Open ArkDu opened 3 years ago
Hi, @ArkDu, I noticed the default learning rate for KG2E is 0.01, which may have been too high and resulted in a large gradient during the training. Would you like to try decreasing it and see if that helps?
Sure I'll try a smaller learning rate and see how it goes.
I run train.py with python train.py -mn kg2e -exp true -device cuda. It first seemed alright, but after around 400 epochs it's mini-test results became NaN or 0.000000.
This is kg2e_Test_results.csv after training finished. It indicates that the model stopped working at around 400 epochs