صفحهٔ اصلی گشت‌و‌گذار راهنما
ورود
liudawei
/
compete
1
0
انشعاب 0
پرونده‌ها مشکلات 0 درخواست واکشی 0 ویکی
شاخه: master
شاخه‌ها تگ‌ها
compete
/
app
/
logs
/
2025-05-23
/
south-forecast.2025-05-23.0.log

south-forecast.2025-05-23.0.log 30 KB
لینک دائمی تاريخچه خام

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361 
  1. 2025-05-23 08:22:27,699 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
    2. 

  2.  - _tfmw_add_deprecation_warning
    3. 

  3. 2025-05-23 08:22:28,041 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
    4. 

  4. 2025-05-23 08:22:30,660 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
    5. 

  5.  - _tfmw_add_deprecation_warning
    6. 

  6. 2025-05-23 08:22:33,584 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
    7. 

  7.  - _tfmw_add_deprecation_warning
    8. 

  8. 2025-05-23 08:22:33,590 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
    9. 

  9.  - _tfmw_add_deprecation_warning
    10. 

  10. 2025-05-23 08:22:33,866 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
    11. 

  11. 2025-05-23 08:22:33,866 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
    12. 

  12. 2025-05-23 08:22:33,892 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
    13. 

  13. 2025-05-23 08:22:33,892 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
    14. 

  14. 2025-05-23 08:22:33,900 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
    15. 

  15. 2025-05-23 08:22:33,900 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
    16. 

  16. 2025-05-23 08:22:33,937 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
    17. 

  17. 2025-05-23 08:22:33,937 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
    18. 

  18. 2025-05-23 08:22:33,937 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
    19. 

  19. 2025-05-23 08:22:33,937 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
    20. 

  20. 2025-05-23 08:22:33,937 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
    21. 

  21. 2025-05-23 08:22:33,937 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
    22. 

  22. 2025-05-23 08:22:34,920 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
    23. 

  23. 2025-05-23 08:22:34,920 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
    24. 

  24. 2025-05-23 08:22:34,937 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
    25. 

  25. 2025-05-23 08:22:34,937 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
    26. 

  26. 2025-05-23 08:22:49,417 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
    27. 

  27. 2025-05-23 08:22:49,417 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
    28. 

  28. 2025-05-23 08:22:49,418 - tf_lstm.py - INFO - 训练集损失函数为：[8.9987e-01 3.1557e-01 9.8220e-02 2.7320e-02 7.0100e-03 1.9300e-03
    29. 

  29.  8.2000e-04 6.0000e-04 5.5000e-04 5.5000e-04 5.4000e-04 5.4000e-04
    30. 

  30.  5.4000e-04 5.4000e-04 5.4000e-04 5.4000e-04 5.3000e-04 5.3000e-04
    31. 

  31.  5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
    32. 

  32.  5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
    33. 

  33.  5.3000e-04 5.3000e-04 5.3000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    34. 

  34.  5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    35. 

  35.  5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    36. 

  36.  5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    37. 

  37.  5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    38. 

  38.  5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    39. 

  39.  5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    40. 

  40.  5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    41. 

  41.  5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    42. 

  42.  5.2000e-04 5.2000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
    43. 

  43.  5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
    44. 

  44.  5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04] - training
    45. 

  45. 2025-05-23 08:22:49,418 - tf_lstm.py - INFO - 训练集损失函数为：[8.9367e-01 3.1262e-01 9.6830e-02 2.6540e-02 6.4300e-03 1.4200e-03
    46. 

  46.  3.2000e-04 1.0000e-04 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
    47. 

  47.  6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
    48. 

  48.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    49. 

  49.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    50. 

  50.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    51. 

  51.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    52. 

  52.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    53. 

  53.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    54. 

  54.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    55. 

  55.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    56. 

  56.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    57. 

  57.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    58. 

  58.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    59. 

  59.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    60. 

  60.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    61. 

  61.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05] - training
    62. 

  62. 2025-05-23 08:22:49,418 - tf_lstm.py - INFO - 验证集损失函数为：[0.51006 0.16613 0.04846 0.01297 0.00362 0.00146 0.00101 0.00092 0.00091
    63. 

  63.  0.0009  0.00089 0.00089 0.00088 0.00088 0.00088 0.00088 0.00087 0.00087
    64. 

  64.  0.00087 0.00087 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086
    65. 

  65.  0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085
    66. 

  66.  0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
    67. 

  67.  0.00084 0.00084 0.00084 0.00084 0.00083 0.00083 0.00083 0.00083 0.00083
    68. 

  68.  0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
    69. 

  69.  0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
    70. 

  70.  0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
    71. 

  71.  0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
    72. 

  72.  0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
    73. 

  73.  0.00082] - training
    74. 

  74. 2025-05-23 08:22:49,418 - tf_lstm.py - INFO - 验证集损失函数为：[5.0543e-01 1.6387e-01 4.7130e-02 1.1960e-02 2.7300e-03 6.1000e-04
    75. 

  75.  1.8000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    76. 

  76.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    77. 

  77.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    78. 

  78.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    79. 

  79.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    80. 

  80.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    81. 

  81.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    82. 

  82.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    83. 

  83.  8.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    84. 

  84.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    85. 

  85.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    86. 

  86.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    87. 

  87.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    88. 

  88.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    89. 

  89.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    90. 

  90.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
    91. 

  91. 2025-05-23 08:22:49,454 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682fbfd9db527f0bfe137dbd - insert_trained_model_into_mongo
    92. 

  92. 2025-05-23 08:22:49,467 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682fbfd99a32f7c1241a3c80 - insert_trained_model_into_mongo
    93. 

  93. 2025-05-23 08:22:49,476 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682fbfd99a32f7c1241a3c82 - insert_scaler_model_into_mongo
    94. 

  94. 2025-05-23 08:22:49,488 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682fbfd9db527f0bfe137dbf - insert_scaler_model_into_mongo
    95. 

  95. 2025-05-23 08:22:50,948 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
    96. 

  96. 2025-05-23 08:22:50,948 - task_worker.py - ERROR - Area 1002 failed: 'station_id' - region_task
    97. 

  97. 2025-05-23 08:28:12,866 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
    98. 

  98.  - _tfmw_add_deprecation_warning
    99. 

  99. 2025-05-23 08:28:12,981 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
    100. 

  100. 2025-05-23 08:28:15,622 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
    101. 

  101.  - _tfmw_add_deprecation_warning
    102. 

  102. 2025-05-23 08:28:18,516 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
    103. 

  103.  - _tfmw_add_deprecation_warning
    104. 

  104. 2025-05-23 08:28:18,524 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
    105. 

  105.  - _tfmw_add_deprecation_warning
    106. 

  106. 2025-05-23 08:28:18,724 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
    107. 

  107. 2025-05-23 08:28:18,726 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
    108. 

  108. 2025-05-23 08:28:18,742 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
    109. 

  109. 2025-05-23 08:28:18,749 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
    110. 

  110. 2025-05-23 08:28:18,750 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
    111. 

  111. 2025-05-23 08:28:18,757 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
    112. 

  112. 2025-05-23 08:28:18,778 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
    113. 

  113. 2025-05-23 08:28:18,778 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
    114. 

  114. 2025-05-23 08:28:18,779 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
    115. 

  115. 2025-05-23 08:28:18,784 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
    116. 

  116. 2025-05-23 08:28:18,784 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
    117. 

  117. 2025-05-23 08:28:18,785 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
    118. 

  118. 2025-05-23 08:28:19,722 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
    119. 

  119. 2025-05-23 08:28:19,724 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
    120. 

  120. 2025-05-23 08:28:19,729 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
    121. 

  121. 2025-05-23 08:28:19,730 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
    122. 

  122. 2025-05-23 08:28:32,613 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
    123. 

  123. 2025-05-23 08:28:32,614 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
    124. 

  124. 2025-05-23 08:28:32,614 - tf_lstm.py - INFO - 训练集损失函数为：[8.9933e-01 3.1451e-01 9.7470e-02 2.6750e-02 6.5000e-03 1.4300e-03
    125. 

  125.  3.2000e-04 1.0000e-04 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
    126. 

  126.  6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 5.0000e-05
    127. 

  127.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    128. 

  128.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    129. 

  129.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    130. 

  130.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    131. 

  131.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    132. 

  132.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    133. 

  133.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    134. 

  134.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    135. 

  135.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    136. 

  136.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    137. 

  137.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    138. 

  138.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    139. 

  139.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    140. 

  140.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05] - training
    141. 

  141. 2025-05-23 08:28:32,614 - tf_lstm.py - INFO - 验证集损失函数为：[5.0852e-01 1.6489e-01 4.7480e-02 1.2060e-02 2.7600e-03 6.1000e-04
    142. 

  142.  1.8000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    143. 

  143.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    144. 

  144.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    145. 

  145.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    146. 

  146.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    147. 

  147.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    148. 

  148.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    149. 

  149.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 7.0000e-05 7.0000e-05
    150. 

  150.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    151. 

  151.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    152. 

  152.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    153. 

  153.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    154. 

  154.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    155. 

  155.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    156. 

  156.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    157. 

  157.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
    158. 

  158. 2025-05-23 08:28:32,614 - tf_lstm.py - INFO - 训练集损失函数为：[8.9252e-01 3.1244e-01 9.7110e-02 2.6970e-02 6.9100e-03 1.9100e-03
    159. 

  159.  8.1000e-04 5.9000e-04 5.5000e-04 5.5000e-04 5.4000e-04 5.4000e-04
    160. 

  160.  5.4000e-04 5.4000e-04 5.4000e-04 5.4000e-04 5.3000e-04 5.3000e-04
    161. 

  161.  5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
    162. 

  162.  5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04 5.3000e-04
    163. 

  163.  5.3000e-04 5.3000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    164. 

  164.  5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    165. 

  165.  5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    166. 

  166.  5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    167. 

  167.  5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    168. 

  168.  5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    169. 

  169.  5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    170. 

  170.  5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    171. 

  171.  5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04 5.2000e-04
    172. 

  172.  5.2000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
    173. 

  173.  5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04
    174. 

  174.  5.1000e-04 5.1000e-04 5.1000e-04 5.1000e-04] - training
    175. 

  175. 2025-05-23 08:28:32,614 - tf_lstm.py - INFO - 验证集损失函数为：[0.50531 0.16435 0.04786 0.01279 0.00357 0.00145 0.00101 0.00092 0.0009
    176. 

  176.  0.00089 0.00089 0.00089 0.00088 0.00088 0.00088 0.00087 0.00087 0.00087
    177. 

  177.  0.00087 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00085
    178. 

  178.  0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085
    179. 

  179.  0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
    180. 

  180.  0.00084 0.00084 0.00084 0.00084 0.00083 0.00083 0.00083 0.00083 0.00083
    181. 

  181.  0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
    182. 

  182.  0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
    183. 

  183.  0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
    184. 

  184.  0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
    185. 

  185.  0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
    186. 

  186.  0.00082] - training
    187. 

  187. 2025-05-23 08:28:32,657 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682fc130b586703a111ee9bb - insert_trained_model_into_mongo
    188. 

  188. 2025-05-23 08:28:32,692 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682fc130da054ff2159993e3 - insert_trained_model_into_mongo
    189. 

  189. 2025-05-23 08:28:32,696 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682fc130b586703a111ee9bd - insert_scaler_model_into_mongo
    190. 

  190. 2025-05-23 08:28:32,711 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682fc130da054ff2159993e5 - insert_scaler_model_into_mongo
    191. 

  191. 2025-05-23 08:28:34,015 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
    192. 

  192. 2025-05-23 08:28:34,034 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
    193. 

  193. 2025-05-23 08:28:34,042 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
    194. 

  194. 2025-05-23 08:28:34,069 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
    195. 

  195. 2025-05-23 08:28:34,069 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
    196. 

  196. 2025-05-23 08:28:34,069 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
    197. 

  197. 2025-05-23 08:28:35,005 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
    198. 

  198. 2025-05-23 08:28:35,006 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
    199. 

  199. 2025-05-23 08:28:46,672 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
    200. 

  200. 2025-05-23 08:28:46,672 - tf_lstm.py - INFO - 训练集损失函数为：[9.1275e-01 3.2207e-01 1.0061e-01 2.7740e-02 6.7200e-03 1.4400e-03
    201. 

  201.  2.8000e-04 5.0000e-05 1.0000e-05 0.0000e+00 0.0000e+00 0.0000e+00
    202. 

  202.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    203. 

  203.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    204. 

  204.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    205. 

  205.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    206. 

  206.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    207. 

  207.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    208. 

  208.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    209. 

  209.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    210. 

  210.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    211. 

  211.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    212. 

  212.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    213. 

  213.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    214. 

  214.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    215. 

  215.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    216. 

  216.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00] - training
    217. 

  217. 2025-05-23 08:28:46,672 - tf_lstm.py - INFO - 验证集损失函数为：[5.1888e-01 1.6976e-01 4.9170e-02 1.2490e-02 2.8000e-03 5.6000e-04
    218. 

  218.  1.0000e-04 2.0000e-05 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    219. 

  219.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    220. 

  220.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    221. 

  221.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    222. 

  222.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    223. 

  223.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    224. 

  224.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    225. 

  225.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    226. 

  226.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    227. 

  227.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    228. 

  228.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    229. 

  229.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    230. 

  230.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    231. 

  231.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    232. 

  232.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    233. 

  233.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00] - training
    234. 

  234. 2025-05-23 08:28:46,673 - tf_model_train.py - ERROR - Training failed: can only concatenate str (not "int") to str
    235. 

  235. Traceback (most recent call last):
    236. 

  236.   File "E:\compete\app\model\tf_model_train.py", line 94, in train
    237. 

  237.     'model_table': self.config['model_table'] + f'_{pre_type}_' + pre_id,
    238. 

  238.                    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~
    239. 

  239. TypeError: can only concatenate str (not "int") to str
    240. 

  240.  - _handle_error
    241. 

  241. 2025-05-23 08:35:44,723 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
    242. 

  242.  - _tfmw_add_deprecation_warning
    243. 

  243. 2025-05-23 08:35:44,847 - main.py - INFO - 输入文件目录: E:/compete/app/model/data/DQYC/qy/62/1002/2025-04-21/IN - main
    244. 

  244. 2025-05-23 08:35:47,468 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
    245. 

  245.  - _tfmw_add_deprecation_warning
    246. 

  246. 2025-05-23 08:35:50,450 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
    247. 

  247.  - _tfmw_add_deprecation_warning
    248. 

  248. 2025-05-23 08:35:50,453 - module_wrapper.py - WARNING - From E:\compete\app\model\losses.py:10: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
    249. 

  249.  - _tfmw_add_deprecation_warning
    250. 

  250. 2025-05-23 08:35:50,668 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
    251. 

  251. 2025-05-23 08:35:50,670 - tf_model_train.py - INFO - GPU 2 allocated - _setup_resources
    252. 

  252. 2025-05-23 08:35:50,686 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
    253. 

  253. 2025-05-23 08:35:50,689 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
    254. 

  254. 2025-05-23 08:35:50,694 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
    255. 

  255. 2025-05-23 08:35:50,696 - data_cleaning.py - INFO - 行清洗：清洗的行数有：69，缺失的列有： - key_field_row_cleaning
    256. 

  256. 2025-05-23 08:35:50,723 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
    257. 

  257. 2025-05-23 08:35:50,723 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
    258. 

  258. 2025-05-23 08:35:50,723 - data_handler.py - INFO - 数据总数：2907, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
    259. 

  259. 2025-05-23 08:35:50,723 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
    260. 

  260. 2025-05-23 08:35:50,724 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
    261. 

  261. 2025-05-23 08:35:50,724 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
    262. 

  262. 2025-05-23 08:35:51,687 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
    263. 

  263. 2025-05-23 08:35:51,689 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
    264. 

  264. 2025-05-23 08:35:51,695 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
    265. 

  265. 2025-05-23 08:35:51,696 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
    266. 

  266. 2025-05-23 08:36:06,600 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
    267. 

  267. 2025-05-23 08:36:06,600 - tf_lstm.py - INFO - 训练集损失函数为：[9.0568e-01 3.1741e-01 9.8600e-02 2.7150e-02 6.6200e-03 1.4700e-03
    268. 

  268.  3.3000e-04 1.0000e-04 6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05
    269. 

  269.  6.0000e-05 6.0000e-05 6.0000e-05 6.0000e-05 5.0000e-05 5.0000e-05
    270. 

  270.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    271. 

  271.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    272. 

  272.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    273. 

  273.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    274. 

  274.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    275. 

  275.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    276. 

  276.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    277. 

  277.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    278. 

  278.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    279. 

  279.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    280. 

  280.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    281. 

  281.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    282. 

  282.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05
    283. 

  283.  5.0000e-05 5.0000e-05 5.0000e-05 5.0000e-05] - training
    284. 

  284. 2025-05-23 08:36:06,601 - tf_lstm.py - INFO - 验证集损失函数为：[0.50575 0.165   0.04822 0.01292 0.00361 0.00145 0.00101 0.00092 0.0009
    285. 

  285.  0.00089 0.00089 0.00088 0.00088 0.00088 0.00087 0.00087 0.00087 0.00087
    286. 

  286.  0.00087 0.00086 0.00086 0.00086 0.00086 0.00086 0.00086 0.00085 0.00085
    287. 

  287.  0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00085 0.00084
    288. 

  288.  0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084 0.00084
    289. 

  289.  0.00084 0.00084 0.00084 0.00084 0.00083 0.00083 0.00083 0.00083 0.00083
    290. 

  290.  0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
    291. 

  291.  0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083 0.00083
    292. 

  292.  0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
    293. 

  293.  0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
    294. 

  294.  0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082 0.00082
    295. 

  295.  0.00082] - training
    296. 

  296. 2025-05-23 08:36:06,601 - tf_lstm.py - INFO - 验证集损失函数为：[5.1277e-01 1.6664e-01 4.8130e-02 1.2280e-02 2.8200e-03 6.3000e-04
    297. 

  297.  1.8000e-04 1.0000e-04 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    298. 

  298.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    299. 

  299.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    300. 

  300.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    301. 

  301.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    302. 

  302.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    303. 

  303.  8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05 8.0000e-05
    304. 

  304.  8.0000e-05 8.0000e-05 8.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    305. 

  305.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    306. 

  306.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    307. 

  307.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    308. 

  308.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    309. 

  309.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    310. 

  310.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    311. 

  311.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05
    312. 

  312.  7.0000e-05 7.0000e-05 7.0000e-05 7.0000e-05] - training
    313. 

  313. 2025-05-23 08:36:06,647 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682fc2f63ef80176b2f4bf7e - insert_trained_model_into_mongo
    314. 

  314. 2025-05-23 08:36:06,657 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682fc2f63ef80176b2f4bf80 - insert_scaler_model_into_mongo
    315. 

  315. 2025-05-23 08:36:06,668 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682fc2f649c4c6cb3fd6c5b2 - insert_trained_model_into_mongo
    316. 

  316. 2025-05-23 08:36:06,685 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682fc2f649c4c6cb3fd6c5b4 - insert_scaler_model_into_mongo
    317. 

  317. 2025-05-23 08:36:08,118 - tf_model_train.py - INFO - GPU 1 allocated - _setup_resources
    318. 

  318. 2025-05-23 08:36:08,137 - data_cleaning.py - INFO - 开始清洗：训练集…… - cleaning
    319. 

  319. 2025-05-23 08:36:08,145 - data_cleaning.py - INFO - 行清洗：清洗的行数有：68，缺失的列有： - key_field_row_cleaning
    320. 

  320. 2025-05-23 08:36:08,172 - data_handler.py - INFO - 数据总数：2908, 时序缺失的间隔：0, 其中，较长的时间间隔：0 - missing_time_splite
    321. 

  321. 2025-05-23 08:36:08,172 - data_handler.py - INFO - 需要补值的总点数：0 - missing_time_splite
    322. 

  322. 2025-05-23 08:36:08,173 - data_handler.py - INFO - 再次测算，需要插值的总点数为：0.0 - fill_train_data
    323. 

  323. 2025-05-23 08:36:09,113 - dbmg.py - INFO - ⚠️ 未找到模型 'lstm' 的有效记录 - get_keras_model_from_mongo
    324. 

  324. 2025-05-23 08:36:09,114 - tf_lstm.py - INFO - 加强训练加载模型权重失败:('cannot unpack non-iterable NoneType object',) - train_init
    325. 

  325. 2025-05-23 08:36:22,336 - tf_lstm.py - INFO - -----模型训练经过100轮迭代----- - training
    326. 

  326. 2025-05-23 08:36:22,337 - tf_lstm.py - INFO - 训练集损失函数为：[9.1068e-01 3.2140e-01 1.0044e-01 2.7720e-02 6.7200e-03 1.4400e-03
    327. 

  327.  2.8000e-04 5.0000e-05 1.0000e-05 0.0000e+00 0.0000e+00 0.0000e+00
    328. 

  328.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    329. 

  329.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    330. 

  330.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    331. 

  331.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    332. 

  332.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    333. 

  333.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    334. 

  334.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    335. 

  335.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    336. 

  336.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    337. 

  337.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    338. 

  338.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    339. 

  339.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    340. 

  340.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    341. 

  341.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    342. 

  342.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00] - training
    343. 

  343. 2025-05-23 08:36:22,337 - tf_lstm.py - INFO - 验证集损失函数为：[5.1778e-01 1.6943e-01 4.9120e-02 1.2490e-02 2.8000e-03 5.6000e-04
    344. 

  344.  1.0000e-04 2.0000e-05 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    345. 

  345.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    346. 

  346.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    347. 

  347.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    348. 

  348.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    349. 

  349.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    350. 

  350.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    351. 

  351.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    352. 

  352.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    353. 

  353.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    354. 

  354.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    355. 

  355.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    356. 

  356.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    357. 

  357.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    358. 

  358.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00
    359. 

  359.  0.0000e+00 0.0000e+00 0.0000e+00 0.0000e+00] - training
    360. 

  360. 2025-05-23 08:36:22,426 - dbmg.py - INFO - ✅ 模型 lstm 保存成功 | 文档ID: 682fc3061866c0ded50f27e9 - insert_trained_model_into_mongo
    361. 

  361. 2025-05-23 08:36:22,446 - dbmg.py - INFO - ✅ 缩放器 lstm 保存成功 | 文档ID: 682fc3061866c0ded50f27eb - insert_scaler_model_into_mongo
    362.