Back to Home

Hyperparameters

Configure and tune hyperparameters for optimal model performance.

Common Hyperparameters

learning_rateDefault: 0.001

Controls how quickly the model learns

batch_sizeDefault: 32

Number of samples per gradient update

epochsDefault: 10

Number of complete passes through the dataset

dropoutDefault: 0.5

Regularization to prevent overfitting

Automatic Tuning

oneml tune --method bayesian --trials 100
Data ManagementBack to Docs