The following have been reloaded with a version change:
  1) cuDNN/7.4.1-CUDA-9.0.176 => cuDNN/7.0.5-CUDA-9.0.176


The following have been reloaded with a version change:
  1) CUDA/9.0.176 => CUDA/9.1.85
  2) cuDNN/7.0.5-CUDA-9.0.176 => cuDNN/7.0.5-CUDA-9.1.85

[2019-03-25 13:14:32,473 INFO] Loading checkpoint from models/tedpure_step_73600.pt
[2019-03-25 13:14:39,412 INFO] Loading vocab from checkpoint at models/tedpure_step_73600.pt.
[2019-03-25 13:14:39,418 INFO]  * src vocab size = 12245
[2019-03-25 13:14:39,428 INFO]  * tgt vocab size = 15721
[2019-03-25 13:14:39,438 INFO] Building model...
[2019-03-25 13:14:53,643 INFO] NMTModel(
  (encoder): RNNEncoder(
    (embeddings): Embeddings(
      (make_embedding): Sequential(
        (emb_luts): Elementwise(
          (0): Embedding(12245, 512, padding_idx=1)
        )
      )
    )
    (rnn): LSTM(512, 256, num_layers=3, dropout=0.2, bidirectional=True)
  )
  (decoder): InputFeedRNNDecoder(
    (embeddings): Embeddings(
      (make_embedding): Sequential(
        (emb_luts): Elementwise(
          (0): Embedding(15721, 512, padding_idx=1)
        )
      )
    )
    (dropout): Dropout(p=0.2)
    (rnn): StackedLSTM(
      (dropout): Dropout(p=0.2)
      (layers): ModuleList(
        (0): LSTMCell(1024, 512)
        (1): LSTMCell(512, 512)
        (2): LSTMCell(512, 512)
      )
    )
    (attn): GlobalAttention(
      (linear_context): Linear(in_features=512, out_features=512, bias=False)
      (linear_query): Linear(in_features=512, out_features=512, bias=True)
      (v): Linear(in_features=512, out_features=1, bias=False)
      (linear_out): Linear(in_features=1024, out_features=512, bias=True)
      (linear_cover): Linear(in_features=1, out_features=512, bias=False)
    )
  )
  (generator): Sequential(
    (0): Linear(in_features=512, out_features=15721, bias=True)
    (1): LogSoftmax()
  )
)
[2019-03-25 13:14:53,648 INFO] encoder: 11000320
[2019-03-25 13:14:53,651 INFO] decoder: 24516969
[2019-03-25 13:14:53,653 INFO] * number of parameters: 35517289
[2019-03-25 13:14:54,210 INFO] Starting training on GPU: [0]
[2019-03-25 13:14:54,211 INFO] Start training loop and validate every 50 steps...