diff --git a/keras/optimizer_v2/learning_rate_schedule.py b/keras/optimizer_v2/learning_rate_schedule.py index 5aa2c511eb494e0ebb030a592cebc8503e9f15a9..949ad05dc0fe5574aa1a4d3125c4bd3f1c717c34 100644 --- a/keras/optimizer_v2/learning_rate_schedule.py +++ b/keras/optimizer_v2/learning_rate_schedule.py @@ -662,7 +662,7 @@ class CosineDecayRestarts(LearningRateSchedule): The learning rate multiplier first decays from 1 to `alpha` for `first_decay_steps` steps. Then, a warm restart is performed. Each new warm restart runs for `t_mul` times more - steps and with `m_mul` times larger initial learning rate. + steps and with `m_mul` times initial learning rate as the new learning rate. Example usage: ```python