metadata
library_name: keras
tags:
- 0.1.1
- classification
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
| Hyperparameters | Value |
|---|---|
| inner_optimizer.module | keras.optimizers |
| inner_optimizer.class_name | Adam |
| inner_optimizer.config.name | Adam |
| inner_optimizer.config.weight_decay | None |
| inner_optimizer.config.clipnorm | None |
| inner_optimizer.config.global_clipnorm | None |
| inner_optimizer.config.clipvalue | None |
| inner_optimizer.config.use_ema | False |
| inner_optimizer.config.ema_momentum | 0.99 |
| inner_optimizer.config.ema_overwrite_frequency | None |
| inner_optimizer.config.jit_compile | False |
| inner_optimizer.config.is_legacy_optimizer | False |
| inner_optimizer.config.learning_rate | 9.999999747378752e-06 |
| inner_optimizer.config.beta_1 | 0.9 |
| inner_optimizer.config.beta_2 | 0.999 |
| inner_optimizer.config.epsilon | 1e-07 |
| inner_optimizer.config.amsgrad | False |
| inner_optimizer.registered_name | None |
| dynamic | True |
| initial_scale | 32768.0 |
| dynamic_growth_steps | 2000 |
| training_precision | float32 |