Startsida Utforska Hjälp
Logga in
sebastian
/
androidMotionLogger
1
0
Fork 0
Filer Ärenden 0 Pull-förfrågningar 0 Wiki
Träd: d37586271e
Grenar Taggar
androidMotio...
/
julia
/
logs
/
log_18_09_2019.log

log_18_09_2019.log 9.8 KB
Historik Rå

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188 
  1. 

  2. --------[18_09_2019 15:33:43]--------
    3. 

  3. Random Grid Search
    4. 

  4. 

  5. Search 1 of 500
    6. 

  6. momentum0.92, features=[32, 32, 32], dropout_rate=0.1
    7. 

  7. kernel=Tuple{Int64,Int64}[(3, 1), (3, 1), (2, 6)], pooldims=Tuple{Int64,Int64}[(3, 1), (3, 1)], learning_rate=0.1
    8. 

  8. 

  9. [15:34:55] INIT Loss(val): 0.125317
    10. 

  10. [15:36:49] Epoch   2: Loss(train): 0.075287 Loss(val): 0.075063
    11. 

  11. [15:37:26] Epoch   4: Loss(train): 0.068476 Loss(val): 0.069180
    12. 

  12. [15:37:55] Epoch   6: Loss(train): 0.065515 Loss(val): 0.066542
    13. 

  13. [15:38:22] Epoch   8: Loss(train): 0.063886 Loss(val): 0.064420
    14. 

  14. [15:38:53] Epoch  10: Loss(train): 0.063473 Loss(val): 0.062857
    15. 

  15. [15:39:23] Epoch  12: Loss(train): 0.061911 Loss(val): 0.061451
    16. 

  16. [15:39:52] Epoch  14: Loss(train): 0.060242 Loss(val): 0.059912
    17. 

  17. [15:40:22] Epoch  16: Loss(train): 0.058877 Loss(val): 0.058791
    18. 

  18. [15:40:51] Epoch  18: Loss(train): 0.058132 Loss(val): 0.058110
    19. 

  19. [15:41:19] Epoch  20: Loss(train): 0.057336 Loss(val): 0.057570
    20. 

  20. [15:41:49] Epoch  22: Loss(train): 0.056594 Loss(val): 0.056818
    21. 

  21. Early stopping at 0
    22. 

  22. Search 2 of 500
    23. 

  23. momentum0.94, features=[64, 64, 64], dropout_rate=0.6
    24. 

  24. kernel=Tuple{Int64,Int64}[(3, 1), (3, 1), (2, 6)], pooldims=Tuple{Int64,Int64}[(2, 1), (2, 1)], learning_rate=0.01
    25. 

  25. 

  26. [15:41:55] INIT Loss(val): 0.129147
    27. 

  27. [15:42:23] Epoch   2: Loss(train): 0.078632 Loss(val): 0.078414
    28. 

  28. [15:42:54] Epoch   4: Loss(train): 0.070202 Loss(val): 0.070887
    29. 

  29. [15:43:22] Epoch   6: Loss(train): 0.066139 Loss(val): 0.066908
    30. 

  30. [15:43:51] Epoch   8: Loss(train): 0.063795 Loss(val): 0.063834
    31. 

  31. [15:44:19] Epoch  10: Loss(train): 0.063544 Loss(val): 0.062947
    32. 

  32. [15:44:48] Epoch  12: Loss(train): 0.061362 Loss(val): 0.060898
    33. 

  33. [15:45:18] Epoch  14: Loss(train): 0.060353 Loss(val): 0.060166
    34. 

  34. [15:45:51] Epoch  16: Loss(train): 0.058804 Loss(val): 0.059007
    35. 

  35. [15:46:21] Epoch  18: Loss(train): 0.057630 Loss(val): 0.057931
    36. 

  36. [15:46:51] Epoch  20: Loss(train): 0.056580 Loss(val): 0.056976
    37. 

  37. [15:47:19] Epoch  22: Loss(train): 0.055983 Loss(val): 0.056418
    38. 

  38. [15:47:48] Epoch  24: Loss(train): 0.055619 Loss(val): 0.055914
    39. 

  39. [15:48:20] Epoch  26: Loss(train): 0.054729 Loss(val): 0.055086
    40. 

  40. [15:48:52] Epoch  28: Loss(train): 0.054222 Loss(val): 0.054575
    41. 

  41. [15:49:27] FINAL(30) Loss(val): 0.054254
    42. 

  42. [15:49:30] FINAL(30) Loss(val): 0.054254
    43. 

  43. 

  44. Search 3 of 500
    45. 

  45. momentum0.94, features=[64, 64, 64], dropout_rate=0.1
    46. 

  46. kernel=Tuple{Int64,Int64}[(7, 1), (7, 1), (2, 6)], pooldims=Tuple{Int64,Int64}[(3, 1), (3, 1)], learning_rate=0.001
    47. 

  47. 

  48. [15:49:31] INIT Loss(val): 0.126161
    49. 

  49. [15:49:59] Epoch   2: Loss(train): 0.077885 Loss(val): 0.078426
    50. 

  50. [15:50:34] Epoch   4: Loss(train): 0.070761 Loss(val): 0.071715
    51. 

  51. [15:51:04] Epoch   6: Loss(train): 0.067634 Loss(val): 0.068910
    52. 

  52. [15:51:33] Epoch   8: Loss(train): 0.065403 Loss(val): 0.066819
    53. 

  53. [15:52:02] Epoch  10: Loss(train): 0.064137 Loss(val): 0.064249
    54. 

  54. [15:52:30] Epoch  12: Loss(train): 0.062744 Loss(val): 0.062782
    55. 

  55. [15:53:00] Epoch  14: Loss(train): 0.061248 Loss(val): 0.061450
    56. 

  56. [15:53:29] Epoch  16: Loss(train): 0.059991 Loss(val): 0.060319
    57. 

  57. [15:53:58] Epoch  18: Loss(train): 0.058670 Loss(val): 0.059030
    58. 

  58. [15:54:29] Epoch  20: Loss(train): 0.057977 Loss(val): 0.058384
    59. 

  59. [15:55:01] Epoch  22: Loss(train): 0.056949 Loss(val): 0.057303
    60. 

  60. [15:55:30] Epoch  24: Loss(train): 0.056464 Loss(val): 0.056771
    61. 

  61. [15:55:59] Epoch  26: Loss(train): 0.055319 Loss(val): 0.055677
    62. 

  62. [15:56:29] Epoch  28: Loss(train): 0.055020 Loss(val): 0.055222
    63. 

  63. [15:56:59] FINAL(30) Loss(val): 0.054447
    64. 

  64. [15:57:02] FINAL(30) Loss(val): 0.054447
    65. 

  65. 

  66. Search 4 of 500
    67. 

  67. momentum0.94, features=[96, 192, 192], dropout_rate=0.1
    68. 

  68. kernel=Tuple{Int64,Int64}[(5, 1), (3, 1), (2, 6)], pooldims=Tuple{Int64,Int64}[(2, 1), (2, 1)], learning_rate=0.01
    69. 

  69. 

  70. [15:57:03] INIT Loss(val): 0.143514
    71. 

  71. [15:57:29] Epoch   2: Loss(train): 0.077462 Loss(val): 0.078461
    72. 

  72. [15:57:59] Epoch   4: Loss(train): 0.070687 Loss(val): 0.072219
    73. 

  73. [15:58:30] Epoch   6: Loss(train): 0.067443 Loss(val): 0.068943
    74. 

  74. [15:58:58] Epoch   8: Loss(train): 0.064753 Loss(val): 0.064823
    75. 

  75. [15:59:28] Epoch  10: Loss(train): 0.063935 Loss(val): 0.063728
    76. 

  76. [15:59:57] Epoch  12: Loss(train): 0.061962 Loss(val): 0.061995
    77. 

  77. [16:00:27] Epoch  14: Loss(train): 0.061007 Loss(val): 0.061087
    78. 

  78. [16:00:57] Epoch  16: Loss(train): 0.059649 Loss(val): 0.059899
    79. 

  79. [16:01:26] Epoch  18: Loss(train): 0.059178 Loss(val): 0.059439
    80. 

  80. [16:01:56] Epoch  20: Loss(train): 0.058152 Loss(val): 0.058421
    81. 

  81. [16:02:25] Epoch  22: Loss(train): 0.057042 Loss(val): 0.057437
    82. 

  82. [16:02:55] Epoch  24: Loss(train): 0.056095 Loss(val): 0.056463
    83. 

  83. [16:03:25] Epoch  26: Loss(train): 0.055047 Loss(val): 0.055456
    84. 

  84. [16:03:54] Epoch  28: Loss(train): 0.054421 Loss(val): 0.054925
    85. 

  85. [16:04:24] FINAL(30) Loss(val): 0.054328
    86. 

  86. [16:04:27] FINAL(30) Loss(val): 0.054328
    87. 

  87. 

  88. Search 5 of 500
    89. 

  89. momentum0.94, features=[32, 32, 32], dropout_rate=0.3
    90. 

  90. kernel=Tuple{Int64,Int64}[(3, 1), (3, 1), (3, 6)], pooldims=Tuple{Int64,Int64}[(2, 1), (2, 1)], learning_rate=0.03
    91. 

  91. 

  92. [16:04:27] INIT Loss(val): 0.142138
    93. 

  93. [16:04:55] Epoch   2: Loss(train): 0.078344 Loss(val): 0.079304
    94. 

  94. [16:05:24] Epoch   4: Loss(train): 0.069910 Loss(val): 0.070895
    95. 

  95. [16:05:54] Epoch   6: Loss(train): 0.066428 Loss(val): 0.067457
    96. 

  96. [16:06:23] Epoch   8: Loss(train): 0.063501 Loss(val): 0.064552
    97. 

  97. [16:06:53] Epoch  10: Loss(train): 0.062729 Loss(val): 0.062416
    98. 

  98. [16:07:23] Epoch  12: Loss(train): 0.061756 Loss(val): 0.061395
    99. 

  99. [16:07:53] Epoch  14: Loss(train): 0.059968 Loss(val): 0.059828
    100. 

  100. [16:08:22] Epoch  16: Loss(train): 0.059002 Loss(val): 0.058909
    101. 

  101. [16:08:52] Epoch  18: Loss(train): 0.058062 Loss(val): 0.058228
    102. 

  102. [16:09:22] Epoch  20: Loss(train): 0.057697 Loss(val): 0.057969
    103. 

  103. [16:09:52] Epoch  22: Loss(train): 0.057117 Loss(val): 0.057452
    104. 

  104. [16:10:22] Epoch  24: Loss(train): 0.056149 Loss(val): 0.056525
    105. 

  105. [16:10:53] Epoch  26: Loss(train): 0.055586 Loss(val): 0.055998
    106. 

  106. [16:11:23] Epoch  28: Loss(train): 0.054670 Loss(val): 0.055118
    107. 

  107. [16:11:53] FINAL(30) Loss(val): 0.054470
    108. 

  108. [16:11:56] FINAL(30) Loss(val): 0.054470
    109. 

  109. 

  110. Search 6 of 500
    111. 

  111. momentum0.9, features=[64, 64, 64], dropout_rate=0.1
    112. 

  112. kernel=Tuple{Int64,Int64}[(7, 1), (5, 1), (3, 6)], pooldims=Tuple{Int64,Int64}[(2, 1), (2, 1)], learning_rate=0.1
    113. 

  113. 

  114. [16:11:57] INIT Loss(val): 0.130219
    115. 

  115. [16:12:25] Epoch   2: Loss(train): 0.077388 Loss(val): 0.077279
    116. 

  116. [16:12:55] Epoch   4: Loss(train): 0.068726 Loss(val): 0.069355
    117. 

  117. [16:13:26] Epoch   6: Loss(train): 0.065969 Loss(val): 0.066996
    118. 

  118. [16:13:56] Epoch   8: Loss(train): 0.064049 Loss(val): 0.065168
    119. 

  119. [16:14:26] Epoch  10: Loss(train): 0.062873 Loss(val): 0.062917
    120. 

  120. [16:14:56] Epoch  12: Loss(train): 0.063614 Loss(val): 0.063174
    121. 

  121. [16:15:26] Epoch  14: Loss(train): 0.061988 Loss(val): 0.061926
    122. 

  122. [16:15:56] Epoch  16: Loss(train): 0.060946 Loss(val): 0.061109
    123. 

  123. Early stopping at 0
    124. 

  124. Search 7 of 500
    125. 

  125. momentum0.92, features=[96, 192, 192], dropout_rate=0.1
    126. 

  126. kernel=Tuple{Int64,Int64}[(7, 1), (7, 1), (3, 6)], pooldims=Tuple{Int64,Int64}[(3, 1), (3, 1)], learning_rate=0.01
    127. 

  127. 

  128. [16:16:01] INIT Loss(val): 0.158887
    129. 

  129. [16:16:29] Epoch   2: Loss(train): 0.077085 Loss(val): 0.077593
    130. 

  130. [16:16:59] Epoch   4: Loss(train): 0.068976 Loss(val): 0.070250
    131. 

  131. [16:17:28] Epoch   6: Loss(train): 0.065539 Loss(val): 0.066987
    132. 

  132. [16:17:58] Epoch   8: Loss(train): 0.062972 Loss(val): 0.064571
    133. 

  133. [16:18:29] Epoch  10: Loss(train): 0.060879 Loss(val): 0.061406
    134. 

  134. [16:18:58] Epoch  12: Loss(train): 0.060074 Loss(val): 0.060140
    135. 

  135. [16:19:28] Epoch  14: Loss(train): 0.058958 Loss(val): 0.059320
    136. 

  136. [16:19:58] Epoch  16: Loss(train): 0.057612 Loss(val): 0.058114
    137. 

  137. [16:20:29] Epoch  18: Loss(train): 0.056968 Loss(val): 0.057745
    138. 

  138. [16:20:59] Epoch  20: Loss(train): 0.056104 Loss(val): 0.056927
    139. 

  139. [16:21:30] Epoch  22: Loss(train): 0.055559 Loss(val): 0.056354
    140. 

  140. [16:22:20] Epoch  24: Loss(train): 0.055063 Loss(val): 0.055935
    141. 

  141. [16:23:07] Epoch  26: Loss(train): 0.054734 Loss(val): 0.055537
    142. 

  142. [16:23:56] Epoch  28: Loss(train): 0.054243 Loss(val): 0.055037
    143. 

  143. [16:24:42] FINAL(30) Loss(val): 0.054857
    144. 

  144. [16:24:45] FINAL(30) Loss(val): 0.054857
    145. 

  145. 

  146. Search 8 of 500
    147. 

  147. momentum0.96, features=[64, 64, 64], dropout_rate=0.1
    148. 

  148. kernel=Tuple{Int64,Int64}[(5, 1), (5, 1), (3, 6)], pooldims=Tuple{Int64,Int64}[(3, 1), (3, 1)], learning_rate=0.001
    149. 

  149. 

  150. [16:24:47] INIT Loss(val): 0.138277
    151. 

  151. [16:25:30] Epoch   2: Loss(train): 0.079859 Loss(val): 0.080827
    152. 

  152. [16:26:20] Epoch   4: Loss(train): 0.069111 Loss(val): 0.070549
    153. 

  153. [16:27:11] Epoch   6: Loss(train): 0.065782 Loss(val): 0.067275
    154. 

  154. [16:28:05] Epoch   8: Loss(train): 0.062852 Loss(val): 0.064066
    155. 

  155. [16:29:03] Epoch  10: Loss(train): 0.061824 Loss(val): 0.061692
    156. 

  156. [16:29:56] Epoch  12: Loss(train): 0.061533 Loss(val): 0.060959
    157. 

  157. [16:30:49] Epoch  14: Loss(train): 0.060054 Loss(val): 0.059820
    158. 

  158. [16:31:44] Epoch  16: Loss(train): 0.058679 Loss(val): 0.058628
    159. 

  159. [16:32:37] Epoch  18: Loss(train): 0.057629 Loss(val): 0.057877
    160. 

  160. [16:33:29] Epoch  20: Loss(train): 0.056418 Loss(val): 0.056854
    161. 

  161. [16:34:21] Epoch  22: Loss(train): 0.056054 Loss(val): 0.056538
    162. 

  162. [16:35:13] Epoch  24: Loss(train): 0.055056 Loss(val): 0.055656
    163. 

  163. [16:36:01] Epoch  26: Loss(train): 0.054567 Loss(val): 0.055133
    164. 

  164. [16:36:50] Epoch  28: Loss(train): 0.053922 Loss(val): 0.054542
    165. 

  165. [16:37:37] FINAL(30) Loss(val): 0.053926
    166. 

  166. [16:37:42] FINAL(30) Loss(val): 0.053926
    167. 

  167. 

  168. Search 9 of 500
    169. 

  169. momentum0.9, features=[32, 64, 128], dropout_rate=0.3
    170. 

  170. kernel=Tuple{Int64,Int64}[(7, 1), (7, 1), (2, 6)], pooldims=Tuple{Int64,Int64}[(3, 1), (3, 1)], learning_rate=0.1
    171. 

  171. 

  172. [16:37:43] INIT Loss(val): 0.149463
    173. 

  173. [16:38:18] Epoch   2: Loss(train): 0.076049 Loss(val): 0.076722
    174. 

  174. [16:39:03] Epoch   4: Loss(train): 0.068973 Loss(val): 0.069592
    175. 

  175. [16:39:53] Epoch   6: Loss(train): 0.065072 Loss(val): 0.066030
    176. 

  176. [16:40:37] Epoch   8: Loss(train): 0.063404 Loss(val): 0.064415
    177. 

  177. [16:41:20] Epoch  10: Loss(train): 0.061349 Loss(val): 0.061938
    178. 

  178. Early stopping at 0
    179. 

  179. Search 10 of 500
    180. 

  180. momentum0.98, features=[32, 32, 32], dropout_rate=0.4
    181. 

  181. kernel=Tuple{Int64,Int64}[(5, 1), (3, 1), (2, 6)], pooldims=Tuple{Int64,Int64}[(3, 1), (3, 1)], learning_rate=0.1
    182. 

  182. 

  183. [16:41:41] INIT Loss(val): 0.127935
    184. 

  184. [16:42:10] Epoch   2: Loss(train): 0.076783 Loss(val): 0.078367
    185. 

  185. [16:42:43] Epoch   4: Loss(train): 0.069196 Loss(val): 0.070709
    186. 

  186. [16:43:22] Epoch   6: Loss(train): 0.066136 Loss(val): 0.067725
    187. 

  187. [16:43:54] Epoch   8: Loss(train): 0.063826 Loss(val): 0.065215
    188. 

  188. [16:44:26] Epoch  10: Loss(train): 0.062568 Loss(val): 0.063721
    189.