Model saving and load

[irfanfadhullah]

I was wondering, how do we save the model in this framework? Is it same as saving torch model? And can we test the model after the training cycle is done? An example would be great. Thank you

[czjghost]

I think it is the same as saving torch model, but for the testing samples are not the same among all runs, you should save those sample at the same time after the end of each run. If you want to reduplicate each incremental step (like the figure 2 in ASER), you could just save the model after finishing trainning each task.

[Frapais]

@czjghost Can you please give an example code of how to save the model and the training and evaluation results? Thanks in advance