Parameter | Value |
---|---|
Penalty for regularization | 0.0001 |
Batch size | 200 |
Tolerance of optimization | 10−4 |
Whether to shuffle samples in each iteration | True |
Whether to use early stopping to terminate training when the validation score is not improving | False |
β1 for adam | 0.9 |
β2 for adam | 0.999 |
ϵ for adam | 10−8 |