Baseline

gistfile1.txt

[01/30/17 13:57:47 INFO] Using GPU(s): 1	
[01/30/17 13:57:47 INFO] Loading data from '../data/translate-train.t7'...	
[01/30/17 13:57:51 INFO]  * vocabulary size: source = 50004; target = 50004	
[01/30/17 13:57:51 INFO]  * additional features: source = 0; target = 0	
[01/30/17 13:57:51 INFO]  * maximum sequence length: source = 50; target = 51	
[01/30/17 13:57:51 INFO]  * number of training sentences: 100000	
[01/30/17 13:57:51 INFO]  * maximum batch size: 64	
[01/30/17 13:57:51 INFO] Building model...	
[01/30/17 13:57:55 INFO]  * using input feeding	
[01/30/17 13:57:56 INFO] Initializing parameters...	
[01/30/17 13:57:58 INFO]  * number of parameters: 80810004	
[01/30/17 13:57:58 INFO] Preparing memory optimization...	
[01/30/17 13:57:58 INFO]  * sharing 67% of output/gradInput tensors memory between clones	
[01/30/17 13:57:58 INFO] Start training...	
[01/30/17 13:57:58 INFO] 	
[01/30/17 13:58:39 INFO] Epoch 1 ; Iteration 50/1588 ; Learning rate 1.0000 ; Source tokens/s 1694 ; Perplexity 59815.69	
[01/30/17 13:59:14 INFO] Epoch 1 ; Iteration 100/1588 ; Learning rate 1.0000 ; Source tokens/s 1850 ; Perplexity 23257.21	
[01/30/17 13:59:49 INFO] Epoch 1 ; Iteration 150/1588 ; Learning rate 1.0000 ; Source tokens/s 1888 ; Perplexity 12214.27	
[01/30/17 14:00:23 INFO] Epoch 1 ; Iteration 200/1588 ; Learning rate 1.0000 ; Source tokens/s 1906 ; Perplexity 16475.29	
[01/30/17 14:00:59 INFO] Epoch 1 ; Iteration 250/1588 ; Learning rate 1.0000 ; Source tokens/s 1893 ; Perplexity 11417.76	
[01/30/17 14:01:37 INFO] Epoch 1 ; Iteration 300/1588 ; Learning rate 1.0000 ; Source tokens/s 1870 ; Perplexity 8347.42	
[01/30/17 14:02:47 INFO] Epoch 1 ; Iteration 350/1588 ; Learning rate 1.0000 ; Source tokens/s 1686 ; Perplexity 6312.13	
[01/30/17 14:03:46 INFO] Epoch 1 ; Iteration 400/1588 ; Learning rate 1.0000 ; Source tokens/s 1584 ; Perplexity 5105.10	
[01/30/17 14:04:42 INFO] Epoch 1 ; Iteration 450/1588 ; Learning rate 1.0000 ; Source tokens/s 1539 ; Perplexity 4215.84	
[01/30/17 14:05:16 INFO] Epoch 1 ; Iteration 500/1588 ; Learning rate 1.0000 ; Source tokens/s 1585 ; Perplexity 3583.24	
[01/30/17 14:05:52 INFO] Epoch 1 ; Iteration 550/1588 ; Learning rate 1.0000 ; Source tokens/s 1618 ; Perplexity 3101.76	
[01/30/17 14:06:29 INFO] Epoch 1 ; Iteration 600/1588 ; Learning rate 1.0000 ; Source tokens/s 1659 ; Perplexity 2691.09	
[01/30/17 14:07:03 INFO] Epoch 1 ; Iteration 650/1588 ; Learning rate 1.0000 ; Source tokens/s 1678 ; Perplexity 2403.07	
[01/30/17 14:07:37 INFO] Epoch 1 ; Iteration 700/1588 ; Learning rate 1.0000 ; Source tokens/s 1700 ; Perplexity 2166.73	
[01/30/17 14:08:12 INFO] Epoch 1 ; Iteration 750/1588 ; Learning rate 1.0000 ; Source tokens/s 1722 ; Perplexity 1964.68	
[01/30/17 14:08:44 INFO] Epoch 1 ; Iteration 800/1588 ; Learning rate 1.0000 ; Source tokens/s 1735 ; Perplexity 1805.84	
[01/30/17 14:09:20 INFO] Epoch 1 ; Iteration 850/1588 ; Learning rate 1.0000 ; Source tokens/s 1756 ; Perplexity 1657.17	
[01/30/17 14:09:55 INFO] Epoch 1 ; Iteration 900/1588 ; Learning rate 1.0000 ; Source tokens/s 1770 ; Perplexity 1535.65	
[01/30/17 14:10:31 INFO] Epoch 1 ; Iteration 950/1588 ; Learning rate 1.0000 ; Source tokens/s 1787 ; Perplexity 1423.09	
[01/30/17 14:11:08 INFO] Epoch 1 ; Iteration 1000/1588 ; Learning rate 1.0000 ; Source tokens/s 1808 ; Perplexity 1322.60	
[01/30/17 14:11:42 INFO] Epoch 1 ; Iteration 1050/1588 ; Learning rate 1.0000 ; Source tokens/s 1815 ; Perplexity 1245.38	
[01/30/17 14:12:14 INFO] Epoch 1 ; Iteration 1100/1588 ; Learning rate 1.0000 ; Source tokens/s 1819 ; Perplexity 1179.19	
[01/30/17 14:12:47 INFO] Epoch 1 ; Iteration 1150/1588 ; Learning rate 1.0000 ; Source tokens/s 1827 ; Perplexity 1116.86	
[01/30/17 14:13:22 INFO] Epoch 1 ; Iteration 1200/1588 ; Learning rate 1.0000 ; Source tokens/s 1835 ; Perplexity 1057.75	
[01/30/17 14:13:59 INFO] Epoch 1 ; Iteration 1250/1588 ; Learning rate 1.0000 ; Source tokens/s 1846 ; Perplexity 1001.85	
[01/30/17 14:14:31 INFO] Epoch 1 ; Iteration 1300/1588 ; Learning rate 1.0000 ; Source tokens/s 1853 ; Perplexity 954.77	
[01/30/17 14:15:08 INFO] Epoch 1 ; Iteration 1350/1588 ; Learning rate 1.0000 ; Source tokens/s 1859 ; Perplexity 910.43	
[01/30/17 14:15:42 INFO] Epoch 1 ; Iteration 1400/1588 ; Learning rate 1.0000 ; Source tokens/s 1865 ; Perplexity 869.99	
[01/30/17 14:16:17 INFO] Epoch 1 ; Iteration 1450/1588 ; Learning rate 1.0000 ; Source tokens/s 1870 ; Perplexity 832.83	
[01/30/17 14:16:52 INFO] Epoch 1 ; Iteration 1500/1588 ; Learning rate 1.0000 ; Source tokens/s 1876 ; Perplexity 798.39	
[01/30/17 14:17:27 INFO] Epoch 1 ; Iteration 1550/1588 ; Learning rate 1.0000 ; Source tokens/s 1884 ; Perplexity 766.12	
[01/30/17 14:18:02 INFO] Validation perplexity: 233.49	
[01/30/17 14:18:02 INFO] Saving checkpoint to 'model_epoch1_233.49.t7'...	
[01/30/17 14:18:05 INFO] 	
[01/30/17 14:18:37 INFO] Epoch 2 ; Iteration 50/1588 ; Learning rate 1.0000 ; Source tokens/s 2026 ; Perplexity 198.42	
[01/30/17 14:19:10 INFO] Epoch 2 ; Iteration 100/1588 ; Learning rate 1.0000 ; Source tokens/s 1993 ; Perplexity 195.34	
[01/30/17 14:19:46 INFO] Epoch 2 ; Iteration 150/1588 ; Learning rate 1.0000 ; Source tokens/s 1999 ; Perplexity 192.29	
[01/30/17 14:20:23 INFO] Epoch 2 ; Iteration 200/1588 ; Learning rate 1.0000 ; Source tokens/s 2056 ; Perplexity 192.42