr=1.1330e-05) (hash(x)=19448608) +4724 train 7.018332 (lr=1.1321e-05) (hash(x)=24888040) +4725 train 6.861415 (lr=1.1311e-05) (hash(x)=23203503) +4726 train 6.592945 (lr=1.1302e-05) (hash(x)=20387787) +4727 train 6.721162 (lr=1.1292e-05) (hash(x)=22529445) +4728 train 7.014311 (lr=1.1283e-05) (hash(x)=22455471) +4729 train 7.009926 (lr=1.1274e-05) (hash(x)=25661132) +4730 train 7.009212 (lr=1.1264e-05) (hash(x)=24997711) +4731 train 7.073264 (lr=1.1255e-05) (hash(x)=22575521) +4732 train 6.864859 (lr=1.1246e-05) (hash(x)=22640285) +4733 train 6.720747 (lr=1.1236e-05) (hash(x)=18637357) +4734 train 6.854917 (lr=1.1227e-05) (hash(x)=22845826) +4735 train 7.049508 (lr=1.1218e-05) (hash(x)=24484543) +4736 train 6.910498 (lr=1.1209e-05) (hash(x)=23352320) +4737 train 6.689065 (lr=1.1200e-05) (hash(x)=21544758) +4738 train 6.450278 (lr=1.1191e-05) (hash(x)=18292136) +4739 train 7.184358 (lr=1.1182e-05) (hash(x)=24893614) +4740 train 7.006746 (lr=1.1173e-05) (hash(x)=28103443) +4741 train 6.839227 (lr=1.1164e-05) (hash(x)=22233356) +4742 train 6.695085 (lr=1.1155e-05) (hash(x)=21133541) +4743 train 6.994540 (lr=1.1146e-05) (hash(x)=24043998) +4744 train 7.220361 (lr=1.1137e-05) (hash(x)=24801185) +4745 train 6.990356 (lr=1.1128e-05) (hash(x)=23858358) +4746 train 7.076707 (lr=1.1119e-05) (hash(x)=23926989) +4747 train 7.116892 (lr=1.1111e-05) (hash(x)=24813708) +4748 train 6.934648 (lr=1.1102e-05) (hash(x)=26339467) +4749 train 6.796023 (lr=1.1093e-05) (hash(x)=21850656) +4750 val loss 7.0884 +4750 val perplexity 1197.9528 +4750 train 6.779459 (lr=1.1085e-05) (hash(x)=21475802) +4751 train 6.983655 (lr=1.1076e-05) (hash(x)=24301906) +4752 train 6.810463 (lr=1.1067e-05) (hash(x)=22748495) +4753 train 6.959894 (lr=1.1059e-05) (hash(x)=25649256) +4754 train 6.881046 (lr=1.1050e-05) (hash(x)=23934346) +4755 train 7.010499 (lr=1.1042e-05) (hash(x)=26332892) +4756 train 6.875810 (lr=1.1033e-05) (hash(x)=23279389) +4757 train 6.941088 (lr=1.1025e-05) (hash(x)=23146858) +4758 train 7.275696 (lr=1.1017e-05) (hash(x)=26892932) +4759 train 6.845168 (lr=1.1008e-05) (hash(x)=26328881) +4760 train 6.907201 (lr=1.1000e-05) (hash(x)=24394655) +4761 train 6.860703 (lr=1.0992e-05) (hash(x)=22122308) +4762 train 7.037306 (lr=1.0983e-05) (hash(x)=24200369) +4763 train 7.192356 (lr=1.0975e-05) (hash(x)=26841776) +4764 train 7.129761 (lr=1.0967e-05) (hash(x)=27196641) +4765 train 6.859166 (lr=1.0959e-05) (hash(x)=24912822) +4766 train 7.150794 (lr=1.0951e-05) (hash(x)=25946055) +4767 train 6.721988 (lr=1.0943e-05) (hash(x)=23101508) +4768 train 6.896549 (lr=1.0935e-05) (hash(x)=24287798) +4769 train 6.994409 (lr=1.0927e-05) (hash(x)=22798964) +4770 train 6.910236 (lr=1.0919e-05) (hash(x)=24164479) +4771 train 6.956940 (lr=1.0911e-05) (hash(x)=24946464) +4772 train 7.099877 (lr=1.0903e-05) (hash(x)=25154423) +4773 train 6.801537 (lr=1.0895e-05) (hash(x)=23173476) +4774 train 7.056564 (lr=1.0887e-05) (hash(x)=25373559) +4775 train 7.015210 (lr=1.0879e-05) (hash(x)=23527176) +4776 train 6.988245 (lr=1.0871e-05) (hash(x)=24865403) +4777 train 6.898094 (lr=1.0864e-05) (hash(x)=24451067) +4778 train 7.553460 (lr=1.0856e-05) (hash(x)=28187162) +4779 train 7.704915 (lr=1.0848e-05) (hash(x)=31163350) +4780 train 7.878345 (lr=1.0841e-05) (hash(x)=33563280) +4781 train 7.947614 (lr=1.0833e-05) (hash(x)=34939183) +4782 train 7.507332 (lr=1.0826e-05) (hash(x)=30263543) +4783 train 6.876906 (lr=1.0818e-05) (hash(x)=22705673) +4784 train 6.721644 (lr=1.0810e-05) (hash(x)=21415023) +4785 train 7.005359 (lr=1.0803e-05) (hash(x)=26079097) +4786 train 7.298593 (lr=1.0796e-05) (hash(x)=25503836) +4787 train 7.166533 (lr=1.0788e-05) (hash(x)=24705721) +4788 train 7.013421 (lr=1.0781e-05) (hash(x)=24384657) +4789 train 6.916793 (lr=1.0774e-05) (hash(x)=22550579) +4790 train 6.962284 (lr=1.0766e-05) (hash(x)=22452164) +4791 train 7.270017 (lr=1.0759e-05) (hash(x)=28664796) +4792 train 7.634901 (lr=1.0752e-05) (hash(x)=26139280) +4793 train 7.254762 (lr=1.0745e-05) (hash(x)=23862341) +4794 train 6.859175 (lr=1.0737e-05) (hash(x)=23784757) +4795 train 6.698361 (lr=1.0730e-05) (hash(x)=22659441) +4796 train 7.444501 (lr=1.0723e-05) (hash(x)=29744216) +4797 train 7.380544 (lr=1.0716e-05) (hash(x)=25822591) +4798 train 6.792095 (lr=1.0709e-05) (hash(x)=22370895) +4799 train 7.237840 (lr=1.0702e-05) (hash(x)=27102890) +4800 val loss 7.0894 +4800 val perplexity 1199.1815 +4800 train 7.288059 (lr=1.0695e-05) (hash(x)=27014625) +4801 train 7.025254 (lr=1.0688e-05) (hash(x)=25755963) +4802 train 7.258436 (lr=1.0681e-05) (hash(x)=29675278) +4803 train 7.399154 (lr=1.0675e-05) (hash(x)=26660930) +4804 train 7.315671 (lr=1.0668e-05) (hash(x)=24557060) +4805 train 7.430753 (lr=1.0661e-05) (hash(x)=24622741) +4806 train 7.483802 (lr=1.0654e-05) (hash(x)=23952601) +4807 train 7.141628 (lr=1.0647e-05) (hash(x)=26787259) +4808 train 7.384847 (lr=1.0641e-05) (hash(x)=28919605) +4809 train 7.688222 (lr=1.0634e-05) (hash(x)=37061654) +4810 train 7.438852 (lr=1.0628e-05) (hash(x)=30379739) +4811 train 7.234415 (lr=1.0621e-05) (hash(x)=26097180) +4812 train 7.374493 (lr=1.0614e-05) (hash(x)=26327092) +4813 train 7.146974 (lr=1.0608e-05) (hash(x)=23258030) +4814 train 7.218340 (lr=1.0601e-05) (hash(x)=25582015) +4815 train 6.910239 (lr=1.0595e-05) (hash(x)=23396088) +4816 train 6.874506 (lr=1.0589e-05) (hash(x)=21904146) +4817 train 7.086426 (lr=1.0582e-05) (hash(x)=26281676) +4818 train 6.841072 (lr=1.0576e-05) (hash(x)=23140470) +4819 train 7.126607 (lr=1.0570e-05) (hash(x)=24611098) +4820 train 6.973358 (lr=1.0563e-05) (hash(x)=23832642) +4821 train 7.155143 (lr=1.0557e-05) (hash(x)=21439671) +4822 train 7.011614 (lr=1.0551e-05) (hash(x)=25128845) +4823 train 6.944921 (lr=1.0545e-05) (hash(x)=24911831) +4824 train 7.118054 (lr=1.0539e-05) (hash(x)=26051723) +4825 train 7.135850 (lr=1.0533e-05) (hash(x)=26479565) +4826 train 7.247248 (lr=1.0526e-05) (hash(x)=26228987) +4827 train 7.118112 (lr=1.0520e-05) (hash(x)=25131300) +4828 train 6.833572 (lr=1.0514e-05) (hash(x)=19921978) +4829 train 6.827638 (lr=1.0509e-05) (hash(x)=23173449) +4830 train 7.189958 (lr=1.0503e-05) (hash(x)=24791832) +4831 train 6.859269 (lr=1.0497e-05) (hash(x)=23453491) +4832 train 7.059496 (lr=1.0491e-05) (hash(x)=22564139) +4833 train 6.884889 (lr=1.0485e-05) (hash(x)=21659918) +4834 train 6.971438 (lr=1.0479e-05) (hash(x)=22956076) +4835 train 7.077940 (lr=1.0474e-05) (hash(x)=22237612) +4836 train 7.224403 (lr=1.0468e-05) (hash(x)=24736427) +4837 train 7.295050 (lr=1.0462e-05) (hash(x)=24939751) +4838 train 7.123821 (lr=1.0456e-05) (hash(x)=25059298) +4839 train 7.035450 (lr=1.0451e-05) (hash(x)=23453396) +4840 train 6.532455 (lr=1.0445e-05) (hash(x)=17919338) +4841 train 7.093072 (lr=1.0440e-05) (hash(x)=23428815) +4842 train 7.371167 (lr=1.0434e-05) (hash(x)=27042659) +4843 train 7.429933 (lr=1.0429e-05) (hash(x)=25161278) +4844 train 7.203746 (lr=1.0423e-05) (hash(x)=24113253) +4845 train 7.332673 (lr=1.0418e-05) (hash(x)=26139263) +4846 train 7.360538 (lr=1.0413e-05) (hash(x)=27787006) +4847 train 7.079163 (lr=1.0407e-05) (hash(x)=23869612) +4848 train 7.220172 (lr=1.0402e-05) (hash(x)=26092193) +4849 train 7.271541 (lr=1.0397e-05) (hash(x)=29351182) +4850 val loss 7.0827 +4850 val perplexity 1191.2079 +4850 train 7.480474 (lr=1.0391e-05) (hash(x)=28773463) +4851 train 7.373806 (lr=1.0386e-05) (hash(x)=28207741) +4852 train 6.889978 (lr=1.0381e-05) (hash(x)=23280878) +4853 train 7.343446 (lr=1.0376e-05) (hash(x)=26742336) +4854 train 7.138003 (lr=1.0371e-05) (hash(x)=23543321) +4855 train 7.505071 (lr=1.0366e-05) (hash(x)=26581590) +4856 train 6.969032 (lr=1.0361e-05) (hash(x)=22728668) +4857 train 6.805406 (lr=1.0356e-05) (hash(x)=19854534) +4858 train 7.224955 (lr=1.0351e-05) (hash(x)=26612813) +4859 train 7.341438 (lr=1.0346e-05) (hash(x)=25827863) +4860 train 7.038347 (lr=1.0341e-05) (hash(x)=24574997) +4861 train 7.201024 (lr=1.0336e-05) (hash(x)=26187830) +4862 train 7.161120 (lr=1.0331e-05) (hash(x)=25105823) +4863 train 7.218709 (lr=1.0327e-05) (hash(x)=28056342) +4864 train 7.055343 (lr=1.0322e-05) (hash(x)=21885801) +4865 train 7.274740 (lr=1.0317e-05) (hash(x)=25659043) +4866 train 7.226547 (lr=1.0313e-05) (hash(x)=23852824) +4867 train 7.036115 (lr=1.0308e-05) (hash(x)=23965470) +4868 train 7.067922 (lr=1.0303e-05) (hash(x)=25035012) +4869 train 7.234742 (lr=1.0299e-05) (hash(x)=26639165) +4870 train 7.246190 (lr=1.0294e-05) (hash(x)=29205362) +4871 train 7.089748 (lr=1.0290e-05) (hash(x)=25900866) +4872 train 7.133659 (lr=1.0285e-05) (hash(x)=25636242) +4873 train 7.190197 (lr=1.0281e-05) (hash(x)=25430698) +4874 train 7.183979 (lr=1.0276e-05) (hash(x)=27629981) +4875 train 7.155259 (lr=1.0272e-05) (hash(x)=27682625) +4876 train 7.422226 (lr=1.0268e-05) (hash(x)=27549409) +4877 train 7.110723 (lr=1.0263e-05) (hash(x)=24661627) +4878 train 7.199180 (lr=1.0259e-05) (hash(x)=25196542) +4879 train 7.067441 (lr=1.0255e-05) (hash(x)=24549177) +4880 train 7.025465 (lr=1.0251e-05) (hash(x)=23740600) +4881 train 6.915493 (lr=1.0247e-05) (hash(x)=21460850) +4882 train 7.216927 (lr=1.0242e-05) (hash(x)=27101400) +4883 train 7.214847 (lr=1.0238e-05) (hash(x)=24193076) +4884 train 7.112216 (lr=1.0234e-05) (hash(x)=24582947) +4885 train 7.071767 (lr=1.0230e-05) (hash(x)=25133839) +4886 train 7.075011 (lr=1.0226e-05) (hash(x)=24759454) +4887 train 7.149517 (lr=1.0222e-05) (hash(x)=28239583) +4888 train 7.416078 (lr=1.0218e-05) (hash(x)=29594489) +4889 train 7.125206 (lr=1.0215e-05) (hash(x)=23833431) +4890 train 7.099210 (lr=1.0211e-05) (hash(x)=23139411) +4891 train 7.018710 (lr=1.0207e-05) (hash(x)=20885864) +4892 train 7.378715 (lr=1.0203e-05) (hash(x)=26217418) +4893 train 7.147714 (lr=1.0199e-05) (hash(x)=27321870) +4894 train 6.680453 (lr=1.0196e-05) (hash(x)=19912955) +4895 train 6.990701 (lr=1.0192e-05) (hash(x)=23223554) +4896 train 7.203104 (lr=1.0188e-05) (hash(x)=25667219) +4897 train 7.446117 (lr=1.0185e-05) (hash(x)=28007972) +4898 train 7.258470 (lr=1.0181e-05) (hash(x)=27748764) +4899 train 7.186131 (lr=1.0178e-05) (hash(x)=27425770) +4900 val loss 7.0782 +4900 val perplexity 1185.8641 +4900 train 7.299536 (lr=1.0174e-05) (hash(x)=28394020) +4901 train 7.153018 (lr=1.0171e-05) (hash(x)=24080235) +4902 train 6.967613 (lr=1.0167e-05) (hash(x)=23309527) +4903 train 7.000795 (lr=1.0164e-05) (hash(x)=24793480) +4904 train 7.180003 (lr=1.0160e-05) (hash(x)=25344456) +4905 train 7.145199 (lr=1.0157e-05) (hash(x)=24590670) +4906 train 7.098444 (lr=1.0154e-05) (hash(x)=26937171) +4907 train 7.236556 (lr=1.0151e-05) (hash(x)=26949097) +4908 train 6.907418 (lr=1.0147e-05) (hash(x)=22443915) +4909 train 6.951519 (lr=1.0144e-05) (hash(x)=23814995) +4910 train 7.070104 (lr=1.0141e-05) (hash(x)=26135871) +4911 train 6.879327 (lr=1.0138e-05) (hash(x)=25415570) +4912 train 7.205623 (lr=1.0135e-05) (hash(x)=26756326) +4913 train 7.102364 (lr=1.0132e-05) (hash(x)=22920200) +4914 train 7.139538 (lr=1.0129e-05) (hash(x)=26710977) +4915 train 7.036518 (lr=1.0126e-05) (hash(x)=24985634) +4916 train 7.190801 (lr=1.0123e-05) (hash(x)=26004335) +4917 train 7.104208 (lr=1.0120e-05) (hash(x)=25637457) +4918 train 7.338362 (lr=1.0117e-05) (hash(x)=26645180) +4919 train 7.166247 (lr=1.0114e-05) (hash(x)=24425760) +4920 train 7.405048 (lr=1.0111e-05) (hash(x)=28223544) +4921 train 7.097162 (lr=1.0109e-05) (hash(x)=25538618) +4922 train 7.350530 (lr=1.0106e-05) (hash(x)=26984784) +4923 train 7.370726 (lr=1.0103e-05) (hash(x)=29154578) +4924 train 7.080763 (lr=1.0101e-05) (hash(x)=25308123) +4925 train 7.398511 (lr=1.0098e-05) (hash(x)=27939259) +4926 train 6.983239 (lr=1.0095e-05) (hash(x)=21984545) +4927 train 7.018201 (lr=1.0093e-05) (hash(x)=23707134) +4928 train 7.072609 (lr=1.0090e-05) (hash(x)=27201034) +4929 train 7.423499 (lr=1.0088e-05) (hash(x)=31623877) +4930 train 7.087982 (lr=1.0085e-05) (hash(x)=22162782) +4931 train 7.023441 (lr=1.0083e-05) (hash(x)=20049335) +4932 train 6.921688 (lr=1.0081e-05) (hash(x)=25594665) +4933 train 7.051377 (lr=1.0078e-05) (hash(x)=25265312) +4934 train 7.218410 (lr=1.0076e-05) (hash(x)=27094896) +4935 train 7.543857 (lr=1.0074e-05) (hash(x)=28321697) +4936 train 7.030614 (lr=1.0071e-05) (hash(x)=25006013) +4937 train 7.236183 (lr=1.0069e-05) (hash(x)=24596431) +4938 train 7.269666 (lr=1.0067e-05) (hash(x)=25150510) +4939 train 6.759898 (lr=1.0065e-05) (hash(x)=21497535) +4940 train 7.071587 (lr=1.0063e-05) (hash(x)=25094669) +4941 train 6.939561 (lr=1.0061e-05) (hash(x)=24024557) +4942 train 7.214127 (lr=1.0059e-05) (hash(x)=24370776) +4943 train 7.087398 (lr=1.0057e-05) (hash(x)=23434031) +4944 train 7.082397 (lr=1.0055e-05) (hash(x)=24383517) +4945 train 7.106288 (lr=1.0053e-05) (hash(x)=25858759) +4946 train 6.672843 (lr=1.0051e-05) (hash(x)=20409561) +4947 train 7.401134 (lr=1.0049e-05) (hash(x)=27469117) +4948 train 6.909782 (lr=1.0047e-05) (hash(x)=22086623) +4949 train 7.236282 (lr=1.0045e-05) (hash(x)=25759281) +4950 val loss 7.0756 +4950 val perplexity 1182.7063 +4950 train 7.140523 (lr=1.0044e-05) (hash(x)=27130117) +4951 train 7.001671 (lr=1.0042e-05) (hash(x)=27003481) +4952 train 7.342761 (lr=1.0040e-05) (hash(x)=26725937) +4953 train 7.074339 (lr=1.0038e-05) (hash(x)=22691119) +4954 train 7.112000 (lr=1.0037e-05) (hash(x)=17272898) +4955 train 6.931888 (lr=1.0035e-05) (hash(x)=17850370) +4956 train 6.914366 (lr=1.0034e-05) (hash(x)=18729639) +4957 train 7.148876 (lr=1.0032e-05) (hash(x)=25327160) +4958 train 7.291921 (lr=1.0031e-05) (hash(x)=28709044) +4959 train 6.859293 (lr=1.0029e-05) (hash(x)=22236893) +4960 train 6.794166 (lr=1.0028e-05) (hash(x)=21729251) +4961 train 6.930537 (lr=1.0026e-05) (hash(x)=23852346) +4962 train 7.150684 (lr=1.0025e-05) (hash(x)=23974368) +4963 train 7.079048 (lr=1.0024e-05) (hash(x)=25764691) +4964 train 7.487229 (lr=1.0023e-05) (hash(x)=28341865) +4965 train 6.979198 (lr=1.0021e-05) (hash(x)=23856238) +4966 train 7.200853 (lr=1.0020e-05) (hash(x)=24568904) +4967 train 7.111212 (lr=1.0019e-05) (hash(x)=26857458) +4968 train 6.931979 (lr=1.0018e-05) (hash(x)=20507972) +4969 train 7.143672 (lr=1.0017e-05) (hash(x)=23139455) +4970 train 7.028279 (lr=1.0016e-05) (hash(x)=24853703) +4971 train 7.068115 (lr=1.0015e-05) (hash(x)=25654849) +4972 train 6.855597 (lr=1.0014e-05) (hash(x)=22963710) +4973 train 7.232880 (lr=1.0013e-05) (hash(x)=25652110) +4974 train 7.162337 (lr=1.0012e-05) (hash(x)=24085957) +4975 train 7.386886 (lr=1.0011e-05) (hash(x)=26413122) +4976 train 7.534336 (lr=1.0010e-05) (hash(x)=26989387) +4977 train 7.183459 (lr=1.0009e-05) (hash(x)=22784033) +4978 train 7.538877 (lr=1.0008e-05) (hash(x)=26694945) +4979 train 7.488463 (lr=1.0008e-05) (hash(x)=24507726) +4980 train 7.532880 (lr=1.0007e-05) (hash(x)=26490335) +4981 train 7.505742 (lr=1.0006e-05) (hash(x)=25624751) +4982 train 7.442994 (lr=1.0006e-05) (hash(x)=27846204) +4983 train 7.304925 (lr=1.0005e-05) (hash(x)=27696537) +4984 train 7.205808 (lr=1.0004e-05) (hash(x)=28915842) +4985 train 7.257692 (lr=1.0004e-05) (hash(x)=28274576) +4986 train 7.299189 (lr=1.0003e-05) (hash(x)=28923892) +4987 train 6.878114 (lr=1.0003e-05) (hash(x)=21602520) +4988 train 6.823575 (lr=1.0003e-05) (hash(x)=21061011) +4989 train 7.322203 (lr=1.0002e-05) (hash(x)=28060542) +4990 train 7.099358 (lr=1.0002e-05) (hash(x)=24838134) +4991 train 7.040760 (lr=1.0001e-05) (hash(x)=21950234) +4992 train 7.325396 (lr=1.0001e-05) (hash(x)=27192740) +4993 train 7.292316 (lr=1.0001e-05) (hash(x)=26770105) +4994 train 6.936022 (lr=1.0001e-05) (hash(x)=23721261) +4995 train 6.998892 (lr=1.0000e-05) (hash(x)=26064895) +4996 train 7.240196 (lr=1.0000e-05) (hash(x)=25651075) +4997 train 7.058351 (lr=1.0000e-05) (hash(x)=25029447) +4998 train 7.234657 (lr=1.0000e-05) (hash(x)=26088225) +4999 val loss 7.0749 +4999 val perplexity 1181.9176 +4999 train 7.121097 (lr=1.0000e-05) (hash(x)=24051952)