Euler2 RGCN speed

Hi,
I am using the RGCN implementation from examples directory on a custom dataset with 1137061 nodes and 58336927 edges. I have 6 node types and 67 edge types. There are no node features and 1 edge feature(which is equal to the edge type). The issue I am facing is that the training is extremely slow.
The training was done on an n1-standard-64 machine of Google Cloud Platform (see here : https://cloud.google.com/compute/docs/machine-types) [64 cores, 240GB mem]
I used the following parameters :
`layers = 1
num_negs = 2
lr = 0.01
optimizer = adam
hidden_dim = 4
num_epochs = 1
embedding_dim 4
batch_size 1024`
The training took total 183m51.489s. I have used very low settings here, and want to use higher settings like more dimensions, more number of epochs etc, but training time is an issue.
Is such large training time expected for such kind of dataset? Or something is going wrong here?
My training logs can be seen here => https://drive.google.com/file/d/1DyEPa9abK3X0UCiOqsemWZ8yxP5GjXBl/view?usp=sharing

Start with the RGCN implementation in the examples directory and inspect the linked training logs alongside the stated dataset, batch, and epoch settings. Reproduce or profile the one-epoch run if the environment is available; done means determining whether the runtime is expected or identifying a documented, actionable bottleneck.

Written by the indexing model from the issue text.