Open xunil17 opened 11 months ago
However, I'm receiving the same adapt_loss and loss at every timestep.
This is weird, indeed you should receive different loss values. Maybe you can proposal
by learner()
everywhere and see what happens?
I see that the proposal and maml have the same parameters but the learner.module._parameters are different.
Where exactly are you doing the print
statement?
Am I understanding that the proposal and maml model should have different parameters after learner.adapt is called?
I would expect that too, yes..
Hello, I am running the
toy_example.py
and printing out the loss and adapt_loss as shown below.However, I'm receiving the same adapt_loss and loss at every timestep. I'm also looking at the parameters inside the maml, proposal, and learner. I see that the proposal and maml have the same parameters but the learner.module._parameters are different. Am I understanding that the proposal and maml model should have different parameters after learner.adapt is called?
Thank you so much!