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 |
---|---|
name | AdamWeightDecay |
learning_rate.module | official.nlp.optimization |
learning_rate.class_name | WarmUp |
learning_rate.config.initial_learning_rate.class_name | tensor |
learning_rate.config.initial_learning_rate.config.value | 1.799999881768599e-05 |
learning_rate.config.initial_learning_rate.config.dtype | float32 |
learning_rate.config.decay_schedule_fn.module | keras.optimizers.schedules |
learning_rate.config.decay_schedule_fn.class_name | PolynomialDecay |
learning_rate.config.decay_schedule_fn.config.initial_learning_rate | 2e-05 |
learning_rate.config.decay_schedule_fn.config.decay_steps | 5848 |
learning_rate.config.decay_schedule_fn.config.end_learning_rate | 0 |
learning_rate.config.decay_schedule_fn.config.power | 1.0 |
learning_rate.config.decay_schedule_fn.config.cycle | False |
learning_rate.config.decay_schedule_fn.config.name | None |
learning_rate.config.decay_schedule_fn.registered_name | None |
learning_rate.config.warmup_steps | 584.8000000000001 |
learning_rate.config.power | 1.0 |
learning_rate.config.name | None |
learning_rate.registered_name | WarmUp |
decay | 0.0 |
beta_1 | 0.9 |
beta_2 | 0.999 |
epsilon | 1e-06 |
amsgrad | False |
weight_decay_rate | 0.95 |
training_precision | float32 |
Model Plot
<details> <summary>View Model Plot</summary>
</details>