SHARE
TWEET

Untitled

a guest Apr 23rd, 2019 90 Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
  1. ['__call__', '__class__', '__delattr__', '__dict__', '__dir__', '__doc__', '__eq__', '__format__', '__ge__', '__getattr__', '__getattribute__', '__gt__', '__hash__', '__init__', '__init_subclass__', '__le__', '__lt__', '__module__', '__ne__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__setattr__', '__setstate__', '__sizeof__', '__str__', '__subclasshook__', '__weakref__', '_apply', '_backend', '_backward_hooks', '_buffers', '_forward_hooks', '_forward_pre_hooks', '_get_name', '_load_from_state_dict', '_load_state_dict_pre_hooks', '_modules', '_named_members', '_parameters', '_register_load_state_dict_pre_hook', '_register_state_dict_hook', '_slow_forward', '_state_dict_hooks', '_tracing_name', '_version', 'add_module', 'apply', 'buffers', 'children', 'cpu', 'cuda', 'device_ids', 'dim', 'double', 'dump_patches', 'eval', 'extra_repr', 'float', 'forward', 'gather', 'half', 'load_state_dict', 'module', 'modules', 'named_buffers', 'named_children', 'named_modules', 'named_parameters', 'output_device', 'parallel_apply', 'parameters', 'register_backward_hook', 'register_buffer', 'register_forward_hook', 'register_forward_pre_hook', 'register_parameter', 'replicate', 'scatter', 'share_memory', 'state_dict', 'to', 'train', 'training', 'type', 'zero_grad']
  2. <bound method Module.__dir__ of DataParallel(
  3.   (module): BertForMultiLabelSequenceClassification(
  4.     (bert): BertModel(
  5.       (embeddings): BertEmbeddings(
  6.         (word_embeddings): Embedding(30522, 768)
  7.         (position_embeddings): Embedding(512, 768)
  8.         (token_type_embeddings): Embedding(2, 768)
  9.         (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  10.         (dropout): Dropout(p=0.1)
  11.       )
  12.       (encoder): BertEncoder(
  13.         (layer): ModuleList(
  14.           (0): BertLayer(
  15.             (attention): BertAttention(
  16.               (self): BertSelfAttention(
  17.                 (query): Linear(in_features=768, out_features=768, bias=True)
  18.                 (key): Linear(in_features=768, out_features=768, bias=True)
  19.                 (value): Linear(in_features=768, out_features=768, bias=True)
  20.                 (dropout): Dropout(p=0.1)
  21.               )
  22.               (output): BertSelfOutput(
  23.                 (dense): Linear(in_features=768, out_features=768, bias=True)
  24.                 (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  25.                 (dropout): Dropout(p=0.1)
  26.               )
  27.             )
  28.             (intermediate): BertIntermediate(
  29.               (dense): Linear(in_features=768, out_features=3072, bias=True)
  30.             )
  31.             (output): BertOutput(
  32.               (dense): Linear(in_features=3072, out_features=768, bias=True)
  33.               (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  34.               (dropout): Dropout(p=0.1)
  35.             )
  36.           )
  37.           (1): BertLayer(
  38.             (attention): BertAttention(
  39.               (self): BertSelfAttention(
  40.                 (query): Linear(in_features=768, out_features=768, bias=True)
  41.                 (key): Linear(in_features=768, out_features=768, bias=True)
  42.                 (value): Linear(in_features=768, out_features=768, bias=True)
  43.                 (dropout): Dropout(p=0.1)
  44.               )
  45.               (output): BertSelfOutput(
  46.                 (dense): Linear(in_features=768, out_features=768, bias=True)
  47.                 (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  48.                 (dropout): Dropout(p=0.1)
  49.               )
  50.             )
  51.             (intermediate): BertIntermediate(
  52.               (dense): Linear(in_features=768, out_features=3072, bias=True)
  53.             )
  54.             (output): BertOutput(
  55.               (dense): Linear(in_features=3072, out_features=768, bias=True)
  56.               (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  57.               (dropout): Dropout(p=0.1)
  58.             )
  59.           )
  60.           (2): BertLayer(
  61.             (attention): BertAttention(
  62.               (self): BertSelfAttention(
  63.                 (query): Linear(in_features=768, out_features=768, bias=True)
  64.                 (key): Linear(in_features=768, out_features=768, bias=True)
  65.                 (value): Linear(in_features=768, out_features=768, bias=True)
  66.                 (dropout): Dropout(p=0.1)
  67.               )
  68.               (output): BertSelfOutput(
  69.                 (dense): Linear(in_features=768, out_features=768, bias=True)
  70.                 (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  71.                 (dropout): Dropout(p=0.1)
  72.               )
  73.             )
  74.             (intermediate): BertIntermediate(
  75.               (dense): Linear(in_features=768, out_features=3072, bias=True)
  76.             )
  77.             (output): BertOutput(
  78.               (dense): Linear(in_features=3072, out_features=768, bias=True)
  79.               (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  80.               (dropout): Dropout(p=0.1)
  81.             )
  82.           )
  83.           (3): BertLayer(
  84.             (attention): BertAttention(
  85.               (self): BertSelfAttention(
  86.                 (query): Linear(in_features=768, out_features=768, bias=True)
  87.                 (key): Linear(in_features=768, out_features=768, bias=True)
  88.                 (value): Linear(in_features=768, out_features=768, bias=True)
  89.                 (dropout): Dropout(p=0.1)
  90.               )
  91.               (output): BertSelfOutput(
  92.                 (dense): Linear(in_features=768, out_features=768, bias=True)
  93.                 (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  94.                 (dropout): Dropout(p=0.1)
  95.               )
  96.             )
  97.             (intermediate): BertIntermediate(
  98.               (dense): Linear(in_features=768, out_features=3072, bias=True)
  99.             )
  100.             (output): BertOutput(
  101.               (dense): Linear(in_features=3072, out_features=768, bias=True)
  102.               (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  103.               (dropout): Dropout(p=0.1)
  104.             )
  105.           )
  106.           (4): BertLayer(
  107.             (attention): BertAttention(
  108.               (self): BertSelfAttention(
  109.                 (query): Linear(in_features=768, out_features=768, bias=True)
  110.                 (key): Linear(in_features=768, out_features=768, bias=True)
  111.                 (value): Linear(in_features=768, out_features=768, bias=True)
  112.                 (dropout): Dropout(p=0.1)
  113.               )
  114.               (output): BertSelfOutput(
  115.                 (dense): Linear(in_features=768, out_features=768, bias=True)
  116.                 (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  117.                 (dropout): Dropout(p=0.1)
  118.               )
  119.             )
  120.             (intermediate): BertIntermediate(
  121.               (dense): Linear(in_features=768, out_features=3072, bias=True)
  122.             )
  123.             (output): BertOutput(
  124.               (dense): Linear(in_features=3072, out_features=768, bias=True)
  125.               (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  126.               (dropout): Dropout(p=0.1)
  127.             )
  128.           )
  129.           (5): BertLayer(
  130.             (attention): BertAttention(
  131.               (self): BertSelfAttention(
  132.                 (query): Linear(in_features=768, out_features=768, bias=True)
  133.                 (key): Linear(in_features=768, out_features=768, bias=True)
  134.                 (value): Linear(in_features=768, out_features=768, bias=True)
  135.                 (dropout): Dropout(p=0.1)
  136.               )
  137.               (output): BertSelfOutput(
  138.                 (dense): Linear(in_features=768, out_features=768, bias=True)
  139.                 (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  140.                 (dropout): Dropout(p=0.1)
  141.               )
  142.             )
  143.             (intermediate): BertIntermediate(
  144.               (dense): Linear(in_features=768, out_features=3072, bias=True)
  145.             )
  146.             (output): BertOutput(
  147.               (dense): Linear(in_features=3072, out_features=768, bias=True)
  148.               (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  149.               (dropout): Dropout(p=0.1)
  150.             )
  151.           )
  152.           (6): BertLayer(
  153.             (attention): BertAttention(
  154.               (self): BertSelfAttention(
  155.                 (query): Linear(in_features=768, out_features=768, bias=True)
  156.                 (key): Linear(in_features=768, out_features=768, bias=True)
  157.                 (value): Linear(in_features=768, out_features=768, bias=True)
  158.                 (dropout): Dropout(p=0.1)
  159.               )
  160.               (output): BertSelfOutput(
  161.                 (dense): Linear(in_features=768, out_features=768, bias=True)
  162.                 (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  163.                 (dropout): Dropout(p=0.1)
  164.               )
  165.             )
  166.             (intermediate): BertIntermediate(
  167.               (dense): Linear(in_features=768, out_features=3072, bias=True)
  168.             )
  169.             (output): BertOutput(
  170.               (dense): Linear(in_features=3072, out_features=768, bias=True)
  171.               (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  172.               (dropout): Dropout(p=0.1)
  173.             )
  174.           )
  175.           (7): BertLayer(
  176.             (attention): BertAttention(
  177.               (self): BertSelfAttention(
  178.                 (query): Linear(in_features=768, out_features=768, bias=True)
  179.                 (key): Linear(in_features=768, out_features=768, bias=True)
  180.                 (value): Linear(in_features=768, out_features=768, bias=True)
  181.                 (dropout): Dropout(p=0.1)
  182.               )
  183.               (output): BertSelfOutput(
  184.                 (dense): Linear(in_features=768, out_features=768, bias=True)
  185.                 (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  186.                 (dropout): Dropout(p=0.1)
  187.               )
  188.             )
  189.             (intermediate): BertIntermediate(
  190.               (dense): Linear(in_features=768, out_features=3072, bias=True)
  191.             )
  192.             (output): BertOutput(
  193.               (dense): Linear(in_features=3072, out_features=768, bias=True)
  194.               (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  195.               (dropout): Dropout(p=0.1)
  196.             )
  197.           )
  198.           (8): BertLayer(
  199.             (attention): BertAttention(
  200.               (self): BertSelfAttention(
  201.                 (query): Linear(in_features=768, out_features=768, bias=True)
  202.                 (key): Linear(in_features=768, out_features=768, bias=True)
  203.                 (value): Linear(in_features=768, out_features=768, bias=True)
  204.                 (dropout): Dropout(p=0.1)
  205.               )
  206.               (output): BertSelfOutput(
  207.                 (dense): Linear(in_features=768, out_features=768, bias=True)
  208.                 (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  209.                 (dropout): Dropout(p=0.1)
  210.               )
  211.             )
  212.             (intermediate): BertIntermediate(
  213.               (dense): Linear(in_features=768, out_features=3072, bias=True)
  214.             )
  215.             (output): BertOutput(
  216.               (dense): Linear(in_features=3072, out_features=768, bias=True)
  217.               (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  218.               (dropout): Dropout(p=0.1)
  219.             )
  220.           )
  221.           (9): BertLayer(
  222.             (attention): BertAttention(
  223.               (self): BertSelfAttention(
  224.                 (query): Linear(in_features=768, out_features=768, bias=True)
  225.                 (key): Linear(in_features=768, out_features=768, bias=True)
  226.                 (value): Linear(in_features=768, out_features=768, bias=True)
  227.                 (dropout): Dropout(p=0.1)
  228.               )
  229.               (output): BertSelfOutput(
  230.                 (dense): Linear(in_features=768, out_features=768, bias=True)
  231.                 (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  232.                 (dropout): Dropout(p=0.1)
  233.               )
  234.             )
  235.             (intermediate): BertIntermediate(
  236.               (dense): Linear(in_features=768, out_features=3072, bias=True)
  237.             )
  238.             (output): BertOutput(
  239.               (dense): Linear(in_features=3072, out_features=768, bias=True)
  240.               (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  241.               (dropout): Dropout(p=0.1)
  242.             )
  243.           )
  244.           (10): BertLayer(
  245.             (attention): BertAttention(
  246.               (self): BertSelfAttention(
  247.                 (query): Linear(in_features=768, out_features=768, bias=True)
  248.                 (key): Linear(in_features=768, out_features=768, bias=True)
  249.                 (value): Linear(in_features=768, out_features=768, bias=True)
  250.                 (dropout): Dropout(p=0.1)
  251.               )
  252.               (output): BertSelfOutput(
  253.                 (dense): Linear(in_features=768, out_features=768, bias=True)
  254.                 (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  255.                 (dropout): Dropout(p=0.1)
  256.               )
  257.             )
  258.             (intermediate): BertIntermediate(
  259.               (dense): Linear(in_features=768, out_features=3072, bias=True)
  260.             )
  261.             (output): BertOutput(
  262.               (dense): Linear(in_features=3072, out_features=768, bias=True)
  263.               (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  264.               (dropout): Dropout(p=0.1)
  265.             )
  266.           )
  267.           (11): BertLayer(
  268.             (attention): BertAttention(
  269.               (self): BertSelfAttention(
  270.                 (query): Linear(in_features=768, out_features=768, bias=True)
  271.                 (key): Linear(in_features=768, out_features=768, bias=True)
  272.                 (value): Linear(in_features=768, out_features=768, bias=True)
  273.                 (dropout): Dropout(p=0.1)
  274.               )
  275.               (output): BertSelfOutput(
  276.                 (dense): Linear(in_features=768, out_features=768, bias=True)
  277.                 (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  278.                 (dropout): Dropout(p=0.1)
  279.               )
  280.             )
  281.             (intermediate): BertIntermediate(
  282.               (dense): Linear(in_features=768, out_features=3072, bias=True)
  283.             )
  284.             (output): BertOutput(
  285.               (dense): Linear(in_features=3072, out_features=768, bias=True)
  286.               (LayerNorm): FusedLayerNorm(torch.Size([768]), eps=1e-12, elementwise_affine=True)
  287.               (dropout): Dropout(p=0.1)
  288.             )
  289.           )
  290.         )
  291.       )
  292.       (pooler): BertPooler(
  293.         (dense): Linear(in_features=768, out_features=768, bias=True)
  294.         (activation): Tanh()
  295.       )
  296.     )
  297.     (dropout): Dropout(p=0.1)
  298.     (classifier): Linear(in_features=768, out_features=50, bias=True)
  299.   )
  300. )>
RAW Paste Data
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
 
Top