学习率预热(transformers.get_linear_schedule_with_warmup)

技术文章 7个月前 完美者
1,648 0

标签:iat   sch   ota   ORC   rate   线性   optimizer   loading   阶段   

学习率预热

  • 在预热期间,学习率从0线性增加到优化器中的初始lr。

  • 在预热阶段之后创建一个schedule,使其学习率从优化器中的初始lr线性降低到0

技术图片

Parameters

  • optimizer (Optimizer) – The optimizer for which to schedule the learning rate.

  • num_warmup_steps (int) – The number of steps for the warmup phase.

  • num_training_steps (int) – The total number of training steps.

  • last_epoch (int, optional, defaults to -1) – The index of the last epoch when resuming training.

Returns

  • torch.optim.lr_scheduler.LambdaLR with the appropriate schedule.
# training steps 的数量: [number of batches] x [number of epochs].
total_steps = len(train_dataloader) * epochs

# 设计 learning rate scheduler
scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps = 50, 
                                            num_training_steps = total_steps)

学习率预热(transformers.get_linear_schedule_with_warmup)

标签:iat   sch   ota   ORC   rate   线性   optimizer   loading   阶段   

原文地址:https://www.cnblogs.com/douzujun/p/13868472.html

版权声明:完美者 发表于 2020-11-01 21:19:24。
转载请注明:学习率预热(transformers.get_linear_schedule_with_warmup) | 完美导航

暂无评论

暂无评论...