Training is so slow.

[cowry5]

my environment

torch                              1.1.0               
torch-cluster                      1.3.0               
torch-geometric                    1.2.1               
torch-scatter                      1.2.0               
torch-sparse                       0.4.0               
torch-spline-conv                  1.1.0                                                

log

python main.py --dataset=diginetica
2019-07-05 16:06:52,703 main.py[line:34] Namespace(batch_size=1024, dataset='diginetica', epoch=10, hidden_size=100, l2=1e-05, lr=0.001, lr_dc=0.1, lr_dc_step=3, top_k=20)
2019-07-05 16:06:57,010 main.py[line:64] GNNModel(
  (embedding): Embedding(43097, 100)
  (gated): GatedGraphConv(100, num_layers=1)
  (e2s): Embedding2Score(
    (W_1): Linear(in_features=100, out_features=100, bias=True)
    (W_2): Linear(in_features=100, out_features=100, bias=True)
    (q): Linear(in_features=100, out_features=1, bias=True)
    (W_3): Linear(in_features=200, out_features=100, bias=True)
  )
  (loss_function): CrossEntropyLoss()
)
 10%|████▌                                        | 1/10 [06:19<56:55, 379.51s/it]

It takes six minutes to train a eopch. How long will it take you to train a eopch? Thank you!