diff options
| author | David Doan <daviddoan@davids-mbp-3.devices.brown.edu> | 2022-05-07 17:37:47 -0400 |
|---|---|---|
| committer | David Doan <daviddoan@davids-mbp-3.devices.brown.edu> | 2022-05-07 17:37:47 -0400 |
| commit | 228d83a47b6c6eb1d0c01b85761a8f6e1db48c1d (patch) | |
| tree | 5b1ae18c8b5e1ae1392c7760e2e741f8eb6e778e /hyperparameters.py | |
| parent | 46a7929942f90d960a0a4d6e35251c900bd45fb2 (diff) | |
| parent | 00991837cc0bbb62b98ab3024ea795a18cf2dde8 (diff) | |
testing
Diffstat (limited to 'hyperparameters.py')
| -rw-r--r-- | hyperparameters.py | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/hyperparameters.py b/hyperparameters.py index 63e51b91..75528742 100644 --- a/hyperparameters.py +++ b/hyperparameters.py @@ -9,17 +9,17 @@ Number of epochs. If you experiment with more complex networks you might need to increase this. Likewise if you add regularization that slows training. """ -num_epochs = 100 +num_epochs = 500 """ A critical parameter that can dramatically affect whether training succeeds or fails. The value for this depends significantly on which optimizer is used. Refer to the default learning rate parameter """ -learning_rate = 3e-2 +learning_rate = 1e2 momentum = 0.01 -alpha = 1e-5 +alpha = 1 -beta = 1e-2 +beta = 100 |