API tools faq
paste
Advertisement
suthagar23

29-03-2018 23:31 Embedding

suthagar23
Mar 29th, 2018
121
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 91.31 KB | None | 0 0
raw download clone embed print report
  1. Data : 10%
  2. Time taken : 09mins
  3.  
  4. batch_size = 128
  5. embedding_size = 128 # Dimension of the embedding vector.
  6. skip_window = 2 # How many words to consider left and right.
  7. num_skips = 2 # How many times to reuse an input to generate a label.
  8. num_sampled = 64 # Number of negative examples to sample.
  9. trianing num_steps = 100001
  10.  
  11. ------------------------------------------------------------------------------------------------------
  12.  
  13. /usr/bin/python3.6 /home/suthagar/PycharmProjects/wordembedding/tensorflow/tf-basic-1.py
  14. 31
  15. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-2-output.txt
  16. Data size 128516
  17. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-0-output.txt
  18. Data size 257642
  19. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-1-output.txt
  20. Data size 386496
  21. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-10-output.txt
  22. Data size 515056
  23. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-11-output.txt
  24. Data size 643900
  25. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-12-output.txt
  26. Data size 772888
  27. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-13-output.txt
  28. Data size 902749
  29. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-14-output.txt
  30. Data size 1032093
  31. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-15-output.txt
  32. Data size 1160996
  33. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-16-output.txt
  34. Data size 1290329
  35. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-17-output.txt
  36. Data size 1419246
  37. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-18-output.txt
  38. Data size 1547816
  39. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-19-output.txt
  40. Data size 1677604
  41. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-20-output.txt
  42. Data size 1806376
  43. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-21-output.txt
  44. Data size 1934628
  45. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-22-output.txt
  46. Data size 2064353
  47. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-23-output.txt
  48. Data size 2193694
  49. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-24-output.txt
  50. Data size 2323519
  51. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-25-output.txt
  52. Data size 2452664
  53. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-26-output.txt
  54. Data size 2580696
  55. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-27-output.txt
  56. Data size 2709547
  57. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-28-output.txt
  58. Data size 2839134
  59. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-29-output.txt
  60. Data size 2967339
  61. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-3-output.txt
  62. Data size 3097342
  63. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-30-output.txt
  64. Data size 3173173
  65. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-4-output.txt
  66. Data size 3302455
  67. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-5-output.txt
  68. Data size 3431952
  69. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-6-output.txt
  70. Data size 3561358
  71. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-7-output.txt
  72. Data size 3690530
  73. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-8-output.txt
  74. Data size 3819956
  75. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00001-of-00100/news.en-00001-of-00100-out-9-output.txt
  76. Data size 3948945
  77. 31
  78. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-2-output.txt
  79. Data size 4077445
  80. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-0-output.txt
  81. Data size 4205863
  82. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-1-output.txt
  83. Data size 4334906
  84. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-10-output.txt
  85. Data size 4463802
  86. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-11-output.txt
  87. Data size 4594170
  88. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-12-output.txt
  89. Data size 4723159
  90. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-13-output.txt
  91. Data size 4851463
  92. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-14-output.txt
  93. Data size 4980526
  94. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-15-output.txt
  95. Data size 5109599
  96. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-16-output.txt
  97. Data size 5237380
  98. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-17-output.txt
  99. Data size 5365879
  100. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-18-output.txt
  101. Data size 5495692
  102. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-19-output.txt
  103. Data size 5625190
  104. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-20-output.txt
  105. Data size 5753760
  106. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-21-output.txt
  107. Data size 5883541
  108. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-22-output.txt
  109. Data size 6012679
  110. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-23-output.txt
  111. Data size 6141511
  112. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-24-output.txt
  113. Data size 6270866
  114. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-25-output.txt
  115. Data size 6400908
  116. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-26-output.txt
  117. Data size 6529719
  118. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-27-output.txt
  119. Data size 6659897
  120. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-28-output.txt
  121. Data size 6789040
  122. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-29-output.txt
  123. Data size 6917674
  124. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-3-output.txt
  125. Data size 7046961
  126. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-30-output.txt
  127. Data size 7136254
  128. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-4-output.txt
  129. Data size 7265195
  130. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-5-output.txt
  131. Data size 7393928
  132. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-6-output.txt
  133. Data size 7523897
  134. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-7-output.txt
  135. Data size 7652253
  136. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-8-output.txt
  137. Data size 7781490
  138. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00002-of-00100/news.en-00002-of-00100-out-9-output.txt
  139. Data size 7910130
  140. 31
  141. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-2-output.txt
  142. Data size 8038646
  143. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-0-output.txt
  144. Data size 8167772
  145. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-1-output.txt
  146. Data size 8296626
  147. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-10-output.txt
  148. Data size 8425186
  149. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-11-output.txt
  150. Data size 8554030
  151. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-12-output.txt
  152. Data size 8683018
  153. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-13-output.txt
  154. Data size 8812879
  155. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-14-output.txt
  156. Data size 8942223
  157. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-15-output.txt
  158. Data size 9071126
  159. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-16-output.txt
  160. Data size 9200459
  161. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-17-output.txt
  162. Data size 9329376
  163. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-18-output.txt
  164. Data size 9457946
  165. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-19-output.txt
  166. Data size 9587734
  167. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-20-output.txt
  168. Data size 9716506
  169. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-21-output.txt
  170. Data size 9844758
  171. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-22-output.txt
  172. Data size 9974483
  173. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-23-output.txt
  174. Data size 10103824
  175. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-24-output.txt
  176. Data size 10233649
  177. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-25-output.txt
  178. Data size 10362794
  179. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-26-output.txt
  180. Data size 10490826
  181. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-27-output.txt
  182. Data size 10619677
  183. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-28-output.txt
  184. Data size 10749264
  185. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-29-output.txt
  186. Data size 10877469
  187. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-3-output.txt
  188. Data size 11007472
  189. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-30-output.txt
  190. Data size 11083303
  191. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-4-output.txt
  192. Data size 11212585
  193. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-5-output.txt
  194. Data size 11342082
  195. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-6-output.txt
  196. Data size 11471488
  197. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-7-output.txt
  198. Data size 11600660
  199. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-8-output.txt
  200. Data size 11730086
  201. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00003-of-00100/news.en-00003-of-00100-out-9-output.txt
  202. Data size 11859075
  203. 31
  204. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-2-output.txt
  205. Data size 11989071
  206. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-0-output.txt
  207. Data size 12118812
  208. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-1-output.txt
  209. Data size 12248449
  210. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-10-output.txt
  211. Data size 12377701
  212. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-11-output.txt
  213. Data size 12507389
  214. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-12-output.txt
  215. Data size 12636343
  216. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-13-output.txt
  217. Data size 12765008
  218. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-14-output.txt
  219. Data size 12893362
  220. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-15-output.txt
  221. Data size 13022361
  222. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-16-output.txt
  223. Data size 13151575
  224. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-17-output.txt
  225. Data size 13281469
  226. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-18-output.txt
  227. Data size 13411025
  228. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-19-output.txt
  229. Data size 13539980
  230. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-20-output.txt
  231. Data size 13669319
  232. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-21-output.txt
  233. Data size 13799528
  234. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-22-output.txt
  235. Data size 13928314
  236. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-23-output.txt
  237. Data size 14057778
  238. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-24-output.txt
  239. Data size 14186868
  240. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-25-output.txt
  241. Data size 14316248
  242. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-26-output.txt
  243. Data size 14445112
  244. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-27-output.txt
  245. Data size 14573723
  246. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-28-output.txt
  247. Data size 14702089
  248. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-29-output.txt
  249. Data size 14830842
  250. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-3-output.txt
  251. Data size 14960442
  252. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-30-output.txt
  253. Data size 15043117
  254. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-4-output.txt
  255. Data size 15170178
  256. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-5-output.txt
  257. Data size 15298572
  258. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-6-output.txt
  259. Data size 15427872
  260. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-7-output.txt
  261. Data size 15556447
  262. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-8-output.txt
  263. Data size 15684962
  264. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00004-of-00100/news.en-00004-of-00100-out-9-output.txt
  265. Data size 15814026
  266. 31
  267. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-2-output.txt
  268. Data size 15942599
  269. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-0-output.txt
  270. Data size 16071651
  271. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-1-output.txt
  272. Data size 16200802
  273. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-10-output.txt
  274. Data size 16329653
  275. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-11-output.txt
  276. Data size 16458086
  277. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-12-output.txt
  278. Data size 16587360
  279. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-13-output.txt
  280. Data size 16715806
  281. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-14-output.txt
  282. Data size 16845354
  283. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-15-output.txt
  284. Data size 16974268
  285. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-16-output.txt
  286. Data size 17102748
  287. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-17-output.txt
  288. Data size 17230940
  289. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-18-output.txt
  290. Data size 17358654
  291. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-19-output.txt
  292. Data size 17488138
  293. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-20-output.txt
  294. Data size 17616049
  295. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-21-output.txt
  296. Data size 17744559
  297. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-22-output.txt
  298. Data size 17873425
  299. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-23-output.txt
  300. Data size 18002521
  301. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-24-output.txt
  302. Data size 18131879
  303. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-25-output.txt
  304. Data size 18260774
  305. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-26-output.txt
  306. Data size 18390433
  307. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-27-output.txt
  308. Data size 18520568
  309. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-28-output.txt
  310. Data size 18648865
  311. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-29-output.txt
  312. Data size 18778412
  313. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-3-output.txt
  314. Data size 18907842
  315. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-30-output.txt
  316. Data size 18982106
  317. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-4-output.txt
  318. Data size 19111546
  319. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-5-output.txt
  320. Data size 19240618
  321. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-6-output.txt
  322. Data size 19370246
  323. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-7-output.txt
  324. Data size 19499727
  325. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-8-output.txt
  326. Data size 19629967
  327. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00005-of-00100/news.en-00005-of-00100-out-9-output.txt
  328. Data size 19758905
  329. 31
  330. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-2-output.txt
  331. Data size 19888689
  332. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-0-output.txt
  333. Data size 20017844
  334. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-1-output.txt
  335. Data size 20147028
  336. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-10-output.txt
  337. Data size 20276372
  338. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-11-output.txt
  339. Data size 20405762
  340. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-12-output.txt
  341. Data size 20534821
  342. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-13-output.txt
  343. Data size 20664771
  344. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-14-output.txt
  345. Data size 20793963
  346. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-15-output.txt
  347. Data size 20924249
  348. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-16-output.txt
  349. Data size 21053983
  350. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-17-output.txt
  351. Data size 21180626
  352. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-18-output.txt
  353. Data size 21308700
  354. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-19-output.txt
  355. Data size 21436046
  356. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-20-output.txt
  357. Data size 21565510
  358. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-21-output.txt
  359. Data size 21695257
  360. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-22-output.txt
  361. Data size 21823971
  362. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-23-output.txt
  363. Data size 21952660
  364. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-24-output.txt
  365. Data size 22081132
  366. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-25-output.txt
  367. Data size 22210309
  368. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-26-output.txt
  369. Data size 22340291
  370. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-27-output.txt
  371. Data size 22468172
  372. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-28-output.txt
  373. Data size 22597593
  374. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-29-output.txt
  375. Data size 22726774
  376. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-3-output.txt
  377. Data size 22856659
  378. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-30-output.txt
  379. Data size 22926549
  380. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-4-output.txt
  381. Data size 23054433
  382. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-5-output.txt
  383. Data size 23183470
  384. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-6-output.txt
  385. Data size 23311500
  386. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-7-output.txt
  387. Data size 23439513
  388. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-8-output.txt
  389. Data size 23569024
  390. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00006-of-00100/news.en-00006-of-00100-out-9-output.txt
  391. Data size 23698447
  392. 31
  393. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-2-output.txt
  394. Data size 23827259
  395. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-0-output.txt
  396. Data size 23956141
  397. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-1-output.txt
  398. Data size 24085753
  399. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-10-output.txt
  400. Data size 24214584
  401. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-11-output.txt
  402. Data size 24343812
  403. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-12-output.txt
  404. Data size 24472452
  405. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-13-output.txt
  406. Data size 24601478
  407. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-14-output.txt
  408. Data size 24729800
  409. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-15-output.txt
  410. Data size 24858628
  411. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-16-output.txt
  412. Data size 24988401
  413. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-17-output.txt
  414. Data size 25117433
  415. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-18-output.txt
  416. Data size 25246974
  417. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-19-output.txt
  418. Data size 25376880
  419. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-20-output.txt
  420. Data size 25505710
  421. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-21-output.txt
  422. Data size 25636093
  423. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-22-output.txt
  424. Data size 25764367
  425. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-23-output.txt
  426. Data size 25894770
  427. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-24-output.txt
  428. Data size 26023237
  429. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-25-output.txt
  430. Data size 26152387
  431. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-26-output.txt
  432. Data size 26281474
  433. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-27-output.txt
  434. Data size 26411349
  435. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-28-output.txt
  436. Data size 26539480
  437. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-29-output.txt
  438. Data size 26669031
  439. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-3-output.txt
  440. Data size 26797967
  441. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-30-output.txt
  442. Data size 26882981
  443. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-4-output.txt
  444. Data size 27011557
  445. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-5-output.txt
  446. Data size 27141214
  447. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-6-output.txt
  448. Data size 27269621
  449. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-7-output.txt
  450. Data size 27399979
  451. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-8-output.txt
  452. Data size 27528023
  453. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00007-of-00100/news.en-00007-of-00100-out-9-output.txt
  454. Data size 27656510
  455. 31
  456. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-2-output.txt
  457. Data size 27786651
  458. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-0-output.txt
  459. Data size 27915536
  460. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-1-output.txt
  461. Data size 28045392
  462. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-10-output.txt
  463. Data size 28174031
  464. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-11-output.txt
  465. Data size 28303345
  466. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-12-output.txt
  467. Data size 28433809
  468. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-13-output.txt
  469. Data size 28563480
  470. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-14-output.txt
  471. Data size 28693791
  472. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-15-output.txt
  473. Data size 28822938
  474. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-16-output.txt
  475. Data size 28951792
  476. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-17-output.txt
  477. Data size 29079751
  478. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-18-output.txt
  479. Data size 29208861
  480. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-19-output.txt
  481. Data size 29336184
  482. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-20-output.txt
  483. Data size 29465143
  484. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-21-output.txt
  485. Data size 29594464
  486. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-22-output.txt
  487. Data size 29723928
  488. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-23-output.txt
  489. Data size 29853983
  490. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-24-output.txt
  491. Data size 29982303
  492. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-25-output.txt
  493. Data size 30110676
  494. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-26-output.txt
  495. Data size 30239494
  496. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-27-output.txt
  497. Data size 30368856
  498. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-28-output.txt
  499. Data size 30498087
  500. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-29-output.txt
  501. Data size 30627186
  502. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-3-output.txt
  503. Data size 30756337
  504. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-30-output.txt
  505. Data size 30846535
  506. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-4-output.txt
  507. Data size 30974613
  508. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-5-output.txt
  509. Data size 31104882
  510. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-6-output.txt
  511. Data size 31233016
  512. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-7-output.txt
  513. Data size 31361489
  514. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-8-output.txt
  515. Data size 31491064
  516. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00008-of-00100/news.en-00008-of-00100-out-9-output.txt
  517. Data size 31620253
  518. 31
  519. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-2-output.txt
  520. Data size 31749021
  521. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-0-output.txt
  522. Data size 31877554
  523. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-1-output.txt
  524. Data size 32006579
  525. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-10-output.txt
  526. Data size 32134943
  527. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-11-output.txt
  528. Data size 32263697
  529. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-12-output.txt
  530. Data size 32392094
  531. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-13-output.txt
  532. Data size 32520776
  533. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-14-output.txt
  534. Data size 32648946
  535. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-15-output.txt
  536. Data size 32777232
  537. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-16-output.txt
  538. Data size 32906543
  539. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-17-output.txt
  540. Data size 33034524
  541. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-18-output.txt
  542. Data size 33161865
  543. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-19-output.txt
  544. Data size 33291150
  545. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-20-output.txt
  546. Data size 33420425
  547. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-21-output.txt
  548. Data size 33549104
  549. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-22-output.txt
  550. Data size 33678340
  551. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-23-output.txt
  552. Data size 33807206
  553. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-24-output.txt
  554. Data size 33935612
  555. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-25-output.txt
  556. Data size 34063347
  557. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-26-output.txt
  558. Data size 34192784
  559. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-27-output.txt
  560. Data size 34321947
  561. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-28-output.txt
  562. Data size 34451372
  563. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-29-output.txt
  564. Data size 34580332
  565. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-3-output.txt
  566. Data size 34710265
  567. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-30-output.txt
  568. Data size 34786171
  569. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-4-output.txt
  570. Data size 34915962
  571. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-5-output.txt
  572. Data size 35046789
  573. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-6-output.txt
  574. Data size 35175649
  575. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-7-output.txt
  576. Data size 35304020
  577. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-8-output.txt
  578. Data size 35432899
  579. Processing file : /media/suthagar/Data/Corpus/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/tmp/pre-processed-final-files/news.en-00009-of-00100/news.en-00009-of-00100-out-9-output.txt
  580. Data size 35562054
  581. Most common words (+UNK) [['UNK', 1882574], ('The_DT', 477451), ('say_V', 378571), ('I_PRP', 181851), ('year_N', 144290)]
  582. Sample data [480, 3443, 7056, 282, 1040, 21802, 10833, 8265, 0, 41225] ['McCain_N', 'campaign_V', 'Nashville_N', 'Saturday_N', 'night_N.', 'Travelers_N', 'Neville_N', 'Catherine_N', 'UNK', 'trekked_N']
  583. 3443 campaign_V -> 480 McCain_N
  584. 3443 campaign_V -> 7056 Nashville_N
  585. 7056 Nashville_N -> 282 Saturday_N
  586. 7056 Nashville_N -> 3443 campaign_V
  587. 282 Saturday_N -> 7056 Nashville_N
  588. 282 Saturday_N -> 1040 night_N.
  589. 1040 night_N. -> 282 Saturday_N
  590. 1040 night_N. -> 21802 Travelers_N
  591. WARNING:tensorflow:From /home/suthagar/PycharmProjects/wordembedding/tensorflow/tf-basic-1.py:204: calling reduce_sum (from tensorflow.python.ops.math_ops) with keep_dims is deprecated and will be removed in a future version.
  592. Instructions for updating:
  593. keep_dims is deprecated, use keepdims instead
  594. 2018-03-29 23:22:47.326391: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
  595. 2018-03-29 23:22:48.083983: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:895] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
  596. 2018-03-29 23:22:48.084598: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1105] Found device 0 with properties:
  597. name: GeForce GT 740M major: 3 minor: 5 memoryClockRate(GHz): 1.0325
  598. pciBusID: 0000:01:00.0
  599. totalMemory: 1.96GiB freeMemory: 1.23GiB
  600. 2018-03-29 23:22:48.084624: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1195] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GT 740M, pci bus id: 0000:01:00.0, compute capability: 3.5)
  601. Initialized
  602. Average loss at step 0 : 275.34576416015625
  603. Nearest to even_R: inconvenient_N, feces_N, flaw_N, Heels_N, inadvertent_N, windy_N, receive_V., Transportation_N,
  604. Nearest to new_A: slows_N., tributary_N, Florida_N., privatise_N, NAO_N, Subaru_N, Southern_A, Samak_N,
  605. Nearest to woman_N: chemist_N, Mir_Hossein_Mousavi_TGRAM, day_N., dissemination_N, vandalise_V, quarrel_N, sprout_V, Shatner_N,
  606. Nearest to three_CD: Rashard_N, midsized_V, Aquino_N, creature_N, refusal_N, MF_N, Treasurer_N, fraudulent_N.,
  607. Nearest to group_N: Monegan_N, possibility_N., captive_N., shipbuilding_N, checked_N, Noonan_N, Development_N, speedboat_N,
  608. Nearest to US_N: proverbial_N, misunderstand_V, Trott_N, diary_A., Cultural_A, Graceland_N, bn_N, lowfat_N,
  609. Nearest to state_N: clenched_N, anyone_N, creditor_N., catastrophic_A., PlayStation_N, direction_N., infertility_N, nook_N,
  610. Nearest to But_CC: antipiracy_N, HRT_N, preach_V, analogue_N, institution_N., Archaeology_N, rheumatoid_N, selfdefence_N,
  611. Nearest to many_A: dabble_V, Mitt_N, That_DT., governorship_N, cyberspace_N, detergent_N, Va_N, Grainger_N,
  612. Nearest to Mr_N: Canadiens_N, Spotlight_N, disorganize_V, Harris_N., government_N, Crowley_N, treason_N, Area_N.,
  613. Nearest to next_A: investor_N., ale_N, runup_N, restrict_V., Introduced_V, forthcoming_V., nonbeliever_N, French_A.,
  614. Nearest to also_R: vicepresidential_N, Rahm_N, nonrecurring_V, climb_N., APS_N, yearolds_N., quo_N, flow_N.,
  615. Nearest to part_N: OK_N., semiautomatic_A, pear_N, Potters_N, UAE_N, Seasonal_A, measure_N., erectile_N,
  616. Nearest to go_V: differentiate_N, manhunt_N, attend_V., assure_V., transgression_N, usable_A, enthusiasm_N, Sending_V,
  617. Nearest to year_N.: together_R., Pilgrims_N, CDMA_N, entrant_N., Sheppard_N, ABS_N, superior_N, prohibit_N,
  618. Nearest to back_R: pricefixing_V, trace_V, Britt_N, polished_N, bulky_N, nosedive_V, Didn_N, Stade_de_France_TGRAM,
  619. Average loss at step 2000 : 126.08367293930054
  620. Average loss at step 4000 : 58.06661507368088
  621. Average loss at step 6000 : 36.36220999312401
  622. Average loss at step 8000 : 25.69445154762268
  623. Average loss at step 10000 : 19.276764664173125
  624. Nearest to even_R: flaw_N, Democrat_N, Albert_N, ingredient_N, credit_N, Transportation_N, defense_N, receive_V.,
  625. Nearest to new_A: Southern_A, local_N, northern_A, Iran_N., Florida_N., sought_N, withholding_N, especially_R,
  626. Nearest to woman_N: day_N., dissemination_N, favour_N, Bahrain_N, turn_V, pas_N, transport_N, pressure_N,
  627. Nearest to three_CD: Brady_N, Constitution_N, pack_N, widespread_A, creature_N, absorbed_N, press_V, arrest_V,
  628. Nearest to group_N: possibility_N., Development_N, checked_N, Monegan_N, captive_N., slam_N, advise_V, dress_V,
  629. Nearest to US_N: bn_N, thorough_N, threaten_V, UNK, force_N, fix_V, do_V., America_N.,
  630. Nearest to state_N: anyone_N, Secretary_Tim_Geithner_TGRAM, ensure_V, ship_N, report_V, Dutch_N, guilty_A, operating_N,
  631. Nearest to But_CC: excite_V, institution_N., Gross_N, count_N, sign_V, Norway_R, Connecticut_N, surround_V,
  632. Nearest to many_A: date_V, Mitt_N, index_N, Va_N, law_N., come_V., marketplace_N, These_DT,
  633. Nearest to Mr_N: government_N, everyone_N, UNK, Canadiens_N, withdraw_N, Crowley_N, voter_N, hurt_N,
  634. Nearest to next_A: investor_N., Sean_N, runup_N, They_PRP, TB_N, regular_A, run_V, brightly_R,
  635. Nearest to also_R: see_V, two_CD, UNK, subpoena_N, Neighbors_N, UBS_N, spoke_N, Steele_N,
  636. Nearest to part_N: measure_N., UAE_N, semiautomatic_A, high_A., phase_N, really_R, America_N, explore_V,
  637. Nearest to go_V: euro_N., fry_V, enthusiasm_N, On_IN, slow_V., press_N, enjoys_N, two_CD,
  638. Nearest to year_N.: together_R., famous_A, marked_N, nonalcoholic_A, enjoy_V, credible_A, celebrity_N, yuan_N,
  639. Nearest to back_R: gun_N, trace_V, Mark_N, White_N, Writers_N, suggestion_N, While_IN, Guardian_A,
  640. Average loss at step 12000 : 15.084676003694534
  641. Average loss at step 14000 : 12.499318482160568
  642. Average loss at step 16000 : 10.57048930168152
  643. Average loss at step 18000 : 9.099439950704575
  644. Average loss at step 20000 : 8.241738182783127
  645. Nearest to even_R: flaw_N, ingredient_N, unheard_A, Democrat_N, financier_N, say_V, Albert_N, youth_N.,
  646. Nearest to new_A: The_DT, local_N, Southern_A, Kline_V, UNK, Iran_N., say_V, Florida_N.,
  647. Nearest to woman_N: chemist_N, Bahrain_N, upscale_A, dissemination_N, day_N., turn_V, sprout_V, favour_N,
  648. Nearest to three_CD: two_CD, Constitution_N, Brady_N, absorbed_N, ushered_A, Bolshoi_N, pack_N, narcotic_N,
  649. Nearest to group_N: Monegan_N, possibility_N., captive_N., slam_N, Noonan_N, Jews_N., checked_N, advise_V,
  650. Nearest to US_N: UNK, bn_N, thorough_N, force_N, Ware_N, local_N, ample_N, The_DT,
  651. Nearest to state_N: clenched_N, anyone_N, Secretary_Tim_Geithner_TGRAM, alien_N, report_V, ensure_V, improperly_R, Dutch_N,
  652. Nearest to But_CC: UNK, The_DT, say_V, would_MD, excite_V, Connecticut_N, mecca_N, Gross_N,
  653. Nearest to many_A: date_V, law_N., defeat_N., detergent_N, Mitt_N, Va_N, These_DT, Mutual_A,
  654. Nearest to Mr_N: UNK, government_N, say_V, Canadiens_N, Spotlight_N, Oncology_N, voter_N, defend_V,
  655. Nearest to next_A: investor_N., Sean_N, two_CD, runup_N, They_PRP, brightly_R, regular_A, humiliate_V,
  656. Nearest to also_R: UNK, say_V, subpoena_N, The_DT, Neighbors_N, see_V, two_CD, festival_N.,
  657. Nearest to part_N: semiautomatic_A, UAE_N, measure_N., high_A., really_R, OK_N., important_A., phase_N,
  658. Nearest to go_V: enthusiasm_N, two_CD, make_V, The_DT, fry_V, I_PRP, euro_N., hold_V,
  659. Nearest to year_N.: together_R., credible_A, superior_N, nonalcoholic_A, Pilgrims_N, yuan_N, Confederate_N, famous_A,
  660. Nearest to back_R: pricefixing_V, trace_V, gun_N, Britt_N, midweek_N, batter_N, Mark_N, Writers_N,
  661. Average loss at step 22000 : 7.513536925077438
  662. Average loss at step 24000 : 7.122500022649765
  663. Average loss at step 26000 : 6.842666110515594
  664. Average loss at step 28000 : 6.489062655568123
  665. Average loss at step 30000 : 6.18164588189125
  666. Nearest to even_R: flaw_N, go_V, make_V, unheard_A, youth_N., Democrat_N, also_R, financier_N,
  667. Nearest to new_A: local_N, Kline_V, UNK, The_DT, Iran_N., plan_N, Southern_A, say_V,
  668. Nearest to woman_N: vandalise_V, upscale_A, turn_V, chemist_N, Bahrain_N, day_N., dissemination_N, sprout_V,
  669. Nearest to three_CD: two_CD, year_N, absorbed_N, postmodern_N, ushered_A, Faith_N, Constitution_N, narcotic_N,
  670. Nearest to group_N: Monegan_N, possibility_N., slam_N, Noonan_N, Jews_N., scarce_N, advise_V, presenter_N,
  671. Nearest to US_N: bn_N, thorough_N, force_N, Ware_N, local_N, UNK, say_V, The_DT,
  672. Nearest to state_N: clenched_N, anyone_N, Secretary_Tim_Geithner_TGRAM, gondola_N, ensure_V, acceleration_N, alien_N, Gov_Arnold_Schwarzenegger_TGRAM,
  673. Nearest to But_CC: The_DT, UNK, It_PRP, would_MD, say_V, Connecticut_N, excite_V, sign_V,
  674. Nearest to many_A: Lunar_N, law_N., defeat_N., detergent_N, date_V, Mitt_N, These_DT, That_DT.,
  675. Nearest to Mr_N: UNK, say_V, government_N, He_PRP, pamphlet_N, Oncology_N, Spotlight_N, Crowley_N,
  676. Nearest to next_A: two_CD, investor_N., last_A, Sean_N, runup_N, They_PRP, run_V, slept_N,
  677. Nearest to also_R: say_V, UNK, subpoena_N, He_PRP, say_V., see_V, two_CD, festival_N.,
  678. Nearest to part_N: semiautomatic_A, UAE_N, pear_N, really_R, one_CD, Guard_N., OK_N., measure_N.,
  679. Nearest to go_V: I_PRP, make_V, get_V, two_CD, even_R, UNK, like_IN, SAFC_N,
  680. Nearest to year_N.: together_R., credible_A, Confederate_N, Pilgrims_N, nonalcoholic_A, superior_N, yuan_N, famous_A,
  681. Nearest to back_R: pricefixing_V, gun_N, trace_V, Britt_N, midweek_N, batter_N, Mark_N, Stade_de_France_TGRAM,
  682. Average loss at step 32000 : 6.049046798706055
  683. Average loss at step 34000 : 5.990114219665528
  684. Average loss at step 36000 : 5.786115090847016
  685. Average loss at step 38000 : 5.6813979418277745
  686. Average loss at step 40000 : 5.603810606241226
  687. Nearest to even_R: go_V, flaw_N, make_V, youth_N., also_R, ingredient_N, unheard_A, redundancy_N.,
  688. Nearest to new_A: UNK, Kline_V, local_N, plan_N, would_MD, The_DT, Iran_N., sought_N,
  689. Nearest to woman_N: vandalise_V, upscale_A, turn_V, Bahrain_N, enigma_N, alias_N, Robin_van_Persie_TGRAM, dream_N.,
  690. Nearest to three_CD: two_CD, year_N, last_A, next_A, absorbed_N, postmodern_N, time_N, ushered_A,
  691. Nearest to group_N: Monegan_N, possibility_N., company_N, slam_N, also_R, presenter_N, scarce_N, captive_N.,
  692. Nearest to US_N: force_N, say_V, bn_N, Ware_N, thorough_N, local_N, assault_N., collect_N,
  693. Nearest to state_N: clenched_N, anyone_N, gondola_N, ensure_V, alien_N, acceleration_N, Secretary_Tim_Geithner_TGRAM, Gov_Arnold_Schwarzenegger_TGRAM,
  694. Nearest to But_CC: The_DT, It_PRP, would_MD, I_PRP, UNK, He_PRP, In_IN, say_V,
  695. Nearest to many_A: Lunar_N, detergent_N, defeat_N., would_MD, law_N., date_V, These_DT, Mitt_N,
  696. Nearest to Mr_N: UNK, He_PRP, also_R, say_V, government_N, appellate_N, pamphlet_N, contention_N,
  697. Nearest to next_A: two_CD, last_A, investor_N., three_CD, Sean_N, first_R, five_CD, runup_N,
  698. Nearest to also_R: say_V, UNK, say_V., He_PRP, subpoena_N, OTCBB_N, one_CD, WAM_N,
  699. Nearest to part_N: pear_N, semiautomatic_A, one_CD, UAE_N, really_R, Guard_N., OK_N., exhilarate_V,
  700. Nearest to go_V: get_V, I_PRP, make_V, like_IN, even_R, one_CD, long_R, SAFC_N,
  701. Nearest to year_N.: year_N, together_R., Confederate_N, credible_A, nonalcoholic_A, Pilgrims_N, superior_N, month_N,
  702. Nearest to back_R: pricefixing_V, gun_N, trace_V, Britt_N, midweek_N, Mark_N, batter_N, redshirted_V,
  703. Average loss at step 42000 : 5.543679899215698
  704. Average loss at step 44000 : 5.472415296077728
  705. Average loss at step 46000 : 5.4293562195301055
  706. Average loss at step 48000 : 5.3920544502735135
  707. Average loss at step 50000 : 5.359578889608383
  708. Nearest to even_R: go_V, flaw_N, make_V, also_R, youth_N., I_PRP, one_CD, redundancy_N.,
  709. Nearest to new_A: plan_N, local_N, would_MD, UNK, Kline_V, sought_N, Iran_N., service_N,
  710. Nearest to woman_N: vandalise_V, Bahrain_N, upscale_A, alias_N, turn_V, enigma_N, Umberger_N, Burgundy_N,
  711. Nearest to three_CD: two_CD, year_N, last_A, four_CD, one_CD, next_A, Faith_N, time_N,
  712. Nearest to group_N: Monegan_N, possibility_N., company_N, captive_N., also_R, slam_N, batter_N, timetable_N.,
  713. Nearest to US_N: force_N, Ware_N, assault_N., bn_N, collect_N, say_V, thorough_N, local_N,
  714. Nearest to state_N: clenched_N, ensure_V, gondola_N, anyone_N, acceleration_N, alien_N, Secretary_Tim_Geithner_TGRAM, possible_A,
  715. Nearest to But_CC: It_PRP, The_DT, He_PRP, In_IN, would_MD, I_PRP, UNK, And_CC,
  716. Nearest to many_A: Lunar_N, would_MD, detergent_N, defeat_N., get_V, These_DT, And_CC, law_N.,
  717. Nearest to Mr_N: UNK, He_PRP, Ms_N, also_R, But_CC, appellate_N, say_V, defend_V,
  718. Nearest to next_A: last_A, two_CD, investor_N., first_R, three_CD, five_CD, four_CD, take_V,
  719. Nearest to also_R: say_V, UNK, say_V., He_PRP, OTCBB_N, one_CD, subpoena_N, see_V,
  720. Nearest to part_N: pear_N, one_CD, semiautomatic_A, UAE_N, Guard_N., gas_N, really_R, exhilarate_V,
  721. Nearest to go_V: get_V, make_V, I_PRP, one_CD, even_R, like_IN, come_V, But_CC,
  722. Nearest to year_N.: year_N, Confederate_N, month_N, together_R., credible_A, superior_N, nonalcoholic_A, Pilgrims_N,
  723. Nearest to back_R: pricefixing_V, gun_N, Mark_N, Britt_N, trace_V, midweek_N, redshirted_V, batter_N,
  724. Average loss at step 52000 : 5.3201841595172885
  725. Average loss at step 54000 : 5.28888946723938
  726. Average loss at step 56000 : 5.280606016874313
  727. Average loss at step 58000 : 5.269149966955185
  728. Average loss at step 60000 : 5.2402068099975585
  729. Nearest to even_R: go_V, make_V, also_R, flaw_N, one_CD, I_PRP, But_CC, Heels_N,
  730. Nearest to new_A: plan_N, UNK, local_N, Kline_V, would_MD, sought_N, inalienable_A, also_R,
  731. Nearest to woman_N: vandalise_V, upscale_A, alias_N, Bahrain_N, people_N, turn_V, Burgundy_N, Robin_van_Persie_TGRAM,
  732. Nearest to three_CD: two_CD, four_CD, last_A, one_CD, six_CD, year_N, time_N, next_A,
  733. Nearest to group_N: Monegan_N, company_N, possibility_N., captive_N., also_R, timetable_N., government_N, member_N,
  734. Nearest to US_N: force_N, Ware_N, assault_N., collect_N, improves_N., bn_N, local_N, thorough_N,
  735. Nearest to state_N: ensure_V, gondola_N, clenched_N, acceleration_N, anyone_N, primary_N., government_N, alien_N,
  736. Nearest to But_CC: The_DT, It_PRP, He_PRP, In_IN, I_PRP, And_CC, would_MD, UNK,
  737. Nearest to many_A: get_V, Lunar_N, would_MD, detergent_N, defeat_N., These_DT, enough_R, And_CC,
  738. Nearest to Mr_N: He_PRP, UNK, Ms_N, also_R, But_CC, appellate_N, defend_V, contention_N,
  739. Nearest to next_A: last_A, two_CD, investor_N., first_R, three_CD, five_CD, take_V, Sean_N,
  740. Nearest to also_R: say_V, UNK, say_V., OTCBB_N, one_CD, He_PRP, government_N, add_V,
  741. Nearest to part_N: pear_N, one_CD, UAE_N, semiautomatic_A, city_N, really_R, Ozawa_N, Guard_N.,
  742. Nearest to go_V: get_V, I_PRP, make_V, come_V, like_IN, one_CD, even_R, But_CC,
  743. Nearest to year_N.: year_N, month_N, Confederate_N, together_R., day_N, credible_A, superior_N, theatre_N.,
  744. Nearest to back_R: pricefixing_V, gun_N, Britt_N, redshirted_V, trace_V, Mark_N, Guardian_A, batter_N,
  745. Average loss at step 62000 : 5.213798620462418
  746. Average loss at step 64000 : 5.21542168712616
  747. Average loss at step 66000 : 5.208661090612411
  748. Average loss at step 68000 : 5.197546833992004
  749. Average loss at step 70000 : 5.172291265249252
  750. Nearest to even_R: go_V, make_V, still_R, also_R, But_CC, I_PRP, get_V, flaw_N,
  751. Nearest to new_A: plan_N, would_MD, UNK, also_R, sought_N, Kline_V, local_N, inalienable_A,
  752. Nearest to woman_N: people_N, vandalise_V, alias_N, Bahrain_N, upscale_A, turn_V, Burgundy_N, Umberger_N,
  753. Nearest to three_CD: two_CD, four_CD, six_CD, one_CD, last_A, year_N, seven_CD, next_A,
  754. Nearest to group_N: company_N, also_R, Monegan_N, possibility_N., captive_N., government_N, member_N, timetable_N.,
  755. Nearest to US_N: force_N, Ware_N, collect_N, improves_N., assault_N., bn_N, government_N, local_N,
  756. Nearest to state_N: ensure_V, government_N, gondola_N, primary_N., clenched_N, acceleration_N, anyone_N, crumple_V,
  757. Nearest to But_CC: It_PRP, The_DT, He_PRP, In_IN, And_CC, I_PRP, We_PRP, That_DT,
  758. Nearest to many_A: get_V, enough_R, Lunar_N, one_CD, defeat_N., would_MD, people_N, And_CC,
  759. Nearest to Mr_N: He_PRP, UNK, Ms_N, But_CC, also_R, appellate_N, Lansing_V, say_V,
  760. Nearest to next_A: last_A, two_CD, three_CD, investor_N., first_R, five_CD, take_V, Sean_N,
  761. Nearest to also_R: say_V, UNK, say_V., government_N, OTCBB_N, add_V, one_CD, company_N,
  762. Nearest to part_N: pear_N, one_CD, UAE_N, America_N, UNK, semiautomatic_A, include_V, city_N,
  763. Nearest to go_V: get_V, come_V, make_V, I_PRP, even_R, see_V, one_CD, like_IN,
  764. Nearest to year_N.: year_N, month_N, Confederate_N, day_N, together_R., week_N, credible_A, theatre_N.,
  765. Nearest to back_R: pricefixing_V, redshirted_V, Britt_N, gun_N, bigot_N, go_V, trace_V, Mark_N,
  766. Average loss at step 72000 : 5.162850735664367
  767. Average loss at step 74000 : 5.160452203989029
  768. Average loss at step 76000 : 5.1545262966156
  769. Average loss at step 78000 : 5.135925965070724
  770. Average loss at step 80000 : 5.12542846083641
  771. Nearest to even_R: go_V, make_V, still_R, one_CD, get_V, come_V, really_R, But_CC,
  772. Nearest to new_A: plan_N, would_MD, also_R, UNK, sought_N, Kline_V, inalienable_A, Samak_N,
  773. Nearest to woman_N: people_N, man_N, alias_N, vandalise_V, Bahrain_N, upscale_A, Burgundy_N, Robin_van_Persie_TGRAM,
  774. Nearest to three_CD: two_CD, four_CD, six_CD, one_CD, last_A, seven_CD, next_A, first_R,
  775. Nearest to group_N: company_N, also_R, Monegan_N, possibility_N., government_N, captive_N., member_N, Xbox_N.,
  776. Nearest to US_N: force_N, Ware_N, collect_N, improves_N., assault_N., bn_N, top_N, consumer_N.,
  777. Nearest to state_N: government_N, ensure_V, gondola_N, primary_N., authority_N, acceleration_N, clenched_N, crumple_V,
  778. Nearest to But_CC: It_PRP, The_DT, He_PRP, And_CC, In_IN, That_DT, I_PRP, We_PRP,
  779. Nearest to many_A: one_CD, get_V, people_N, would_MD, need_N, Lunar_N, enough_R, keep_V,
  780. Nearest to Mr_N: He_PRP, Ms_N, also_R, UNK, But_CC, appellate_N, cleft_N, Lansing_V,
  781. Nearest to next_A: last_A, two_CD, three_CD, first_R, investor_N., five_CD, take_V, four_CD,
  782. Nearest to also_R: say_V, UNK, say_V., one_CD, add_V, government_N, OTCBB_N, Mr_N,
  783. Nearest to part_N: one_CD, pear_N, UAE_N, include_V, America_N, city_N, many_A, semiautomatic_A,
  784. Nearest to go_V: get_V, come_V, make_V, I_PRP, one_CD, see_V, even_R, like_IN,
  785. Nearest to year_N.: year_N, month_N, day_N, week_N, month_N., Confederate_N, together_R., theatre_N.,
  786. Nearest to back_R: pricefixing_V, go_V, away_R, redshirted_V, gun_N, Britt_N, bigot_N, trace_V,
  787. Average loss at step 82000 : 5.12895014333725
  788. Average loss at step 84000 : 5.11982547044754
  789. Average loss at step 86000 : 5.120021118879318
  790. Average loss at step 88000 : 5.109159954071045
  791. Average loss at step 90000 : 5.107910221815109
  792. Nearest to even_R: go_V, still_R, come_V, one_CD, get_V, make_V, also_R, need_N,
  793. Nearest to new_A: plan_N, UNK, would_MD, sought_N, also_R, company_N, development_N, inalienable_A,
  794. Nearest to woman_N: people_N, man_N, upscale_A, alias_N, Bahrain_N, turn_V, vandalise_V, Burgundy_N,
  795. Nearest to three_CD: two_CD, four_CD, six_CD, one_CD, five_CD, last_A, seven_CD, eight_CD,
  796. Nearest to group_N: company_N, Monegan_N, also_R, government_N, possibility_N., leader_N, Xbox_N., captive_N.,
  797. Nearest to US_N: force_N, collect_N, Ware_N, improves_N., assault_N., bn_N, consumer_N., local_N,
  798. Nearest to state_N: government_N, ensure_V, gondola_N, primary_N., authority_N, acceleration_N, Spanishlanguage_N, Thursday_N,
  799. Nearest to But_CC: It_PRP, The_DT, He_PRP, And_CC, That_DT, In_IN, We_PRP, They_PRP,
  800. Nearest to many_A: one_CD, get_V, people_N, keep_V, need_N, life_N, enough_R, may_MD,
  801. Nearest to Mr_N: He_PRP, Ms_N, But_CC, also_R, UNK, appellate_N, cleft_N, Lansing_V,
  802. Nearest to next_A: last_A, two_CD, three_CD, first_R, five_CD, investor_N., take_V, four_CD,
  803. Nearest to also_R: UNK, say_V, say_V., government_N, add_V, company_N, Eng_N, OTCBB_N,
  804. Nearest to part_N: one_CD, pear_N, many_A, include_V, UAE_N, city_N, America_N, semiautomatic_A,
  805. Nearest to go_V: get_V, come_V, I_PRP, see_V, make_V, one_CD, even_R, well_R,
  806. Nearest to year_N.: year_N, month_N, day_N, week_N, month_N., Confederate_N, say_V., together_R.,
  807. Nearest to back_R: pricefixing_V, go_V, away_R, redshirted_V, bigot_N, gun_N, home_N, overtly_R,
  808. Average loss at step 92000 : 5.101416747093201
  809. Average loss at step 94000 : 5.08804456782341
  810. Average loss at step 96000 : 5.087678480386734
  811. Average loss at step 98000 : 5.088137490510941
  812. Average loss at step 100000 : 5.083970499515534
  813. Nearest to even_R: go_V, still_R, come_V, one_CD, make_V, get_V, also_R, need_N,
  814. Nearest to new_A: plan_N, would_MD, sought_N, company_N, well_R, inalienable_A, also_R, development_N,
  815. Nearest to woman_N: people_N, man_N, men_N, child_N, upscale_A, turn_V, Bahrain_N, Burgundy_N,
  816. Nearest to three_CD: two_CD, four_CD, six_CD, five_CD, one_CD, last_A, seven_CD, eight_CD,
  817. Nearest to group_N: company_N, Monegan_N, government_N, also_R, leader_N, possibility_N., captive_N., party_N,
  818. Nearest to US_N: force_N, collect_N, improves_N., Ware_N, assault_N., bn_N, consumer_N., dispatch_V,
  819. Nearest to state_N: government_N, ensure_V, authority_N, gondola_N, primary_N., party_N, official_N, Siddle_N,
  820. Nearest to But_CC: It_PRP, The_DT, He_PRP, And_CC, In_IN, That_DT, We_PRP, They_PRP,
  821. Nearest to many_A: one_CD, get_V, people_N, need_N, keep_V, may_MD, life_N, still_R,
  822. Nearest to Mr_N: He_PRP, Ms_N, also_R, But_CC, UNK, appellate_N, cleft_N, contention_N,
  823. Nearest to next_A: last_A, two_CD, three_CD, first_R, five_CD, four_CD, investor_N., later_R,
  824. Nearest to also_R: say_V, UNK, say_V., add_V, government_N, Mr_N, company_N, Eng_N,
  825. Nearest to part_N: one_CD, many_A, pear_N, include_V, city_N, UAE_N, America_N, somewhat_R.,
  826. Nearest to go_V: get_V, come_V, see_V, I_PRP, make_V, well_R, even_R, still_R,
  827. Nearest to year_N.: year_N, month_N, week_N, month_N., day_N, Confederate_N, say_V., week_N.,
  828. Nearest to back_R: pricefixing_V, go_V, away_R, home_N, redshirted_V, get_V, bigot_N, gun_N,
  829. plot saved
  830.  
  831. Process finished with exit code 0
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!