Created
May 5, 2015 13:33
-
-
Save szagoruyko/b4b153f52e1a8a95bd16 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Using 1-th gpu | |
Loading ./data/ptb.train.txt, size of data = 929589 | |
Loading ./data/ptb.valid.txt, size of data = 73760 | |
Loading ./data/ptb.test.txt, size of data = 82430 | |
Network parameters: | |
{ | |
layers : 2 | |
lr : 1 | |
max_max_epoch : 13 | |
max_grad_norm : 5 | |
max_epoch : 4 | |
init_weight : 0.1 | |
decay : 2 | |
vocab_size : 10000 | |
seq_length : 20 | |
batch_size : 20 | |
dropout : 0 | |
rnn_size : 200 | |
} | |
Creating a RNN LSTM network. | |
Starting training. | |
epoch = 0.004, train perp. = 9917.064, wps = 4371, dw:norm() = 4.221, lr = 1.000, since beginning = 0 mins. | |
epoch = 0.104, train perp. = 7734.153, wps = 5802, dw:norm() = 3.223, lr = 1.000, since beginning = 0 mins. | |
epoch = 0.204, train perp. = 5736.531, wps = 5917, dw:norm() = 3.785, lr = 1.000, since beginning = 1 mins. | |
epoch = 0.304, train perp. = 4114.988, wps = 5958, dw:norm() = 4.435, lr = 1.000, since beginning = 1 mins. | |
epoch = 0.404, train perp. = 2893.520, wps = 5979, dw:norm() = 4.360, lr = 1.000, since beginning = 1 mins. | |
epoch = 0.504, train perp. = 2012.100, wps = 5992, dw:norm() = 4.767, lr = 1.000, since beginning = 1 mins. | |
epoch = 0.604, train perp. = 1371.406, wps = 6002, dw:norm() = 4.756, lr = 1.000, since beginning = 2 mins. | |
epoch = 0.703, train perp. = 931.551, wps = 6009, dw:norm() = 4.025, lr = 1.000, since beginning = 2 mins. | |
epoch = 0.803, train perp. = 628.879, wps = 6014, dw:norm() = 4.582, lr = 1.000, since beginning = 2 mins. | |
epoch = 0.903, train perp. = 419.396, wps = 6018, dw:norm() = 4.722, lr = 1.000, since beginning = 2 mins. | |
Validation set perplexity : 181.341 | |
epoch = 1.003, train perp. = 279.842, wps = 5896, dw:norm() = 4.123, lr = 1.000, since beginning = 3 mins. | |
epoch = 1.103, train perp. = 236.158, wps = 5910, dw:norm() = 4.577, lr = 1.000, since beginning = 3 mins. | |
epoch = 1.203, train perp. = 212.386, wps = 5922, dw:norm() = 4.532, lr = 1.000, since beginning = 3 mins. | |
epoch = 1.303, train perp. = 194.677, wps = 5930, dw:norm() = 4.752, lr = 1.000, since beginning = 3 mins. | |
epoch = 1.402, train perp. = 181.680, wps = 5938, dw:norm() = 4.501, lr = 1.000, since beginning = 4 mins. | |
epoch = 1.502, train perp. = 171.193, wps = 5947, dw:norm() = 4.769, lr = 1.000, since beginning = 4 mins. | |
epoch = 1.602, train perp. = 162.405, wps = 5952, dw:norm() = 4.595, lr = 1.000, since beginning = 4 mins. | |
epoch = 1.702, train perp. = 155.512, wps = 5956, dw:norm() = 4.611, lr = 1.000, since beginning = 4 mins. | |
epoch = 1.802, train perp. = 149.490, wps = 5953, dw:norm() = 5.044, lr = 1.000, since beginning = 5 mins. | |
epoch = 1.902, train perp. = 143.469, wps = 5946, dw:norm() = 4.752, lr = 1.000, since beginning = 5 mins. | |
Validation set perplexity : 145.447 | |
epoch = 2.002, train perp. = 138.542, wps = 5888, dw:norm() = 4.721, lr = 1.000, since beginning = 5 mins. | |
epoch = 2.102, train perp. = 133.725, wps = 5895, dw:norm() = 4.875, lr = 1.000, since beginning = 6 mins. | |
epoch = 2.201, train perp. = 129.933, wps = 5902, dw:norm() = 4.589, lr = 1.000, since beginning = 6 mins. | |
epoch = 2.301, train perp. = 126.118, wps = 5909, dw:norm() = 4.897, lr = 1.000, since beginning = 6 mins. | |
epoch = 2.401, train perp. = 122.758, wps = 5914, dw:norm() = 5.228, lr = 1.000, since beginning = 6 mins. | |
epoch = 2.501, train perp. = 119.639, wps = 5919, dw:norm() = 5.107, lr = 1.000, since beginning = 7 mins. | |
epoch = 2.601, train perp. = 116.710, wps = 5923, dw:norm() = 5.269, lr = 1.000, since beginning = 7 mins. | |
epoch = 2.701, train perp. = 114.168, wps = 5927, dw:norm() = 5.042, lr = 1.000, since beginning = 7 mins. | |
epoch = 2.801, train perp. = 111.823, wps = 5931, dw:norm() = 4.907, lr = 1.000, since beginning = 7 mins. | |
epoch = 2.901, train perp. = 109.392, wps = 5935, dw:norm() = 5.382, lr = 1.000, since beginning = 8 mins. | |
Validation set perplexity : 133.951 | |
epoch = 3.000, train perp. = 107.199, wps = 5896, dw:norm() = 5.677, lr = 1.000, since beginning = 8 mins. | |
epoch = 3.100, train perp. = 104.977, wps = 5900, dw:norm() = 5.456, lr = 1.000, since beginning = 8 mins. | |
epoch = 3.200, train perp. = 103.157, wps = 5904, dw:norm() = 5.183, lr = 1.000, since beginning = 8 mins. | |
epoch = 3.300, train perp. = 101.241, wps = 5908, dw:norm() = 5.057, lr = 1.000, since beginning = 9 mins. | |
epoch = 3.400, train perp. = 99.492, wps = 5912, dw:norm() = 5.338, lr = 1.000, since beginning = 9 mins. | |
epoch = 3.500, train perp. = 97.796, wps = 5916, dw:norm() = 5.140, lr = 1.000, since beginning = 9 mins. | |
epoch = 3.600, train perp. = 96.223, wps = 5919, dw:norm() = 5.509, lr = 1.000, since beginning = 9 mins. | |
epoch = 3.700, train perp. = 94.739, wps = 5920, dw:norm() = 5.301, lr = 1.000, since beginning = 10 mins. | |
epoch = 3.799, train perp. = 93.312, wps = 5922, dw:norm() = 5.879, lr = 1.000, since beginning = 10 mins. | |
epoch = 3.899, train perp. = 91.883, wps = 5925, dw:norm() = 5.287, lr = 1.000, since beginning = 10 mins. | |
epoch = 3.999, train perp. = 90.557, wps = 5928, dw:norm() = 5.871, lr = 1.000, since beginning = 10 mins. | |
Validation set perplexity : 129.228 | |
epoch = 4.099, train perp. = 89.258, wps = 5900, dw:norm() = 6.362, lr = 1.000, since beginning = 11 mins. | |
epoch = 4.199, train perp. = 88.041, wps = 5904, dw:norm() = 5.872, lr = 1.000, since beginning = 11 mins. | |
epoch = 4.299, train perp. = 86.847, wps = 5907, dw:norm() = 5.515, lr = 1.000, since beginning = 11 mins. | |
epoch = 4.399, train perp. = 85.725, wps = 5910, dw:norm() = 5.669, lr = 1.000, since beginning = 12 mins. | |
epoch = 4.498, train perp. = 84.619, wps = 5912, dw:norm() = 6.013, lr = 1.000, since beginning = 12 mins. | |
epoch = 4.598, train perp. = 83.630, wps = 5915, dw:norm() = 5.475, lr = 1.000, since beginning = 12 mins. | |
epoch = 4.698, train perp. = 82.630, wps = 5917, dw:norm() = 5.926, lr = 1.000, since beginning = 12 mins. | |
epoch = 4.798, train perp. = 81.651, wps = 5920, dw:norm() = 6.337, lr = 1.000, since beginning = 13 mins. | |
epoch = 4.898, train perp. = 80.736, wps = 5922, dw:norm() = 5.998, lr = 1.000, since beginning = 13 mins. | |
epoch = 4.998, train perp. = 79.884, wps = 5924, dw:norm() = 5.797, lr = 1.000, since beginning = 13 mins. | |
Validation set perplexity : 127.408 | |
epoch = 5.098, train perp. = 78.803, wps = 5901, dw:norm() = 6.709, lr = 0.500, since beginning = 13 mins. | |
epoch = 5.198, train perp. = 77.477, wps = 5903, dw:norm() = 5.780, lr = 0.500, since beginning = 14 mins. | |
epoch = 5.297, train perp. = 75.903, wps = 5906, dw:norm() = 6.548, lr = 0.500, since beginning = 14 mins. | |
epoch = 5.397, train perp. = 74.283, wps = 5898, dw:norm() = 5.748, lr = 0.500, since beginning = 14 mins. | |
epoch = 5.497, train perp. = 72.535, wps = 5885, dw:norm() = 6.706, lr = 0.500, since beginning = 14 mins. | |
epoch = 5.597, train perp. = 70.703, wps = 5884, dw:norm() = 6.130, lr = 0.500, since beginning = 15 mins. | |
epoch = 5.697, train perp. = 68.802, wps = 5886, dw:norm() = 6.020, lr = 0.500, since beginning = 15 mins. | |
epoch = 5.797, train perp. = 66.852, wps = 5889, dw:norm() = 6.667, lr = 0.500, since beginning = 15 mins. | |
epoch = 5.897, train perp. = 64.812, wps = 5891, dw:norm() = 6.888, lr = 0.500, since beginning = 15 mins. | |
epoch = 5.997, train perp. = 62.675, wps = 5894, dw:norm() = 6.477, lr = 0.500, since beginning = 16 mins. | |
Validation set perplexity : 120.604 | |
epoch = 6.096, train perp. = 61.519, wps = 5876, dw:norm() = 7.066, lr = 0.250, since beginning = 16 mins. | |
epoch = 6.196, train perp. = 60.450, wps = 5878, dw:norm() = 6.206, lr = 0.250, since beginning = 16 mins. | |
epoch = 6.296, train perp. = 59.331, wps = 5881, dw:norm() = 6.496, lr = 0.250, since beginning = 17 mins. | |
epoch = 6.396, train perp. = 58.248, wps = 5883, dw:norm() = 6.420, lr = 0.250, since beginning = 17 mins. | |
epoch = 6.496, train perp. = 57.159, wps = 5885, dw:norm() = 6.532, lr = 0.250, since beginning = 17 mins. | |
epoch = 6.596, train perp. = 56.044, wps = 5888, dw:norm() = 6.597, lr = 0.250, since beginning = 17 mins. | |
epoch = 6.696, train perp. = 54.947, wps = 5888, dw:norm() = 6.321, lr = 0.250, since beginning = 18 mins. | |
epoch = 6.796, train perp. = 53.831, wps = 5889, dw:norm() = 6.719, lr = 0.250, since beginning = 18 mins. | |
epoch = 6.895, train perp. = 52.683, wps = 5892, dw:norm() = 7.492, lr = 0.250, since beginning = 18 mins. | |
epoch = 6.995, train perp. = 51.514, wps = 5894, dw:norm() = 6.759, lr = 0.250, since beginning = 18 mins. | |
Validation set perplexity : 119.888 | |
epoch = 7.095, train perp. = 50.914, wps = 5878, dw:norm() = 7.124, lr = 0.125, since beginning = 19 mins. | |
epoch = 7.195, train perp. = 50.357, wps = 5880, dw:norm() = 6.863, lr = 0.125, since beginning = 19 mins. | |
epoch = 7.295, train perp. = 49.787, wps = 5882, dw:norm() = 6.866, lr = 0.125, since beginning = 19 mins. | |
epoch = 7.395, train perp. = 49.225, wps = 5884, dw:norm() = 6.902, lr = 0.125, since beginning = 19 mins. | |
epoch = 7.495, train perp. = 48.669, wps = 5886, dw:norm() = 6.994, lr = 0.125, since beginning = 20 mins. | |
epoch = 7.594, train perp. = 48.101, wps = 5887, dw:norm() = 7.311, lr = 0.125, since beginning = 20 mins. | |
epoch = 7.694, train perp. = 47.532, wps = 5889, dw:norm() = 6.200, lr = 0.125, since beginning = 20 mins. | |
epoch = 7.794, train perp. = 46.964, wps = 5891, dw:norm() = 7.147, lr = 0.125, since beginning = 20 mins. | |
epoch = 7.894, train perp. = 46.371, wps = 5890, dw:norm() = 7.208, lr = 0.125, since beginning = 21 mins. | |
epoch = 7.994, train perp. = 45.763, wps = 5866, dw:norm() = 7.007, lr = 0.125, since beginning = 21 mins. | |
Validation set perplexity : 120.694 | |
epoch = 8.094, train perp. = 45.463, wps = 5836, dw:norm() = 6.953, lr = 0.062, since beginning = 21 mins. | |
epoch = 8.194, train perp. = 45.191, wps = 5838, dw:norm() = 7.360, lr = 0.062, since beginning = 22 mins. | |
epoch = 8.294, train perp. = 44.910, wps = 5840, dw:norm() = 6.803, lr = 0.062, since beginning = 22 mins. | |
epoch = 8.393, train perp. = 44.628, wps = 5843, dw:norm() = 7.038, lr = 0.062, since beginning = 22 mins. | |
epoch = 8.493, train perp. = 44.356, wps = 5844, dw:norm() = 7.071, lr = 0.062, since beginning = 23 mins. | |
epoch = 8.593, train perp. = 44.078, wps = 5847, dw:norm() = 7.185, lr = 0.062, since beginning = 23 mins. | |
epoch = 8.693, train perp. = 43.787, wps = 5849, dw:norm() = 6.847, lr = 0.062, since beginning = 23 mins. | |
epoch = 8.793, train perp. = 43.503, wps = 5851, dw:norm() = 7.154, lr = 0.062, since beginning = 23 mins. | |
epoch = 8.893, train perp. = 43.206, wps = 5853, dw:norm() = 7.368, lr = 0.062, since beginning = 24 mins. | |
epoch = 8.993, train perp. = 42.904, wps = 5855, dw:norm() = 6.851, lr = 0.062, since beginning = 24 mins. | |
Validation set perplexity : 121.126 | |
epoch = 9.093, train perp. = 42.749, wps = 5843, dw:norm() = 7.673, lr = 0.031, since beginning = 24 mins. | |
epoch = 9.192, train perp. = 42.609, wps = 5845, dw:norm() = 7.562, lr = 0.031, since beginning = 24 mins. | |
epoch = 9.292, train perp. = 42.467, wps = 5846, dw:norm() = 7.170, lr = 0.031, since beginning = 25 mins. | |
epoch = 9.392, train perp. = 42.326, wps = 5848, dw:norm() = 7.043, lr = 0.031, since beginning = 25 mins. | |
epoch = 9.492, train perp. = 42.182, wps = 5850, dw:norm() = 7.302, lr = 0.031, since beginning = 25 mins. | |
epoch = 9.592, train perp. = 42.040, wps = 5851, dw:norm() = 6.767, lr = 0.031, since beginning = 25 mins. | |
epoch = 9.692, train perp. = 41.890, wps = 5853, dw:norm() = 6.562, lr = 0.031, since beginning = 26 mins. | |
epoch = 9.792, train perp. = 41.741, wps = 5854, dw:norm() = 7.022, lr = 0.031, since beginning = 26 mins. | |
epoch = 9.892, train perp. = 41.587, wps = 5856, dw:norm() = 6.936, lr = 0.031, since beginning = 26 mins. | |
epoch = 9.991, train perp. = 41.427, wps = 5857, dw:norm() = 7.196, lr = 0.031, since beginning = 26 mins. | |
Validation set perplexity : 121.279 | |
epoch = 10.091, train perp. = 41.344, wps = 5847, dw:norm() = 7.943, lr = 0.016, since beginning = 27 mins. | |
epoch = 10.191, train perp. = 41.268, wps = 5848, dw:norm() = 7.833, lr = 0.016, since beginning = 27 mins. | |
epoch = 10.291, train perp. = 41.191, wps = 5850, dw:norm() = 6.838, lr = 0.016, since beginning = 27 mins. | |
epoch = 10.391, train perp. = 41.117, wps = 5851, dw:norm() = 7.905, lr = 0.016, since beginning = 27 mins. | |
epoch = 10.491, train perp. = 41.040, wps = 5853, dw:norm() = 7.777, lr = 0.016, since beginning = 28 mins. | |
epoch = 10.591, train perp. = 40.963, wps = 5855, dw:norm() = 7.496, lr = 0.016, since beginning = 28 mins. | |
epoch = 10.690, train perp. = 40.883, wps = 5856, dw:norm() = 6.996, lr = 0.016, since beginning = 28 mins. | |
epoch = 10.790, train perp. = 40.800, wps = 5858, dw:norm() = 6.884, lr = 0.016, since beginning = 29 mins. | |
epoch = 10.890, train perp. = 40.712, wps = 5859, dw:norm() = 6.615, lr = 0.016, since beginning = 29 mins. | |
epoch = 10.990, train perp. = 40.622, wps = 5861, dw:norm() = 7.243, lr = 0.016, since beginning = 29 mins. | |
Validation set perplexity : 121.220 | |
epoch = 11.090, train perp. = 40.575, wps = 5851, dw:norm() = 7.736, lr = 0.008, since beginning = 29 mins. | |
epoch = 11.190, train perp. = 40.533, wps = 5852, dw:norm() = 7.366, lr = 0.008, since beginning = 30 mins. | |
epoch = 11.290, train perp. = 40.489, wps = 5854, dw:norm() = 7.565, lr = 0.008, since beginning = 30 mins. | |
epoch = 11.390, train perp. = 40.446, wps = 5855, dw:norm() = 7.204, lr = 0.008, since beginning = 30 mins. | |
epoch = 11.489, train perp. = 40.404, wps = 5857, dw:norm() = 7.290, lr = 0.008, since beginning = 30 mins. | |
epoch = 11.589, train perp. = 40.362, wps = 5858, dw:norm() = 7.373, lr = 0.008, since beginning = 31 mins. | |
epoch = 11.689, train perp. = 40.317, wps = 5860, dw:norm() = 7.427, lr = 0.008, since beginning = 31 mins. | |
epoch = 11.789, train perp. = 40.269, wps = 5861, dw:norm() = 7.377, lr = 0.008, since beginning = 31 mins. | |
epoch = 11.889, train perp. = 40.218, wps = 5862, dw:norm() = 7.501, lr = 0.008, since beginning = 31 mins. | |
epoch = 11.989, train perp. = 40.167, wps = 5864, dw:norm() = 7.092, lr = 0.008, since beginning = 32 mins. | |
Validation set perplexity : 120.997 | |
epoch = 12.089, train perp. = 40.137, wps = 5855, dw:norm() = 8.201, lr = 0.004, since beginning = 32 mins. | |
epoch = 12.189, train perp. = 40.113, wps = 5856, dw:norm() = 6.993, lr = 0.004, since beginning = 32 mins. | |
epoch = 12.288, train perp. = 40.090, wps = 5858, dw:norm() = 7.350, lr = 0.004, since beginning = 32 mins. | |
epoch = 12.388, train perp. = 40.065, wps = 5859, dw:norm() = 7.076, lr = 0.004, since beginning = 33 mins. | |
epoch = 12.488, train perp. = 40.042, wps = 5860, dw:norm() = 7.277, lr = 0.004, since beginning = 33 mins. | |
epoch = 12.588, train perp. = 40.020, wps = 5862, dw:norm() = 7.907, lr = 0.004, since beginning = 33 mins. | |
epoch = 12.688, train perp. = 39.995, wps = 5863, dw:norm() = 7.579, lr = 0.004, since beginning = 34 mins. | |
epoch = 12.788, train perp. = 39.967, wps = 5864, dw:norm() = 6.889, lr = 0.004, since beginning = 34 mins. | |
epoch = 12.888, train perp. = 39.940, wps = 5865, dw:norm() = 7.454, lr = 0.004, since beginning = 34 mins. | |
epoch = 12.988, train perp. = 39.912, wps = 5866, dw:norm() = 6.979, lr = 0.004, since beginning = 34 mins. | |
Validation set perplexity : 120.722 | |
Test set perplexity : 116.110 | |
Training is over. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment