<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/lamb.py) |

Layer-wise Adaptive Moments (LAMB) optimizer.

See paper [Large Batch Optimization for Deep Learning: Training BERT in
76 minutes](https://arxiv.org/abs/1904.00962).

## Classes

[`class LAMB`](https://www.tensorflow.org/api_docs/python/tfm/optimization/lamb/LAMB): Optimizer that implements the Layer-wise Adaptive Moments (LAMB).

## Type Aliases

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