Albert Zeyer

Currently `learning_rates` is either a list or lrs or dict epoch -> lr (so a sparse list or lrs). I'm not sure if extending/changing `learning_rates` to also cover initial/default lr...

I think @JackTemaki is right in the way, when `learning_rates` also specifies the LR of epoch 1. However, I don't see this too much of a problem. And this also...

> But then we are still left with `learning_rate` and `learning_rates`, Yes, this is what I meant. I would prefer to keep both. > Merging this into a single variable...

Can you post the error?

Please always also post relevant snippets directly here. In this case: ``` layer /'data' output: Data{'data', [B,T|'time:var:extern_data:data'[B],F|F'feature:data'(5)]} layer /'output' output: Data{'output_output', [T|'time:var:extern_data:data'[B&Beam{'output/output'}(3)],B&Beam{'output/output'}(3)], dtype='int32', sparse_dim=DimensionTag{F'classes:sparse-dim'(5)}} Rec layer 'output' (search True, train...

And also relevant config parts for what you get the error. (The issue should contain all relevant information.) In this case, the net dict: ``` network = { "output": {"class":...

Related is also #487.

Note that I don't think it has caused us more than 5 minutes of work in the last few years in total, if at all. And I would expect that...

Yes we don't need to argue that it's good to have this cleaned up. But I again should note that this will really not have such a (or even any)...

I'm not really sure that's needed. We can just say, commit 23cc84aa2b389737aa15e8a84c88c475bfd007a1 is one of the latest. This information is enough I think.