diff options
| author | Logan Bauman <logan_bauman@brown.edu> | 2022-05-07 08:35:31 -0400 |
|---|---|---|
| committer | Logan Bauman <logan_bauman@brown.edu> | 2022-05-07 08:35:31 -0400 |
| commit | e7150a281f23175fd289e3e3050db44717df3a4a (patch) | |
| tree | eb3a6f23221fc73d23aedaeff52431965cca6ae5 /hyperparameters.py | |
| parent | b9051e0ec773095dcf84ec26a02248a46dcf1786 (diff) | |
hi
Diffstat (limited to 'hyperparameters.py')
| -rw-r--r-- | hyperparameters.py | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/hyperparameters.py b/hyperparameters.py index fedd4dd7..75d58118 100644 --- a/hyperparameters.py +++ b/hyperparameters.py @@ -9,7 +9,7 @@ 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 = 150 +num_epochs = 1000 """ A critical parameter that can dramatically affect whether training @@ -20,6 +20,6 @@ learning_rate = 1e-2 momentum = 0.01 -alpha = 1e1 +alpha = 1e-3 -beta = 1e2 +beta = 1e-1 |