Table 6.
Hyperparameter values for experiments based on the collection 3 and TDE architectures
| Name of the hyperparameter | Hyperparameter value |
|---|---|
| Learning rate | 3e-5 |
| Batch size | 32 |
| Anneal factor | 0.5 |
| Patience | 3 |
| Max. number of epochs | 10 |
Official websites use .gov
A
.gov website belongs to an official
government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you've safely
connected to the .gov website. Share sensitive
information only on official, secure websites.