diff options
| author | Logan Bauman <logan_bauman@brown.edu> | 2022-05-07 11:21:54 -0400 |
|---|---|---|
| committer | Logan Bauman <logan_bauman@brown.edu> | 2022-05-07 11:21:54 -0400 |
| commit | 96b69eac697100499e54c8ac18c10313bd460f3b (patch) | |
| tree | 30ccc21e55668cb8c395d388ba0ca23eb0084be3 /hyperparameters.py | |
| parent | bc14ecf3c19ac8fdacd5e8057986b3c20dd7cb6c (diff) | |
hi
Diffstat (limited to 'hyperparameters.py')
| -rw-r--r-- | hyperparameters.py | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/hyperparameters.py b/hyperparameters.py index d5eb2f47..594368f7 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 = 5000 +num_epochs = 2000 """ A critical parameter that can dramatically affect whether training @@ -22,4 +22,4 @@ momentum = 0.01 alpha = 1e-2 -beta = 5e-1 +beta = 7e-1 |