<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/models/blob/v2.20.0/official/modeling/optimization/lr_schedule.py#L340-L389) |

Power learning rate decay with offset.

#### View aliases


**Main aliases**

[`tfm.optimization.lr_schedule.PowerDecayWithOffset`](https://www.tensorflow.org/api_docs/python/tfm/optimization/PowerDecayWithOffset)

<br />

    tfm.optimization.PowerDecayWithOffset(
        initial_learning_rate: float,
        power: float = 1.0,
        offset: int = 0,
        pre_offset_learning_rate: float = 1000000.0,
        name: str = 'PowerDecayWithOffset'
    )

Learning rate equals to `pre_offset_learning_rate` if `step` \< `offset`.
Otherwise, learning rate equals to lr \* (step - offset)\^power.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `initial_learning_rate` | The initial learning rate. |
| `power` | The order of the polynomial. |
| `offset` | The offset when computing the power decay. |
| `pre_offset_learning_rate` | The maximum learning rate we'll use. |
| `name` | Optional, name of learning rate schedule. |

<br />

## Methods

### `from_config`

    @classmethod
    from_config(
        config
    )

Instantiates a `LearningRateSchedule` from its config.

<br />

<br />

<br />

| Args ||
|---|---|
| `config` | Output of `get_config()`. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `LearningRateSchedule` instance. ||

<br />

### `get_config`

[View source](https://github.com/tensorflow/models/blob/v2.20.0/official/modeling/optimization/lr_schedule.py#L381-L389)

    get_config()

Get the configuration of the learning rate schedule.

### `__call__`

[View source](https://github.com/tensorflow/models/blob/v2.20.0/official/modeling/optimization/lr_schedule.py#L369-L379)

    __call__(
        step
    )

Call self as a function.