Below is the command to time the gpu_jobs.bash on P100 machine:

time bash gpu_jobs.bash > gpu_jobs.log.txt

real    459m39.202s
user    634m16.646s
sys     113m9.866s

Below is the output:
--------------------
loading file 1000
loading file 2000
loading file 3000
loading file 4000
loading file 5000
loading file 6000
loading file 7000
loading file 8000
loading file 9000
loading file 10000
num_batches 30809
train step loss recon_loss kl_loss
step 500 63.9669 31.9433 32.0236
step 1000 60.1238 27.7435 32.3803
step 1500 62.471 30.1637 32.3073
step 2000 47.9941 15.9298 32.0643
step 2500 48.515 16.3701 32.1449
step 3000 46.9001 14.7312 32.1689
step 3500 46.0562 13.9151 32.1411
step 4000 45.6654 13.6176 32.0478
step 4500 41.616 9.6088 32.0072
step 5000 40.3252 8.32518 32.0
step 5500 44.1429 12.0637 32.0792
step 6000 51.1892 19.0007 32.1885
step 6500 42.7435 10.6553 32.0882
step 7000 49.1642 17.1169 32.0474
step 7500 43.1182 11.0869 32.0313
step 8000 40.0909 8.00695 32.084
step 8500 41.8995 9.82894 32.0706
step 9000 42.8877 10.7984 32.0893
step 9500 39.9986 7.99856 32.0
step 10000 40.1154 8.06914 32.0463
step 10500 43.84 11.7868 32.0532
step 11000 40.1219 8.10845 32.0135
step 11500 40.0398 8.01431 32.0255
step 12000 41.9617 9.93801 32.0237
step 12500 42.1444 10.1411 32.0033
step 13000 42.0796 10.0559 32.0238
step 13500 39.7397 7.69401 32.0457
step 14000 40.1974 8.12413 32.0732
step 14500 41.0106 8.97135 32.0392
step 15000 38.9607 6.9605 32.0002
step 15500 40.0199 8.00465 32.0153
step 16000 39.8893 7.88261 32.0067
step 16500 42.674 10.6503 32.0238
step 17000 42.9615 10.9236 32.0379
step 17500 41.6598 9.61957 32.0402
step 18000 39.8022 7.80159 32.0006
step 18500 36.949 4.94855 32.0005
step 19000 41.4997 9.43176 32.0679
step 19500 38.5638 6.56377 32.0
step 20000 39.2957 7.27809 32.0177
step 20500 39.6702 7.6005 32.0697
step 21000 39.0685 7.06853 32.0
step 21500 40.1826 8.14816 32.0344
step 22000 38.6045 6.52593 32.0786
step 22500 41.1816 9.106 32.0756
step 23000 39.3475 7.29918 32.0484
step 23500 39.2041 7.20412 32.0
step 24000 38.5422 6.53247 32.0098
step 24500 38.7198 6.70758 32.0122
step 25000 38.5218 6.5218 32.0
step 25500 37.8076 5.80253 32.0051
step 26000 38.7826 6.74428 32.0383
step 26500 38.5393 6.48498 32.0543
step 27000 38.8786 6.87578 32.0028
step 27500 38.6608 6.64405 32.0168
step 28000 39.4471 7.44677 32.0003
step 28500 38.2744 6.2697 32.0047
step 29000 42.4821 10.2532 32.2289
step 29500 38.485 6.46508 32.02
step 30000 38.3335 6.29446 32.0391
step 30500 38.5675 6.56745 32.0
step 31000 37.2354 5.23538 32.0
step 31500 38.7748 6.77477 32.0
step 32000 37.6225 5.62252 32.0
step 32500 38.3786 6.36644 32.0122
step 33000 37.6405 5.63462 32.0059
step 33500 40.3596 8.31847 32.0411
step 34000 38.8601 6.83275 32.0274
step 34500 39.3566 7.30607 32.0506
step 35000 40.9656 8.77421 32.1914
step 35500 38.451 6.45105 32.0
step 36000 37.4477 5.43528 32.0124
step 36500 38.8474 6.79411 32.0533
step 37000 37.3324 5.3099 32.0225
step 37500 38.438 6.39456 32.0434
step 38000 36.8105 4.80164 32.0089
step 38500 37.7428 5.73121 32.0116
step 39000 36.7257 4.7251 32.0006
step 39500 38.5576 6.54193 32.0156
step 40000 38.4959 6.48839 32.0075
step 40500 36.8376 4.83225 32.0053
step 41000 37.6966 5.66443 32.0322
step 41500 36.9046 4.90462 32.0
step 42000 36.9562 4.83845 32.1177
step 42500 37.9011 5.86507 32.036
step 43000 37.2929 5.2749 32.018
step 43500 37.252 5.23811 32.0139
step 44000 39.3796 7.30017 32.0794
step 44500 39.2373 7.13512 32.1021
step 45000 39.0268 6.95431 32.0725
step 45500 40.0399 7.90392 32.136
step 46000 36.7557 4.7486 32.0071
step 46500 36.7355 4.73166 32.0039
step 47000 37.6181 5.5901 32.028
step 47500 37.6312 5.58337 32.0478
step 48000 38.946 6.90275 32.0432
step 48500 37.0328 5.02807 32.0047
step 49000 36.2487 4.19168 32.057
step 49500 37.1619 5.09667 32.0652
step 50000 37.9425 5.89842 32.0441
step 50500 36.2029 4.20295 32.0
step 51000 37.3017 5.30029 32.0014
step 51500 37.2799 5.27994 32.0
step 52000 38.7226 6.67502 32.0476
step 52500 37.0196 4.98996 32.0296
step 53000 37.7988 5.71899 32.0798
step 53500 37.1285 5.11969 32.0088
step 54000 37.5624 5.56108 32.0013
step 54500 38.6591 6.59252 32.0666
step 55000 38.7965 6.74269 32.0538
step 55500 38.5074 6.44242 32.065
step 56000 37.7935 5.77917 32.0143
step 56500 36.3108 4.29795 32.0128
step 57000 36.3124 4.30936 32.003
step 57500 36.1689 4.16463 32.0043
step 58000 37.3456 5.33467 32.0109
step 58500 36.0951 4.08672 32.0084
step 59000 37.0728 5.07204 32.0008
step 59500 37.0605 5.04991 32.0106
step 60000 38.1794 6.09345 32.086
step 60500 36.3296 4.31345 32.0162
step 61000 36.5089 4.49852 32.0104
step 61500 37.3062 5.24438 32.0618
step 62000 37.2926 5.29261 32.0
step 62500 36.9672 4.93172 32.0355
step 63000 36.8701 4.86599 32.0041
step 63500 36.8932 4.86879 32.0244
step 64000 37.7834 5.76091 32.0225
step 64500 37.5023 5.47994 32.0224
step 65000 37.3693 5.35165 32.0177
step 65500 37.1998 5.09935 32.1004
step 66000 37.9073 5.87179 32.0355
step 66500 36.0683 4.0449 32.0234
step 67000 36.5226 4.50302 32.0196
step 67500 38.0092 6.00071 32.0085
step 68000 37.1492 5.14099 32.0082
step 68500 38.3883 6.32893 32.0594
step 69000 37.2094 5.20273 32.0066
step 69500 36.7056 4.67408 32.0315
step 70000 35.6393 3.6318 32.0075
step 70500 36.3878 4.38023 32.0076
step 71000 36.9328 4.91001 32.0228
step 71500 35.3386 3.32959 32.009
step 72000 37.0479 5.03471 32.0132
step 72500 38.6196 6.5423 32.0773
step 73000 37.7026 5.67643 32.0261
step 73500 36.7698 4.76152 32.0082
step 74000 37.6827 5.65632 32.0264
step 74500 37.2028 5.19775 32.0051
step 75000 36.8594 4.85172 32.0077
step 75500 38.9435 6.90775 32.0358
step 76000 36.4292 4.34154 32.0876
step 76500 36.4266 4.41888 32.0077
step 77000 36.9093 4.87233 32.037
step 77500 38.0615 6.02339 32.0382
step 78000 38.0696 5.97643 32.0932
step 78500 37.3663 5.36573 32.0005
step 79000 36.7239 4.69086 32.033
step 79500 36.288 4.24172 32.0463
step 80000 38.3828 6.29362 32.0892
step 80500 37.7131 5.71246 32.0006
step 81000 37.0107 4.98201 32.0287
step 81500 37.1181 5.07305 32.0451
step 82000 35.6074 3.59687 32.0105
step 82500 38.1595 6.11021 32.0493
step 83000 36.6634 4.64371 32.0197
step 83500 36.9013 4.89418 32.0071
step 84000 38.5111 6.43144 32.0796
step 84500 38.0603 6.02147 32.0388
step 85000 37.4397 5.4247 32.015
step 85500 37.0869 5.07457 32.0123
step 86000 37.1391 5.09113 32.048
step 86500 37.3749 5.37487 32.0
step 87000 37.4011 5.32874 32.0724
step 87500 36.307 4.24861 32.0584
step 88000 38.1082 6.0868 32.0214
step 88500 36.0715 4.05452 32.0169
step 89000 35.8767 3.87494 32.0018
step 89500 38.9699 6.92214 32.0478
step 90000 35.0336 3.03187 32.0017
step 90500 41.5673 9.53541 32.0318
step 91000 36.8555 4.84238 32.0131
step 91500 37.7426 5.71336 32.0292
step 92000 37.421 5.37695 32.0441
step 92500 37.3649 5.31651 32.0484
step 93000 36.9909 4.98321 32.0077
step 93500 35.4169 3.41613 32.0007
step 94000 37.1086 5.08499 32.0236
step 94500 37.2761 5.27 32.0061
step 95000 39.8864 7.75925 32.1272
step 95500 37.3002 5.26385 32.0363
step 96000 36.6347 4.60922 32.0255
step 96500 35.6948 3.69476 32.0
step 97000 36.8639 4.85939 32.0045
step 97500 35.5612 3.54847 32.0127
step 98000 35.9357 3.92009 32.0157
step 98500 35.2704 3.2704 32.0
step 99000 38.1212 6.00819 32.113
step 99500 35.868 3.85754 32.0105
step 100000 36.0019 3.93862 32.0633
step 100500 36.6083 4.60833 32.0
step 101000 39.6446 7.62418 32.0204
step 101500 37.2402 5.15548 32.0847
step 102000 36.153 4.12327 32.0297
step 102500 35.4648 3.46387 32.0009
step 103000 36.3554 4.35109 32.0043
step 103500 35.9815 3.95896 32.0226
step 104000 36.2147 4.20755 32.0071
step 104500 36.0161 3.99264 32.0235
step 105000 35.5814 3.57204 32.0093
step 105500 36.5222 4.5015 32.0207
step 106000 37.3568 5.28785 32.0689
step 106500 36.4609 4.41392 32.047
step 107000 36.4565 4.40155 32.0549
step 107500 36.2647 4.25188 32.0128
step 108000 36.5189 4.49295 32.026
step 108500 37.851 5.81547 32.0355
step 109000 37.3687 5.30406 32.0646
step 109500 37.4471 5.38863 32.0585
step 110000 36.8764 4.83779 32.0386
step 110500 36.5221 4.48225 32.0399
step 111000 36.8024 4.79784 32.0045
step 111500 38.974 6.90341 32.0706
step 112000 37.4657 5.44773 32.018
step 112500 36.6307 4.56579 32.0649
step 113000 36.0585 4.01872 32.0398
step 113500 35.2547 3.25468 32.0
step 114000 36.3689 4.34581 32.0231
step 114500 35.4865 3.48261 32.0038
step 115000 36.61 4.58858 32.0214
step 115500 36.2982 4.2712 32.027
step 116000 35.9698 3.94088 32.0289
step 116500 37.0848 5.00582 32.079
step 117000 36.3431 4.3138 32.0293
step 117500 37.4078 5.36616 32.0417
step 118000 36.0329 4.01827 32.0146
step 118500 35.1402 3.13454 32.0056
step 119000 37.695 5.67261 32.0224
step 119500 38.5597 6.5153 32.0444
step 120000 35.7759 3.76038 32.0156
step 120500 37.0924 5.0755 32.0169
step 121000 36.6056 4.5679 32.0377
step 121500 36.7088 4.67377 32.0351
step 122000 37.5346 5.50407 32.0305
step 122500 36.5909 4.57177 32.0192
step 123000 37.9559 5.91579 32.0401
step 123500 36.1351 4.09814 32.037
step 124000 36.9039 4.88513 32.0188
step 124500 37.823 5.71048 32.1125
step 125000 36.1534 4.15269 32.0007
step 125500 35.8358 3.83471 32.0011
step 126000 36.9183 4.90906 32.0092
step 126500 36.788 4.77812 32.0098
step 127000 37.1647 5.0795 32.0852
step 127500 36.1052 4.06387 32.0413
step 128000 36.7746 4.69693 32.0777
step 128500 38.1877 6.08681 32.1009
step 129000 36.6996 4.6821 32.0175
step 129500 35.8292 3.80939 32.0198
step 130000 37.4244 5.37741 32.047
step 130500 35.6264 3.62461 32.0018
step 131000 36.2173 4.18619 32.0311
step 131500 35.8319 3.8051 32.0268
step 132000 37.7856 5.76654 32.0191
step 132500 37.5922 5.54289 32.0493
step 133000 36.137 4.13413 32.0029
step 133500 36.7088 4.69093 32.0179
step 134000 35.4976 3.49119 32.0064
step 134500 37.5032 5.39059 32.1126
step 135000 37.1236 5.0764 32.0472
step 135500 37.614 5.58146 32.0325
step 136000 38.2721 6.26917 32.0029
step 136500 35.8589 3.84573 32.0131
step 137000 35.3895 3.3415 32.048
step 137500 36.5517 4.49097 32.0607
step 138000 37.6089 5.59606 32.0128
step 138500 37.1203 5.1078 32.0125
step 139000 36.4127 4.4028 32.0099
step 139500 39.8434 7.81739 32.0261
step 140000 35.4491 3.43788 32.0112
step 140500 37.0432 5.01684 32.0264
step 141000 35.8194 3.78057 32.0388
step 141500 36.0914 4.07944 32.0119
step 142000 35.6637 3.65167 32.012
step 142500 36.3867 4.36137 32.0253
step 143000 37.1419 5.13297 32.009
step 143500 35.8171 3.75028 32.0668
step 144000 36.2648 4.2622 32.0026
step 144500 36.3743 4.35456 32.0198
step 145000 35.7458 3.73672 32.0091
step 145500 37.2299 5.22407 32.0058
step 146000 36.222 4.13967 32.0824
step 146500 35.927 3.91306 32.0139
step 147000 36.2541 4.24536 32.0087
step 147500 36.2117 4.19291 32.0188
step 148000 36.4813 4.46266 32.0186
step 148500 35.1219 3.1152 32.0067
step 149000 35.5652 3.53459 32.0306
step 149500 35.8154 3.80855 32.0069
step 150000 35.5431 3.52133 32.0218
step 150500 36.4414 4.41784 32.0236
step 151000 36.4725 4.47198 32.0005
step 151500 35.995 3.97653 32.0184
step 152000 35.6963 3.67131 32.025
step 152500 36.0092 3.99986 32.0094
step 153000 36.2442 4.23308 32.0112
step 153500 40.0817 8.02144 32.0602
step 154000 37.0467 4.94078 32.1059
step 154500 37.6243 5.51112 32.1132
step 155000 35.757 3.74424 32.0128
step 155500 36.2574 4.239 32.0184
step 156000 35.9251 3.92047 32.0046
step 156500 36.3622 4.35468 32.0076
step 157000 35.4924 3.47532 32.0171
step 157500 38.3853 6.38077 32.0045
step 158000 37.2945 5.29453 32.0
step 158500 36.9758 4.95153 32.0243
step 159000 35.5273 3.48327 32.044
step 159500 36.56 4.54351 32.0165
step 160000 35.416 3.41114 32.0049
step 160500 39.048 6.99618 32.0518
step 161000 36.5243 4.48022 32.0441
step 161500 37.7298 5.63911 32.0907
step 162000 37.2833 5.23897 32.0443
step 162500 35.3729 3.35985 32.0131
step 163000 36.869 4.8089 32.0601
step 163500 37.9863 5.97913 32.0071
step 164000 36.2868 4.25698 32.0299
step 164500 36.8156 4.79172 32.0238
step 165000 34.9092 2.90202 32.0071
step 165500 35.8246 3.80055 32.0241
step 166000 36.9749 4.91368 32.0612
step 166500 36.241 4.17585 32.0651
step 167000 35.2357 3.23172 32.0039
step 167500 35.6543 3.63515 32.0192
step 168000 35.3263 3.32062 32.0057
step 168500 36.2035 4.15179 32.0517
step 169000 36.056 4.05597 32.0
step 169500 36.2794 4.25271 32.0267
step 170000 36.1709 4.14753 32.0234
step 170500 35.5988 3.57881 32.02
step 171000 36.0585 4.02967 32.0288
step 171500 34.7238 2.71966 32.0041
step 172000 36.4048 4.36901 32.0358
step 172500 35.3518 3.35122 32.0006
step 173000 35.0287 3.02587 32.0029
step 173500 35.7162 3.67736 32.0388
step 174000 36.663 4.54442 32.1186
step 174500 35.06 3.03822 32.0218
step 175000 35.3628 3.36285 32.0
step 175500 36.2444 4.23507 32.0093
step 176000 36.3205 4.27545 32.045
step 176500 35.9588 3.92121 32.0375
step 177000 35.2015 3.20133 32.0002
step 177500 37.4321 5.40573 32.0263
step 178000 36.7332 4.61466 32.1185
step 178500 36.4987 4.33193 32.1667
step 179000 36.5821 4.57831 32.0038
step 179500 35.3039 3.28991 32.014
step 180000 34.9582 2.95433 32.0039
step 180500 35.7045 3.70054 32.0039
step 181000 35.9505 3.94215 32.0084
step 181500 36.3355 4.32626 32.0092
step 182000 36.1817 4.15521 32.0265
step 182500 35.9047 3.88115 32.0236
step 183000 35.8964 3.87952 32.0169
step 183500 35.6232 3.55583 32.0674
step 184000 35.7502 3.72914 32.021
step 184500 35.422 3.42196 32.0
step 185000 36.4761 4.46157 32.0145
step 185500 36.7165 4.66209 32.0544
step 186000 35.5873 3.58524 32.0021
step 186500 36.9286 4.8664 32.0622
step 187000 35.91 3.90209 32.0079
step 187500 37.5903 5.48035 32.11
step 188000 35.3845 3.34931 32.0352
step 188500 36.0924 4.08835 32.004
step 189000 34.9793 2.973 32.0063
step 189500 35.628 3.61695 32.0111
step 190000 36.7761 4.74894 32.0272
step 190500 35.4026 3.3836 32.019
step 191000 34.8957 2.89471 32.001
step 191500 35.9583 3.95176 32.0065
step 192000 36.0801 4.04608 32.034
step 192500 36.4692 4.44907 32.0201
step 193000 36.3476 4.3128 32.0348
step 193500 37.6586 5.6104 32.0482
step 194000 35.3776 3.35688 32.0207
step 194500 38.1884 6.15396 32.0344
step 195000 36.1499 4.12956 32.0203
step 195500 36.2318 4.20209 32.0297
step 196000 35.1971 3.18534 32.0118
step 196500 36.203 4.19422 32.0088
step 197000 35.5999 3.57854 32.0214
step 197500 35.5974 3.59589 32.0015
step 198000 36.4238 4.41579 32.008
step 198500 35.553 3.53996 32.0131
step 199000 35.5272 3.52001 32.0072
step 199500 36.2074 4.20369 32.0037
step 200000 36.0688 4.04436 32.0245
step 200500 37.3652 5.28947 32.0758
step 201000 39.5669 7.33732 32.2296
step 201500 36.9831 4.83951 32.1435
step 202000 40.3006 8.1955 32.1051
step 202500 34.5854 2.57479 32.0106
step 203000 37.2111 5.13921 32.0719
step 203500 34.9631 2.92207 32.0411
step 204000 36.6388 4.60192 32.0369
step 204500 36.2481 4.21384 32.0343
step 205000 35.5465 3.5342 32.0123
step 205500 36.1537 4.13396 32.0197
step 206000 37.8722 5.84854 32.0237
step 206500 36.1 4.08725 32.0128
step 207000 37.1403 5.09475 32.0455
step 207500 35.969 3.94792 32.0211
step 208000 36.9901 4.98403 32.0061
step 208500 35.7577 3.74824 32.0095
step 209000 35.2378 3.23757 32.0002
step 209500 35.5659 3.53298 32.0329
step 210000 35.9278 3.88733 32.0405
step 210500 35.084 3.08002 32.004
step 211000 35.9366 3.92527 32.0113
step 211500 34.6314 2.62715 32.0043
step 212000 36.64 4.63676 32.0032
step 212500 36.1913 4.16021 32.0311
step 213000 36.6758 4.60898 32.0668
step 213500 37.8833 5.83058 32.0527
step 214000 36.1689 4.16758 32.0014
step 214500 36.1426 4.11384 32.0287
step 215000 36.2347 4.23469 32.0
step 215500 36.131 4.12157 32.0094
step 216000 35.2088 3.18696 32.0219
step 216500 36.4337 4.42564 32.0081
step 217000 36.1476 4.09598 32.0516
step 217500 35.9902 3.9879 32.0023
step 218000 37.6593 5.55777 32.1015
step 218500 36.6249 4.594 32.0309
step 219000 36.244 4.21868 32.0253
step 219500 36.6017 4.53265 32.069
step 220000 37.5903 5.49417 32.0961
step 220500 36.8806 4.74391 32.1367
step 221000 35.8419 3.82912 32.0128
step 221500 35.719 3.71338 32.0056
step 222000 35.1316 3.11361 32.018
step 222500 35.3288 3.30754 32.0212
step 223000 36.2288 4.22229 32.0065
step 223500 38.9539 6.90935 32.0445
step 224000 35.3569 3.34355 32.0134
step 224500 37.201 5.18024 32.0208
step 225000 36.1844 4.16597 32.0184
step 225500 34.8212 2.81057 32.0106
step 226000 35.0028 3.00268 32.0002
step 226500 36.1638 4.14746 32.0163
step 227000 38.0268 6.0209 32.0059
step 227500 36.627 4.60009 32.0269
step 228000 35.5362 3.4943 32.0419
step 228500 37.9722 5.8581 32.1141
step 229000 36.7548 4.73925 32.0156
step 229500 36.6492 4.64479 32.0044
step 230000 35.8784 3.83918 32.0393
step 230500 35.6564 3.65331 32.0031
step 231000 36.9152 4.88625 32.0289
step 231500 38.5879 6.498 32.0899
step 232000 36.2334 4.22011 32.0133
step 232500 35.0603 3.04471 32.0156
step 233000 35.8242 3.81072 32.0135
step 233500 35.4972 3.48889 32.0083
step 234000 36.1545 4.08719 32.0674
step 234500 36.4909 4.47241 32.0185
step 235000 35.2847 3.25791 32.0268
step 235500 37.0254 5.00931 32.0161
step 236000 34.8589 2.85504 32.0038
step 236500 35.4926 3.45458 32.038
step 237000 36.3401 4.28898 32.0511
step 237500 35.7715 3.73392 32.0376
step 238000 35.5786 3.56589 32.0127
step 238500 35.2532 3.2217 32.0315
step 239000 35.6389 3.61688 32.0221
step 239500 35.6062 3.58234 32.0239
step 240000 35.8027 3.80275 32.0
step 240500 35.9931 3.9271 32.066
step 241000 38.1002 6.06517 32.035
step 241500 36.2263 4.21472 32.0116
step 242000 35.7213 3.70511 32.0162
step 242500 34.5562 2.55359 32.0026
step 243000 37.2784 5.24148 32.0369
step 243500 35.3714 3.36002 32.0113
step 244000 35.432 3.42639 32.0056
step 244500 35.8035 3.76412 32.0394
step 245000 35.6258 3.62334 32.0025
step 245500 35.9074 3.89393 32.0135
step 246000 35.6499 3.64432 32.0056
step 246500 35.1846 3.17691 32.0077
step 247000 36.9307 4.86958 32.0611
step 247500 36.8626 4.80432 32.0583
step 248000 35.3532 3.343 32.0102
step 248500 36.3149 4.30086 32.014
step 249000 35.6433 3.62973 32.0136
step 249500 36.32 4.29091 32.0291
step 250000 35.9422 3.94022 32.0019
step 250500 35.1908 3.17389 32.0169
step 251000 35.7149 3.69501 32.0198
step 251500 35.6415 3.63 32.0115
step 252000 37.6309 5.58561 32.0453
step 252500 35.204 3.2018 32.0022
step 253000 37.222 5.06861 32.1534
step 253500 34.8164 2.79972 32.0167
step 254000 36.3502 4.34111 32.0091
step 254500 35.2086 3.20404 32.0046
step 255000 36.3495 4.33032 32.0192
step 255500 37.3246 5.28528 32.0393
step 256000 35.9565 3.93141 32.0251
step 256500 36.7935 4.66687 32.1266
step 257000 34.2939 2.29181 32.0021
step 257500 36.0168 4.01078 32.0061
step 258000 37.6936 5.54708 32.1465
step 258500 35.4885 3.47712 32.0114
step 259000 35.2188 3.20933 32.0095
step 259500 34.6679 2.66219 32.0057
step 260000 35.2926 3.27965 32.0129
step 260500 34.8321 2.82746 32.0047
step 261000 35.9888 3.98878 32.0
step 261500 35.8761 3.86783 32.0083
step 262000 36.0261 3.99441 32.0317
step 262500 34.703 2.70301 32.0
step 263000 37.7758 5.69023 32.0856
step 263500 36.6787 4.66424 32.0144
step 264000 36.9007 4.86252 32.0382
step 264500 35.2125 3.1966 32.0159
step 265000 36.4412 4.41461 32.0266
step 265500 34.6693 2.6428 32.0265
step 266000 38.1145 6.03278 32.0817
step 266500 35.4123 3.40598 32.0063
step 267000 39.1012 6.78849 32.3127
step 267500 35.2751 3.25552 32.0196
step 268000 37.2462 5.19402 32.0522
step 268500 35.1719 3.16157 32.0103
step 269000 35.461 3.43832 32.0227
step 269500 35.745 3.74415 32.0008
step 270000 35.7812 3.77481 32.0064
step 270500 36.1566 4.1131 32.0435
step 271000 36.4341 4.38974 32.0444
step 271500 36.0399 4.03111 32.0088
step 272000 35.9249 3.91586 32.0091
step 272500 36.3023 4.26432 32.038
step 273000 36.0585 4.03767 32.0208
step 273500 36.2962 4.27429 32.0219
step 274000 35.3903 3.38342 32.0069
step 274500 35.5918 3.57658 32.0152
step 275000 35.3027 3.28225 32.0204
step 275500 35.5665 3.56541 32.001
step 276000 36.3976 4.31078 32.0869
step 276500 35.0091 2.9852 32.0239
step 277000 35.6798 3.6491 32.0307
step 277500 35.5121 3.49984 32.0123
step 278000 38.0331 5.85893 32.1742
step 278500 35.7411 3.7411 32.0
step 279000 36.8783 4.84923 32.0291
step 279500 35.3046 3.28864 32.0159
step 280000 35.873 3.85408 32.0189
step 280500 35.3468 3.33505 32.0117
step 281000 36.1342 4.10046 32.0337
step 281500 36.2852 4.24582 32.0394
step 282000 35.3166 3.30339 32.0132
step 282500 36.2849 4.26726 32.0177
step 283000 37.2427 5.17445 32.0683
step 283500 35.5588 3.53608 32.0227
step 284000 35.3983 3.38915 32.0091
step 284500 36.475 4.43956 32.0354
step 285000 35.2961 3.27156 32.0246
step 285500 36.1339 4.10152 32.0324
step 286000 34.6093 2.60429 32.005
step 286500 36.3137 4.29061 32.0231
step 287000 36.708 4.65893 32.0491
step 287500 34.7797 2.77893 32.0007
step 288000 36.1246 4.09361 32.031
step 288500 34.9183 2.90651 32.0118
step 289000 36.1371 4.12623 32.0108
step 289500 35.5109 3.49176 32.0191
step 290000 34.4456 2.4456 32.0
step 290500 35.2539 3.2367 32.0172
step 291000 36.7413 4.62872 32.1126
step 291500 36.0826 4.03489 32.0477
step 292000 35.7353 3.73107 32.0042
step 292500 35.9133 3.89909 32.0142
step 293000 36.8831 4.83771 32.0454
step 293500 35.4488 3.44628 32.0025
step 294000 35.9131 3.91122 32.0019
step 294500 35.3672 3.36397 32.0033
step 295000 34.4677 2.46436 32.0033
step 295500 34.9821 2.97796 32.0041
step 296000 37.0986 5.09157 32.007
step 296500 34.8414 2.83902 32.0023
step 297000 38.9142 6.76172 32.1525
step 297500 35.8264 3.77563 32.0508
step 298000 37.0112 4.98874 32.0225
step 298500 35.5065 3.46805 32.0384
step 299000 35.5059 3.48692 32.019
step 299500 35.8099 3.77322 32.0367
step 300000 35.821 3.81678 32.0042
step 300500 35.9244 3.89177 32.0326
step 301000 36.2414 4.23032 32.0111
step 301500 36.3113 4.28987 32.0214
step 302000 37.1002 4.98404 32.1162
step 302500 35.0893 3.08411 32.0052
step 303000 35.2441 3.23145 32.0127
step 303500 34.8747 2.85492 32.0198
step 304000 35.8855 3.86151 32.024
step 304500 35.9294 3.81581 32.1136
step 305000 36.3827 4.29951 32.0832
step 305500 34.8784 2.87116 32.0073
step 306000 34.9048 2.9048 32.0
step 306500 35.5518 3.53367 32.0181
step 307000 34.229 2.21848 32.0105
step 307500 35.5934 3.57688 32.0166
step 308000 35.5726 3.56631 32.0063
loading file 1000
loading file 2000
loading file 3000
loading file 4000
loading file 5000
loading file 6000
loading file 7000
loading file 8000
loading file 9000
loading file 10000
100
200
300
400
500
600
700
800
900
1000
1100
1200
1300
1400
1500
1600
1700
1800
1900
2000
2100
2200
2300
2400
2500
2600
2700
2800
2900
3000
3100
3200
3300
3400
3500
3600
3700
3800
3900
4000
4100
4200
4300
4400
4500
4600
4700
4800
4900
5000
5100
5200
5300
5400
5500
5600
5700
5800
5900
6000
6100
6200
6300
6400
6500
6600
6700
6800
6900
7000
7100
7200
7300
7400
7500
7600
7700
7800
7900
8000
8100
8200
8300
8400
8500
8600
8700
8800
8900
9000
9100
9200
9300
9400
9500
9600
9700
9800
9900
10000
model using gpu
input dropout mode = False
output dropout mode = False
recurrent dropout mode = False
preparing data for epoch 1
number of batches 61
time taken to create batches 0.583728551864624
step: 20, lr: 0.001000, cost: 1.4259, z_cost: 1.3136, r_cost: 0.1123, train_time_taken: 19.5200
step: 40, lr: 0.001000, cost: 1.3486, z_cost: 1.2436, r_cost: 0.1050, train_time_taken: 11.9290
step: 60, lr: 0.000999, cost: 1.2698, z_cost: 1.1825, r_cost: 0.0873, train_time_taken: 11.8576
preparing data for epoch 2
number of batches 61
time taken to create batches 0.6043760776519775
step: 80, lr: 0.000999, cost: 1.2343, z_cost: 1.1441, r_cost: 0.0902, train_time_taken: 12.3234
step: 100, lr: 0.000999, cost: 1.1954, z_cost: 1.1178, r_cost: 0.0776, train_time_taken: 11.6632
step: 120, lr: 0.000999, cost: 1.1856, z_cost: 1.1093, r_cost: 0.0763, train_time_taken: 11.5906
preparing data for epoch 3
number of batches 61
time taken to create batches 1.1820096969604492
step: 140, lr: 0.000999, cost: 1.1697, z_cost: 1.0944, r_cost: 0.0753, train_time_taken: 12.4241
step: 160, lr: 0.000998, cost: 1.1686, z_cost: 1.0922, r_cost: 0.0764, train_time_taken: 11.8333
step: 180, lr: 0.000998, cost: 1.1665, z_cost: 1.0958, r_cost: 0.0707, train_time_taken: 11.8162
preparing data for epoch 4
number of batches 61
time taken to create batches 1.78902006149292
step: 200, lr: 0.000998, cost: 1.1493, z_cost: 1.0822, r_cost: 0.0671, train_time_taken: 12.2584
step: 220, lr: 0.000998, cost: 1.1519, z_cost: 1.0833, r_cost: 0.0686, train_time_taken: 11.7504
step: 240, lr: 0.000998, cost: 1.1495, z_cost: 1.0792, r_cost: 0.0703, train_time_taken: 11.6031
preparing data for epoch 5
number of batches 61
time taken to create batches 2.3507094383239746
step: 260, lr: 0.000997, cost: 1.1324, z_cost: 1.0747, r_cost: 0.0577, train_time_taken: 12.4252
step: 280, lr: 0.000997, cost: 1.1279, z_cost: 1.0744, r_cost: 0.0535, train_time_taken: 11.9467
step: 300, lr: 0.000997, cost: 1.1236, z_cost: 1.0709, r_cost: 0.0526, train_time_taken: 11.8302
preparing data for epoch 6
number of batches 61
time taken to create batches 2.963026523590088
step: 320, lr: 0.000997, cost: 1.1196, z_cost: 1.0650, r_cost: 0.0547, train_time_taken: 12.3276
step: 340, lr: 0.000997, cost: 1.1219, z_cost: 1.0698, r_cost: 0.0520, train_time_taken: 11.6526
step: 360, lr: 0.000996, cost: 1.1347, z_cost: 1.0708, r_cost: 0.0639, train_time_taken: 11.6468
preparing data for epoch 7
number of batches 61
time taken to create batches 3.512359380722046
step: 380, lr: 0.000996, cost: 1.1221, z_cost: 1.0625, r_cost: 0.0596, train_time_taken: 12.3917
step: 400, lr: 0.000996, cost: 1.1167, z_cost: 1.0621, r_cost: 0.0546, train_time_taken: 11.8316
step: 420, lr: 0.000996, cost: 1.1133, z_cost: 1.0648, r_cost: 0.0485, train_time_taken: 11.8442
preparing data for epoch 8
number of batches 61
time taken to create batches 4.1471946239471436
step: 440, lr: 0.000996, cost: 1.1046, z_cost: 1.0620, r_cost: 0.0426, train_time_taken: 12.3199
step: 460, lr: 0.000995, cost: 1.1094, z_cost: 1.0592, r_cost: 0.0502, train_time_taken: 11.6532
step: 480, lr: 0.000995, cost: 1.1061, z_cost: 1.0599, r_cost: 0.0462, train_time_taken: 11.7075
preparing data for epoch 9
number of batches 61
time taken to create batches 4.671537160873413
step: 500, lr: 0.000995, cost: 1.1055, z_cost: 1.0592, r_cost: 0.0463, train_time_taken: 12.3008
step: 520, lr: 0.000995, cost: 1.1017, z_cost: 1.0595, r_cost: 0.0422, train_time_taken: 11.8338
step: 540, lr: 0.000995, cost: 1.0981, z_cost: 1.0543, r_cost: 0.0438, train_time_taken: 11.8532
preparing data for epoch 10
number of batches 61
time taken to create batches 5.34063196182251
step: 560, lr: 0.000994, cost: 1.1004, z_cost: 1.0571, r_cost: 0.0433, train_time_taken: 12.3555
step: 580, lr: 0.000994, cost: 1.1092, z_cost: 1.0553, r_cost: 0.0540, train_time_taken: 11.6386
step: 600, lr: 0.000994, cost: 1.1014, z_cost: 1.0548, r_cost: 0.0466, train_time_taken: 11.6885
preparing data for epoch 11
number of batches 61
time taken to create batches 5.84415864944458
step: 620, lr: 0.000994, cost: 1.0929, z_cost: 1.0531, r_cost: 0.0398, train_time_taken: 12.3652
step: 640, lr: 0.000994, cost: 1.1039, z_cost: 1.0537, r_cost: 0.0502, train_time_taken: 11.8558
step: 660, lr: 0.000993, cost: 1.1037, z_cost: 1.0543, r_cost: 0.0494, train_time_taken: 11.8763
preparing data for epoch 12
number of batches 61
time taken to create batches 6.497986078262329
step: 680, lr: 0.000993, cost: 1.0929, z_cost: 1.0510, r_cost: 0.0419, train_time_taken: 12.2807
step: 700, lr: 0.000993, cost: 1.0953, z_cost: 1.0534, r_cost: 0.0419, train_time_taken: 11.6588
step: 720, lr: 0.000993, cost: 1.0986, z_cost: 1.0502, r_cost: 0.0484, train_time_taken: 11.6391
preparing data for epoch 13
number of batches 61
time taken to create batches 6.987829208374023
step: 740, lr: 0.000993, cost: 1.0908, z_cost: 1.0496, r_cost: 0.0412, train_time_taken: 12.3193
step: 760, lr: 0.000993, cost: 1.0915, z_cost: 1.0507, r_cost: 0.0408, train_time_taken: 11.8705
step: 780, lr: 0.000992, cost: 1.0885, z_cost: 1.0505, r_cost: 0.0379, train_time_taken: 11.9203
preparing data for epoch 14
number of batches 61
time taken to create batches 7.717854261398315
step: 800, lr: 0.000992, cost: 1.0794, z_cost: 1.0453, r_cost: 0.0341, train_time_taken: 12.3639
step: 820, lr: 0.000992, cost: 1.0949, z_cost: 1.0511, r_cost: 0.0438, train_time_taken: 11.6620
step: 840, lr: 0.000992, cost: 1.0897, z_cost: 1.0489, r_cost: 0.0408, train_time_taken: 11.6328
preparing data for epoch 15
number of batches 61
time taken to create batches 8.141668558120728
step: 860, lr: 0.000992, cost: 1.0922, z_cost: 1.0475, r_cost: 0.0447, train_time_taken: 12.2873
step: 880, lr: 0.000991, cost: 1.0860, z_cost: 1.0482, r_cost: 0.0378, train_time_taken: 11.8443
step: 900, lr: 0.000991, cost: 1.0891, z_cost: 1.0440, r_cost: 0.0452, train_time_taken: 11.8706
preparing data for epoch 16
number of batches 61
time taken to create batches 8.975575685501099
step: 920, lr: 0.000991, cost: 1.0821, z_cost: 1.0469, r_cost: 0.0352, train_time_taken: 12.4979
step: 940, lr: 0.000991, cost: 1.0808, z_cost: 1.0475, r_cost: 0.0333, train_time_taken: 11.6660
step: 960, lr: 0.000991, cost: 1.0839, z_cost: 1.0437, r_cost: 0.0402, train_time_taken: 11.7882
preparing data for epoch 17
number of batches 61
time taken to create batches 9.333021640777588
step: 980, lr: 0.000990, cost: 1.0827, z_cost: 1.0457, r_cost: 0.0370, train_time_taken: 12.3793
step: 1000, lr: 0.000990, cost: 1.0874, z_cost: 1.0465, r_cost: 0.0409, train_time_taken: 11.8314
step: 1020, lr: 0.000990, cost: 1.0852, z_cost: 1.0433, r_cost: 0.0420, train_time_taken: 11.7972
preparing data for epoch 18
number of batches 61
time taken to create batches 10.121344089508057
step: 1040, lr: 0.000990, cost: 1.0722, z_cost: 1.0422, r_cost: 0.0300, train_time_taken: 12.4585
step: 1060, lr: 0.000990, cost: 1.0829, z_cost: 1.0461, r_cost: 0.0368, train_time_taken: 11.6326
step: 1080, lr: 0.000989, cost: 1.0762, z_cost: 1.0412, r_cost: 0.0351, train_time_taken: 11.7730
preparing data for epoch 19
number of batches 61
time taken to create batches 10.511152029037476
step: 1100, lr: 0.000989, cost: 1.0740, z_cost: 1.0423, r_cost: 0.0317, train_time_taken: 12.2867
step: 1120, lr: 0.000989, cost: 1.0811, z_cost: 1.0421, r_cost: 0.0390, train_time_taken: 11.9495
step: 1140, lr: 0.000989, cost: 1.0750, z_cost: 1.0460, r_cost: 0.0290, train_time_taken: 11.8344
preparing data for epoch 20
number of batches 61
time taken to create batches 11.274752378463745
step: 1160, lr: 0.000989, cost: 1.0715, z_cost: 1.0414, r_cost: 0.0301, train_time_taken: 12.4458
step: 1180, lr: 0.000988, cost: 1.0817, z_cost: 1.0437, r_cost: 0.0380, train_time_taken: 11.6312
step: 1200, lr: 0.000988, cost: 1.0719, z_cost: 1.0425, r_cost: 0.0294, train_time_taken: 11.6533
preparing data for epoch 21
number of batches 61
time taken to create batches 11.6293785572052
step: 1220, lr: 0.000988, cost: 1.0815, z_cost: 1.0450, r_cost: 0.0365, train_time_taken: 12.2174
step: 1240, lr: 0.000988, cost: 1.0772, z_cost: 1.0419, r_cost: 0.0353, train_time_taken: 11.8111
step: 1260, lr: 0.000988, cost: 1.0740, z_cost: 1.0409, r_cost: 0.0332, train_time_taken: 11.8156
step: 1280, lr: 0.000987, cost: 1.0731, z_cost: 1.0400, r_cost: 0.0331, train_time_taken: 11.8289
preparing data for epoch 22
number of batches 61
time taken to create batches 0.6067173480987549
step: 1300, lr: 0.000987, cost: 1.0693, z_cost: 1.0375, r_cost: 0.0319, train_time_taken: 12.2493
step: 1320, lr: 0.000987, cost: 1.0679, z_cost: 1.0393, r_cost: 0.0286, train_time_taken: 11.6602
step: 1340, lr: 0.000987, cost: 1.0724, z_cost: 1.0408, r_cost: 0.0315, train_time_taken: 11.6808
preparing data for epoch 23
number of batches 61
time taken to create batches 1.194284439086914
step: 1360, lr: 0.000987, cost: 1.0630, z_cost: 1.0392, r_cost: 0.0237, train_time_taken: 12.4200
step: 1380, lr: 0.000986, cost: 1.0657, z_cost: 1.0385, r_cost: 0.0272, train_time_taken: 11.8118
step: 1400, lr: 0.000986, cost: 1.0705, z_cost: 1.0365, r_cost: 0.0341, train_time_taken: 11.8499
preparing data for epoch 24
number of batches 61
time taken to create batches 1.808335781097412
step: 1420, lr: 0.000986, cost: 1.0639, z_cost: 1.0353, r_cost: 0.0286, train_time_taken: 12.2947
step: 1440, lr: 0.000986, cost: 1.0690, z_cost: 1.0364, r_cost: 0.0326, train_time_taken: 11.6344
step: 1460, lr: 0.000986, cost: 1.0701, z_cost: 1.0387, r_cost: 0.0314, train_time_taken: 11.6468
preparing data for epoch 25
number of batches 61
time taken to create batches 2.3598952293395996
step: 1480, lr: 0.000985, cost: 1.0658, z_cost: 1.0409, r_cost: 0.0249, train_time_taken: 12.4353
step: 1500, lr: 0.000985, cost: 1.0668, z_cost: 1.0380, r_cost: 0.0287, train_time_taken: 11.8605
step: 1520, lr: 0.000985, cost: 1.0662, z_cost: 1.0383, r_cost: 0.0279, train_time_taken: 11.8866
preparing data for epoch 26
number of batches 61
time taken to create batches 2.970200538635254
step: 1540, lr: 0.000985, cost: 1.0661, z_cost: 1.0341, r_cost: 0.0320, train_time_taken: 12.2839
step: 1560, lr: 0.000985, cost: 1.0617, z_cost: 1.0348, r_cost: 0.0269, train_time_taken: 11.6720
step: 1580, lr: 0.000984, cost: 1.0580, z_cost: 1.0346, r_cost: 0.0235, train_time_taken: 11.7603
preparing data for epoch 27
number of batches 61
time taken to create batches 3.502258539199829
step: 1600, lr: 0.000984, cost: 1.0654, z_cost: 1.0387, r_cost: 0.0267, train_time_taken: 12.4029
step: 1620, lr: 0.000984, cost: 1.0662, z_cost: 1.0363, r_cost: 0.0299, train_time_taken: 11.8486
step: 1640, lr: 0.000984, cost: 1.0594, z_cost: 1.0355, r_cost: 0.0240, train_time_taken: 11.9535
preparing data for epoch 28
number of batches 61
time taken to create batches 4.191471815109253
step: 1660, lr: 0.000984, cost: 1.0620, z_cost: 1.0382, r_cost: 0.0239, train_time_taken: 12.3518
step: 1680, lr: 0.000984, cost: 1.0709, z_cost: 1.0354, r_cost: 0.0355, train_time_taken: 11.6877
step: 1700, lr: 0.000983, cost: 1.0650, z_cost: 1.0378, r_cost: 0.0272, train_time_taken: 11.5986
preparing data for epoch 29
number of batches 61
time taken to create batches 4.768455505371094
step: 1720, lr: 0.000983, cost: 1.0562, z_cost: 1.0338, r_cost: 0.0224, train_time_taken: 12.4852
step: 1740, lr: 0.000983, cost: 1.0566, z_cost: 1.0361, r_cost: 0.0205, train_time_taken: 11.8208
step: 1760, lr: 0.000983, cost: 1.0578, z_cost: 1.0365, r_cost: 0.0213, train_time_taken: 11.9045
preparing data for epoch 30
number of batches 61
time taken to create batches 5.357701301574707
step: 1780, lr: 0.000983, cost: 1.0605, z_cost: 1.0337, r_cost: 0.0267, train_time_taken: 12.3765
step: 1800, lr: 0.000982, cost: 1.0585, z_cost: 1.0354, r_cost: 0.0230, train_time_taken: 11.6701
step: 1820, lr: 0.000982, cost: 1.0571, z_cost: 1.0325, r_cost: 0.0245, train_time_taken: 11.6432
preparing data for epoch 31
number of batches 61
time taken to create batches 5.862726211547852
step: 1840, lr: 0.000982, cost: 1.0527, z_cost: 1.0335, r_cost: 0.0192, train_time_taken: 12.4297
step: 1860, lr: 0.000982, cost: 1.0570, z_cost: 1.0335, r_cost: 0.0235, train_time_taken: 11.9211
step: 1880, lr: 0.000982, cost: 1.0615, z_cost: 1.0335, r_cost: 0.0280, train_time_taken: 11.8394
preparing data for epoch 32
number of batches 61
time taken to create batches 6.5857415199279785
step: 1900, lr: 0.000981, cost: 1.0515, z_cost: 1.0326, r_cost: 0.0189, train_time_taken: 12.3859
step: 1920, lr: 0.000981, cost: 1.0547, z_cost: 1.0332, r_cost: 0.0215, train_time_taken: 11.7106
step: 1940, lr: 0.000981, cost: 1.0533, z_cost: 1.0310, r_cost: 0.0223, train_time_taken: 11.7049
preparing data for epoch 33
number of batches 61
time taken to create batches 7.048130512237549
step: 1960, lr: 0.000981, cost: 1.0514, z_cost: 1.0335, r_cost: 0.0179, train_time_taken: 12.3507
step: 1980, lr: 0.000981, cost: 1.0577, z_cost: 1.0349, r_cost: 0.0229, train_time_taken: 11.8033
step: 2000, lr: 0.000980, cost: 1.0555, z_cost: 1.0336, r_cost: 0.0218, train_time_taken: 11.8281
preparing data for epoch 34
number of batches 61
time taken to create batches 7.741727590560913
step: 2020, lr: 0.000980, cost: 1.0493, z_cost: 1.0302, r_cost: 0.0191, train_time_taken: 12.4197
step: 2040, lr: 0.000980, cost: 1.0531, z_cost: 1.0329, r_cost: 0.0201, train_time_taken: 11.6537
step: 2060, lr: 0.000980, cost: 1.0517, z_cost: 1.0285, r_cost: 0.0232, train_time_taken: 11.6980
preparing data for epoch 35
number of batches 61
time taken to create batches 8.245218992233276
step: 2080, lr: 0.000980, cost: 1.0511, z_cost: 1.0351, r_cost: 0.0159, train_time_taken: 12.3964
step: 2100, lr: 0.000979, cost: 1.0430, z_cost: 1.0276, r_cost: 0.0154, train_time_taken: 11.8780
step: 2120, lr: 0.000979, cost: 1.0459, z_cost: 1.0284, r_cost: 0.0175, train_time_taken: 11.9032
preparing data for epoch 36
number of batches 61
time taken to create batches 8.999712944030762
step: 2140, lr: 0.000979, cost: 1.0481, z_cost: 1.0314, r_cost: 0.0167, train_time_taken: 12.5765
step: 2160, lr: 0.000979, cost: 1.0516, z_cost: 1.0326, r_cost: 0.0190, train_time_taken: 11.6960
step: 2180, lr: 0.000979, cost: 1.0507, z_cost: 1.0321, r_cost: 0.0185, train_time_taken: 11.6742
preparing data for epoch 37
number of batches 61
time taken to create batches 9.330268144607544
step: 2200, lr: 0.000978, cost: 1.0483, z_cost: 1.0305, r_cost: 0.0178, train_time_taken: 12.2870
step: 2220, lr: 0.000978, cost: 1.0531, z_cost: 1.0331, r_cost: 0.0200, train_time_taken: 11.8352
step: 2240, lr: 0.000978, cost: 1.0491, z_cost: 1.0325, r_cost: 0.0166, train_time_taken: 11.8913
preparing data for epoch 38
number of batches 61
time taken to create batches 10.044757843017578
step: 2260, lr: 0.000978, cost: 1.0491, z_cost: 1.0318, r_cost: 0.0173, train_time_taken: 12.3603
step: 2280, lr: 0.000978, cost: 1.0488, z_cost: 1.0325, r_cost: 0.0162, train_time_taken: 11.6817
step: 2300, lr: 0.000977, cost: 1.0472, z_cost: 1.0303, r_cost: 0.0170, train_time_taken: 11.7006
preparing data for epoch 39
number of batches 61
time taken to create batches 10.650620222091675
step: 2320, lr: 0.000977, cost: 1.0447, z_cost: 1.0284, r_cost: 0.0163, train_time_taken: 12.4211
step: 2340, lr: 0.000977, cost: 1.0458, z_cost: 1.0305, r_cost: 0.0152, train_time_taken: 11.7988
step: 2360, lr: 0.000977, cost: 1.0509, z_cost: 1.0301, r_cost: 0.0207, train_time_taken: 11.9113
preparing data for epoch 40
number of batches 61
time taken to create batches 11.287450551986694
step: 2380, lr: 0.000977, cost: 1.0484, z_cost: 1.0302, r_cost: 0.0182, train_time_taken: 12.4573
step: 2400, lr: 0.000977, cost: 1.0493, z_cost: 1.0323, r_cost: 0.0170, train_time_taken: 11.8113
step: 2420, lr: 0.000976, cost: 1.0473, z_cost: 1.0300, r_cost: 0.0173, train_time_taken: 11.6301
preparing data for epoch 41
number of batches 61
time taken to create batches 11.683674335479736
step: 2440, lr: 0.000976, cost: 1.0550, z_cost: 1.0357, r_cost: 0.0193, train_time_taken: 12.2854
step: 2460, lr: 0.000976, cost: 1.0445, z_cost: 1.0284, r_cost: 0.0161, train_time_taken: 11.9697
step: 2480, lr: 0.000976, cost: 1.0453, z_cost: 1.0298, r_cost: 0.0155, train_time_taken: 11.8521
step: 2500, lr: 0.000976, cost: 1.0468, z_cost: 1.0300, r_cost: 0.0168, train_time_taken: 11.8770
preparing data for epoch 42
number of batches 61
time taken to create batches 0.6108145713806152
step: 2520, lr: 0.000975, cost: 1.0398, z_cost: 1.0264, r_cost: 0.0134, train_time_taken: 12.2355
step: 2540, lr: 0.000975, cost: 1.0432, z_cost: 1.0272, r_cost: 0.0161, train_time_taken: 11.6610
step: 2560, lr: 0.000975, cost: 1.0411, z_cost: 1.0266, r_cost: 0.0144, train_time_taken: 11.6405
preparing data for epoch 43
number of batches 61
time taken to create batches 1.199455976486206
step: 2580, lr: 0.000975, cost: 1.0440, z_cost: 1.0277, r_cost: 0.0163, train_time_taken: 12.4611
step: 2600, lr: 0.000975, cost: 1.0452, z_cost: 1.0293, r_cost: 0.0159, train_time_taken: 11.8104
step: 2620, lr: 0.000974, cost: 1.0406, z_cost: 1.0275, r_cost: 0.0131, train_time_taken: 11.8767
preparing data for epoch 44
number of batches 61
time taken to create batches 1.7966322898864746
step: 2640, lr: 0.000974, cost: 1.0434, z_cost: 1.0291, r_cost: 0.0143, train_time_taken: 12.2459
step: 2660, lr: 0.000974, cost: 1.0391, z_cost: 1.0253, r_cost: 0.0138, train_time_taken: 11.6443
step: 2680, lr: 0.000974, cost: 1.0440, z_cost: 1.0311, r_cost: 0.0130, train_time_taken: 11.6280
preparing data for epoch 45
number of batches 61
time taken to create batches 2.360095739364624
step: 2700, lr: 0.000974, cost: 1.0403, z_cost: 1.0274, r_cost: 0.0129, train_time_taken: 12.3865
step: 2720, lr: 0.000973, cost: 1.0412, z_cost: 1.0282, r_cost: 0.0130, train_time_taken: 11.8368
step: 2740, lr: 0.000973, cost: 1.0414, z_cost: 1.0250, r_cost: 0.0164, train_time_taken: 11.8065
preparing data for epoch 46
number of batches 61
time taken to create batches 2.960254192352295
step: 2760, lr: 0.000973, cost: 1.0368, z_cost: 1.0262, r_cost: 0.0106, train_time_taken: 12.2710
step: 2780, lr: 0.000973, cost: 1.0376, z_cost: 1.0246, r_cost: 0.0130, train_time_taken: 11.6784
step: 2800, lr: 0.000973, cost: 1.0412, z_cost: 1.0275, r_cost: 0.0137, train_time_taken: 11.7093
preparing data for epoch 47
number of batches 61
time taken to create batches 3.541144609451294
step: 2820, lr: 0.000972, cost: 1.0369, z_cost: 1.0252, r_cost: 0.0117, train_time_taken: 12.4162
step: 2840, lr: 0.000972, cost: 1.0353, z_cost: 1.0246, r_cost: 0.0106, train_time_taken: 11.8098
step: 2860, lr: 0.000972, cost: 1.0376, z_cost: 1.0263, r_cost: 0.0112, train_time_taken: 11.8888
preparing data for epoch 48
number of batches 61
time taken to create batches 4.201434850692749
step: 2880, lr: 0.000972, cost: 1.0384, z_cost: 1.0276, r_cost: 0.0108, train_time_taken: 12.3366
step: 2900, lr: 0.000972, cost: 1.0404, z_cost: 1.0272, r_cost: 0.0132, train_time_taken: 11.6183
step: 2920, lr: 0.000972, cost: 1.0379, z_cost: 1.0258, r_cost: 0.0121, train_time_taken: 11.6424
preparing data for epoch 49
number of batches 61
time taken to create batches 4.730048179626465
step: 2940, lr: 0.000971, cost: 1.0368, z_cost: 1.0245, r_cost: 0.0123, train_time_taken: 12.5658
step: 2960, lr: 0.000971, cost: 1.0386, z_cost: 1.0259, r_cost: 0.0127, train_time_taken: 11.8487
step: 2980, lr: 0.000971, cost: 1.0415, z_cost: 1.0292, r_cost: 0.0123, train_time_taken: 11.8625
preparing data for epoch 50
number of batches 61
time taken to create batches 5.3816399574279785
step: 3000, lr: 0.000971, cost: 1.0363, z_cost: 1.0244, r_cost: 0.0119, train_time_taken: 12.4023
step: 3020, lr: 0.000971, cost: 1.0381, z_cost: 1.0257, r_cost: 0.0124, train_time_taken: 11.6173
step: 3040, lr: 0.000970, cost: 1.0370, z_cost: 1.0260, r_cost: 0.0110, train_time_taken: 11.6478
preparing data for epoch 51
number of batches 61
time taken to create batches 5.869588136672974
step: 3060, lr: 0.000970, cost: 1.0352, z_cost: 1.0248, r_cost: 0.0104, train_time_taken: 12.3541
step: 3080, lr: 0.000970, cost: 1.0382, z_cost: 1.0263, r_cost: 0.0119, train_time_taken: 11.9103
step: 3100, lr: 0.000970, cost: 1.0412, z_cost: 1.0270, r_cost: 0.0142, train_time_taken: 11.8146
preparing data for epoch 52
number of batches 61
time taken to create batches 6.503089666366577
step: 3120, lr: 0.000970, cost: 1.0374, z_cost: 1.0277, r_cost: 0.0098, train_time_taken: 12.2960
step: 3140, lr: 0.000969, cost: 1.0397, z_cost: 1.0261, r_cost: 0.0136, train_time_taken: 11.6613
step: 3160, lr: 0.000969, cost: 1.0383, z_cost: 1.0254, r_cost: 0.0130, train_time_taken: 11.6811
preparing data for epoch 53
number of batches 61
time taken to create batches 6.988792419433594
step: 3180, lr: 0.000969, cost: 1.0338, z_cost: 1.0228, r_cost: 0.0110, train_time_taken: 12.3264
step: 3200, lr: 0.000969, cost: 1.0354, z_cost: 1.0259, r_cost: 0.0096, train_time_taken: 11.8688
step: 3220, lr: 0.000969, cost: 1.0368, z_cost: 1.0245, r_cost: 0.0123, train_time_taken: 11.8732
preparing data for epoch 54
number of batches 61
time taken to create batches 7.711009502410889
step: 3240, lr: 0.000968, cost: 1.0340, z_cost: 1.0241, r_cost: 0.0099, train_time_taken: 12.3614
step: 3260, lr: 0.000968, cost: 1.0363, z_cost: 1.0237, r_cost: 0.0126, train_time_taken: 11.6223
step: 3280, lr: 0.000968, cost: 1.0347, z_cost: 1.0226, r_cost: 0.0120, train_time_taken: 11.5645
preparing data for epoch 55
number of batches 61
time taken to create batches 8.13210940361023
step: 3300, lr: 0.000968, cost: 1.0362, z_cost: 1.0250, r_cost: 0.0112, train_time_taken: 12.2611
step: 3320, lr: 0.000968, cost: 1.0300, z_cost: 1.0206, r_cost: 0.0093, train_time_taken: 11.8029
step: 3340, lr: 0.000967, cost: 1.0365, z_cost: 1.0268, r_cost: 0.0097, train_time_taken: 11.8267
preparing data for epoch 56
number of batches 61
time taken to create batches 8.926363945007324
step: 3360, lr: 0.000967, cost: 1.0330, z_cost: 1.0238, r_cost: 0.0092, train_time_taken: 12.4239
step: 3380, lr: 0.000967, cost: 1.0327, z_cost: 1.0201, r_cost: 0.0125, train_time_taken: 11.7405
step: 3400, lr: 0.000967, cost: 1.0320, z_cost: 1.0208, r_cost: 0.0112, train_time_taken: 11.7137
preparing data for epoch 57
number of batches 61
time taken to create batches 9.332966089248657
step: 3420, lr: 0.000967, cost: 1.0293, z_cost: 1.0205, r_cost: 0.0088, train_time_taken: 12.2734
step: 3440, lr: 0.000967, cost: 1.0279, z_cost: 1.0190, r_cost: 0.0089, train_time_taken: 11.9587
step: 3460, lr: 0.000966, cost: 1.0298, z_cost: 1.0215, r_cost: 0.0083, train_time_taken: 11.8949
preparing data for epoch 58
number of batches 61
time taken to create batches 10.086072444915771
step: 3480, lr: 0.000966, cost: 1.0339, z_cost: 1.0243, r_cost: 0.0096, train_time_taken: 12.4021
step: 3500, lr: 0.000966, cost: 1.0309, z_cost: 1.0219, r_cost: 0.0089, train_time_taken: 11.7173
step: 3520, lr: 0.000966, cost: 1.0350, z_cost: 1.0222, r_cost: 0.0129, train_time_taken: 11.6498
preparing data for epoch 59
number of batches 61
time taken to create batches 10.540801048278809
step: 3540, lr: 0.000966, cost: 1.0315, z_cost: 1.0220, r_cost: 0.0095, train_time_taken: 12.3141
step: 3560, lr: 0.000965, cost: 1.0346, z_cost: 1.0260, r_cost: 0.0087, train_time_taken: 11.8573
step: 3580, lr: 0.000965, cost: 1.0273, z_cost: 1.0184, r_cost: 0.0090, train_time_taken: 11.9466
preparing data for epoch 60
number of batches 61
time taken to create batches 11.303971767425537
step: 3600, lr: 0.000965, cost: 1.0285, z_cost: 1.0205, r_cost: 0.0080, train_time_taken: 12.4764
step: 3620, lr: 0.000965, cost: 1.0321, z_cost: 1.0235, r_cost: 0.0086, train_time_taken: 11.6468
step: 3640, lr: 0.000965, cost: 1.0316, z_cost: 1.0212, r_cost: 0.0105, train_time_taken: 11.6666
preparing data for epoch 61
number of batches 61
time taken to create batches 11.658757448196411
step: 3660, lr: 0.000964, cost: 1.0364, z_cost: 1.0239, r_cost: 0.0125, train_time_taken: 12.2512
step: 3680, lr: 0.000964, cost: 1.0322, z_cost: 1.0251, r_cost: 0.0071, train_time_taken: 11.8361
step: 3700, lr: 0.000964, cost: 1.0299, z_cost: 1.0214, r_cost: 0.0085, train_time_taken: 11.8506
step: 3720, lr: 0.000964, cost: 1.0329, z_cost: 1.0247, r_cost: 0.0081, train_time_taken: 11.8483
preparing data for epoch 62
number of batches 61
time taken to create batches 0.6077618598937988
step: 3740, lr: 0.000964, cost: 1.0323, z_cost: 1.0217, r_cost: 0.0106, train_time_taken: 12.2798
step: 3760, lr: 0.000963, cost: 1.0277, z_cost: 1.0201, r_cost: 0.0076, train_time_taken: 11.7254
step: 3780, lr: 0.000963, cost: 1.0334, z_cost: 1.0242, r_cost: 0.0092, train_time_taken: 11.6573
preparing data for epoch 63
number of batches 61
time taken to create batches 1.1848163604736328
step: 3800, lr: 0.000963, cost: 1.0288, z_cost: 1.0208, r_cost: 0.0080, train_time_taken: 12.5275
step: 3820, lr: 0.000963, cost: 1.0303, z_cost: 1.0216, r_cost: 0.0088, train_time_taken: 11.8702
step: 3840, lr: 0.000963, cost: 1.0309, z_cost: 1.0214, r_cost: 0.0095, train_time_taken: 11.8562
preparing data for epoch 64
number of batches 61
time taken to create batches 1.787219762802124
step: 3860, lr: 0.000963, cost: 1.0268, z_cost: 1.0200, r_cost: 0.0068, train_time_taken: 12.3107
step: 3880, lr: 0.000962, cost: 1.0278, z_cost: 1.0184, r_cost: 0.0094, train_time_taken: 11.6891
step: 3900, lr: 0.000962, cost: 1.0295, z_cost: 1.0197, r_cost: 0.0098, train_time_taken: 11.7056
preparing data for epoch 65
number of batches 61
time taken to create batches 2.3496861457824707
step: 3920, lr: 0.000962, cost: 1.0298, z_cost: 1.0199, r_cost: 0.0099, train_time_taken: 12.4414
step: 3940, lr: 0.000962, cost: 1.0297, z_cost: 1.0186, r_cost: 0.0111, train_time_taken: 11.9546
step: 3960, lr: 0.000962, cost: 1.0311, z_cost: 1.0220, r_cost: 0.0091, train_time_taken: 11.8241
preparing data for epoch 66
number of batches 61
time taken to create batches 2.974731683731079
step: 3980, lr: 0.000961, cost: 1.0262, z_cost: 1.0192, r_cost: 0.0070, train_time_taken: 12.3394
step: 4000, lr: 0.000961, cost: 1.0306, z_cost: 1.0232, r_cost: 0.0074, train_time_taken: 11.7941
step: 4020, lr: 0.000961, cost: 1.0243, z_cost: 1.0144, r_cost: 0.0100, train_time_taken: 11.7229
preparing data for epoch 67
number of batches 61
time taken to create batches 3.519029140472412
step: 4040, lr: 0.000961, cost: 1.0275, z_cost: 1.0200, r_cost: 0.0076, train_time_taken: 12.4047
step: 4060, lr: 0.000961, cost: 1.0295, z_cost: 1.0212, r_cost: 0.0083, train_time_taken: 11.8673
step: 4080, lr: 0.000960, cost: 1.0286, z_cost: 1.0202, r_cost: 0.0084, train_time_taken: 11.9862
preparing data for epoch 68
number of batches 61
time taken to create batches 4.162505626678467
step: 4100, lr: 0.000960, cost: 1.0255, z_cost: 1.0179, r_cost: 0.0076, train_time_taken: 12.3541
step: 4120, lr: 0.000960, cost: 1.0274, z_cost: 1.0194, r_cost: 0.0079, train_time_taken: 11.7207
step: 4140, lr: 0.000960, cost: 1.0285, z_cost: 1.0195, r_cost: 0.0091, train_time_taken: 11.6663
preparing data for epoch 69
number of batches 61
time taken to create batches 4.690137147903442
step: 4160, lr: 0.000960, cost: 1.0283, z_cost: 1.0203, r_cost: 0.0080, train_time_taken: 12.3880
step: 4180, lr: 0.000959, cost: 1.0258, z_cost: 1.0181, r_cost: 0.0077, train_time_taken: 11.8729
step: 4200, lr: 0.000959, cost: 1.0272, z_cost: 1.0195, r_cost: 0.0076, train_time_taken: 11.8141
preparing data for epoch 70
number of batches 61
time taken to create batches 5.341128349304199
step: 4220, lr: 0.000959, cost: 1.0277, z_cost: 1.0204, r_cost: 0.0073, train_time_taken: 12.3387
step: 4240, lr: 0.000959, cost: 1.0294, z_cost: 1.0216, r_cost: 0.0078, train_time_taken: 11.6851
step: 4260, lr: 0.000959, cost: 1.0255, z_cost: 1.0174, r_cost: 0.0081, train_time_taken: 11.6290
preparing data for epoch 71
number of batches 61
time taken to create batches 5.867477655410767
step: 4280, lr: 0.000959, cost: 1.0255, z_cost: 1.0174, r_cost: 0.0081, train_time_taken: 12.4214
step: 4300, lr: 0.000958, cost: 1.0276, z_cost: 1.0188, r_cost: 0.0089, train_time_taken: 11.8417
step: 4320, lr: 0.000958, cost: 1.0255, z_cost: 1.0193, r_cost: 0.0062, train_time_taken: 11.8339
preparing data for epoch 72
number of batches 61
time taken to create batches 6.5518012046813965
step: 4340, lr: 0.000958, cost: 1.0270, z_cost: 1.0192, r_cost: 0.0078, train_time_taken: 12.3838
step: 4360, lr: 0.000958, cost: 1.0288, z_cost: 1.0204, r_cost: 0.0084, train_time_taken: 11.6846
step: 4380, lr: 0.000958, cost: 1.0267, z_cost: 1.0191, r_cost: 0.0075, train_time_taken: 11.6468
preparing data for epoch 73
number of batches 61
time taken to create batches 7.0285255908966064
step: 4400, lr: 0.000957, cost: 1.0234, z_cost: 1.0172, r_cost: 0.0062, train_time_taken: 12.3747
step: 4420, lr: 0.000957, cost: 1.0246, z_cost: 1.0182, r_cost: 0.0064, train_time_taken: 11.8250
step: 4440, lr: 0.000957, cost: 1.0234, z_cost: 1.0171, r_cost: 0.0063, train_time_taken: 11.7948
preparing data for epoch 74
number of batches 61
time taken to create batches 7.6890716552734375
step: 4460, lr: 0.000957, cost: 1.0258, z_cost: 1.0186, r_cost: 0.0072, train_time_taken: 12.3435
step: 4480, lr: 0.000957, cost: 1.0239, z_cost: 1.0158, r_cost: 0.0081, train_time_taken: 11.6235
step: 4500, lr: 0.000956, cost: 1.0254, z_cost: 1.0167, r_cost: 0.0087, train_time_taken: 11.6551
preparing data for epoch 75
number of batches 61
time taken to create batches 8.169343948364258
step: 4520, lr: 0.000956, cost: 1.0247, z_cost: 1.0173, r_cost: 0.0074, train_time_taken: 12.2926
step: 4540, lr: 0.000956, cost: 1.0223, z_cost: 1.0149, r_cost: 0.0073, train_time_taken: 11.8346
step: 4560, lr: 0.000956, cost: 1.0245, z_cost: 1.0189, r_cost: 0.0056, train_time_taken: 11.7888
preparing data for epoch 76
number of batches 61
time taken to create batches 8.938186407089233
step: 4580, lr: 0.000956, cost: 1.0234, z_cost: 1.0170, r_cost: 0.0063, train_time_taken: 12.4550
step: 4600, lr: 0.000955, cost: 1.0210, z_cost: 1.0143, r_cost: 0.0067, train_time_taken: 11.6560
step: 4620, lr: 0.000955, cost: 1.0264, z_cost: 1.0190, r_cost: 0.0075, train_time_taken: 11.6543
preparing data for epoch 77
number of batches 61
time taken to create batches 9.351977586746216
step: 4640, lr: 0.000955, cost: 1.0237, z_cost: 1.0171, r_cost: 0.0066, train_time_taken: 12.3240
step: 4660, lr: 0.000955, cost: 1.0268, z_cost: 1.0182, r_cost: 0.0086, train_time_taken: 11.8211
step: 4680, lr: 0.000955, cost: 1.0225, z_cost: 1.0170, r_cost: 0.0055, train_time_taken: 11.8065
preparing data for epoch 78
number of batches 61
time taken to create batches 10.070953130722046
step: 4700, lr: 0.000955, cost: 1.0214, z_cost: 1.0155, r_cost: 0.0059, train_time_taken: 12.3744
step: 4720, lr: 0.000954, cost: 1.0202, z_cost: 1.0140, r_cost: 0.0062, train_time_taken: 11.6784
step: 4740, lr: 0.000954, cost: 1.0234, z_cost: 1.0159, r_cost: 0.0075, train_time_taken: 11.6293
preparing data for epoch 79
number of batches 61
time taken to create batches 10.49364686012268
step: 4760, lr: 0.000954, cost: 1.0243, z_cost: 1.0181, r_cost: 0.0063, train_time_taken: 12.2999
step: 4780, lr: 0.000954, cost: 1.0228, z_cost: 1.0149, r_cost: 0.0079, train_time_taken: 11.8636
step: 4800, lr: 0.000954, cost: 1.0277, z_cost: 1.0189, r_cost: 0.0088, train_time_taken: 11.8390
preparing data for epoch 80
number of batches 61
time taken to create batches 11.238297462463379
step: 4820, lr: 0.000953, cost: 1.0218, z_cost: 1.0168, r_cost: 0.0050, train_time_taken: 12.4061
step: 4840, lr: 0.000953, cost: 1.0221, z_cost: 1.0155, r_cost: 0.0066, train_time_taken: 11.6588
step: 4860, lr: 0.000953, cost: 1.0194, z_cost: 1.0137, r_cost: 0.0057, train_time_taken: 11.6809
preparing data for epoch 81
number of batches 61
time taken to create batches 11.829681873321533
step: 4880, lr: 0.000953, cost: 1.0301, z_cost: 1.0196, r_cost: 0.0105, train_time_taken: 12.4160
step: 4900, lr: 0.000953, cost: 1.0211, z_cost: 1.0155, r_cost: 0.0055, train_time_taken: 11.8311
step: 4920, lr: 0.000952, cost: 1.0222, z_cost: 1.0157, r_cost: 0.0065, train_time_taken: 11.8923
step: 4940, lr: 0.000952, cost: 1.0223, z_cost: 1.0150, r_cost: 0.0073, train_time_taken: 11.8920
preparing data for epoch 82
number of batches 61
time taken to create batches 0.6642501354217529
step: 4960, lr: 0.000952, cost: 1.0189, z_cost: 1.0145, r_cost: 0.0044, train_time_taken: 12.3272
step: 4980, lr: 0.000952, cost: 1.0212, z_cost: 1.0160, r_cost: 0.0052, train_time_taken: 11.6733
step: 5000, lr: 0.000952, cost: 1.0228, z_cost: 1.0161, r_cost: 0.0067, train_time_taken: 11.6524
preparing data for epoch 83
number of batches 61
time taken to create batches 1.183410882949829
step: 5020, lr: 0.000952, cost: 1.0208, z_cost: 1.0156, r_cost: 0.0052, train_time_taken: 12.4033
step: 5040, lr: 0.000951, cost: 1.0195, z_cost: 1.0126, r_cost: 0.0068, train_time_taken: 11.8630
step: 5060, lr: 0.000951, cost: 1.0220, z_cost: 1.0162, r_cost: 0.0059, train_time_taken: 11.9154
preparing data for epoch 84
number of batches 61
time taken to create batches 1.790602207183838
step: 5080, lr: 0.000951, cost: 1.0233, z_cost: 1.0179, r_cost: 0.0054, train_time_taken: 12.2881
step: 5100, lr: 0.000951, cost: 1.0229, z_cost: 1.0164, r_cost: 0.0065, train_time_taken: 11.6447
step: 5120, lr: 0.000951, cost: 1.0246, z_cost: 1.0187, r_cost: 0.0060, train_time_taken: 11.6347
preparing data for epoch 85
number of batches 61
time taken to create batches 2.353635549545288
step: 5140, lr: 0.000950, cost: 1.0252, z_cost: 1.0205, r_cost: 0.0047, train_time_taken: 12.4322
step: 5160, lr: 0.000950, cost: 1.0211, z_cost: 1.0152, r_cost: 0.0059, train_time_taken: 11.8484
step: 5180, lr: 0.000950, cost: 1.0202, z_cost: 1.0148, r_cost: 0.0054, train_time_taken: 11.8161
preparing data for epoch 86
number of batches 61
time taken to create batches 2.9984922409057617
step: 5200, lr: 0.000950, cost: 1.0199, z_cost: 1.0120, r_cost: 0.0079, train_time_taken: 12.3167
step: 5220, lr: 0.000950, cost: 1.0188, z_cost: 1.0132, r_cost: 0.0056, train_time_taken: 11.5767
step: 5240, lr: 0.000949, cost: 1.0211, z_cost: 1.0152, r_cost: 0.0060, train_time_taken: 11.6335
preparing data for epoch 87
number of batches 61
time taken to create batches 3.562281608581543
step: 5260, lr: 0.000949, cost: 1.0229, z_cost: 1.0162, r_cost: 0.0066, train_time_taken: 12.5126
step: 5280, lr: 0.000949, cost: 1.0192, z_cost: 1.0145, r_cost: 0.0047, train_time_taken: 11.8449
step: 5300, lr: 0.000949, cost: 1.0190, z_cost: 1.0112, r_cost: 0.0078, train_time_taken: 11.9135
preparing data for epoch 88
number of batches 61
time taken to create batches 4.15708065032959
step: 5320, lr: 0.000949, cost: 1.0177, z_cost: 1.0120, r_cost: 0.0057, train_time_taken: 12.2866
step: 5340, lr: 0.000949, cost: 1.0237, z_cost: 1.0167, r_cost: 0.0070, train_time_taken: 11.7019
step: 5360, lr: 0.000948, cost: 1.0188, z_cost: 1.0124, r_cost: 0.0064, train_time_taken: 11.6351
preparing data for epoch 89
number of batches 61
time taken to create batches 4.675752401351929
step: 5380, lr: 0.000948, cost: 1.0178, z_cost: 1.0129, r_cost: 0.0049, train_time_taken: 12.4348
step: 5400, lr: 0.000948, cost: 1.0178, z_cost: 1.0120, r_cost: 0.0058, train_time_taken: 11.8491
step: 5420, lr: 0.000948, cost: 1.0211, z_cost: 1.0151, r_cost: 0.0061, train_time_taken: 11.8361
preparing data for epoch 90
number of batches 61
time taken to create batches 5.360905647277832
step: 5440, lr: 0.000948, cost: 1.0187, z_cost: 1.0147, r_cost: 0.0040, train_time_taken: 12.3558
step: 5460, lr: 0.000947, cost: 1.0206, z_cost: 1.0143, r_cost: 0.0064, train_time_taken: 11.6565
step: 5480, lr: 0.000947, cost: 1.0199, z_cost: 1.0142, r_cost: 0.0057, train_time_taken: 11.6291
preparing data for epoch 91
number of batches 61
time taken to create batches 5.8342249393463135
step: 5500, lr: 0.000947, cost: 1.0228, z_cost: 1.0144, r_cost: 0.0084, train_time_taken: 12.3692
step: 5520, lr: 0.000947, cost: 1.0182, z_cost: 1.0136, r_cost: 0.0046, train_time_taken: 11.8832
step: 5540, lr: 0.000947, cost: 1.0197, z_cost: 1.0137, r_cost: 0.0060, train_time_taken: 11.8619
preparing data for epoch 92
number of batches 61
time taken to create batches 6.574188947677612
step: 5560, lr: 0.000946, cost: 1.0187, z_cost: 1.0126, r_cost: 0.0061, train_time_taken: 12.4227
step: 5580, lr: 0.000946, cost: 1.0193, z_cost: 1.0138, r_cost: 0.0055, train_time_taken: 11.6891
step: 5600, lr: 0.000946, cost: 1.0215, z_cost: 1.0146, r_cost: 0.0068, train_time_taken: 11.6827
preparing data for epoch 93
number of batches 61
time taken to create batches 7.0465898513793945
step: 5620, lr: 0.000946, cost: 1.0160, z_cost: 1.0113, r_cost: 0.0047, train_time_taken: 12.3785
step: 5640, lr: 0.000946, cost: 1.0183, z_cost: 1.0125, r_cost: 0.0057, train_time_taken: 11.9615
step: 5660, lr: 0.000946, cost: 1.0171, z_cost: 1.0129, r_cost: 0.0041, train_time_taken: 11.9295
preparing data for epoch 94
number of batches 61
time taken to create batches 7.76680326461792
step: 5680, lr: 0.000945, cost: 1.0179, z_cost: 1.0115, r_cost: 0.0064, train_time_taken: 12.4515
step: 5700, lr: 0.000945, cost: 1.0154, z_cost: 1.0100, r_cost: 0.0054, train_time_taken: 11.6417
step: 5720, lr: 0.000945, cost: 1.0158, z_cost: 1.0114, r_cost: 0.0044, train_time_taken: 11.6918
preparing data for epoch 95
number of batches 61
time taken to create batches 8.187846660614014
step: 5740, lr: 0.000945, cost: 1.0194, z_cost: 1.0147, r_cost: 0.0046, train_time_taken: 12.3408
step: 5760, lr: 0.000945, cost: 1.0212, z_cost: 1.0150, r_cost: 0.0062, train_time_taken: 11.9016
step: 5780, lr: 0.000944, cost: 1.0152, z_cost: 1.0102, r_cost: 0.0050, train_time_taken: 11.8412
preparing data for epoch 96
number of batches 61
time taken to create batches 8.927306175231934
step: 5800, lr: 0.000944, cost: 1.0196, z_cost: 1.0137, r_cost: 0.0059, train_time_taken: 12.4470
step: 5820, lr: 0.000944, cost: 1.0191, z_cost: 1.0139, r_cost: 0.0052, train_time_taken: 11.7242
step: 5840, lr: 0.000944, cost: 1.0164, z_cost: 1.0116, r_cost: 0.0048, train_time_taken: 11.6860
preparing data for epoch 97
number of batches 61
time taken to create batches 9.394816398620605
step: 5860, lr: 0.000944, cost: 1.0156, z_cost: 1.0117, r_cost: 0.0039, train_time_taken: 12.3661
step: 5880, lr: 0.000943, cost: 1.0172, z_cost: 1.0127, r_cost: 0.0045, train_time_taken: 11.8640
step: 5900, lr: 0.000943, cost: 1.0176, z_cost: 1.0128, r_cost: 0.0049, train_time_taken: 11.8791
preparing data for epoch 98
number of batches 61
time taken to create batches 10.167203426361084
step: 5920, lr: 0.000943, cost: 1.0164, z_cost: 1.0118, r_cost: 0.0047, train_time_taken: 12.5388
step: 5940, lr: 0.000943, cost: 1.0170, z_cost: 1.0113, r_cost: 0.0057, train_time_taken: 11.6922
step: 5960, lr: 0.000943, cost: 1.0175, z_cost: 1.0119, r_cost: 0.0056, train_time_taken: 11.6810
preparing data for epoch 99
number of batches 61
time taken to create batches 10.519267797470093
step: 5980, lr: 0.000943, cost: 1.0161, z_cost: 1.0113, r_cost: 0.0049, train_time_taken: 12.2624
step: 6000, lr: 0.000942, cost: 1.0166, z_cost: 1.0116, r_cost: 0.0050, train_time_taken: 11.8099
step: 6020, lr: 0.000942, cost: 1.0170, z_cost: 1.0134, r_cost: 0.0036, train_time_taken: 11.8855
preparing data for epoch 100
number of batches 61
time taken to create batches 11.306283950805664
step: 6040, lr: 0.000942, cost: 1.0152, z_cost: 1.0111, r_cost: 0.0040, train_time_taken: 12.4719
step: 6060, lr: 0.000942, cost: 1.0185, z_cost: 1.0122, r_cost: 0.0063, train_time_taken: 11.6678
step: 6080, lr: 0.000942, cost: 1.0195, z_cost: 1.0140, r_cost: 0.0055, train_time_taken: 11.7830
preparing data for epoch 101
number of batches 61
time taken to create batches 11.738228797912598
step: 6100, lr: 0.000941, cost: 1.0263, z_cost: 1.0129, r_cost: 0.0134, train_time_taken: 12.3262
step: 6120, lr: 0.000941, cost: 1.0168, z_cost: 1.0118, r_cost: 0.0050, train_time_taken: 11.8710
step: 6140, lr: 0.000941, cost: 1.0164, z_cost: 1.0112, r_cost: 0.0052, train_time_taken: 11.8739
step: 6160, lr: 0.000941, cost: 1.0157, z_cost: 1.0101, r_cost: 0.0056, train_time_taken: 11.8292
preparing data for epoch 102
number of batches 61
time taken to create batches 0.6113393306732178
step: 6180, lr: 0.000941, cost: 1.0154, z_cost: 1.0118, r_cost: 0.0036, train_time_taken: 12.2623
step: 6200, lr: 0.000940, cost: 1.0163, z_cost: 1.0117, r_cost: 0.0047, train_time_taken: 11.6993
step: 6220, lr: 0.000940, cost: 1.0160, z_cost: 1.0111, r_cost: 0.0049, train_time_taken: 11.7022
preparing data for epoch 103
number of batches 61
time taken to create batches 1.182699203491211
step: 6240, lr: 0.000940, cost: 1.0128, z_cost: 1.0086, r_cost: 0.0042, train_time_taken: 12.4183
step: 6260, lr: 0.000940, cost: 1.0160, z_cost: 1.0117, r_cost: 0.0043, train_time_taken: 11.9297
step: 6280, lr: 0.000940, cost: 1.0148, z_cost: 1.0107, r_cost: 0.0041, train_time_taken: 11.8959
preparing data for epoch 104
number of batches 61
time taken to create batches 1.807776689529419
step: 6300, lr: 0.000940, cost: 1.0141, z_cost: 1.0105, r_cost: 0.0036, train_time_taken: 12.4028
step: 6320, lr: 0.000939, cost: 1.0168, z_cost: 1.0109, r_cost: 0.0059, train_time_taken: 11.7907
step: 6340, lr: 0.000939, cost: 1.0161, z_cost: 1.0106, r_cost: 0.0056, train_time_taken: 11.6645
preparing data for epoch 105
number of batches 61
time taken to create batches 2.3468120098114014
step: 6360, lr: 0.000939, cost: 1.0146, z_cost: 1.0099, r_cost: 0.0047, train_time_taken: 12.3734
step: 6380, lr: 0.000939, cost: 1.0153, z_cost: 1.0116, r_cost: 0.0037, train_time_taken: 11.8063
step: 6400, lr: 0.000939, cost: 1.0154, z_cost: 1.0101, r_cost: 0.0053, train_time_taken: 11.7826
preparing data for epoch 106
number of batches 61
time taken to create batches 2.985290050506592
step: 6420, lr: 0.000938, cost: 1.0153, z_cost: 1.0115, r_cost: 0.0039, train_time_taken: 12.2935
step: 6440, lr: 0.000938, cost: 1.0110, z_cost: 1.0064, r_cost: 0.0046, train_time_taken: 11.6870
step: 6460, lr: 0.000938, cost: 1.0183, z_cost: 1.0130, r_cost: 0.0053, train_time_taken: 11.6187
preparing data for epoch 107
number of batches 61
time taken to create batches 3.722876787185669
step: 6480, lr: 0.000938, cost: 1.0139, z_cost: 1.0102, r_cost: 0.0037, train_time_taken: 12.6032
step: 6500, lr: 0.000938, cost: 1.0132, z_cost: 1.0094, r_cost: 0.0038, train_time_taken: 11.8423
step: 6520, lr: 0.000938, cost: 1.0156, z_cost: 1.0107, r_cost: 0.0050, train_time_taken: 11.8962
preparing data for epoch 108
number of batches 61
time taken to create batches 4.2078821659088135
step: 6540, lr: 0.000937, cost: 1.0161, z_cost: 1.0104, r_cost: 0.0057, train_time_taken: 12.3358
step: 6560, lr: 0.000937, cost: 1.0167, z_cost: 1.0131, r_cost: 0.0036, train_time_taken: 11.6006
step: 6580, lr: 0.000937, cost: 1.0203, z_cost: 1.0151, r_cost: 0.0052, train_time_taken: 11.6543
preparing data for epoch 109
number of batches 61
time taken to create batches 4.7032153606414795
step: 6600, lr: 0.000937, cost: 1.0175, z_cost: 1.0122, r_cost: 0.0053, train_time_taken: 12.3718
step: 6620, lr: 0.000937, cost: 1.0129, z_cost: 1.0091, r_cost: 0.0038, train_time_taken: 11.8147
step: 6640, lr: 0.000936, cost: 1.0117, z_cost: 1.0079, r_cost: 0.0037, train_time_taken: 11.7348
preparing data for epoch 110
number of batches 61
time taken to create batches 5.3309166431427
step: 6660, lr: 0.000936, cost: 1.0172, z_cost: 1.0121, r_cost: 0.0051, train_time_taken: 12.3241
step: 6680, lr: 0.000936, cost: 1.0151, z_cost: 1.0113, r_cost: 0.0038, train_time_taken: 11.6151
step: 6700, lr: 0.000936, cost: 1.0118, z_cost: 1.0065, r_cost: 0.0053, train_time_taken: 11.5926
preparing data for epoch 111
number of batches 61
time taken to create batches 5.830847501754761
step: 6720, lr: 0.000936, cost: 1.0117, z_cost: 1.0077, r_cost: 0.0040, train_time_taken: 12.3168
step: 6740, lr: 0.000935, cost: 1.0133, z_cost: 1.0088, r_cost: 0.0045, train_time_taken: 11.8055
step: 6760, lr: 0.000935, cost: 1.0136, z_cost: 1.0107, r_cost: 0.0029, train_time_taken: 11.8073
preparing data for epoch 112
number of batches 61
time taken to create batches 6.571560382843018
step: 6780, lr: 0.000935, cost: 1.0118, z_cost: 1.0074, r_cost: 0.0044, train_time_taken: 12.3984
step: 6800, lr: 0.000935, cost: 1.0121, z_cost: 1.0077, r_cost: 0.0043, train_time_taken: 11.6330
step: 6820, lr: 0.000935, cost: 1.0148, z_cost: 1.0097, r_cost: 0.0051, train_time_taken: 11.6210
preparing data for epoch 113
number of batches 61
time taken to create batches 7.0279858112335205
step: 6840, lr: 0.000935, cost: 1.0126, z_cost: 1.0088, r_cost: 0.0038, train_time_taken: 12.3835
step: 6860, lr: 0.000934, cost: 1.0156, z_cost: 1.0101, r_cost: 0.0056, train_time_taken: 11.7862
step: 6880, lr: 0.000934, cost: 1.0126, z_cost: 1.0075, r_cost: 0.0050, train_time_taken: 11.8005
preparing data for epoch 114
number of batches 61
time taken to create batches 7.692800283432007
step: 6900, lr: 0.000934, cost: 1.0132, z_cost: 1.0095, r_cost: 0.0037, train_time_taken: 12.3439
step: 6920, lr: 0.000934, cost: 1.0164, z_cost: 1.0111, r_cost: 0.0053, train_time_taken: 11.6052
step: 6940, lr: 0.000934, cost: 1.0150, z_cost: 1.0095, r_cost: 0.0055, train_time_taken: 11.6624
preparing data for epoch 115
number of batches 61
time taken to create batches 8.151145458221436
step: 6960, lr: 0.000933, cost: 1.0126, z_cost: 1.0084, r_cost: 0.0042, train_time_taken: 12.2692
step: 6980, lr: 0.000933, cost: 1.0157, z_cost: 1.0119, r_cost: 0.0038, train_time_taken: 11.8203
step: 7000, lr: 0.000933, cost: 1.0182, z_cost: 1.0140, r_cost: 0.0042, train_time_taken: 11.8091
preparing data for epoch 116
number of batches 61
time taken to create batches 8.843949317932129
step: 7020, lr: 0.000933, cost: 1.0097, z_cost: 1.0071, r_cost: 0.0026, train_time_taken: 12.3598
step: 7040, lr: 0.000933, cost: 1.0123, z_cost: 1.0082, r_cost: 0.0041, train_time_taken: 11.6735
step: 7060, lr: 0.000933, cost: 1.0099, z_cost: 1.0065, r_cost: 0.0035, train_time_taken: 11.6126
preparing data for epoch 117
number of batches 61
time taken to create batches 9.334757089614868
step: 7080, lr: 0.000932, cost: 1.0135, z_cost: 1.0096, r_cost: 0.0038, train_time_taken: 12.2952
step: 7100, lr: 0.000932, cost: 1.0129, z_cost: 1.0079, r_cost: 0.0050, train_time_taken: 11.7590
step: 7120, lr: 0.000932, cost: 1.0116, z_cost: 1.0080, r_cost: 0.0036, train_time_taken: 11.8212
preparing data for epoch 118
number of batches 61
time taken to create batches 10.014579057693481
step: 7140, lr: 0.000932, cost: 1.0132, z_cost: 1.0093, r_cost: 0.0039, train_time_taken: 12.3263
step: 7160, lr: 0.000932, cost: 1.0108, z_cost: 1.0067, r_cost: 0.0041, train_time_taken: 11.5795
step: 7180, lr: 0.000931, cost: 1.0089, z_cost: 1.0064, r_cost: 0.0026, train_time_taken: 11.5921
preparing data for epoch 119
number of batches 61
time taken to create batches 10.526982545852661
step: 7200, lr: 0.000931, cost: 1.0091, z_cost: 1.0068, r_cost: 0.0023, train_time_taken: 12.2820
step: 7220, lr: 0.000931, cost: 1.0126, z_cost: 1.0080, r_cost: 0.0046, train_time_taken: 11.8364
step: 7240, lr: 0.000931, cost: 1.0145, z_cost: 1.0102, r_cost: 0.0043, train_time_taken: 11.7994
preparing data for epoch 120
number of batches 61
time taken to create batches 11.258150339126587
step: 7260, lr: 0.000931, cost: 1.0085, z_cost: 1.0051, r_cost: 0.0034, train_time_taken: 12.4277
step: 7280, lr: 0.000930, cost: 1.0112, z_cost: 1.0085, r_cost: 0.0027, train_time_taken: 11.6497
step: 7300, lr: 0.000930, cost: 1.0119, z_cost: 1.0094, r_cost: 0.0025, train_time_taken: 11.5725
preparing data for epoch 121
number of batches 61
time taken to create batches 11.601844310760498
step: 7320, lr: 0.000930, cost: 1.0143, z_cost: 1.0084, r_cost: 0.0059, train_time_taken: 12.1870
step: 7340, lr: 0.000930, cost: 1.0125, z_cost: 1.0084, r_cost: 0.0041, train_time_taken: 11.8271
step: 7360, lr: 0.000930, cost: 1.0076, z_cost: 1.0037, r_cost: 0.0039, train_time_taken: 11.7947
step: 7380, lr: 0.000930, cost: 1.0107, z_cost: 1.0061, r_cost: 0.0047, train_time_taken: 11.7961
preparing data for epoch 122
number of batches 61
time taken to create batches 0.609548807144165
step: 7400, lr: 0.000929, cost: 1.0124, z_cost: 1.0088, r_cost: 0.0036, train_time_taken: 12.2079
step: 7420, lr: 0.000929, cost: 1.0084, z_cost: 1.0039, r_cost: 0.0045, train_time_taken: 11.6425
step: 7440, lr: 0.000929, cost: 1.0124, z_cost: 1.0081, r_cost: 0.0043, train_time_taken: 11.5847
preparing data for epoch 123
number of batches 61
time taken to create batches 1.1834509372711182
step: 7460, lr: 0.000929, cost: 1.0116, z_cost: 1.0085, r_cost: 0.0031, train_time_taken: 12.3935
step: 7480, lr: 0.000929, cost: 1.0123, z_cost: 1.0071, r_cost: 0.0052, train_time_taken: 11.8207
step: 7500, lr: 0.000928, cost: 1.0108, z_cost: 1.0076, r_cost: 0.0032, train_time_taken: 11.8486
preparing data for epoch 124
number of batches 61
time taken to create batches 1.7818403244018555
step: 7520, lr: 0.000928, cost: 1.0095, z_cost: 1.0049, r_cost: 0.0046, train_time_taken: 12.2351
step: 7540, lr: 0.000928, cost: 1.0105, z_cost: 1.0066, r_cost: 0.0039, train_time_taken: 11.5967
step: 7560, lr: 0.000928, cost: 1.0080, z_cost: 1.0049, r_cost: 0.0031, train_time_taken: 11.6275
preparing data for epoch 125
number of batches 61
time taken to create batches 2.3545405864715576
step: 7580, lr: 0.000928, cost: 1.0112, z_cost: 1.0066, r_cost: 0.0046, train_time_taken: 12.4045
step: 7600, lr: 0.000928, cost: 1.0143, z_cost: 1.0080, r_cost: 0.0064, train_time_taken: 11.7627
step: 7620, lr: 0.000927, cost: 1.0105, z_cost: 1.0078, r_cost: 0.0027, train_time_taken: 11.7900
preparing data for epoch 126
number of batches 61
time taken to create batches 2.990365743637085
step: 7640, lr: 0.000927, cost: 1.0092, z_cost: 1.0046, r_cost: 0.0047, train_time_taken: 12.2454
step: 7660, lr: 0.000927, cost: 1.0102, z_cost: 1.0075, r_cost: 0.0027, train_time_taken: 11.6197
step: 7680, lr: 0.000927, cost: 1.0080, z_cost: 1.0043, r_cost: 0.0037, train_time_taken: 11.6348
preparing data for epoch 127
number of batches 61
time taken to create batches 3.521848440170288
step: 7700, lr: 0.000927, cost: 1.0099, z_cost: 1.0054, r_cost: 0.0045, train_time_taken: 12.3495
step: 7720, lr: 0.000926, cost: 1.0097, z_cost: 1.0046, r_cost: 0.0051, train_time_taken: 11.8168
step: 7740, lr: 0.000926, cost: 1.0108, z_cost: 1.0069, r_cost: 0.0040, train_time_taken: 11.7666
preparing data for epoch 128
number of batches 61
time taken to create batches 4.164450407028198
step: 7760, lr: 0.000926, cost: 1.0093, z_cost: 1.0062, r_cost: 0.0031, train_time_taken: 12.3037
step: 7780, lr: 0.000926, cost: 1.0118, z_cost: 1.0079, r_cost: 0.0039, train_time_taken: 11.6250
step: 7800, lr: 0.000926, cost: 1.0128, z_cost: 1.0084, r_cost: 0.0044, train_time_taken: 11.6453
preparing data for epoch 129
number of batches 61
time taken to create batches 4.681049108505249
step: 7820, lr: 0.000926, cost: 1.0102, z_cost: 1.0074, r_cost: 0.0028, train_time_taken: 12.3432
step: 7840, lr: 0.000925, cost: 1.0116, z_cost: 1.0082, r_cost: 0.0034, train_time_taken: 11.7966
step: 7860, lr: 0.000925, cost: 1.0085, z_cost: 1.0047, r_cost: 0.0038, train_time_taken: 11.8561
preparing data for epoch 130
number of batches 61
time taken to create batches 5.326170444488525
step: 7880, lr: 0.000925, cost: 1.0149, z_cost: 1.0079, r_cost: 0.0070, train_time_taken: 12.3069
step: 7900, lr: 0.000925, cost: 1.0109, z_cost: 1.0063, r_cost: 0.0046, train_time_taken: 11.6105
step: 7920, lr: 0.000925, cost: 1.0111, z_cost: 1.0068, r_cost: 0.0043, train_time_taken: 11.5944
preparing data for epoch 131
number of batches 61
time taken to create batches 5.85863995552063
step: 7940, lr: 0.000924, cost: 1.0098, z_cost: 1.0060, r_cost: 0.0038, train_time_taken: 12.3438
step: 7960, lr: 0.000924, cost: 1.0106, z_cost: 1.0075, r_cost: 0.0031, train_time_taken: 11.8106
step: 7980, lr: 0.000924, cost: 1.0082, z_cost: 1.0030, r_cost: 0.0052, train_time_taken: 11.8206
preparing data for epoch 132
number of batches 61
time taken to create batches 6.486612796783447
step: 8000, lr: 0.000924, cost: 1.0089, z_cost: 1.0040, r_cost: 0.0049, train_time_taken: 12.2886
step: 8020, lr: 0.000924, cost: 1.0042, z_cost: 1.0007, r_cost: 0.0035, train_time_taken: 11.6128
step: 8040, lr: 0.000924, cost: 1.0065, z_cost: 1.0032, r_cost: 0.0033, train_time_taken: 11.5738
preparing data for epoch 133
number of batches 61
time taken to create batches 6.965039968490601
step: 8060, lr: 0.000923, cost: 1.0086, z_cost: 1.0045, r_cost: 0.0041, train_time_taken: 12.2494
step: 8080, lr: 0.000923, cost: 1.0078, z_cost: 1.0041, r_cost: 0.0037, train_time_taken: 11.8161
step: 8100, lr: 0.000923, cost: 1.0073, z_cost: 1.0043, r_cost: 0.0030, train_time_taken: 11.8455
preparing data for epoch 134
number of batches 61
time taken to create batches 7.686926364898682
step: 8120, lr: 0.000923, cost: 1.0096, z_cost: 1.0067, r_cost: 0.0029, train_time_taken: 12.3579
step: 8140, lr: 0.000923, cost: 1.0083, z_cost: 1.0043, r_cost: 0.0040, train_time_taken: 11.6829
step: 8160, lr: 0.000922, cost: 1.0106, z_cost: 1.0070, r_cost: 0.0036, train_time_taken: 11.5682
preparing data for epoch 135
number of batches 61
time taken to create batches 8.141927003860474
step: 8180, lr: 0.000922, cost: 1.0055, z_cost: 1.0020, r_cost: 0.0035, train_time_taken: 12.2327
step: 8200, lr: 0.000922, cost: 1.0045, z_cost: 1.0021, r_cost: 0.0025, train_time_taken: 11.7585
step: 8220, lr: 0.000922, cost: 1.0066, z_cost: 1.0023, r_cost: 0.0043, train_time_taken: 11.7733
preparing data for epoch 136
number of batches 61
time taken to create batches 8.850430965423584
step: 8240, lr: 0.000922, cost: 1.0084, z_cost: 1.0043, r_cost: 0.0041, train_time_taken: 12.3345
step: 8260, lr: 0.000922, cost: 1.0067, z_cost: 1.0035, r_cost: 0.0031, train_time_taken: 11.7277
step: 8280, lr: 0.000921, cost: 1.0079, z_cost: 1.0030, r_cost: 0.0049, train_time_taken: 11.5829
preparing data for epoch 137
number of batches 61
time taken to create batches 9.259485721588135
step: 8300, lr: 0.000921, cost: 1.0121, z_cost: 1.0087, r_cost: 0.0033, train_time_taken: 12.1908
step: 8320, lr: 0.000921, cost: 1.0065, z_cost: 1.0028, r_cost: 0.0037, train_time_taken: 11.8058
step: 8340, lr: 0.000921, cost: 1.0065, z_cost: 1.0019, r_cost: 0.0046, train_time_taken: 11.8954
preparing data for epoch 138
number of batches 61
time taken to create batches 10.105161666870117
step: 8360, lr: 0.000921, cost: 1.0110, z_cost: 1.0076, r_cost: 0.0034, train_time_taken: 12.4390
step: 8380, lr: 0.000920, cost: 1.0073, z_cost: 1.0025, r_cost: 0.0048, train_time_taken: 11.6520
step: 8400, lr: 0.000920, cost: 1.0079, z_cost: 1.0046, r_cost: 0.0033, train_time_taken: 11.6220
preparing data for epoch 139
number of batches 61
time taken to create batches 10.472846269607544
step: 8420, lr: 0.000920, cost: 1.0114, z_cost: 1.0060, r_cost: 0.0054, train_time_taken: 12.2308
step: 8440, lr: 0.000920, cost: 1.0100, z_cost: 1.0053, r_cost: 0.0047, train_time_taken: 11.8219
step: 8460, lr: 0.000920, cost: 1.0106, z_cost: 1.0069, r_cost: 0.0037, train_time_taken: 11.8201
preparing data for epoch 140
number of batches 61
time taken to create batches 11.315131425857544
step: 8480, lr: 0.000920, cost: 1.0074, z_cost: 1.0045, r_cost: 0.0029, train_time_taken: 12.4854
step: 8500, lr: 0.000919, cost: 1.0073, z_cost: 1.0040, r_cost: 0.0033, train_time_taken: 11.6661
step: 8520, lr: 0.000919, cost: 1.0133, z_cost: 1.0064, r_cost: 0.0069, train_time_taken: 11.7002
preparing data for epoch 141
number of batches 61
time taken to create batches 11.64825439453125
step: 8540, lr: 0.000919, cost: 1.0101, z_cost: 1.0031, r_cost: 0.0070, train_time_taken: 12.2528
step: 8560, lr: 0.000919, cost: 1.0045, z_cost: 1.0019, r_cost: 0.0026, train_time_taken: 11.8300
step: 8580, lr: 0.000919, cost: 1.0052, z_cost: 1.0021, r_cost: 0.0031, train_time_taken: 11.8033
step: 8600, lr: 0.000918, cost: 1.0100, z_cost: 1.0063, r_cost: 0.0037, train_time_taken: 11.8261
preparing data for epoch 142
number of batches 61
time taken to create batches 0.6066718101501465
step: 8620, lr: 0.000918, cost: 1.0078, z_cost: 1.0027, r_cost: 0.0051, train_time_taken: 12.2467
step: 8640, lr: 0.000918, cost: 1.0076, z_cost: 1.0042, r_cost: 0.0034, train_time_taken: 11.6106
step: 8660, lr: 0.000918, cost: 1.0067, z_cost: 1.0022, r_cost: 0.0045, train_time_taken: 11.5985
preparing data for epoch 143
number of batches 61
time taken to create batches 1.1854743957519531
step: 8680, lr: 0.000918, cost: 1.0085, z_cost: 1.0045, r_cost: 0.0041, train_time_taken: 12.4108
step: 8700, lr: 0.000918, cost: 1.0033, z_cost: 1.0014, r_cost: 0.0019, train_time_taken: 11.8687
step: 8720, lr: 0.000917, cost: 1.0037, z_cost: 1.0008, r_cost: 0.0029, train_time_taken: 11.8372
preparing data for epoch 144
number of batches 61
time taken to create batches 1.7763786315917969
step: 8740, lr: 0.000917, cost: 1.0067, z_cost: 1.0046, r_cost: 0.0022, train_time_taken: 12.2408
step: 8760, lr: 0.000917, cost: 1.0013, z_cost: 0.9987, r_cost: 0.0026, train_time_taken: 11.6223
step: 8780, lr: 0.000917, cost: 1.0072, z_cost: 1.0050, r_cost: 0.0022, train_time_taken: 11.6716
preparing data for epoch 145
number of batches 61
time taken to create batches 2.3654026985168457
step: 8800, lr: 0.000917, cost: 1.0045, z_cost: 1.0019, r_cost: 0.0027, train_time_taken: 12.4577
step: 8820, lr: 0.000916, cost: 1.0077, z_cost: 1.0036, r_cost: 0.0042, train_time_taken: 11.8023
step: 8840, lr: 0.000916, cost: 1.0069, z_cost: 1.0039, r_cost: 0.0030, train_time_taken: 11.9049
preparing data for epoch 146
number of batches 61
time taken to create batches 2.9699606895446777
step: 8860, lr: 0.000916, cost: 1.0063, z_cost: 1.0038, r_cost: 0.0025, train_time_taken: 12.2413
step: 8880, lr: 0.000916, cost: 1.0100, z_cost: 1.0038, r_cost: 0.0062, train_time_taken: 11.6335
step: 8900, lr: 0.000916, cost: 1.0084, z_cost: 1.0054, r_cost: 0.0030, train_time_taken: 11.5794
preparing data for epoch 147
number of batches 61
time taken to create batches 3.50122332572937
step: 8920, lr: 0.000916, cost: 1.0081, z_cost: 1.0039, r_cost: 0.0042, train_time_taken: 12.3403
step: 8940, lr: 0.000915, cost: 1.0082, z_cost: 1.0026, r_cost: 0.0055, train_time_taken: 11.8344
step: 8960, lr: 0.000915, cost: 1.0061, z_cost: 1.0027, r_cost: 0.0034, train_time_taken: 11.8338
preparing data for epoch 148
number of batches 61
time taken to create batches 4.130783319473267
step: 8980, lr: 0.000915, cost: 1.0087, z_cost: 1.0047, r_cost: 0.0040, train_time_taken: 12.2661
step: 9000, lr: 0.000915, cost: 1.0074, z_cost: 1.0039, r_cost: 0.0035, train_time_taken: 11.6193
step: 9020, lr: 0.000915, cost: 1.0034, z_cost: 1.0008, r_cost: 0.0026, train_time_taken: 11.6255
preparing data for epoch 149
number of batches 61
time taken to create batches 4.67220401763916
step: 9040, lr: 0.000914, cost: 1.0043, z_cost: 1.0018, r_cost: 0.0025, train_time_taken: 12.3290
step: 9060, lr: 0.000914, cost: 1.0055, z_cost: 1.0014, r_cost: 0.0042, train_time_taken: 11.8278
step: 9080, lr: 0.000914, cost: 1.0047, z_cost: 1.0002, r_cost: 0.0045, train_time_taken: 11.7933
preparing data for epoch 150
number of batches 61
time taken to create batches 5.335885286331177
step: 9100, lr: 0.000914, cost: 1.0043, z_cost: 1.0014, r_cost: 0.0029, train_time_taken: 12.3020
step: 9120, lr: 0.000914, cost: 1.0058, z_cost: 1.0026, r_cost: 0.0033, train_time_taken: 11.5779
step: 9140, lr: 0.000914, cost: 1.0076, z_cost: 1.0046, r_cost: 0.0030, train_time_taken: 11.6436
preparing data for epoch 151
number of batches 61
time taken to create batches 5.839466094970703
step: 9160, lr: 0.000913, cost: 1.0067, z_cost: 1.0036, r_cost: 0.0031, train_time_taken: 12.3303
step: 9180, lr: 0.000913, cost: 1.0038, z_cost: 1.0017, r_cost: 0.0021, train_time_taken: 11.8264
step: 9200, lr: 0.000913, cost: 1.0059, z_cost: 1.0028, r_cost: 0.0031, train_time_taken: 11.8545
preparing data for epoch 152
number of batches 61
time taken to create batches 6.489222288131714
step: 9220, lr: 0.000913, cost: 1.0041, z_cost: 1.0013, r_cost: 0.0028, train_time_taken: 12.3061
step: 9240, lr: 0.000913, cost: 1.0056, z_cost: 1.0020, r_cost: 0.0036, train_time_taken: 11.6224
step: 9260, lr: 0.000912, cost: 1.0054, z_cost: 1.0021, r_cost: 0.0033, train_time_taken: 11.6259
preparing data for epoch 153
number of batches 61
time taken to create batches 6.971751689910889
step: 9280, lr: 0.000912, cost: 1.0037, z_cost: 1.0011, r_cost: 0.0026, train_time_taken: 12.2681
step: 9300, lr: 0.000912, cost: 1.0076, z_cost: 1.0000, r_cost: 0.0076, train_time_taken: 11.7793
step: 9320, lr: 0.000912, cost: 1.0030, z_cost: 0.9987, r_cost: 0.0043, train_time_taken: 11.8112
preparing data for epoch 154
number of batches 61
time taken to create batches 7.709702968597412
step: 9340, lr: 0.000912, cost: 1.0035, z_cost: 1.0013, r_cost: 0.0022, train_time_taken: 12.3252
step: 9360, lr: 0.000912, cost: 1.0064, z_cost: 1.0029, r_cost: 0.0035, train_time_taken: 11.5536
step: 9380, lr: 0.000911, cost: 1.0032, z_cost: 1.0008, r_cost: 0.0023, train_time_taken: 11.6594
preparing data for epoch 155
number of batches 61
time taken to create batches 8.166057109832764
step: 9400, lr: 0.000911, cost: 1.0081, z_cost: 1.0043, r_cost: 0.0038, train_time_taken: 12.2861
step: 9420, lr: 0.000911, cost: 1.0053, z_cost: 1.0020, r_cost: 0.0033, train_time_taken: 11.8569
step: 9440, lr: 0.000911, cost: 1.0058, z_cost: 1.0031, r_cost: 0.0027, train_time_taken: 11.8063
preparing data for epoch 156
number of batches 61
time taken to create batches 8.883002042770386
step: 9460, lr: 0.000911, cost: 1.0066, z_cost: 1.0033, r_cost: 0.0033, train_time_taken: 12.3409
step: 9480, lr: 0.000910, cost: 1.0031, z_cost: 0.9995, r_cost: 0.0036, train_time_taken: 11.5752
step: 9500, lr: 0.000910, cost: 1.0063, z_cost: 1.0036, r_cost: 0.0027, train_time_taken: 11.5616
preparing data for epoch 157
number of batches 61
time taken to create batches 9.273877382278442
step: 9520, lr: 0.000910, cost: 1.0029, z_cost: 1.0011, r_cost: 0.0018, train_time_taken: 12.2121
step: 9540, lr: 0.000910, cost: 1.0051, z_cost: 1.0030, r_cost: 0.0021, train_time_taken: 11.7651
step: 9560, lr: 0.000910, cost: 1.0030, z_cost: 1.0006, r_cost: 0.0024, train_time_taken: 11.8139
preparing data for epoch 158
number of batches 61
time taken to create batches 10.081682205200195
step: 9580, lr: 0.000910, cost: 1.0049, z_cost: 1.0016, r_cost: 0.0033, train_time_taken: 12.3885
step: 9600, lr: 0.000909, cost: 1.0034, z_cost: 1.0006, r_cost: 0.0028, train_time_taken: 11.6338
step: 9620, lr: 0.000909, cost: 1.0032, z_cost: 1.0002, r_cost: 0.0029, train_time_taken: 11.5875
preparing data for epoch 159
number of batches 61
time taken to create batches 10.458354234695435
step: 9640, lr: 0.000909, cost: 1.0065, z_cost: 1.0037, r_cost: 0.0027, train_time_taken: 12.2002
step: 9660, lr: 0.000909, cost: 1.0034, z_cost: 1.0004, r_cost: 0.0030, train_time_taken: 11.7842
step: 9680, lr: 0.000909, cost: 1.0031, z_cost: 0.9998, r_cost: 0.0033, train_time_taken: 11.8649
preparing data for epoch 160
number of batches 61
time taken to create batches 11.279820680618286
step: 9700, lr: 0.000908, cost: 1.0063, z_cost: 1.0028, r_cost: 0.0035, train_time_taken: 12.4592
step: 9720, lr: 0.000908, cost: 1.0017, z_cost: 0.9991, r_cost: 0.0027, train_time_taken: 11.6896
step: 9740, lr: 0.000908, cost: 1.0029, z_cost: 0.9995, r_cost: 0.0034, train_time_taken: 11.6140
preparing data for epoch 161
number of batches 61
time taken to create batches 11.669277429580688
step: 9760, lr: 0.000908, cost: 1.0117, z_cost: 1.0032, r_cost: 0.0085, train_time_taken: 12.2561
step: 9780, lr: 0.000908, cost: 1.0041, z_cost: 1.0015, r_cost: 0.0025, train_time_taken: 11.8251
step: 9800, lr: 0.000908, cost: 1.0067, z_cost: 1.0038, r_cost: 0.0028, train_time_taken: 11.8052
step: 9820, lr: 0.000907, cost: 1.0048, z_cost: 1.0014, r_cost: 0.0034, train_time_taken: 11.8038
preparing data for epoch 162
number of batches 61
time taken to create batches 0.6074423789978027
step: 9840, lr: 0.000907, cost: 1.0070, z_cost: 1.0036, r_cost: 0.0034, train_time_taken: 12.1452
step: 9860, lr: 0.000907, cost: 1.0029, z_cost: 1.0002, r_cost: 0.0026, train_time_taken: 11.6774
step: 9880, lr: 0.000907, cost: 1.0058, z_cost: 1.0022, r_cost: 0.0037, train_time_taken: 11.5975
preparing data for epoch 163
number of batches 61
time taken to create batches 1.1947839260101318
step: 9900, lr: 0.000907, cost: 1.0056, z_cost: 1.0030, r_cost: 0.0027, train_time_taken: 12.3491
step: 9920, lr: 0.000907, cost: 1.0033, z_cost: 1.0010, r_cost: 0.0023, train_time_taken: 11.8308
step: 9940, lr: 0.000906, cost: 1.0040, z_cost: 1.0013, r_cost: 0.0027, train_time_taken: 11.8342
preparing data for epoch 164
number of batches 61
time taken to create batches 1.7832870483398438
step: 9960, lr: 0.000906, cost: 1.0037, z_cost: 1.0005, r_cost: 0.0032, train_time_taken: 12.2257
step: 9980, lr: 0.000906, cost: 1.0067, z_cost: 1.0023, r_cost: 0.0044, train_time_taken: 11.6061
step: 10000, lr: 0.000906, cost: 1.0057, z_cost: 1.0010, r_cost: 0.0047, train_time_taken: 11.6008
preparing data for epoch 165
number of batches 61
time taken to create batches 2.3349649906158447
step: 10020, lr: 0.000906, cost: 1.0065, z_cost: 1.0022, r_cost: 0.0043, train_time_taken: 12.3912
step: 10040, lr: 0.000905, cost: 1.0044, z_cost: 1.0025, r_cost: 0.0019, train_time_taken: 11.8563
step: 10060, lr: 0.000905, cost: 1.0049, z_cost: 1.0020, r_cost: 0.0029, train_time_taken: 11.8474
preparing data for epoch 166
number of batches 61
time taken to create batches 2.9877851009368896
step: 10080, lr: 0.000905, cost: 1.0014, z_cost: 0.9996, r_cost: 0.0018, train_time_taken: 12.3415
step: 10100, lr: 0.000905, cost: 1.0009, z_cost: 0.9979, r_cost: 0.0030, train_time_taken: 11.6652
step: 10120, lr: 0.000905, cost: 1.0050, z_cost: 1.0014, r_cost: 0.0036, train_time_taken: 11.6351
preparing data for epoch 167
number of batches 61
time taken to create batches 3.5250532627105713
step: 10140, lr: 0.000905, cost: 1.0054, z_cost: 1.0011, r_cost: 0.0043, train_time_taken: 12.3784
step: 10160, lr: 0.000904, cost: 0.9990, z_cost: 0.9967, r_cost: 0.0024, train_time_taken: 11.8684
step: 10180, lr: 0.000904, cost: 1.0035, z_cost: 1.0006, r_cost: 0.0029, train_time_taken: 11.8593
preparing data for epoch 168
number of batches 61
time taken to create batches 4.140754699707031
step: 10200, lr: 0.000904, cost: 1.0052, z_cost: 1.0011, r_cost: 0.0041, train_time_taken: 12.2964
step: 10220, lr: 0.000904, cost: 1.0061, z_cost: 1.0023, r_cost: 0.0038, train_time_taken: 11.5889
step: 10240, lr: 0.000904, cost: 1.0055, z_cost: 1.0030, r_cost: 0.0025, train_time_taken: 11.6128
preparing data for epoch 169
number of batches 61
time taken to create batches 4.645027160644531
step: 10260, lr: 0.000903, cost: 1.0044, z_cost: 1.0019, r_cost: 0.0025, train_time_taken: 12.3413
step: 10280, lr: 0.000903, cost: 1.0023, z_cost: 1.0000, r_cost: 0.0022, train_time_taken: 11.9209
step: 10300, lr: 0.000903, cost: 1.0036, z_cost: 1.0012, r_cost: 0.0024, train_time_taken: 11.8141
preparing data for epoch 170
number of batches 61
time taken to create batches 5.307693243026733
step: 10320, lr: 0.000903, cost: 1.0050, z_cost: 1.0013, r_cost: 0.0037, train_time_taken: 12.2718
step: 10340, lr: 0.000903, cost: 1.0025, z_cost: 0.9993, r_cost: 0.0033, train_time_taken: 11.6137
step: 10360, lr: 0.000903, cost: 1.0038, z_cost: 1.0020, r_cost: 0.0018, train_time_taken: 11.6565
preparing data for epoch 171
number of batches 61
time taken to create batches 5.835989236831665
step: 10380, lr: 0.000902, cost: 1.0051, z_cost: 1.0025, r_cost: 0.0026, train_time_taken: 12.3379
step: 10400, lr: 0.000902, cost: 1.0015, z_cost: 0.9997, r_cost: 0.0018, train_time_taken: 11.7823
step: 10420, lr: 0.000902, cost: 1.0011, z_cost: 0.9982, r_cost: 0.0030, train_time_taken: 11.8373
preparing data for epoch 172
number of batches 61
time taken to create batches 6.549823045730591
step: 10440, lr: 0.000902, cost: 1.0018, z_cost: 0.9996, r_cost: 0.0022, train_time_taken: 12.3475
step: 10460, lr: 0.000902, cost: 1.0043, z_cost: 1.0006, r_cost: 0.0038, train_time_taken: 11.6439
step: 10480, lr: 0.000901, cost: 1.0010, z_cost: 0.9984, r_cost: 0.0026, train_time_taken: 11.5637
preparing data for epoch 173
number of batches 61
time taken to create batches 7.0335564613342285
step: 10500, lr: 0.000901, cost: 1.0030, z_cost: 0.9994, r_cost: 0.0036, train_time_taken: 12.3213
step: 10520, lr: 0.000901, cost: 0.9989, z_cost: 0.9971, r_cost: 0.0018, train_time_taken: 11.8419
step: 10540, lr: 0.000901, cost: 1.0020, z_cost: 1.0005, r_cost: 0.0015, train_time_taken: 11.8152
preparing data for epoch 174
number of batches 61
time taken to create batches 7.763982057571411
step: 10560, lr: 0.000901, cost: 1.0012, z_cost: 0.9994, r_cost: 0.0019, train_time_taken: 12.4239
step: 10580, lr: 0.000901, cost: 1.0003, z_cost: 0.9982, r_cost: 0.0021, train_time_taken: 11.6266
step: 10600, lr: 0.000900, cost: 1.0029, z_cost: 0.9997, r_cost: 0.0032, train_time_taken: 11.6682
preparing data for epoch 175
number of batches 61
time taken to create batches 8.183627843856812
step: 10620, lr: 0.000900, cost: 1.0023, z_cost: 0.9996, r_cost: 0.0027, train_time_taken: 12.2956
step: 10640, lr: 0.000900, cost: 1.0066, z_cost: 1.0014, r_cost: 0.0051, train_time_taken: 11.8642
step: 10660, lr: 0.000900, cost: 1.0042, z_cost: 0.9995, r_cost: 0.0047, train_time_taken: 11.8476
preparing data for epoch 176
number of batches 61
time taken to create batches 8.881457567214966
step: 10680, lr: 0.000900, cost: 1.0147, z_cost: 1.0033, r_cost: 0.0114, train_time_taken: 12.3588
step: 10700, lr: 0.000900, cost: 1.0048, z_cost: 1.0020, r_cost: 0.0028, train_time_taken: 11.6890
step: 10720, lr: 0.000899, cost: 1.0057, z_cost: 1.0020, r_cost: 0.0037, train_time_taken: 11.6610
preparing data for epoch 177
number of batches 61
time taken to create batches 9.284560203552246
step: 10740, lr: 0.000899, cost: 1.0061, z_cost: 1.0021, r_cost: 0.0041, train_time_taken: 12.2261
step: 10760, lr: 0.000899, cost: 1.0236, z_cost: 1.0148, r_cost: 0.0087, train_time_taken: 11.8138
step: 10780, lr: 0.000899, cost: 1.0178, z_cost: 1.0074, r_cost: 0.0104, train_time_taken: 11.8497
preparing data for epoch 178
number of batches 61
time taken to create batches 10.036723375320435
step: 10800, lr: 0.000899, cost: 1.0125, z_cost: 1.0049, r_cost: 0.0076, train_time_taken: 12.3822
step: 10820, lr: 0.000898, cost: 1.0086, z_cost: 1.0035, r_cost: 0.0051, train_time_taken: 11.6549
step: 10840, lr: 0.000898, cost: 1.0056, z_cost: 1.0005, r_cost: 0.0050, train_time_taken: 11.5811
preparing data for epoch 179
number of batches 61
time taken to create batches 10.45596432685852
step: 10860, lr: 0.000898, cost: 1.0030, z_cost: 1.0001, r_cost: 0.0028, train_time_taken: 12.2358
step: 10880, lr: 0.000898, cost: 0.9992, z_cost: 0.9967, r_cost: 0.0025, train_time_taken: 11.7713
step: 10900, lr: 0.000898, cost: 1.0020, z_cost: 0.9984, r_cost: 0.0036, train_time_taken: 11.8599
preparing data for epoch 180
number of batches 61
time taken to create batches 11.276696920394897
step: 10920, lr: 0.000898, cost: 1.0042, z_cost: 1.0022, r_cost: 0.0019, train_time_taken: 12.4447
step: 10940, lr: 0.000897, cost: 1.0028, z_cost: 1.0003, r_cost: 0.0024, train_time_taken: 11.6691
step: 10960, lr: 0.000897, cost: 1.0029, z_cost: 1.0008, r_cost: 0.0021, train_time_taken: 11.6073
preparing data for epoch 181
number of batches 61
time taken to create batches 11.620575189590454
step: 10980, lr: 0.000897, cost: 1.0110, z_cost: 1.0040, r_cost: 0.0070, train_time_taken: 12.2123
step: 11000, lr: 0.000897, cost: 1.0026, z_cost: 1.0008, r_cost: 0.0018, train_time_taken: 11.7950
step: 11020, lr: 0.000897, cost: 1.0020, z_cost: 0.9988, r_cost: 0.0031, train_time_taken: 11.8254
step: 11040, lr: 0.000897, cost: 0.9972, z_cost: 0.9954, r_cost: 0.0018, train_time_taken: 11.8055
preparing data for epoch 182
number of batches 61
time taken to create batches 0.6073513031005859
step: 11060, lr: 0.000896, cost: 1.0009, z_cost: 0.9963, r_cost: 0.0046, train_time_taken: 12.2841
step: 11080, lr: 0.000896, cost: 1.0008, z_cost: 0.9988, r_cost: 0.0020, train_time_taken: 11.6661
step: 11100, lr: 0.000896, cost: 1.0005, z_cost: 0.9979, r_cost: 0.0026, train_time_taken: 11.5976
preparing data for epoch 183
number of batches 61
time taken to create batches 1.1803033351898193
step: 11120, lr: 0.000896, cost: 1.0010, z_cost: 0.9988, r_cost: 0.0022, train_time_taken: 12.4416
step: 11140, lr: 0.000896, cost: 1.0013, z_cost: 0.9987, r_cost: 0.0026, train_time_taken: 11.7978
step: 11160, lr: 0.000895, cost: 0.9996, z_cost: 0.9979, r_cost: 0.0017, train_time_taken: 11.7963
preparing data for epoch 184
number of batches 61
time taken to create batches 1.796013355255127
step: 11180, lr: 0.000895, cost: 0.9994, z_cost: 0.9971, r_cost: 0.0023, train_time_taken: 12.2490
step: 11200, lr: 0.000895, cost: 0.9984, z_cost: 0.9963, r_cost: 0.0021, train_time_taken: 11.6558
step: 11220, lr: 0.000895, cost: 0.9977, z_cost: 0.9958, r_cost: 0.0019, train_time_taken: 11.6725
preparing data for epoch 185
number of batches 61
time taken to create batches 2.362952947616577
step: 11240, lr: 0.000895, cost: 0.9975, z_cost: 0.9965, r_cost: 0.0010, train_time_taken: 12.3847
step: 11260, lr: 0.000895, cost: 0.9990, z_cost: 0.9970, r_cost: 0.0020, train_time_taken: 11.8140
step: 11280, lr: 0.000894, cost: 0.9979, z_cost: 0.9961, r_cost: 0.0018, train_time_taken: 11.8351
preparing data for epoch 186
number of batches 61
time taken to create batches 2.955298662185669
step: 11300, lr: 0.000894, cost: 0.9996, z_cost: 0.9977, r_cost: 0.0018, train_time_taken: 12.2246
step: 11320, lr: 0.000894, cost: 0.9956, z_cost: 0.9940, r_cost: 0.0016, train_time_taken: 11.5647
step: 11340, lr: 0.000894, cost: 1.0011, z_cost: 0.9995, r_cost: 0.0016, train_time_taken: 11.6464
preparing data for epoch 187
number of batches 61
time taken to create batches 3.522149085998535
step: 11360, lr: 0.000894, cost: 0.9999, z_cost: 0.9985, r_cost: 0.0014, train_time_taken: 12.3644
step: 11380, lr: 0.000894, cost: 1.0011, z_cost: 0.9992, r_cost: 0.0020, train_time_taken: 11.8470
step: 11400, lr: 0.000893, cost: 1.0011, z_cost: 0.9990, r_cost: 0.0021, train_time_taken: 11.8527
preparing data for epoch 188
number of batches 61
time taken to create batches 4.1475770473480225
step: 11420, lr: 0.000893, cost: 1.0000, z_cost: 0.9963, r_cost: 0.0037, train_time_taken: 12.2686
step: 11440, lr: 0.000893, cost: 1.0008, z_cost: 0.9985, r_cost: 0.0023, train_time_taken: 11.6036
step: 11460, lr: 0.000893, cost: 0.9983, z_cost: 0.9966, r_cost: 0.0017, train_time_taken: 11.5893
preparing data for epoch 189
number of batches 61
time taken to create batches 4.679548740386963
step: 11480, lr: 0.000893, cost: 0.9975, z_cost: 0.9938, r_cost: 0.0037, train_time_taken: 12.3896
step: 11500, lr: 0.000892, cost: 0.9995, z_cost: 0.9974, r_cost: 0.0022, train_time_taken: 11.8326
step: 11520, lr: 0.000892, cost: 1.0008, z_cost: 0.9976, r_cost: 0.0031, train_time_taken: 11.8230
preparing data for epoch 190
number of batches 61
time taken to create batches 5.315539836883545
step: 11540, lr: 0.000892, cost: 0.9991, z_cost: 0.9964, r_cost: 0.0028, train_time_taken: 12.2551
step: 11560, lr: 0.000892, cost: 1.0010, z_cost: 0.9978, r_cost: 0.0032, train_time_taken: 11.6324
step: 11580, lr: 0.000892, cost: 1.0013, z_cost: 0.9987, r_cost: 0.0025, train_time_taken: 11.6192
preparing data for epoch 191
number of batches 61
time taken to create batches 5.856399059295654
step: 11600, lr: 0.000892, cost: 0.9992, z_cost: 0.9964, r_cost: 0.0027, train_time_taken: 12.3319
step: 11620, lr: 0.000891, cost: 1.0009, z_cost: 0.9991, r_cost: 0.0018, train_time_taken: 11.8074
step: 11640, lr: 0.000891, cost: 0.9973, z_cost: 0.9951, r_cost: 0.0022, train_time_taken: 11.7953
preparing data for epoch 192
number of batches 61
time taken to create batches 6.553921937942505
step: 11660, lr: 0.000891, cost: 0.9976, z_cost: 0.9958, r_cost: 0.0018, train_time_taken: 12.4153
step: 11680, lr: 0.000891, cost: 0.9987, z_cost: 0.9967, r_cost: 0.0019, train_time_taken: 11.6176
step: 11700, lr: 0.000891, cost: 0.9989, z_cost: 0.9955, r_cost: 0.0034, train_time_taken: 11.7149
preparing data for epoch 193
number of batches 61
time taken to create batches 7.0234057903289795
step: 11720, lr: 0.000891, cost: 1.0026, z_cost: 0.9999, r_cost: 0.0027, train_time_taken: 12.3891
step: 11740, lr: 0.000890, cost: 1.0017, z_cost: 0.9996, r_cost: 0.0021, train_time_taken: 11.9444
step: 11760, lr: 0.000890, cost: 1.0042, z_cost: 1.0013, r_cost: 0.0029, train_time_taken: 11.8497
preparing data for epoch 194
number of batches 61
time taken to create batches 7.66941499710083
step: 11780, lr: 0.000890, cost: 1.0027, z_cost: 0.9986, r_cost: 0.0041, train_time_taken: 12.3348
step: 11800, lr: 0.000890, cost: 1.0020, z_cost: 0.9985, r_cost: 0.0035, train_time_taken: 11.6531
step: 11820, lr: 0.000890, cost: 1.0004, z_cost: 0.9983, r_cost: 0.0020, train_time_taken: 11.6273
preparing data for epoch 195
number of batches 61
time taken to create batches 8.158254861831665
step: 11840, lr: 0.000889, cost: 1.0016, z_cost: 0.9993, r_cost: 0.0023, train_time_taken: 12.2785
step: 11860, lr: 0.000889, cost: 1.0030, z_cost: 0.9997, r_cost: 0.0033, train_time_taken: 11.8372
step: 11880, lr: 0.000889, cost: 0.9994, z_cost: 0.9977, r_cost: 0.0017, train_time_taken: 11.8376
preparing data for epoch 196
number of batches 61
time taken to create batches 8.851836442947388
step: 11900, lr: 0.000889, cost: 1.0032, z_cost: 0.9991, r_cost: 0.0041, train_time_taken: 12.3363
step: 11920, lr: 0.000889, cost: 0.9990, z_cost: 0.9969, r_cost: 0.0020, train_time_taken: 11.6245
step: 11940, lr: 0.000889, cost: 0.9994, z_cost: 0.9970, r_cost: 0.0024, train_time_taken: 11.6829
preparing data for epoch 197
number of batches 61
time taken to create batches 9.323750495910645
step: 11960, lr: 0.000888, cost: 0.9998, z_cost: 0.9969, r_cost: 0.0029, train_time_taken: 12.2841
step: 11980, lr: 0.000888, cost: 1.0005, z_cost: 0.9975, r_cost: 0.0030, train_time_taken: 11.7909
step: 12000, lr: 0.000888, cost: 1.0004, z_cost: 0.9977, r_cost: 0.0028, train_time_taken: 11.8210
preparing data for epoch 198
number of batches 61
time taken to create batches 10.049629926681519
step: 12020, lr: 0.000888, cost: 0.9996, z_cost: 0.9972, r_cost: 0.0024, train_time_taken: 12.3972
step: 12040, lr: 0.000888, cost: 0.9988, z_cost: 0.9961, r_cost: 0.0026, train_time_taken: 11.6794
step: 12060, lr: 0.000888, cost: 1.0013, z_cost: 0.9981, r_cost: 0.0033, train_time_taken: 11.6517
preparing data for epoch 199
number of batches 61
time taken to create batches 10.621201753616333
step: 12080, lr: 0.000887, cost: 0.9970, z_cost: 0.9943, r_cost: 0.0027, train_time_taken: 12.3636
step: 12100, lr: 0.000887, cost: 0.9995, z_cost: 0.9978, r_cost: 0.0017, train_time_taken: 11.7894
step: 12120, lr: 0.000887, cost: 1.0026, z_cost: 0.9994, r_cost: 0.0031, train_time_taken: 11.7713
preparing data for epoch 200
number of batches 61
time taken to create batches 11.28429889678955
step: 12140, lr: 0.000887, cost: 0.9994, z_cost: 0.9965, r_cost: 0.0029, train_time_taken: 12.4381
step: 12160, lr: 0.000887, cost: 1.0007, z_cost: 0.9979, r_cost: 0.0028, train_time_taken: 11.6135
step: 12180, lr: 0.000886, cost: 1.0015, z_cost: 0.9996, r_cost: 0.0019, train_time_taken: 11.6467
preparing data for epoch 201
number of batches 61
time taken to create batches 11.692180633544922
step: 12200, lr: 0.000886, cost: 1.0054, z_cost: 0.9961, r_cost: 0.0093, train_time_taken: 12.2798
step: 12220, lr: 0.000886, cost: 0.9973, z_cost: 0.9954, r_cost: 0.0019, train_time_taken: 11.8865
step: 12240, lr: 0.000886, cost: 0.9985, z_cost: 0.9964, r_cost: 0.0021, train_time_taken: 11.7943
step: 12260, lr: 0.000886, cost: 0.9959, z_cost: 0.9946, r_cost: 0.0014, train_time_taken: 12.0104
preparing data for epoch 202
number of batches 61
time taken to create batches 0.6078193187713623
step: 12280, lr: 0.000886, cost: 0.9988, z_cost: 0.9962, r_cost: 0.0026, train_time_taken: 12.3265
step: 12300, lr: 0.000885, cost: 0.9959, z_cost: 0.9944, r_cost: 0.0015, train_time_taken: 11.6028
step: 12320, lr: 0.000885, cost: 0.9975, z_cost: 0.9943, r_cost: 0.0032, train_time_taken: 11.6588
preparing data for epoch 203
number of batches 61
time taken to create batches 1.1794066429138184
step: 12340, lr: 0.000885, cost: 0.9986, z_cost: 0.9966, r_cost: 0.0020, train_time_taken: 12.3642
step: 12360, lr: 0.000885, cost: 0.9982, z_cost: 0.9970, r_cost: 0.0012, train_time_taken: 11.8008
step: 12380, lr: 0.000885, cost: 0.9981, z_cost: 0.9962, r_cost: 0.0018, train_time_taken: 11.8453
preparing data for epoch 204
number of batches 61
time taken to create batches 1.8333065509796143
step: 12400, lr: 0.000885, cost: 0.9994, z_cost: 0.9974, r_cost: 0.0021, train_time_taken: 12.2724
step: 12420, lr: 0.000884, cost: 0.9957, z_cost: 0.9937, r_cost: 0.0020, train_time_taken: 11.6070
step: 12440, lr: 0.000884, cost: 0.9993, z_cost: 0.9970, r_cost: 0.0023, train_time_taken: 11.5900
preparing data for epoch 205
number of batches 61
time taken to create batches 2.350984811782837
step: 12460, lr: 0.000884, cost: 0.9996, z_cost: 0.9969, r_cost: 0.0027, train_time_taken: 12.4215
step: 12480, lr: 0.000884, cost: 1.0013, z_cost: 0.9981, r_cost: 0.0032, train_time_taken: 11.9220
step: 12500, lr: 0.000884, cost: 1.0002, z_cost: 0.9968, r_cost: 0.0034, train_time_taken: 11.8226
preparing data for epoch 206
number of batches 61
time taken to create batches 2.971344232559204
step: 12520, lr: 0.000883, cost: 0.9989, z_cost: 0.9957, r_cost: 0.0032, train_time_taken: 12.3128
step: 12540, lr: 0.000883, cost: 0.9995, z_cost: 0.9967, r_cost: 0.0029, train_time_taken: 11.6541
step: 12560, lr: 0.000883, cost: 1.0009, z_cost: 0.9976, r_cost: 0.0033, train_time_taken: 11.5800
preparing data for epoch 207
number of batches 61
time taken to create batches 3.511833429336548
step: 12580, lr: 0.000883, cost: 0.9994, z_cost: 0.9965, r_cost: 0.0029, train_time_taken: 12.3120
step: 12600, lr: 0.000883, cost: 0.9972, z_cost: 0.9941, r_cost: 0.0031, train_time_taken: 11.7837
step: 12620, lr: 0.000883, cost: 0.9969, z_cost: 0.9939, r_cost: 0.0030, train_time_taken: 11.8687
preparing data for epoch 208
number of batches 61
time taken to create batches 4.144530534744263
step: 12640, lr: 0.000882, cost: 0.9991, z_cost: 0.9973, r_cost: 0.0018, train_time_taken: 12.2776
step: 12660, lr: 0.000882, cost: 0.9965, z_cost: 0.9944, r_cost: 0.0020, train_time_taken: 11.6173
step: 12680, lr: 0.000882, cost: 0.9995, z_cost: 0.9971, r_cost: 0.0024, train_time_taken: 11.5077
preparing data for epoch 209
number of batches 61
time taken to create batches 4.639239549636841
step: 12700, lr: 0.000882, cost: 0.9999, z_cost: 0.9971, r_cost: 0.0028, train_time_taken: 12.2916
step: 12720, lr: 0.000882, cost: 0.9986, z_cost: 0.9963, r_cost: 0.0022, train_time_taken: 11.8179
step: 12740, lr: 0.000882, cost: 0.9997, z_cost: 0.9969, r_cost: 0.0027, train_time_taken: 11.7976
preparing data for epoch 210
number of batches 61
time taken to create batches 5.3244922161102295
step: 12760, lr: 0.000881, cost: 0.9993, z_cost: 0.9978, r_cost: 0.0015, train_time_taken: 12.2856
step: 12780, lr: 0.000881, cost: 0.9989, z_cost: 0.9971, r_cost: 0.0018, train_time_taken: 11.6573
step: 12800, lr: 0.000881, cost: 0.9964, z_cost: 0.9944, r_cost: 0.0020, train_time_taken: 11.5672
preparing data for epoch 211
number of batches 61
time taken to create batches 5.807946443557739
step: 12820, lr: 0.000881, cost: 0.9946, z_cost: 0.9932, r_cost: 0.0014, train_time_taken: 12.2557
step: 12840, lr: 0.000881, cost: 0.9993, z_cost: 0.9979, r_cost: 0.0014, train_time_taken: 11.7625
step: 12860, lr: 0.000881, cost: 0.9926, z_cost: 0.9910, r_cost: 0.0017, train_time_taken: 11.8059
preparing data for epoch 212
number of batches 61
time taken to create batches 6.527689218521118
step: 12880, lr: 0.000880, cost: 0.9951, z_cost: 0.9931, r_cost: 0.0020, train_time_taken: 12.3172
step: 12900, lr: 0.000880, cost: 0.9994, z_cost: 0.9960, r_cost: 0.0034, train_time_taken: 11.6605
step: 12920, lr: 0.000880, cost: 0.9977, z_cost: 0.9955, r_cost: 0.0022, train_time_taken: 11.6171
preparing data for epoch 213
number of batches 61
time taken to create batches 7.008254766464233
step: 12940, lr: 0.000880, cost: 1.0008, z_cost: 0.9988, r_cost: 0.0020, train_time_taken: 12.2981
step: 12960, lr: 0.000880, cost: 0.9975, z_cost: 0.9952, r_cost: 0.0023, train_time_taken: 11.7825
step: 12980, lr: 0.000879, cost: 0.9981, z_cost: 0.9959, r_cost: 0.0022, train_time_taken: 11.9263
preparing data for epoch 214
number of batches 61
time taken to create batches 7.68820333480835
step: 13000, lr: 0.000879, cost: 0.9998, z_cost: 0.9978, r_cost: 0.0020, train_time_taken: 12.3397
step: 13020, lr: 0.000879, cost: 1.0008, z_cost: 0.9972, r_cost: 0.0035, train_time_taken: 11.5829
step: 13040, lr: 0.000879, cost: 0.9978, z_cost: 0.9952, r_cost: 0.0026, train_time_taken: 11.5481
preparing data for epoch 215
number of batches 61
time taken to create batches 8.146972417831421
step: 13060, lr: 0.000879, cost: 1.0002, z_cost: 0.9968, r_cost: 0.0033, train_time_taken: 12.3082
step: 13080, lr: 0.000879, cost: 1.0000, z_cost: 0.9968, r_cost: 0.0032, train_time_taken: 11.8731
step: 13100, lr: 0.000878, cost: 1.0019, z_cost: 0.9986, r_cost: 0.0033, train_time_taken: 11.7776
preparing data for epoch 216
number of batches 61
time taken to create batches 8.855898141860962
step: 13120, lr: 0.000878, cost: 1.0001, z_cost: 0.9969, r_cost: 0.0031, train_time_taken: 12.3419
step: 13140, lr: 0.000878, cost: 0.9973, z_cost: 0.9951, r_cost: 0.0022, train_time_taken: 11.6351
step: 13160, lr: 0.000878, cost: 0.9997, z_cost: 0.9973, r_cost: 0.0024, train_time_taken: 11.6036
preparing data for epoch 217
number of batches 61
time taken to create batches 9.282067060470581
step: 13180, lr: 0.000878, cost: 0.9986, z_cost: 0.9969, r_cost: 0.0017, train_time_taken: 12.2352
step: 13200, lr: 0.000878, cost: 0.9984, z_cost: 0.9969, r_cost: 0.0016, train_time_taken: 11.8339
step: 13220, lr: 0.000877, cost: 0.9983, z_cost: 0.9944, r_cost: 0.0040, train_time_taken: 11.7687
preparing data for epoch 218
number of batches 61
time taken to create batches 10.060696840286255
step: 13240, lr: 0.000877, cost: 0.9945, z_cost: 0.9927, r_cost: 0.0018, train_time_taken: 12.3777
step: 13260, lr: 0.000877, cost: 0.9959, z_cost: 0.9929, r_cost: 0.0031, train_time_taken: 11.6063
step: 13280, lr: 0.000877, cost: 0.9981, z_cost: 0.9965, r_cost: 0.0016, train_time_taken: 11.5556
preparing data for epoch 219
number of batches 61
time taken to create batches 10.552711486816406
step: 13300, lr: 0.000877, cost: 0.9972, z_cost: 0.9954, r_cost: 0.0018, train_time_taken: 12.3133
step: 13320, lr: 0.000877, cost: 0.9966, z_cost: 0.9943, r_cost: 0.0023, train_time_taken: 11.8973
step: 13340, lr: 0.000876, cost: 0.9970, z_cost: 0.9949, r_cost: 0.0021, train_time_taken: 11.9266
preparing data for epoch 220
number of batches 61
time taken to create batches 11.314351797103882
step: 13360, lr: 0.000876, cost: 0.9974, z_cost: 0.9953, r_cost: 0.0021, train_time_taken: 12.4836
step: 13380, lr: 0.000876, cost: 0.9950, z_cost: 0.9935, r_cost: 0.0015, train_time_taken: 11.6017
step: 13400, lr: 0.000876, cost: 0.9951, z_cost: 0.9927, r_cost: 0.0024, train_time_taken: 11.6348
preparing data for epoch 221
number of batches 61
time taken to create batches 11.580733299255371
step: 13420, lr: 0.000876, cost: 1.0073, z_cost: 0.9969, r_cost: 0.0104, train_time_taken: 12.1682
step: 13440, lr: 0.000875, cost: 0.9973, z_cost: 0.9954, r_cost: 0.0019, train_time_taken: 11.8835
step: 13460, lr: 0.000875, cost: 0.9930, z_cost: 0.9915, r_cost: 0.0016, train_time_taken: 11.7807
step: 13480, lr: 0.000875, cost: 0.9966, z_cost: 0.9931, r_cost: 0.0035, train_time_taken: 11.8371
preparing data for epoch 222
number of batches 61
time taken to create batches 0.6034955978393555
step: 13500, lr: 0.000875, cost: 0.9980, z_cost: 0.9946, r_cost: 0.0034, train_time_taken: 12.2484
step: 13520, lr: 0.000875, cost: 0.9944, z_cost: 0.9931, r_cost: 0.0014, train_time_taken: 11.5885
step: 13540, lr: 0.000875, cost: 0.9952, z_cost: 0.9926, r_cost: 0.0026, train_time_taken: 11.6287
preparing data for epoch 223
number of batches 61
time taken to create batches 1.1782937049865723
step: 13560, lr: 0.000874, cost: 0.9969, z_cost: 0.9951, r_cost: 0.0018, train_time_taken: 12.5256
step: 13580, lr: 0.000874, cost: 0.9966, z_cost: 0.9934, r_cost: 0.0032, train_time_taken: 11.7803
step: 13600, lr: 0.000874, cost: 0.9959, z_cost: 0.9947, r_cost: 0.0012, train_time_taken: 11.7723
preparing data for epoch 224
number of batches 61
time taken to create batches 1.7916655540466309
step: 13620, lr: 0.000874, cost: 0.9971, z_cost: 0.9959, r_cost: 0.0012, train_time_taken: 12.2457
step: 13640, lr: 0.000874, cost: 0.9959, z_cost: 0.9943, r_cost: 0.0016, train_time_taken: 11.6176
step: 13660, lr: 0.000874, cost: 0.9942, z_cost: 0.9920, r_cost: 0.0021, train_time_taken: 11.6625
preparing data for epoch 225
number of batches 61
time taken to create batches 2.3626933097839355
step: 13680, lr: 0.000873, cost: 0.9946, z_cost: 0.9912, r_cost: 0.0034, train_time_taken: 12.4071
step: 13700, lr: 0.000873, cost: 0.9978, z_cost: 0.9955, r_cost: 0.0023, train_time_taken: 11.7237
step: 13720, lr: 0.000873, cost: 0.9994, z_cost: 0.9953, r_cost: 0.0041, train_time_taken: 11.7706
preparing data for epoch 226
number of batches 61
time taken to create batches 2.942523717880249
step: 13740, lr: 0.000873, cost: 0.9965, z_cost: 0.9939, r_cost: 0.0026, train_time_taken: 12.1621
step: 13760, lr: 0.000873, cost: 0.9969, z_cost: 0.9949, r_cost: 0.0020, train_time_taken: 11.6373
step: 13780, lr: 0.000873, cost: 0.9993, z_cost: 0.9965, r_cost: 0.0028, train_time_taken: 11.5981
preparing data for epoch 227
number of batches 61
time taken to create batches 3.5265095233917236
step: 13800, lr: 0.000872, cost: 0.9973, z_cost: 0.9953, r_cost: 0.0019, train_time_taken: 12.3999
step: 13820, lr: 0.000872, cost: 1.0020, z_cost: 0.9964, r_cost: 0.0056, train_time_taken: 11.7942
step: 13840, lr: 0.000872, cost: 0.9976, z_cost: 0.9935, r_cost: 0.0040, train_time_taken: 11.8368
preparing data for epoch 228
number of batches 61
time taken to create batches 4.148530006408691
step: 13860, lr: 0.000872, cost: 0.9970, z_cost: 0.9941, r_cost: 0.0029, train_time_taken: 12.3181
step: 13880, lr: 0.000872, cost: 0.9982, z_cost: 0.9950, r_cost: 0.0031, train_time_taken: 11.7040
step: 13900, lr: 0.000872, cost: 0.9972, z_cost: 0.9950, r_cost: 0.0022, train_time_taken: 11.6391
preparing data for epoch 229
number of batches 61
time taken to create batches 4.6903977394104
step: 13920, lr: 0.000871, cost: 0.9984, z_cost: 0.9960, r_cost: 0.0024, train_time_taken: 12.4413
step: 13940, lr: 0.000871, cost: 0.9985, z_cost: 0.9949, r_cost: 0.0035, train_time_taken: 11.7889
step: 13960, lr: 0.000871, cost: 0.9993, z_cost: 0.9964, r_cost: 0.0029, train_time_taken: 11.8372
preparing data for epoch 230
number of batches 61
time taken to create batches 5.3561365604400635
step: 13980, lr: 0.000871, cost: 0.9955, z_cost: 0.9933, r_cost: 0.0022, train_time_taken: 12.3842
step: 14000, lr: 0.000871, cost: 0.9996, z_cost: 0.9969, r_cost: 0.0027, train_time_taken: 11.6183
step: 14020, lr: 0.000870, cost: 0.9980, z_cost: 0.9949, r_cost: 0.0031, train_time_taken: 11.6111
preparing data for epoch 231
number of batches 61
time taken to create batches 5.8606414794921875
step: 14040, lr: 0.000870, cost: 0.9961, z_cost: 0.9935, r_cost: 0.0026, train_time_taken: 12.3160
step: 14060, lr: 0.000870, cost: 0.9966, z_cost: 0.9950, r_cost: 0.0015, train_time_taken: 11.9025
step: 14080, lr: 0.000870, cost: 0.9928, z_cost: 0.9916, r_cost: 0.0013, train_time_taken: 11.8438
preparing data for epoch 232
number of batches 61
time taken to create batches 6.520072937011719
step: 14100, lr: 0.000870, cost: 0.9949, z_cost: 0.9935, r_cost: 0.0013, train_time_taken: 12.3176
step: 14120, lr: 0.000870, cost: 0.9922, z_cost: 0.9903, r_cost: 0.0018, train_time_taken: 11.6545
step: 14140, lr: 0.000869, cost: 0.9953, z_cost: 0.9933, r_cost: 0.0020, train_time_taken: 11.6484
preparing data for epoch 233
number of batches 61
time taken to create batches 7.025856256484985
step: 14160, lr: 0.000869, cost: 0.9941, z_cost: 0.9926, r_cost: 0.0016, train_time_taken: 12.3073
step: 14180, lr: 0.000869, cost: 0.9956, z_cost: 0.9937, r_cost: 0.0019, train_time_taken: 11.8084
step: 14200, lr: 0.000869, cost: 0.9966, z_cost: 0.9945, r_cost: 0.0021, train_time_taken: 11.8482
preparing data for epoch 234
number of batches 61
time taken to create batches 7.713284969329834
step: 14220, lr: 0.000869, cost: 0.9950, z_cost: 0.9932, r_cost: 0.0018, train_time_taken: 12.3688
step: 14240, lr: 0.000869, cost: 0.9955, z_cost: 0.9931, r_cost: 0.0024, train_time_taken: 11.5886
step: 14260, lr: 0.000868, cost: 0.9933, z_cost: 0.9917, r_cost: 0.0016, train_time_taken: 11.6632
preparing data for epoch 235
number of batches 61
time taken to create batches 8.190475702285767
step: 14280, lr: 0.000868, cost: 0.9930, z_cost: 0.9913, r_cost: 0.0016, train_time_taken: 12.3017
step: 14300, lr: 0.000868, cost: 0.9951, z_cost: 0.9909, r_cost: 0.0042, train_time_taken: 11.8185
step: 14320, lr: 0.000868, cost: 0.9963, z_cost: 0.9943, r_cost: 0.0021, train_time_taken: 11.9235
preparing data for epoch 236
number of batches 61
time taken to create batches 8.961607933044434
step: 14340, lr: 0.000868, cost: 0.9974, z_cost: 0.9927, r_cost: 0.0047, train_time_taken: 12.4685
step: 14360, lr: 0.000868, cost: 0.9969, z_cost: 0.9956, r_cost: 0.0014, train_time_taken: 11.6593
step: 14380, lr: 0.000867, cost: 0.9979, z_cost: 0.9958, r_cost: 0.0021, train_time_taken: 11.6285
preparing data for epoch 237
number of batches 61
time taken to create batches 9.312479257583618
step: 14400, lr: 0.000867, cost: 0.9999, z_cost: 0.9978, r_cost: 0.0021, train_time_taken: 12.2935
step: 14420, lr: 0.000867, cost: 0.9975, z_cost: 0.9946, r_cost: 0.0029, train_time_taken: 11.8100
step: 14440, lr: 0.000867, cost: 0.9963, z_cost: 0.9932, r_cost: 0.0032, train_time_taken: 11.8005
preparing data for epoch 238
number of batches 61
time taken to create batches 10.104483366012573
step: 14460, lr: 0.000867, cost: 0.9937, z_cost: 0.9915, r_cost: 0.0022, train_time_taken: 12.4420
step: 14480, lr: 0.000867, cost: 0.9952, z_cost: 0.9935, r_cost: 0.0017, train_time_taken: 11.6254
step: 14500, lr: 0.000866, cost: 0.9974, z_cost: 0.9952, r_cost: 0.0022, train_time_taken: 11.6162
preparing data for epoch 239
number of batches 61
time taken to create batches 10.535722255706787
step: 14520, lr: 0.000866, cost: 0.9958, z_cost: 0.9923, r_cost: 0.0035, train_time_taken: 12.2768
step: 14540, lr: 0.000866, cost: 0.9925, z_cost: 0.9911, r_cost: 0.0013, train_time_taken: 11.8492
step: 14560, lr: 0.000866, cost: 0.9925, z_cost: 0.9907, r_cost: 0.0018, train_time_taken: 11.8209
preparing data for epoch 240
number of batches 61
time taken to create batches 11.247647285461426
step: 14580, lr: 0.000866, cost: 0.9955, z_cost: 0.9935, r_cost: 0.0020, train_time_taken: 12.4143
step: 14600, lr: 0.000866, cost: 0.9923, z_cost: 0.9896, r_cost: 0.0027, train_time_taken: 11.6589
step: 14620, lr: 0.000865, cost: 0.9908, z_cost: 0.9895, r_cost: 0.0013, train_time_taken: 11.6775
preparing data for epoch 241
number of batches 61
time taken to create batches 11.685043811798096
step: 14640, lr: 0.000865, cost: 1.0038, z_cost: 0.9965, r_cost: 0.0073, train_time_taken: 12.2748
step: 14660, lr: 0.000865, cost: 0.9976, z_cost: 0.9954, r_cost: 0.0022, train_time_taken: 11.8237
step: 14680, lr: 0.000865, cost: 0.9962, z_cost: 0.9925, r_cost: 0.0036, train_time_taken: 11.7900
step: 14700, lr: 0.000865, cost: 0.9965, z_cost: 0.9941, r_cost: 0.0024, train_time_taken: 11.8330
preparing data for epoch 242
number of batches 61
time taken to create batches 0.6037623882293701
step: 14720, lr: 0.000864, cost: 0.9962, z_cost: 0.9938, r_cost: 0.0024, train_time_taken: 12.2326
step: 14740, lr: 0.000864, cost: 0.9955, z_cost: 0.9932, r_cost: 0.0023, train_time_taken: 11.6548
step: 14760, lr: 0.000864, cost: 0.9931, z_cost: 0.9905, r_cost: 0.0026, train_time_taken: 11.6496
preparing data for epoch 243
number of batches 61
time taken to create batches 1.192216396331787
step: 14780, lr: 0.000864, cost: 0.9964, z_cost: 0.9931, r_cost: 0.0033, train_time_taken: 12.4145
step: 14800, lr: 0.000864, cost: 0.9930, z_cost: 0.9915, r_cost: 0.0015, train_time_taken: 11.8960
step: 14820, lr: 0.000864, cost: 0.9977, z_cost: 0.9940, r_cost: 0.0037, train_time_taken: 11.8698
preparing data for epoch 244
number of batches 61
time taken to create batches 1.789841651916504
step: 14840, lr: 0.000863, cost: 0.9917, z_cost: 0.9903, r_cost: 0.0015, train_time_taken: 12.2915
step: 14860, lr: 0.000863, cost: 0.9927, z_cost: 0.9900, r_cost: 0.0027, train_time_taken: 11.6334
step: 14880, lr: 0.000863, cost: 0.9918, z_cost: 0.9902, r_cost: 0.0016, train_time_taken: 11.6323
preparing data for epoch 245
number of batches 61
time taken to create batches 2.3373937606811523
step: 14900, lr: 0.000863, cost: 0.9934, z_cost: 0.9919, r_cost: 0.0015, train_time_taken: 12.4102
step: 14920, lr: 0.000863, cost: 0.9903, z_cost: 0.9890, r_cost: 0.0012, train_time_taken: 11.8754
step: 14940, lr: 0.000863, cost: 0.9934, z_cost: 0.9917, r_cost: 0.0017, train_time_taken: 11.9220
preparing data for epoch 246
number of batches 61
time taken to create batches 2.973095417022705
step: 14960, lr: 0.000862, cost: 0.9948, z_cost: 0.9919, r_cost: 0.0029, train_time_taken: 12.3128
step: 14980, lr: 0.000862, cost: 0.9929, z_cost: 0.9900, r_cost: 0.0029, train_time_taken: 11.6290
step: 15000, lr: 0.000862, cost: 0.9938, z_cost: 0.9916, r_cost: 0.0022, train_time_taken: 11.5848
preparing data for epoch 247
number of batches 61
time taken to create batches 3.4995250701904297
step: 15020, lr: 0.000862, cost: 0.9932, z_cost: 0.9905, r_cost: 0.0026, train_time_taken: 12.3498
step: 15040, lr: 0.000862, cost: 0.9929, z_cost: 0.9902, r_cost: 0.0027, train_time_taken: 11.8101
step: 15060, lr: 0.000862, cost: 0.9896, z_cost: 0.9885, r_cost: 0.0012, train_time_taken: 11.8548
preparing data for epoch 248
number of batches 61
time taken to create batches 4.161082029342651
step: 15080, lr: 0.000861, cost: 0.9928, z_cost: 0.9906, r_cost: 0.0022, train_time_taken: 12.3247
step: 15100, lr: 0.000861, cost: 0.9938, z_cost: 0.9916, r_cost: 0.0022, train_time_taken: 11.6013
step: 15120, lr: 0.000861, cost: 0.9944, z_cost: 0.9926, r_cost: 0.0018, train_time_taken: 11.6480
preparing data for epoch 249
number of batches 61
time taken to create batches 4.634283542633057
step: 15140, lr: 0.000861, cost: 0.9923, z_cost: 0.9910, r_cost: 0.0013, train_time_taken: 12.3203
step: 15160, lr: 0.000861, cost: 0.9901, z_cost: 0.9890, r_cost: 0.0011, train_time_taken: 11.9567
step: 15180, lr: 0.000861, cost: 0.9937, z_cost: 0.9920, r_cost: 0.0017, train_time_taken: 11.7666
preparing data for epoch 250
number of batches 61
time taken to create batches 5.342019319534302
step: 15200, lr: 0.000860, cost: 0.9896, z_cost: 0.9885, r_cost: 0.0011, train_time_taken: 12.3418
step: 15220, lr: 0.000860, cost: 0.9950, z_cost: 0.9933, r_cost: 0.0017, train_time_taken: 11.6579
step: 15240, lr: 0.000860, cost: 0.9942, z_cost: 0.9926, r_cost: 0.0016, train_time_taken: 11.6611
preparing data for epoch 251
number of batches 61
time taken to create batches 5.817572116851807
step: 15260, lr: 0.000860, cost: 0.9925, z_cost: 0.9908, r_cost: 0.0016, train_time_taken: 12.2886
step: 15280, lr: 0.000860, cost: 0.9950, z_cost: 0.9937, r_cost: 0.0013, train_time_taken: 11.8427
step: 15300, lr: 0.000860, cost: 0.9944, z_cost: 0.9919, r_cost: 0.0025, train_time_taken: 11.8141
preparing data for epoch 252
number of batches 61
time taken to create batches 6.5520758628845215
step: 15320, lr: 0.000859, cost: 0.9940, z_cost: 0.9923, r_cost: 0.0017, train_time_taken: 12.3848
step: 15340, lr: 0.000859, cost: 0.9928, z_cost: 0.9916, r_cost: 0.0012, train_time_taken: 11.6361
step: 15360, lr: 0.000859, cost: 0.9968, z_cost: 0.9941, r_cost: 0.0028, train_time_taken: 11.6202
preparing data for epoch 253
number of batches 61
time taken to create batches 6.9772114753723145
step: 15380, lr: 0.000859, cost: 0.9948, z_cost: 0.9934, r_cost: 0.0014, train_time_taken: 12.3369
step: 15400, lr: 0.000859, cost: 0.9945, z_cost: 0.9929, r_cost: 0.0016, train_time_taken: 11.8936
step: 15420, lr: 0.000859, cost: 0.9915, z_cost: 0.9900, r_cost: 0.0015, train_time_taken: 11.8273
preparing data for epoch 254
number of batches 61
time taken to create batches 7.724590539932251
step: 15440, lr: 0.000858, cost: 0.9939, z_cost: 0.9909, r_cost: 0.0031, train_time_taken: 12.4053
step: 15460, lr: 0.000858, cost: 0.9937, z_cost: 0.9911, r_cost: 0.0026, train_time_taken: 11.6428
step: 15480, lr: 0.000858, cost: 0.9935, z_cost: 0.9920, r_cost: 0.0014, train_time_taken: 11.6561
preparing data for epoch 255
number of batches 61
time taken to create batches 8.194349527359009
step: 15500, lr: 0.000858, cost: 0.9926, z_cost: 0.9900, r_cost: 0.0026, train_time_taken: 12.3204
step: 15520, lr: 0.000858, cost: 0.9954, z_cost: 0.9933, r_cost: 0.0020, train_time_taken: 11.8218
step: 15540, lr: 0.000858, cost: 0.9923, z_cost: 0.9903, r_cost: 0.0020, train_time_taken: 11.8164
preparing data for epoch 256
number of batches 61
time taken to create batches 8.88496470451355
step: 15560, lr: 0.000857, cost: 0.9933, z_cost: 0.9912, r_cost: 0.0020, train_time_taken: 12.3607
step: 15580, lr: 0.000857, cost: 0.9896, z_cost: 0.9878, r_cost: 0.0017, train_time_taken: 11.6509
step: 15600, lr: 0.000857, cost: 0.9950, z_cost: 0.9919, r_cost: 0.0030, train_time_taken: 11.6257
preparing data for epoch 257
number of batches 61
time taken to create batches 9.289979696273804
step: 15620, lr: 0.000857, cost: 0.9922, z_cost: 0.9903, r_cost: 0.0019, train_time_taken: 12.2335
step: 15640, lr: 0.000857, cost: 0.9921, z_cost: 0.9904, r_cost: 0.0017, train_time_taken: 11.8230
step: 15660, lr: 0.000856, cost: 0.9924, z_cost: 0.9909, r_cost: 0.0015, train_time_taken: 11.8519
preparing data for epoch 258
number of batches 61
time taken to create batches 10.090146541595459
step: 15680, lr: 0.000856, cost: 0.9950, z_cost: 0.9936, r_cost: 0.0013, train_time_taken: 12.4118
step: 15700, lr: 0.000856, cost: 0.9915, z_cost: 0.9901, r_cost: 0.0014, train_time_taken: 11.6254
step: 15720, lr: 0.000856, cost: 0.9929, z_cost: 0.9910, r_cost: 0.0019, train_time_taken: 11.6431
preparing data for epoch 259
number of batches 61
time taken to create batches 10.508017539978027
step: 15740, lr: 0.000856, cost: 0.9920, z_cost: 0.9895, r_cost: 0.0026, train_time_taken: 12.2589
step: 15760, lr: 0.000856, cost: 0.9951, z_cost: 0.9924, r_cost: 0.0026, train_time_taken: 11.8868
step: 15780, lr: 0.000855, cost: 0.9901, z_cost: 0.9890, r_cost: 0.0011, train_time_taken: 11.8647
preparing data for epoch 260
number of batches 61
time taken to create batches 11.32578992843628
step: 15800, lr: 0.000855, cost: 0.9931, z_cost: 0.9917, r_cost: 0.0014, train_time_taken: 12.5080
step: 15820, lr: 0.000855, cost: 0.9916, z_cost: 0.9898, r_cost: 0.0018, train_time_taken: 11.6416
step: 15840, lr: 0.000855, cost: 0.9943, z_cost: 0.9923, r_cost: 0.0020, train_time_taken: 11.7473
preparing data for epoch 261
number of batches 61
time taken to create batches 11.76132869720459
step: 15860, lr: 0.000855, cost: 1.0005, z_cost: 0.9916, r_cost: 0.0089, train_time_taken: 12.3493
step: 15880, lr: 0.000855, cost: 0.9928, z_cost: 0.9903, r_cost: 0.0024, train_time_taken: 11.9837
step: 15900, lr: 0.000854, cost: 0.9923, z_cost: 0.9890, r_cost: 0.0033, train_time_taken: 11.8383
step: 15920, lr: 0.000854, cost: 0.9947, z_cost: 0.9920, r_cost: 0.0027, train_time_taken: 11.8395
preparing data for epoch 262
number of batches 61
time taken to create batches 0.6122398376464844
step: 15940, lr: 0.000854, cost: 0.9921, z_cost: 0.9906, r_cost: 0.0015, train_time_taken: 12.3307
step: 15960, lr: 0.000854, cost: 0.9939, z_cost: 0.9913, r_cost: 0.0026, train_time_taken: 11.6763
step: 15980, lr: 0.000854, cost: 0.9889, z_cost: 0.9867, r_cost: 0.0023, train_time_taken: 11.7612
preparing data for epoch 263
number of batches 61
time taken to create batches 1.1950523853302002
step: 16000, lr: 0.000854, cost: 0.9963, z_cost: 0.9936, r_cost: 0.0027, train_time_taken: 12.5253
step: 16020, lr: 0.000853, cost: 0.9928, z_cost: 0.9912, r_cost: 0.0016, train_time_taken: 11.8677
step: 16040, lr: 0.000853, cost: 0.9924, z_cost: 0.9898, r_cost: 0.0026, train_time_taken: 11.8922
preparing data for epoch 264
number of batches 61
time taken to create batches 1.8035805225372314
step: 16060, lr: 0.000853, cost: 0.9884, z_cost: 0.9863, r_cost: 0.0021, train_time_taken: 12.3277
step: 16080, lr: 0.000853, cost: 0.9928, z_cost: 0.9901, r_cost: 0.0027, train_time_taken: 11.7129
step: 16100, lr: 0.000853, cost: 0.9896, z_cost: 0.9876, r_cost: 0.0020, train_time_taken: 11.6829
preparing data for epoch 265
number of batches 61
time taken to create batches 2.372570514678955
step: 16120, lr: 0.000853, cost: 0.9926, z_cost: 0.9911, r_cost: 0.0015, train_time_taken: 12.4585
step: 16140, lr: 0.000852, cost: 0.9926, z_cost: 0.9899, r_cost: 0.0026, train_time_taken: 11.9232
step: 16160, lr: 0.000852, cost: 0.9932, z_cost: 0.9908, r_cost: 0.0024, train_time_taken: 11.8697
preparing data for epoch 266
number of batches 61
time taken to create batches 2.9784438610076904
step: 16180, lr: 0.000852, cost: 0.9944, z_cost: 0.9921, r_cost: 0.0023, train_time_taken: 12.3248
step: 16200, lr: 0.000852, cost: 0.9903, z_cost: 0.9884, r_cost: 0.0019, train_time_taken: 11.6907
step: 16220, lr: 0.000852, cost: 0.9937, z_cost: 0.9914, r_cost: 0.0023, train_time_taken: 11.6445
preparing data for epoch 267
number of batches 61
time taken to create batches 3.5186257362365723
step: 16240, lr: 0.000852, cost: 0.9907, z_cost: 0.9897, r_cost: 0.0011, train_time_taken: 12.3882
step: 16260, lr: 0.000851, cost: 0.9925, z_cost: 0.9887, r_cost: 0.0038, train_time_taken: 11.8786
step: 16280, lr: 0.000851, cost: 0.9911, z_cost: 0.9889, r_cost: 0.0022, train_time_taken: 11.9028
preparing data for epoch 268
number of batches 61
time taken to create batches 4.191401720046997
step: 16300, lr: 0.000851, cost: 0.9906, z_cost: 0.9889, r_cost: 0.0016, train_time_taken: 12.4133
step: 16320, lr: 0.000851, cost: 0.9905, z_cost: 0.9889, r_cost: 0.0016, train_time_taken: 11.7022
step: 16340, lr: 0.000851, cost: 0.9904, z_cost: 0.9874, r_cost: 0.0030, train_time_taken: 11.6380
preparing data for epoch 269
number of batches 61
time taken to create batches 4.70963716506958
step: 16360, lr: 0.000851, cost: 0.9910, z_cost: 0.9892, r_cost: 0.0018, train_time_taken: 12.4527
step: 16380, lr: 0.000850, cost: 0.9935, z_cost: 0.9917, r_cost: 0.0018, train_time_taken: 11.8381
step: 16400, lr: 0.000850, cost: 0.9949, z_cost: 0.9925, r_cost: 0.0024, train_time_taken: 11.8963
preparing data for epoch 270
number of batches 61
time taken to create batches 5.377029180526733
step: 16420, lr: 0.000850, cost: 0.9899, z_cost: 0.9880, r_cost: 0.0019, train_time_taken: 12.4186
step: 16440, lr: 0.000850, cost: 0.9883, z_cost: 0.9870, r_cost: 0.0013, train_time_taken: 11.6725
step: 16460, lr: 0.000850, cost: 0.9919, z_cost: 0.9886, r_cost: 0.0033, train_time_taken: 11.7020
preparing data for epoch 271
number of batches 61
time taken to create batches 5.903912782669067
step: 16480, lr: 0.000850, cost: 0.9935, z_cost: 0.9904, r_cost: 0.0030, train_time_taken: 12.4284
step: 16500, lr: 0.000849, cost: 0.9867, z_cost: 0.9839, r_cost: 0.0029, train_time_taken: 11.8595
step: 16520, lr: 0.000849, cost: 0.9911, z_cost: 0.9882, r_cost: 0.0029, train_time_taken: 11.8836
preparing data for epoch 272
number of batches 61
time taken to create batches 6.550426959991455
step: 16540, lr: 0.000849, cost: 0.9999, z_cost: 0.9963, r_cost: 0.0036, train_time_taken: 12.3722
step: 16560, lr: 0.000849, cost: 1.0010, z_cost: 0.9983, r_cost: 0.0027, train_time_taken: 11.6864
step: 16580, lr: 0.000849, cost: 0.9953, z_cost: 0.9922, r_cost: 0.0031, train_time_taken: 11.6537
preparing data for epoch 273
number of batches 61
time taken to create batches 7.065083265304565
step: 16600, lr: 0.000849, cost: 0.9935, z_cost: 0.9904, r_cost: 0.0031, train_time_taken: 12.4180
step: 16620, lr: 0.000848, cost: 0.9929, z_cost: 0.9906, r_cost: 0.0022, train_time_taken: 11.8288
step: 16640, lr: 0.000848, cost: 0.9925, z_cost: 0.9898, r_cost: 0.0027, train_time_taken: 11.8370
preparing data for epoch 274
number of batches 61
time taken to create batches 7.740859746932983
step: 16660, lr: 0.000848, cost: 0.9935, z_cost: 0.9889, r_cost: 0.0046, train_time_taken: 12.4040
step: 16680, lr: 0.000848, cost: 0.9931, z_cost: 0.9913, r_cost: 0.0018, train_time_taken: 11.6982
step: 16700, lr: 0.000848, cost: 0.9941, z_cost: 0.9911, r_cost: 0.0030, train_time_taken: 11.6856
preparing data for epoch 275
number of batches 61
time taken to create batches 8.159424781799316
step: 16720, lr: 0.000848, cost: 0.9911, z_cost: 0.9890, r_cost: 0.0021, train_time_taken: 12.2971
step: 16740, lr: 0.000847, cost: 0.9921, z_cost: 0.9899, r_cost: 0.0022, train_time_taken: 11.9046
step: 16760, lr: 0.000847, cost: 0.9925, z_cost: 0.9903, r_cost: 0.0022, train_time_taken: 11.8477
preparing data for epoch 276
number of batches 61
time taken to create batches 9.162927627563477
step: 16780, lr: 0.000847, cost: 0.9911, z_cost: 0.9897, r_cost: 0.0014, train_time_taken: 12.6813
step: 16800, lr: 0.000847, cost: 0.9897, z_cost: 0.9877, r_cost: 0.0019, train_time_taken: 11.7118
step: 16820, lr: 0.000847, cost: 0.9898, z_cost: 0.9876, r_cost: 0.0022, train_time_taken: 11.7175
preparing data for epoch 277
number of batches 61
time taken to create batches 9.487334728240967
step: 16840, lr: 0.000847, cost: 0.9915, z_cost: 0.9882, r_cost: 0.0033, train_time_taken: 12.4611
step: 16860, lr: 0.000846, cost: 0.9921, z_cost: 0.9909, r_cost: 0.0012, train_time_taken: 11.8656
step: 16880, lr: 0.000846, cost: 0.9931, z_cost: 0.9916, r_cost: 0.0015, train_time_taken: 11.8564
preparing data for epoch 278
number of batches 61
time taken to create batches 10.122929811477661
step: 16900, lr: 0.000846, cost: 0.9912, z_cost: 0.9899, r_cost: 0.0014, train_time_taken: 12.4681
step: 16920, lr: 0.000846, cost: 0.9914, z_cost: 0.9903, r_cost: 0.0010, train_time_taken: 11.6371
step: 16940, lr: 0.000846, cost: 0.9917, z_cost: 0.9901, r_cost: 0.0017, train_time_taken: 11.7024
preparing data for epoch 279
number of batches 61
time taken to create batches 10.510354042053223
step: 16960, lr: 0.000846, cost: 0.9916, z_cost: 0.9900, r_cost: 0.0016, train_time_taken: 12.2865
step: 16980, lr: 0.000845, cost: 0.9913, z_cost: 0.9898, r_cost: 0.0016, train_time_taken: 11.8931
step: 17000, lr: 0.000845, cost: 0.9903, z_cost: 0.9884, r_cost: 0.0019, train_time_taken: 11.8706
preparing data for epoch 280
number of batches 61
time taken to create batches 11.278938293457031
step: 17020, lr: 0.000845, cost: 0.9916, z_cost: 0.9899, r_cost: 0.0018, train_time_taken: 12.4507
step: 17040, lr: 0.000845, cost: 0.9906, z_cost: 0.9886, r_cost: 0.0020, train_time_taken: 11.6179
step: 17060, lr: 0.000845, cost: 0.9926, z_cost: 0.9904, r_cost: 0.0023, train_time_taken: 11.6799
preparing data for epoch 281
number of batches 61
time taken to create batches 11.738720417022705
step: 17080, lr: 0.000845, cost: 0.9992, z_cost: 0.9916, r_cost: 0.0076, train_time_taken: 12.3410
step: 17100, lr: 0.000844, cost: 0.9900, z_cost: 0.9877, r_cost: 0.0023, train_time_taken: 11.8879
step: 17120, lr: 0.000844, cost: 0.9895, z_cost: 0.9883, r_cost: 0.0012, train_time_taken: 11.8385
step: 17140, lr: 0.000844, cost: 0.9925, z_cost: 0.9902, r_cost: 0.0023, train_time_taken: 11.8457
preparing data for epoch 282
number of batches 61
time taken to create batches 0.606576681137085
step: 17160, lr: 0.000844, cost: 0.9891, z_cost: 0.9879, r_cost: 0.0012, train_time_taken: 12.3142
step: 17180, lr: 0.000844, cost: 0.9901, z_cost: 0.9887, r_cost: 0.0015, train_time_taken: 11.6676
step: 17200, lr: 0.000844, cost: 0.9882, z_cost: 0.9870, r_cost: 0.0011, train_time_taken: 11.6763
preparing data for epoch 283
number of batches 61
time taken to create batches 1.1915555000305176
step: 17220, lr: 0.000843, cost: 0.9885, z_cost: 0.9872, r_cost: 0.0014, train_time_taken: 12.5132
step: 17240, lr: 0.000843, cost: 0.9898, z_cost: 0.9884, r_cost: 0.0014, train_time_taken: 11.8440
step: 17260, lr: 0.000843, cost: 0.9902, z_cost: 0.9883, r_cost: 0.0019, train_time_taken: 11.8217
preparing data for epoch 284
number of batches 61
time taken to create batches 1.7918083667755127
step: 17280, lr: 0.000843, cost: 0.9911, z_cost: 0.9900, r_cost: 0.0011, train_time_taken: 12.2885
step: 17300, lr: 0.000843, cost: 0.9923, z_cost: 0.9909, r_cost: 0.0014, train_time_taken: 11.6955
step: 17320, lr: 0.000843, cost: 0.9880, z_cost: 0.9868, r_cost: 0.0012, train_time_taken: 11.6517
preparing data for epoch 285
number of batches 61
time taken to create batches 2.335381031036377
step: 17340, lr: 0.000842, cost: 0.9872, z_cost: 0.9849, r_cost: 0.0023, train_time_taken: 12.4356
step: 17360, lr: 0.000842, cost: 0.9862, z_cost: 0.9848, r_cost: 0.0014, train_time_taken: 11.8798
step: 17380, lr: 0.000842, cost: 0.9910, z_cost: 0.9863, r_cost: 0.0046, train_time_taken: 11.8923
preparing data for epoch 286
number of batches 61
time taken to create batches 2.9907524585723877
step: 17400, lr: 0.000842, cost: 0.9912, z_cost: 0.9899, r_cost: 0.0012, train_time_taken: 12.3521
step: 17420, lr: 0.000842, cost: 0.9902, z_cost: 0.9868, r_cost: 0.0034, train_time_taken: 11.7121
step: 17440, lr: 0.000842, cost: 0.9885, z_cost: 0.9875, r_cost: 0.0010, train_time_taken: 11.7108
preparing data for epoch 287
number of batches 61
time taken to create batches 3.549682855606079
step: 17460, lr: 0.000841, cost: 0.9900, z_cost: 0.9883, r_cost: 0.0017, train_time_taken: 12.4370
step: 17480, lr: 0.000841, cost: 0.9846, z_cost: 0.9831, r_cost: 0.0015, train_time_taken: 11.8626
step: 17500, lr: 0.000841, cost: 0.9898, z_cost: 0.9883, r_cost: 0.0015, train_time_taken: 11.8883
preparing data for epoch 288
number of batches 61
time taken to create batches 4.161847829818726
step: 17520, lr: 0.000841, cost: 0.9905, z_cost: 0.9886, r_cost: 0.0018, train_time_taken: 12.3518
step: 17540, lr: 0.000841, cost: 0.9886, z_cost: 0.9873, r_cost: 0.0014, train_time_taken: 11.6547
step: 17560, lr: 0.000841, cost: 0.9884, z_cost: 0.9872, r_cost: 0.0012, train_time_taken: 11.6396
preparing data for epoch 289
number of batches 61
time taken to create batches 4.700049877166748
step: 17580, lr: 0.000840, cost: 0.9897, z_cost: 0.9873, r_cost: 0.0024, train_time_taken: 12.4169
step: 17600, lr: 0.000840, cost: 0.9919, z_cost: 0.9903, r_cost: 0.0016, train_time_taken: 11.8947
step: 17620, lr: 0.000840, cost: 0.9937, z_cost: 0.9907, r_cost: 0.0029, train_time_taken: 11.8883
preparing data for epoch 290
number of batches 61
time taken to create batches 5.387031078338623
step: 17640, lr: 0.000840, cost: 0.9912, z_cost: 0.9892, r_cost: 0.0020, train_time_taken: 12.3555
step: 17660, lr: 0.000840, cost: 0.9898, z_cost: 0.9873, r_cost: 0.0025, train_time_taken: 11.7007
step: 17680, lr: 0.000840, cost: 0.9889, z_cost: 0.9876, r_cost: 0.0013, train_time_taken: 11.6989
preparing data for epoch 291
number of batches 61
time taken to create batches 5.8561859130859375
step: 17700, lr: 0.000839, cost: 0.9909, z_cost: 0.9889, r_cost: 0.0020, train_time_taken: 12.3928
step: 17720, lr: 0.000839, cost: 0.9857, z_cost: 0.9846, r_cost: 0.0011, train_time_taken: 11.9185
step: 17740, lr: 0.000839, cost: 0.9879, z_cost: 0.9849, r_cost: 0.0030, train_time_taken: 11.9437
preparing data for epoch 292
number of batches 61
time taken to create batches 6.520692348480225
step: 17760, lr: 0.000839, cost: 0.9850, z_cost: 0.9836, r_cost: 0.0014, train_time_taken: 12.3860
step: 17780, lr: 0.000839, cost: 0.9897, z_cost: 0.9882, r_cost: 0.0015, train_time_taken: 11.7023
step: 17800, lr: 0.000839, cost: 0.9902, z_cost: 0.9871, r_cost: 0.0031, train_time_taken: 11.7234
preparing data for epoch 293
number of batches 61
time taken to create batches 7.051143646240234
step: 17820, lr: 0.000838, cost: 0.9872, z_cost: 0.9858, r_cost: 0.0013, train_time_taken: 12.4076
step: 17840, lr: 0.000838, cost: 0.9898, z_cost: 0.9887, r_cost: 0.0011, train_time_taken: 11.8804
step: 17860, lr: 0.000838, cost: 0.9913, z_cost: 0.9879, r_cost: 0.0033, train_time_taken: 11.8994
preparing data for epoch 294
number of batches 61
time taken to create batches 7.704822301864624
step: 17880, lr: 0.000838, cost: 0.9900, z_cost: 0.9880, r_cost: 0.0020, train_time_taken: 12.3438
step: 17900, lr: 0.000838, cost: 0.9882, z_cost: 0.9864, r_cost: 0.0017, train_time_taken: 11.6455
step: 17920, lr: 0.000838, cost: 0.9884, z_cost: 0.9868, r_cost: 0.0016, train_time_taken: 11.6741
preparing data for epoch 295
number of batches 61
time taken to create batches 8.193936586380005
step: 17940, lr: 0.000837, cost: 0.9896, z_cost: 0.9869, r_cost: 0.0027, train_time_taken: 12.3458
step: 17960, lr: 0.000837, cost: 0.9883, z_cost: 0.9868, r_cost: 0.0015, train_time_taken: 11.9345
step: 17980, lr: 0.000837, cost: 0.9913, z_cost: 0.9901, r_cost: 0.0012, train_time_taken: 11.9520
preparing data for epoch 296
number of batches 61
time taken to create batches 8.924809455871582
step: 18000, lr: 0.000837, cost: 0.9894, z_cost: 0.9883, r_cost: 0.0011, train_time_taken: 12.4378
step: 18020, lr: 0.000837, cost: 0.9886, z_cost: 0.9875, r_cost: 0.0012, train_time_taken: 11.7009
step: 18040, lr: 0.000837, cost: 0.9893, z_cost: 0.9870, r_cost: 0.0023, train_time_taken: 11.7272
preparing data for epoch 297
number of batches 61
time taken to create batches 9.408047437667847
step: 18060, lr: 0.000836, cost: 0.9858, z_cost: 0.9847, r_cost: 0.0011, train_time_taken: 12.3984
step: 18080, lr: 0.000836, cost: 0.9881, z_cost: 0.9868, r_cost: 0.0013, train_time_taken: 11.9072
step: 18100, lr: 0.000836, cost: 0.9879, z_cost: 0.9859, r_cost: 0.0019, train_time_taken: 11.8619
preparing data for epoch 298
number of batches 61
time taken to create batches 10.131187200546265
step: 18120, lr: 0.000836, cost: 0.9875, z_cost: 0.9862, r_cost: 0.0013, train_time_taken: 12.4677
step: 18140, lr: 0.000836, cost: 0.9860, z_cost: 0.9842, r_cost: 0.0018, train_time_taken: 11.7905
step: 18160, lr: 0.000836, cost: 0.9875, z_cost: 0.9863, r_cost: 0.0012, train_time_taken: 11.7288
preparing data for epoch 299
number of batches 61
time taken to create batches 10.542558670043945
step: 18180, lr: 0.000835, cost: 0.9887, z_cost: 0.9876, r_cost: 0.0011, train_time_taken: 12.3149
step: 18200, lr: 0.000835, cost: 0.9887, z_cost: 0.9862, r_cost: 0.0026, train_time_taken: 11.8512
step: 18220, lr: 0.000835, cost: 0.9865, z_cost: 0.9857, r_cost: 0.0008, train_time_taken: 11.9459
preparing data for epoch 300
number of batches 61
time taken to create batches 11.311485290527344
step: 18240, lr: 0.000835, cost: 0.9885, z_cost: 0.9863, r_cost: 0.0021, train_time_taken: 12.4787
step: 18260, lr: 0.000835, cost: 0.9881, z_cost: 0.9870, r_cost: 0.0011, train_time_taken: 11.6587
step: 18280, lr: 0.000835, cost: 0.9860, z_cost: 0.9839, r_cost: 0.0021, train_time_taken: 11.6857
preparing data for epoch 301
number of batches 61
time taken to create batches 11.67967963218689
step: 18300, lr: 0.000834, cost: 0.9968, z_cost: 0.9877, r_cost: 0.0091, train_time_taken: 12.2670
step: 18320, lr: 0.000834, cost: 0.9935, z_cost: 0.9898, r_cost: 0.0036, train_time_taken: 11.9249
step: 18340, lr: 0.000834, cost: 0.9880, z_cost: 0.9868, r_cost: 0.0012, train_time_taken: 11.8952
step: 18360, lr: 0.000834, cost: 0.9915, z_cost: 0.9893, r_cost: 0.0022, train_time_taken: 11.8892
preparing data for epoch 302
number of batches 61
time taken to create batches 0.6045763492584229
step: 18380, lr: 0.000834, cost: 0.9877, z_cost: 0.9855, r_cost: 0.0023, train_time_taken: 12.2863
step: 18400, lr: 0.000834, cost: 0.9878, z_cost: 0.9856, r_cost: 0.0022, train_time_taken: 11.7076
step: 18420, lr: 0.000833, cost: 0.9869, z_cost: 0.9854, r_cost: 0.0015, train_time_taken: 11.6538
preparing data for epoch 303
number of batches 61
time taken to create batches 1.1818947792053223
step: 18440, lr: 0.000833, cost: 0.9903, z_cost: 0.9882, r_cost: 0.0021, train_time_taken: 12.4599
step: 18460, lr: 0.000833, cost: 0.9882, z_cost: 0.9861, r_cost: 0.0021, train_time_taken: 11.9006
step: 18480, lr: 0.000833, cost: 0.9904, z_cost: 0.9881, r_cost: 0.0023, train_time_taken: 11.9008
preparing data for epoch 304
number of batches 61
time taken to create batches 1.8081762790679932
step: 18500, lr: 0.000833, cost: 0.9885, z_cost: 0.9873, r_cost: 0.0012, train_time_taken: 12.3770
step: 18520, lr: 0.000833, cost: 0.9874, z_cost: 0.9860, r_cost: 0.0015, train_time_taken: 11.7452
step: 18540, lr: 0.000832, cost: 0.9891, z_cost: 0.9879, r_cost: 0.0012, train_time_taken: 11.7445
preparing data for epoch 305
number of batches 61
time taken to create batches 2.357088804244995
step: 18560, lr: 0.000832, cost: 0.9879, z_cost: 0.9856, r_cost: 0.0022, train_time_taken: 12.5093
step: 18580, lr: 0.000832, cost: 0.9917, z_cost: 0.9907, r_cost: 0.0010, train_time_taken: 11.9225
step: 18600, lr: 0.000832, cost: 0.9897, z_cost: 0.9873, r_cost: 0.0024, train_time_taken: 11.9342
preparing data for epoch 306
number of batches 61
time taken to create batches 2.9986305236816406
step: 18620, lr: 0.000832, cost: 0.9907, z_cost: 0.9890, r_cost: 0.0017, train_time_taken: 12.3630
step: 18640, lr: 0.000832, cost: 0.9880, z_cost: 0.9859, r_cost: 0.0021, train_time_taken: 11.7115
step: 18660, lr: 0.000831, cost: 0.9869, z_cost: 0.9855, r_cost: 0.0013, train_time_taken: 11.6919
preparing data for epoch 307
number of batches 61
time taken to create batches 3.5353941917419434
step: 18680, lr: 0.000831, cost: 0.9909, z_cost: 0.9896, r_cost: 0.0014, train_time_taken: 12.4437
step: 18700, lr: 0.000831, cost: 0.9886, z_cost: 0.9870, r_cost: 0.0016, train_time_taken: 11.9306
step: 18720, lr: 0.000831, cost: 0.9883, z_cost: 0.9851, r_cost: 0.0031, train_time_taken: 11.9180
preparing data for epoch 308
number of batches 61
time taken to create batches 4.191442966461182
step: 18740, lr: 0.000831, cost: 0.9902, z_cost: 0.9890, r_cost: 0.0012, train_time_taken: 12.3666
step: 18760, lr: 0.000831, cost: 0.9884, z_cost: 0.9867, r_cost: 0.0017, train_time_taken: 11.7485
step: 18780, lr: 0.000830, cost: 0.9863, z_cost: 0.9851, r_cost: 0.0013, train_time_taken: 11.6628
preparing data for epoch 309
number of batches 61
time taken to create batches 4.660548448562622
step: 18800, lr: 0.000830, cost: 0.9928, z_cost: 0.9882, r_cost: 0.0046, train_time_taken: 12.3815
step: 18820, lr: 0.000830, cost: 0.9867, z_cost: 0.9841, r_cost: 0.0026, train_time_taken: 11.8660
step: 18840, lr: 0.000830, cost: 0.9896, z_cost: 0.9882, r_cost: 0.0014, train_time_taken: 11.8864
preparing data for epoch 310
number of batches 61
time taken to create batches 5.391284465789795
step: 18860, lr: 0.000830, cost: 0.9863, z_cost: 0.9856, r_cost: 0.0007, train_time_taken: 12.4145
step: 18880, lr: 0.000830, cost: 0.9840, z_cost: 0.9829, r_cost: 0.0011, train_time_taken: 11.6542
step: 18900, lr: 0.000830, cost: 0.9874, z_cost: 0.9863, r_cost: 0.0011, train_time_taken: 11.6895
preparing data for epoch 311
number of batches 61
time taken to create batches 5.8983542919158936
step: 18920, lr: 0.000829, cost: 0.9872, z_cost: 0.9856, r_cost: 0.0016, train_time_taken: 12.4452
step: 18940, lr: 0.000829, cost: 0.9841, z_cost: 0.9831, r_cost: 0.0010, train_time_taken: 11.9135
step: 18960, lr: 0.000829, cost: 0.9898, z_cost: 0.9877, r_cost: 0.0020, train_time_taken: 11.9230
preparing data for epoch 312
number of batches 61
time taken to create batches 6.562680721282959
step: 18980, lr: 0.000829, cost: 0.9859, z_cost: 0.9840, r_cost: 0.0019, train_time_taken: 12.4469
step: 19000, lr: 0.000829, cost: 0.9851, z_cost: 0.9837, r_cost: 0.0014, train_time_taken: 11.7183
step: 19020, lr: 0.000829, cost: 0.9867, z_cost: 0.9852, r_cost: 0.0014, train_time_taken: 11.7105
preparing data for epoch 313
number of batches 61
time taken to create batches 7.0321290493011475
step: 19040, lr: 0.000828, cost: 0.9857, z_cost: 0.9848, r_cost: 0.0009, train_time_taken: 12.3654
step: 19060, lr: 0.000828, cost: 0.9851, z_cost: 0.9838, r_cost: 0.0013, train_time_taken: 11.9148
step: 19080, lr: 0.000828, cost: 0.9854, z_cost: 0.9844, r_cost: 0.0010, train_time_taken: 11.9219
preparing data for epoch 314
number of batches 61
time taken to create batches 7.765607595443726
step: 19100, lr: 0.000828, cost: 0.9868, z_cost: 0.9858, r_cost: 0.0010, train_time_taken: 12.4420
step: 19120, lr: 0.000828, cost: 0.9865, z_cost: 0.9857, r_cost: 0.0009, train_time_taken: 11.6562
step: 19140, lr: 0.000828, cost: 0.9836, z_cost: 0.9830, r_cost: 0.0007, train_time_taken: 11.6586
preparing data for epoch 315
number of batches 61
time taken to create batches 8.187822818756104
step: 19160, lr: 0.000827, cost: 0.9858, z_cost: 0.9835, r_cost: 0.0023, train_time_taken: 12.3259
step: 19180, lr: 0.000827, cost: 0.9871, z_cost: 0.9857, r_cost: 0.0014, train_time_taken: 11.8504
step: 19200, lr: 0.000827, cost: 0.9844, z_cost: 0.9830, r_cost: 0.0014, train_time_taken: 11.8282
preparing data for epoch 316
number of batches 61
time taken to create batches 8.946260929107666
step: 19220, lr: 0.000827, cost: 0.9863, z_cost: 0.9853, r_cost: 0.0009, train_time_taken: 12.4304
step: 19240, lr: 0.000827, cost: 0.9915, z_cost: 0.9901, r_cost: 0.0015, train_time_taken: 11.6545
step: 19260, lr: 0.000827, cost: 0.9903, z_cost: 0.9884, r_cost: 0.0020, train_time_taken: 11.7360
preparing data for epoch 317
number of batches 61
time taken to create batches 9.428310871124268
step: 19280, lr: 0.000826, cost: 0.9870, z_cost: 0.9853, r_cost: 0.0017, train_time_taken: 12.4003
step: 19300, lr: 0.000826, cost: 0.9859, z_cost: 0.9842, r_cost: 0.0017, train_time_taken: 11.8648
step: 19320, lr: 0.000826, cost: 0.9896, z_cost: 0.9871, r_cost: 0.0025, train_time_taken: 11.9084
preparing data for epoch 318
number of batches 61
time taken to create batches 10.134018898010254
step: 19340, lr: 0.000826, cost: 0.9871, z_cost: 0.9845, r_cost: 0.0026, train_time_taken: 12.4678
step: 19360, lr: 0.000826, cost: 0.9876, z_cost: 0.9862, r_cost: 0.0014, train_time_taken: 11.6866
step: 19380, lr: 0.000826, cost: 0.9892, z_cost: 0.9861, r_cost: 0.0031, train_time_taken: 11.6832
preparing data for epoch 319
number of batches 61
time taken to create batches 10.567818880081177
step: 19400, lr: 0.000825, cost: 0.9871, z_cost: 0.9861, r_cost: 0.0010, train_time_taken: 12.3317
step: 19420, lr: 0.000825, cost: 0.9856, z_cost: 0.9843, r_cost: 0.0013, train_time_taken: 11.9072
step: 19440, lr: 0.000825, cost: 0.9858, z_cost: 0.9850, r_cost: 0.0008, train_time_taken: 11.8909
preparing data for epoch 320
number of batches 61
time taken to create batches 11.294448614120483
step: 19460, lr: 0.000825, cost: 0.9867, z_cost: 0.9858, r_cost: 0.0008, train_time_taken: 12.4695
step: 19480, lr: 0.000825, cost: 0.9860, z_cost: 0.9851, r_cost: 0.0009, train_time_taken: 11.6971
step: 19500, lr: 0.000825, cost: 0.9835, z_cost: 0.9827, r_cost: 0.0007, train_time_taken: 11.7405
preparing data for epoch 321
number of batches 61
time taken to create batches 11.729886770248413
step: 19520, lr: 0.000824, cost: 0.9955, z_cost: 0.9880, r_cost: 0.0075, train_time_taken: 12.3176
step: 19540, lr: 0.000824, cost: 0.9842, z_cost: 0.9825, r_cost: 0.0016, train_time_taken: 11.9127
step: 19560, lr: 0.000824, cost: 0.9875, z_cost: 0.9864, r_cost: 0.0012, train_time_taken: 11.9551
step: 19580, lr: 0.000824, cost: 0.9856, z_cost: 0.9845, r_cost: 0.0012, train_time_taken: 11.8829
preparing data for epoch 322
number of batches 61
time taken to create batches 0.6086900234222412
step: 19600, lr: 0.000824, cost: 0.9854, z_cost: 0.9840, r_cost: 0.0014, train_time_taken: 12.2587
step: 19620, lr: 0.000824, cost: 0.9825, z_cost: 0.9819, r_cost: 0.0007, train_time_taken: 11.6681
step: 19640, lr: 0.000823, cost: 0.9852, z_cost: 0.9836, r_cost: 0.0016, train_time_taken: 11.6749
preparing data for epoch 323
number of batches 61
time taken to create batches 1.1911249160766602
step: 19660, lr: 0.000823, cost: 0.9838, z_cost: 0.9827, r_cost: 0.0012, train_time_taken: 12.4748
step: 19680, lr: 0.000823, cost: 0.9854, z_cost: 0.9844, r_cost: 0.0010, train_time_taken: 11.9017
step: 19700, lr: 0.000823, cost: 0.9829, z_cost: 0.9819, r_cost: 0.0010, train_time_taken: 11.8583
preparing data for epoch 324
number of batches 61
time taken to create batches 1.7897486686706543
step: 19720, lr: 0.000823, cost: 0.9854, z_cost: 0.9840, r_cost: 0.0014, train_time_taken: 12.3108
step: 19740, lr: 0.000823, cost: 0.9855, z_cost: 0.9847, r_cost: 0.0007, train_time_taken: 11.6725
step: 19760, lr: 0.000822, cost: 0.9862, z_cost: 0.9851, r_cost: 0.0011, train_time_taken: 11.7131
preparing data for epoch 325
number of batches 61
time taken to create batches 2.3444602489471436
step: 19780, lr: 0.000822, cost: 0.9867, z_cost: 0.9853, r_cost: 0.0014, train_time_taken: 12.4372
step: 19800, lr: 0.000822, cost: 0.9876, z_cost: 0.9857, r_cost: 0.0020, train_time_taken: 11.8774
step: 19820, lr: 0.000822, cost: 0.9833, z_cost: 0.9823, r_cost: 0.0010, train_time_taken: 11.8846
preparing data for epoch 326
number of batches 61
time taken to create batches 2.9993467330932617
step: 19840, lr: 0.000822, cost: 0.9866, z_cost: 0.9850, r_cost: 0.0015, train_time_taken: 12.3876
step: 19860, lr: 0.000822, cost: 0.9847, z_cost: 0.9834, r_cost: 0.0013, train_time_taken: 11.6844
step: 19880, lr: 0.000822, cost: 0.9863, z_cost: 0.9852, r_cost: 0.0011, train_time_taken: 11.7084
preparing data for epoch 327
number of batches 61
time taken to create batches 3.5339982509613037
step: 19900, lr: 0.000821, cost: 0.9865, z_cost: 0.9855, r_cost: 0.0010, train_time_taken: 12.5762
step: 19920, lr: 0.000821, cost: 0.9865, z_cost: 0.9849, r_cost: 0.0016, train_time_taken: 11.8788
step: 19940, lr: 0.000821, cost: 0.9887, z_cost: 0.9866, r_cost: 0.0020, train_time_taken: 11.8920
preparing data for epoch 328
number of batches 61
time taken to create batches 4.171164035797119
step: 19960, lr: 0.000821, cost: 0.9865, z_cost: 0.9853, r_cost: 0.0012, train_time_taken: 12.3310
step: 19980, lr: 0.000821, cost: 0.9845, z_cost: 0.9834, r_cost: 0.0011, train_time_taken: 11.7496
step: 20000, lr: 0.000821, cost: 0.9864, z_cost: 0.9847, r_cost: 0.0017, train_time_taken: 11.6794
preparing data for epoch 329
number of batches 61
time taken to create batches 4.681519985198975
step: 20020, lr: 0.000820, cost: 0.9856, z_cost: 0.9842, r_cost: 0.0014, train_time_taken: 12.4222
step: 20040, lr: 0.000820, cost: 0.9867, z_cost: 0.9844, r_cost: 0.0023, train_time_taken: 11.9470
step: 20060, lr: 0.000820, cost: 0.9886, z_cost: 0.9871, r_cost: 0.0015, train_time_taken: 11.8571
preparing data for epoch 330
number of batches 61
time taken to create batches 5.3771467208862305
step: 20080, lr: 0.000820, cost: 0.9847, z_cost: 0.9837, r_cost: 0.0009, train_time_taken: 12.3866
step: 20100, lr: 0.000820, cost: 0.9871, z_cost: 0.9856, r_cost: 0.0014, train_time_taken: 11.7429
step: 20120, lr: 0.000820, cost: 0.9902, z_cost: 0.9871, r_cost: 0.0032, train_time_taken: 11.7048
preparing data for epoch 331
number of batches 61
time taken to create batches 5.893980979919434
step: 20140, lr: 0.000819, cost: 0.9877, z_cost: 0.9861, r_cost: 0.0016, train_time_taken: 12.4213
step: 20160, lr: 0.000819, cost: 0.9845, z_cost: 0.9837, r_cost: 0.0008, train_time_taken: 11.8834
step: 20180, lr: 0.000819, cost: 0.9877, z_cost: 0.9853, r_cost: 0.0024, train_time_taken: 11.9689
preparing data for epoch 332
number of batches 61
time taken to create batches 6.555803298950195
step: 20200, lr: 0.000819, cost: 0.9865, z_cost: 0.9853, r_cost: 0.0012, train_time_taken: 12.4141
step: 20220, lr: 0.000819, cost: 0.9864, z_cost: 0.9834, r_cost: 0.0030, train_time_taken: 11.6908
step: 20240, lr: 0.000819, cost: 0.9847, z_cost: 0.9826, r_cost: 0.0022, train_time_taken: 11.6784
preparing data for epoch 333
number of batches 61
time taken to create batches 7.034874677658081
step: 20260, lr: 0.000818, cost: 0.9868, z_cost: 0.9853, r_cost: 0.0015, train_time_taken: 12.3831
step: 20280, lr: 0.000818, cost: 0.9850, z_cost: 0.9835, r_cost: 0.0015, train_time_taken: 11.8760
step: 20300, lr: 0.000818, cost: 0.9873, z_cost: 0.9853, r_cost: 0.0019, train_time_taken: 11.8962
preparing data for epoch 334
number of batches 61
time taken to create batches 7.793208837509155
step: 20320, lr: 0.000818, cost: 0.9869, z_cost: 0.9854, r_cost: 0.0016, train_time_taken: 12.4576
step: 20340, lr: 0.000818, cost: 0.9864, z_cost: 0.9851, r_cost: 0.0013, train_time_taken: 11.7187
step: 20360, lr: 0.000818, cost: 0.9873, z_cost: 0.9858, r_cost: 0.0015, train_time_taken: 11.7309
preparing data for epoch 335
number of batches 61
time taken to create batches 8.217919111251831
step: 20380, lr: 0.000817, cost: 0.9852, z_cost: 0.9830, r_cost: 0.0022, train_time_taken: 12.3860
step: 20400, lr: 0.000817, cost: 0.9831, z_cost: 0.9816, r_cost: 0.0014, train_time_taken: 11.8939
step: 20420, lr: 0.000817, cost: 0.9867, z_cost: 0.9855, r_cost: 0.0012, train_time_taken: 11.8562
preparing data for epoch 336
number of batches 61
time taken to create batches 8.910929441452026
step: 20440, lr: 0.000817, cost: 0.9833, z_cost: 0.9816, r_cost: 0.0017, train_time_taken: 12.4288
step: 20460, lr: 0.000817, cost: 0.9859, z_cost: 0.9845, r_cost: 0.0014, train_time_taken: 11.6874
step: 20480, lr: 0.000817, cost: 0.9867, z_cost: 0.9854, r_cost: 0.0013, train_time_taken: 11.6717
preparing data for epoch 337
number of batches 61
time taken to create batches 9.40986180305481
step: 20500, lr: 0.000817, cost: 0.9846, z_cost: 0.9836, r_cost: 0.0010, train_time_taken: 12.4114
step: 20520, lr: 0.000816, cost: 0.9844, z_cost: 0.9834, r_cost: 0.0011, train_time_taken: 11.9515
step: 20540, lr: 0.000816, cost: 0.9861, z_cost: 0.9847, r_cost: 0.0014, train_time_taken: 11.8897
preparing data for epoch 338
number of batches 61
time taken to create batches 10.163134098052979
step: 20560, lr: 0.000816, cost: 0.9847, z_cost: 0.9831, r_cost: 0.0016, train_time_taken: 12.4891
step: 20580, lr: 0.000816, cost: 0.9871, z_cost: 0.9859, r_cost: 0.0012, train_time_taken: 11.7157
step: 20600, lr: 0.000816, cost: 0.9861, z_cost: 0.9841, r_cost: 0.0020, train_time_taken: 11.6844
preparing data for epoch 339
number of batches 61
time taken to create batches 10.515065908432007
step: 20620, lr: 0.000816, cost: 0.9895, z_cost: 0.9864, r_cost: 0.0031, train_time_taken: 12.2919
step: 20640, lr: 0.000815, cost: 0.9847, z_cost: 0.9831, r_cost: 0.0016, train_time_taken: 11.8558
step: 20660, lr: 0.000815, cost: 0.9818, z_cost: 0.9810, r_cost: 0.0008, train_time_taken: 11.8863
preparing data for epoch 340
number of batches 61
time taken to create batches 11.562857151031494
step: 20680, lr: 0.000815, cost: 0.9874, z_cost: 0.9859, r_cost: 0.0014, train_time_taken: 12.7436
step: 20700, lr: 0.000815, cost: 0.9865, z_cost: 0.9851, r_cost: 0.0014, train_time_taken: 11.7320
step: 20720, lr: 0.000815, cost: 0.9867, z_cost: 0.9852, r_cost: 0.0015, train_time_taken: 11.6850
preparing data for epoch 341
number of batches 61
time taken to create batches 11.743866682052612
step: 20740, lr: 0.000815, cost: 0.9924, z_cost: 0.9868, r_cost: 0.0055, train_time_taken: 12.3444
step: 20760, lr: 0.000814, cost: 0.9827, z_cost: 0.9819, r_cost: 0.0008, train_time_taken: 11.9224
step: 20780, lr: 0.000814, cost: 0.9852, z_cost: 0.9837, r_cost: 0.0015, train_time_taken: 11.9468
step: 20800, lr: 0.000814, cost: 0.9857, z_cost: 0.9841, r_cost: 0.0016, train_time_taken: 11.8667
preparing data for epoch 342
number of batches 61
time taken to create batches 0.6060135364532471
step: 20820, lr: 0.000814, cost: 0.9854, z_cost: 0.9843, r_cost: 0.0011, train_time_taken: 12.2532
step: 20840, lr: 0.000814, cost: 0.9879, z_cost: 0.9856, r_cost: 0.0023, train_time_taken: 11.6836
step: 20860, lr: 0.000814, cost: 0.9871, z_cost: 0.9856, r_cost: 0.0015, train_time_taken: 11.6547
preparing data for epoch 343
number of batches 61
time taken to create batches 1.1972289085388184
step: 20880, lr: 0.000813, cost: 0.9853, z_cost: 0.9824, r_cost: 0.0029, train_time_taken: 12.4590
step: 20900, lr: 0.000813, cost: 0.9878, z_cost: 0.9846, r_cost: 0.0032, train_time_taken: 11.8504
step: 20920, lr: 0.000813, cost: 0.9851, z_cost: 0.9827, r_cost: 0.0023, train_time_taken: 11.8330
preparing data for epoch 344
number of batches 61
time taken to create batches 1.8020057678222656
step: 20940, lr: 0.000813, cost: 0.9852, z_cost: 0.9841, r_cost: 0.0012, train_time_taken: 12.3430
step: 20960, lr: 0.000813, cost: 0.9847, z_cost: 0.9832, r_cost: 0.0015, train_time_taken: 11.7222
step: 20980, lr: 0.000813, cost: 0.9866, z_cost: 0.9857, r_cost: 0.0009, train_time_taken: 11.6732
preparing data for epoch 345
number of batches 61
time taken to create batches 2.363755226135254
step: 21000, lr: 0.000812, cost: 0.9833, z_cost: 0.9815, r_cost: 0.0018, train_time_taken: 12.4708
step: 21020, lr: 0.000812, cost: 0.9840, z_cost: 0.9806, r_cost: 0.0034, train_time_taken: 11.8764
step: 21040, lr: 0.000812, cost: 0.9841, z_cost: 0.9814, r_cost: 0.0027, train_time_taken: 11.8930
preparing data for epoch 346
number of batches 61
time taken to create batches 3.0007710456848145
step: 21060, lr: 0.000812, cost: 0.9848, z_cost: 0.9837, r_cost: 0.0010, train_time_taken: 12.3628
step: 21080, lr: 0.000812, cost: 0.9851, z_cost: 0.9831, r_cost: 0.0020, train_time_taken: 11.6661
step: 21100, lr: 0.000812, cost: 0.9849, z_cost: 0.9827, r_cost: 0.0022, train_time_taken: 11.6652
preparing data for epoch 347
number of batches 61
time taken to create batches 3.5247552394866943
step: 21120, lr: 0.000812, cost: 0.9849, z_cost: 0.9836, r_cost: 0.0013, train_time_taken: 12.4257
step: 21140, lr: 0.000811, cost: 0.9839, z_cost: 0.9830, r_cost: 0.0009, train_time_taken: 11.8657
step: 21160, lr: 0.000811, cost: 0.9859, z_cost: 0.9845, r_cost: 0.0014, train_time_taken: 11.8818
preparing data for epoch 348
number of batches 61
time taken to create batches 4.16695761680603
step: 21180, lr: 0.000811, cost: 0.9863, z_cost: 0.9850, r_cost: 0.0013, train_time_taken: 12.3332
step: 21200, lr: 0.000811, cost: 0.9871, z_cost: 0.9852, r_cost: 0.0019, train_time_taken: 11.6600
step: 21220, lr: 0.000811, cost: 0.9855, z_cost: 0.9837, r_cost: 0.0017, train_time_taken: 11.6776
preparing data for epoch 349
number of batches 61
time taken to create batches 4.698591709136963
step: 21240, lr: 0.000811, cost: 0.9851, z_cost: 0.9824, r_cost: 0.0027, train_time_taken: 12.4168
step: 21260, lr: 0.000810, cost: 0.9863, z_cost: 0.9845, r_cost: 0.0018, train_time_taken: 11.8568
step: 21280, lr: 0.000810, cost: 0.9862, z_cost: 0.9854, r_cost: 0.0008, train_time_taken: 11.8036
preparing data for epoch 350
number of batches 61
time taken to create batches 5.361372709274292
step: 21300, lr: 0.000810, cost: 0.9856, z_cost: 0.9844, r_cost: 0.0012, train_time_taken: 12.3703
step: 21320, lr: 0.000810, cost: 0.9856, z_cost: 0.9842, r_cost: 0.0014, train_time_taken: 11.7274
step: 21340, lr: 0.000810, cost: 0.9838, z_cost: 0.9819, r_cost: 0.0019, train_time_taken: 11.7416
preparing data for epoch 351
number of batches 61
time taken to create batches 5.86755633354187
step: 21360, lr: 0.000810, cost: 0.9848, z_cost: 0.9832, r_cost: 0.0016, train_time_taken: 12.3768
step: 21380, lr: 0.000809, cost: 0.9875, z_cost: 0.9853, r_cost: 0.0022, train_time_taken: 11.8751
step: 21400, lr: 0.000809, cost: 0.9864, z_cost: 0.9848, r_cost: 0.0016, train_time_taken: 11.8484
preparing data for epoch 352
number of batches 61
time taken to create batches 6.532688140869141
step: 21420, lr: 0.000809, cost: 0.9857, z_cost: 0.9839, r_cost: 0.0018, train_time_taken: 12.3285
step: 21440, lr: 0.000809, cost: 0.9851, z_cost: 0.9825, r_cost: 0.0026, train_time_taken: 11.5874
step: 21460, lr: 0.000809, cost: 0.9855, z_cost: 0.9841, r_cost: 0.0015, train_time_taken: 11.6997
preparing data for epoch 353
number of batches 61
time taken to create batches 7.046643972396851
step: 21480, lr: 0.000809, cost: 0.9844, z_cost: 0.9836, r_cost: 0.0008, train_time_taken: 12.3875
step: 21500, lr: 0.000808, cost: 0.9836, z_cost: 0.9823, r_cost: 0.0013, train_time_taken: 11.8392
step: 21520, lr: 0.000808, cost: 0.9812, z_cost: 0.9799, r_cost: 0.0013, train_time_taken: 11.8278
preparing data for epoch 354
number of batches 61
time taken to create batches 7.6841208934783936
step: 21540, lr: 0.000808, cost: 0.9853, z_cost: 0.9838, r_cost: 0.0015, train_time_taken: 12.3703
step: 21560, lr: 0.000808, cost: 0.9847, z_cost: 0.9836, r_cost: 0.0012, train_time_taken: 11.6797
step: 21580, lr: 0.000808, cost: 0.9822, z_cost: 0.9816, r_cost: 0.0006, train_time_taken: 11.6637
preparing data for epoch 355
number of batches 61
time taken to create batches 8.098347425460815
step: 21600, lr: 0.000808, cost: 0.9993, z_cost: 0.9975, r_cost: 0.0018, train_time_taken: 12.2746
step: 21620, lr: 0.000808, cost: 0.9867, z_cost: 0.9846, r_cost: 0.0021, train_time_taken: 11.8524
step: 21640, lr: 0.000807, cost: 0.9894, z_cost: 0.9880, r_cost: 0.0015, train_time_taken: 11.8264
preparing data for epoch 356
number of batches 61
time taken to create batches 8.976987838745117
step: 21660, lr: 0.000807, cost: 0.9869, z_cost: 0.9858, r_cost: 0.0011, train_time_taken: 12.4953
step: 21680, lr: 0.000807, cost: 0.9860, z_cost: 0.9843, r_cost: 0.0017, train_time_taken: 11.6624
step: 21700, lr: 0.000807, cost: 0.9874, z_cost: 0.9862, r_cost: 0.0011, train_time_taken: 11.7296
preparing data for epoch 357
number of batches 61
time taken to create batches 9.371444463729858
step: 21720, lr: 0.000807, cost: 0.9857, z_cost: 0.9848, r_cost: 0.0009, train_time_taken: 12.3358
step: 21740, lr: 0.000807, cost: 0.9848, z_cost: 0.9841, r_cost: 0.0007, train_time_taken: 11.8387
step: 21760, lr: 0.000806, cost: 0.9871, z_cost: 0.9849, r_cost: 0.0021, train_time_taken: 11.8608
preparing data for epoch 358
number of batches 61
time taken to create batches 10.083256721496582
step: 21780, lr: 0.000806, cost: 0.9843, z_cost: 0.9832, r_cost: 0.0011, train_time_taken: 12.4278
step: 21800, lr: 0.000806, cost: 0.9883, z_cost: 0.9848, r_cost: 0.0035, train_time_taken: 11.6447
step: 21820, lr: 0.000806, cost: 0.9856, z_cost: 0.9845, r_cost: 0.0011, train_time_taken: 11.7161
preparing data for epoch 359
number of batches 61
time taken to create batches 10.514853239059448
step: 21840, lr: 0.000806, cost: 0.9849, z_cost: 0.9840, r_cost: 0.0010, train_time_taken: 12.2742
step: 21860, lr: 0.000806, cost: 0.9830, z_cost: 0.9822, r_cost: 0.0008, train_time_taken: 11.8762
step: 21880, lr: 0.000805, cost: 0.9838, z_cost: 0.9831, r_cost: 0.0007, train_time_taken: 11.7985
preparing data for epoch 360
number of batches 61
time taken to create batches 11.251185655593872
step: 21900, lr: 0.000805, cost: 0.9843, z_cost: 0.9822, r_cost: 0.0020, train_time_taken: 12.4180
step: 21920, lr: 0.000805, cost: 0.9855, z_cost: 0.9845, r_cost: 0.0010, train_time_taken: 11.6812
step: 21940, lr: 0.000805, cost: 0.9868, z_cost: 0.9850, r_cost: 0.0018, train_time_taken: 11.7184
preparing data for epoch 361
number of batches 61
time taken to create batches 11.705227375030518
step: 21960, lr: 0.000805, cost: 0.9919, z_cost: 0.9861, r_cost: 0.0058, train_time_taken: 12.2949
step: 21980, lr: 0.000805, cost: 0.9862, z_cost: 0.9835, r_cost: 0.0027, train_time_taken: 11.8404
step: 22000, lr: 0.000804, cost: 0.9882, z_cost: 0.9857, r_cost: 0.0025, train_time_taken: 11.8924
step: 22020, lr: 0.000804, cost: 0.9874, z_cost: 0.9850, r_cost: 0.0024, train_time_taken: 11.8295
preparing data for epoch 362
number of batches 61
time taken to create batches 0.6060636043548584
step: 22040, lr: 0.000804, cost: 0.9879, z_cost: 0.9859, r_cost: 0.0020, train_time_taken: 12.2642
step: 22060, lr: 0.000804, cost: 0.9887, z_cost: 0.9858, r_cost: 0.0030, train_time_taken: 11.7240
step: 22080, lr: 0.000804, cost: 0.9867, z_cost: 0.9842, r_cost: 0.0025, train_time_taken: 11.6670
preparing data for epoch 363
number of batches 61
time taken to create batches 1.1904025077819824
step: 22100, lr: 0.000804, cost: 0.9866, z_cost: 0.9850, r_cost: 0.0017, train_time_taken: 12.4330
step: 22120, lr: 0.000804, cost: 0.9850, z_cost: 0.9835, r_cost: 0.0014, train_time_taken: 11.8625
step: 22140, lr: 0.000803, cost: 0.9847, z_cost: 0.9825, r_cost: 0.0023, train_time_taken: 11.9703
preparing data for epoch 364
number of batches 61
time taken to create batches 1.8030877113342285
step: 22160, lr: 0.000803, cost: 0.9804, z_cost: 0.9793, r_cost: 0.0011, train_time_taken: 12.3461
step: 22180, lr: 0.000803, cost: 0.9842, z_cost: 0.9834, r_cost: 0.0008, train_time_taken: 11.7012
step: 22200, lr: 0.000803, cost: 0.9824, z_cost: 0.9816, r_cost: 0.0008, train_time_taken: 11.6509
preparing data for epoch 365
number of batches 61
time taken to create batches 2.347463607788086
step: 22220, lr: 0.000803, cost: 0.9874, z_cost: 0.9855, r_cost: 0.0019, train_time_taken: 12.4358
step: 22240, lr: 0.000803, cost: 0.9862, z_cost: 0.9840, r_cost: 0.0022, train_time_taken: 11.9055
step: 22260, lr: 0.000802, cost: 0.9873, z_cost: 0.9864, r_cost: 0.0009, train_time_taken: 12.0028
preparing data for epoch 366
number of batches 61
time taken to create batches 3.005497932434082
step: 22280, lr: 0.000802, cost: 0.9827, z_cost: 0.9802, r_cost: 0.0026, train_time_taken: 12.3365
step: 22300, lr: 0.000802, cost: 0.9845, z_cost: 0.9832, r_cost: 0.0013, train_time_taken: 11.6626
step: 22320, lr: 0.000802, cost: 0.9828, z_cost: 0.9813, r_cost: 0.0015, train_time_taken: 11.6327
preparing data for epoch 367
number of batches 61
time taken to create batches 3.535865545272827
step: 22340, lr: 0.000802, cost: 0.9834, z_cost: 0.9824, r_cost: 0.0010, train_time_taken: 12.4141
step: 22360, lr: 0.000802, cost: 0.9835, z_cost: 0.9825, r_cost: 0.0010, train_time_taken: 11.8547
step: 22380, lr: 0.000801, cost: 0.9819, z_cost: 0.9812, r_cost: 0.0008, train_time_taken: 11.8685
preparing data for epoch 368
number of batches 61
time taken to create batches 4.16514253616333
step: 22400, lr: 0.000801, cost: 0.9871, z_cost: 0.9852, r_cost: 0.0019, train_time_taken: 12.3423
step: 22420, lr: 0.000801, cost: 0.9864, z_cost: 0.9842, r_cost: 0.0022, train_time_taken: 11.7205
step: 22440, lr: 0.000801, cost: 0.9815, z_cost: 0.9805, r_cost: 0.0010, train_time_taken: 11.6814
preparing data for epoch 369
number of batches 61
time taken to create batches 4.701956272125244
step: 22460, lr: 0.000801, cost: 0.9854, z_cost: 0.9844, r_cost: 0.0010, train_time_taken: 12.4450
step: 22480, lr: 0.000801, cost: 0.9835, z_cost: 0.9826, r_cost: 0.0009, train_time_taken: 11.8715
step: 22500, lr: 0.000801, cost: 0.9839, z_cost: 0.9822, r_cost: 0.0017, train_time_taken: 11.9227
preparing data for epoch 370
number of batches 61
time taken to create batches 5.362117052078247
step: 22520, lr: 0.000800, cost: 0.9853, z_cost: 0.9845, r_cost: 0.0008, train_time_taken: 12.3410
step: 22540, lr: 0.000800, cost: 0.9847, z_cost: 0.9838, r_cost: 0.0009, train_time_taken: 11.6821
step: 22560, lr: 0.000800, cost: 0.9828, z_cost: 0.9821, r_cost: 0.0007, train_time_taken: 11.6430
preparing data for epoch 371
number of batches 61
time taken to create batches 5.863935232162476
step: 22580, lr: 0.000800, cost: 0.9886, z_cost: 0.9846, r_cost: 0.0040, train_time_taken: 12.3731
step: 22600, lr: 0.000800, cost: 0.9848, z_cost: 0.9840, r_cost: 0.0008, train_time_taken: 11.8263
step: 22620, lr: 0.000800, cost: 0.9847, z_cost: 0.9833, r_cost: 0.0014, train_time_taken: 11.8576
preparing data for epoch 372
number of batches 61
time taken to create batches 6.550572633743286
step: 22640, lr: 0.000799, cost: 0.9844, z_cost: 0.9838, r_cost: 0.0007, train_time_taken: 12.3783
step: 22660, lr: 0.000799, cost: 0.9824, z_cost: 0.9816, r_cost: 0.0007, train_time_taken: 11.6336
step: 22680, lr: 0.000799, cost: 0.9830, z_cost: 0.9817, r_cost: 0.0013, train_time_taken: 11.6792
preparing data for epoch 373
number of batches 61
time taken to create batches 7.053798675537109
step: 22700, lr: 0.000799, cost: 0.9825, z_cost: 0.9808, r_cost: 0.0017, train_time_taken: 12.4243
step: 22720, lr: 0.000799, cost: 0.9837, z_cost: 0.9829, r_cost: 0.0008, train_time_taken: 11.8724
step: 22740, lr: 0.000799, cost: 0.9847, z_cost: 0.9838, r_cost: 0.0009, train_time_taken: 11.9035
preparing data for epoch 374
number of batches 61
time taken to create batches 7.711545944213867
step: 22760, lr: 0.000798, cost: 0.9889, z_cost: 0.9867, r_cost: 0.0022, train_time_taken: 12.3840
step: 22780, lr: 0.000798, cost: 0.9848, z_cost: 0.9837, r_cost: 0.0012, train_time_taken: 11.7219
step: 22800, lr: 0.000798, cost: 0.9823, z_cost: 0.9806, r_cost: 0.0017, train_time_taken: 11.6691
preparing data for epoch 375
number of batches 61
time taken to create batches 8.189839601516724
step: 22820, lr: 0.000798, cost: 0.9844, z_cost: 0.9826, r_cost: 0.0017, train_time_taken: 12.3323
step: 22840, lr: 0.000798, cost: 0.9815, z_cost: 0.9802, r_cost: 0.0013, train_time_taken: 11.8829
step: 22860, lr: 0.000798, cost: 0.9837, z_cost: 0.9823, r_cost: 0.0015, train_time_taken: 11.8484
preparing data for epoch 376
number of batches 61
time taken to create batches 8.91621994972229
step: 22880, lr: 0.000798, cost: 0.9824, z_cost: 0.9813, r_cost: 0.0010, train_time_taken: 12.4052
step: 22900, lr: 0.000797, cost: 0.9817, z_cost: 0.9802, r_cost: 0.0014, train_time_taken: 11.6278
step: 22920, lr: 0.000797, cost: 0.9873, z_cost: 0.9853, r_cost: 0.0020, train_time_taken: 11.6780
preparing data for epoch 377
number of batches 61
time taken to create batches 9.356645822525024
step: 22940, lr: 0.000797, cost: 0.9824, z_cost: 0.9814, r_cost: 0.0010, train_time_taken: 12.3154
step: 22960, lr: 0.000797, cost: 0.9868, z_cost: 0.9860, r_cost: 0.0008, train_time_taken: 11.8742
step: 22980, lr: 0.000797, cost: 0.9824, z_cost: 0.9812, r_cost: 0.0012, train_time_taken: 11.8534
preparing data for epoch 378
number of batches 61
time taken to create batches 10.138605833053589
step: 23000, lr: 0.000797, cost: 0.9873, z_cost: 0.9861, r_cost: 0.0012, train_time_taken: 12.4775
step: 23020, lr: 0.000796, cost: 0.9825, z_cost: 0.9802, r_cost: 0.0023, train_time_taken: 11.6880
step: 23040, lr: 0.000796, cost: 0.9828, z_cost: 0.9806, r_cost: 0.0023, train_time_taken: 11.7380
preparing data for epoch 379
number of batches 61
time taken to create batches 10.483687162399292
step: 23060, lr: 0.000796, cost: 0.9843, z_cost: 0.9827, r_cost: 0.0016, train_time_taken: 12.2426
step: 23080, lr: 0.000796, cost: 0.9844, z_cost: 0.9820, r_cost: 0.0024, train_time_taken: 11.8156
step: 23100, lr: 0.000796, cost: 0.9871, z_cost: 0.9846, r_cost: 0.0025, train_time_taken: 11.8670
preparing data for epoch 380
number of batches 61
time taken to create batches 11.316001176834106
step: 23120, lr: 0.000796, cost: 0.9825, z_cost: 0.9808, r_cost: 0.0016, train_time_taken: 12.4981
step: 23140, lr: 0.000795, cost: 0.9863, z_cost: 0.9856, r_cost: 0.0007, train_time_taken: 11.6436
step: 23160, lr: 0.000795, cost: 0.9848, z_cost: 0.9831, r_cost: 0.0017, train_time_taken: 11.6814
preparing data for epoch 381
number of batches 61
time taken to create batches 11.674611330032349
step: 23180, lr: 0.000795, cost: 0.9948, z_cost: 0.9859, r_cost: 0.0089, train_time_taken: 12.2742
step: 23200, lr: 0.000795, cost: 0.9869, z_cost: 0.9842, r_cost: 0.0027, train_time_taken: 11.8759
step: 23220, lr: 0.000795, cost: 0.9860, z_cost: 0.9847, r_cost: 0.0013, train_time_taken: 11.8713
step: 23240, lr: 0.000795, cost: 0.9835, z_cost: 0.9822, r_cost: 0.0013, train_time_taken: 11.8627
preparing data for epoch 382
number of batches 61
time taken to create batches 0.6048502922058105
step: 23260, lr: 0.000795, cost: 0.9821, z_cost: 0.9812, r_cost: 0.0009, train_time_taken: 12.2946
step: 23280, lr: 0.000794, cost: 0.9835, z_cost: 0.9821, r_cost: 0.0013, train_time_taken: 11.6912
step: 23300, lr: 0.000794, cost: 0.9817, z_cost: 0.9806, r_cost: 0.0011, train_time_taken: 11.6063
preparing data for epoch 383
number of batches 61
time taken to create batches 1.1940011978149414
step: 23320, lr: 0.000794, cost: 0.9831, z_cost: 0.9820, r_cost: 0.0011, train_time_taken: 12.4232
step: 23340, lr: 0.000794, cost: 0.9843, z_cost: 0.9811, r_cost: 0.0032, train_time_taken: 11.8754
step: 23360, lr: 0.000794, cost: 0.9824, z_cost: 0.9816, r_cost: 0.0008, train_time_taken: 11.8122
preparing data for epoch 384
number of batches 61
time taken to create batches 1.7777318954467773
step: 23380, lr: 0.000794, cost: 0.9835, z_cost: 0.9824, r_cost: 0.0010, train_time_taken: 12.2544
step: 23400, lr: 0.000793, cost: 0.9850, z_cost: 0.9830, r_cost: 0.0020, train_time_taken: 11.6905
step: 23420, lr: 0.000793, cost: 0.9802, z_cost: 0.9793, r_cost: 0.0008, train_time_taken: 11.6829
preparing data for epoch 385
number of batches 61
time taken to create batches 2.3559720516204834
step: 23440, lr: 0.000793, cost: 0.9818, z_cost: 0.9805, r_cost: 0.0014, train_time_taken: 12.4140
step: 23460, lr: 0.000793, cost: 0.9841, z_cost: 0.9819, r_cost: 0.0022, train_time_taken: 11.9031
step: 23480, lr: 0.000793, cost: 0.9818, z_cost: 0.9804, r_cost: 0.0014, train_time_taken: 11.8760
preparing data for epoch 386
number of batches 61
time taken to create batches 2.9629626274108887
step: 23500, lr: 0.000793, cost: 0.9813, z_cost: 0.9802, r_cost: 0.0011, train_time_taken: 12.2931
step: 23520, lr: 0.000793, cost: 0.9816, z_cost: 0.9810, r_cost: 0.0006, train_time_taken: 11.6291
step: 23540, lr: 0.000792, cost: 0.9813, z_cost: 0.9794, r_cost: 0.0019, train_time_taken: 11.6224
preparing data for epoch 387
number of batches 61
time taken to create batches 3.5211424827575684
step: 23560, lr: 0.000792, cost: 0.9854, z_cost: 0.9839, r_cost: 0.0015, train_time_taken: 12.4287
step: 23580, lr: 0.000792, cost: 0.9825, z_cost: 0.9806, r_cost: 0.0019, train_time_taken: 11.9431
step: 23600, lr: 0.000792, cost: 0.9821, z_cost: 0.9806, r_cost: 0.0015, train_time_taken: 12.0123
preparing data for epoch 388
number of batches 61
time taken to create batches 4.185037136077881
step: 23620, lr: 0.000792, cost: 0.9805, z_cost: 0.9795, r_cost: 0.0010, train_time_taken: 12.3319
step: 23640, lr: 0.000792, cost: 0.9834, z_cost: 0.9816, r_cost: 0.0018, train_time_taken: 11.8080
step: 23660, lr: 0.000791, cost: 0.9843, z_cost: 0.9821, r_cost: 0.0022, train_time_taken: 11.6519
preparing data for epoch 389
number of batches 61
time taken to create batches 4.695260047912598
step: 23680, lr: 0.000791, cost: 0.9840, z_cost: 0.9831, r_cost: 0.0008, train_time_taken: 12.3939
step: 23700, lr: 0.000791, cost: 0.9826, z_cost: 0.9812, r_cost: 0.0014, train_time_taken: 11.8612
step: 23720, lr: 0.000791, cost: 0.9835, z_cost: 0.9827, r_cost: 0.0008, train_time_taken: 11.8398
preparing data for epoch 390
number of batches 61
time taken to create batches 5.380315780639648
step: 23740, lr: 0.000791, cost: 0.9843, z_cost: 0.9830, r_cost: 0.0014, train_time_taken: 12.3960
step: 23760, lr: 0.000791, cost: 0.9836, z_cost: 0.9827, r_cost: 0.0009, train_time_taken: 11.6822
step: 23780, lr: 0.000790, cost: 0.9856, z_cost: 0.9835, r_cost: 0.0021, train_time_taken: 11.7001
preparing data for epoch 391
number of batches 61
time taken to create batches 5.862291574478149
step: 23800, lr: 0.000790, cost: 0.9823, z_cost: 0.9797, r_cost: 0.0026, train_time_taken: 12.3645
step: 23820, lr: 0.000790, cost: 0.9825, z_cost: 0.9803, r_cost: 0.0022, train_time_taken: 11.9312
step: 23840, lr: 0.000790, cost: 0.9847, z_cost: 0.9832, r_cost: 0.0014, train_time_taken: 11.9229
preparing data for epoch 392
number of batches 61
time taken to create batches 6.541719436645508
step: 23860, lr: 0.000790, cost: 0.9843, z_cost: 0.9827, r_cost: 0.0015, train_time_taken: 12.3761
step: 23880, lr: 0.000790, cost: 0.9841, z_cost: 0.9821, r_cost: 0.0020, train_time_taken: 11.6886
step: 23900, lr: 0.000790, cost: 0.9841, z_cost: 0.9821, r_cost: 0.0020, train_time_taken: 11.7042
preparing data for epoch 393
number of batches 61
time taken to create batches 7.033335208892822
step: 23920, lr: 0.000789, cost: 0.9819, z_cost: 0.9804, r_cost: 0.0016, train_time_taken: 12.3857
step: 23940, lr: 0.000789, cost: 0.9861, z_cost: 0.9827, r_cost: 0.0033, train_time_taken: 11.8860
step: 23960, lr: 0.000789, cost: 0.9868, z_cost: 0.9816, r_cost: 0.0052, train_time_taken: 11.8723
preparing data for epoch 394
number of batches 61
time taken to create batches 7.737511157989502
step: 23980, lr: 0.000789, cost: 0.9814, z_cost: 0.9796, r_cost: 0.0018, train_time_taken: 12.4178
step: 24000, lr: 0.000789, cost: 0.9850, z_cost: 0.9828, r_cost: 0.0022, train_time_taken: 11.7065
step: 24020, lr: 0.000789, cost: 0.9822, z_cost: 0.9810, r_cost: 0.0012, train_time_taken: 11.7067
preparing data for epoch 395
number of batches 61
time taken to create batches 8.242401838302612
step: 24040, lr: 0.000788, cost: 0.9835, z_cost: 0.9823, r_cost: 0.0011, train_time_taken: 12.3826
step: 24060, lr: 0.000788, cost: 0.9867, z_cost: 0.9845, r_cost: 0.0022, train_time_taken: 11.8962
step: 24080, lr: 0.000788, cost: 0.9873, z_cost: 0.9843, r_cost: 0.0030, train_time_taken: 11.8469
preparing data for epoch 396
number of batches 61
time taken to create batches 8.888137578964233
step: 24100, lr: 0.000788, cost: 0.9846, z_cost: 0.9828, r_cost: 0.0018, train_time_taken: 12.4090
step: 24120, lr: 0.000788, cost: 0.9840, z_cost: 0.9823, r_cost: 0.0017, train_time_taken: 11.7061
step: 24140, lr: 0.000788, cost: 0.9820, z_cost: 0.9811, r_cost: 0.0009, train_time_taken: 11.7322
preparing data for epoch 397
number of batches 61
time taken to create batches 9.377979755401611
step: 24160, lr: 0.000788, cost: 0.9844, z_cost: 0.9830, r_cost: 0.0014, train_time_taken: 12.3389
step: 24180, lr: 0.000787, cost: 0.9833, z_cost: 0.9821, r_cost: 0.0012, train_time_taken: 11.9012
step: 24200, lr: 0.000787, cost: 0.9850, z_cost: 0.9831, r_cost: 0.0019, train_time_taken: 11.8767
preparing data for epoch 398
number of batches 61
time taken to create batches 10.142464399337769
step: 24220, lr: 0.000787, cost: 0.9836, z_cost: 0.9824, r_cost: 0.0012, train_time_taken: 12.4944
step: 24240, lr: 0.000787, cost: 0.9821, z_cost: 0.9798, r_cost: 0.0023, train_time_taken: 11.7289
step: 24260, lr: 0.000787, cost: 0.9828, z_cost: 0.9821, r_cost: 0.0007, train_time_taken: 11.7797
preparing data for epoch 399
number of batches 61
time taken to create batches 10.536726951599121
step: 24280, lr: 0.000787, cost: 0.9833, z_cost: 0.9828, r_cost: 0.0005, train_time_taken: 12.3146
step: 24300, lr: 0.000786, cost: 0.9820, z_cost: 0.9809, r_cost: 0.0011, train_time_taken: 11.9005
step: 24320, lr: 0.000786, cost: 0.9810, z_cost: 0.9797, r_cost: 0.0013, train_time_taken: 11.9050
preparing data for epoch 400
number of batches 61
time taken to create batches 11.32945442199707
step: 24340, lr: 0.000786, cost: 0.9826, z_cost: 0.9821, r_cost: 0.0005, train_time_taken: 12.5110
step: 24360, lr: 0.000786, cost: 0.9795, z_cost: 0.9789, r_cost: 0.0006, train_time_taken: 11.7133
step: 24380, lr: 0.000786, cost: 0.9839, z_cost: 0.9830, r_cost: 0.0009, train_time_taken: 11.7188
