jiyunjie

训练稍微长点的句子就特别慢

2

用微博做训练语料。如果一句话的字的数量在130个，则这句话的训练时间需要几分钟。设置的batch size =1, 在CPU上训练的时候。这是正常现象吗？

Two approaches to improve the performance

6

Hi, I read your code and found there are two problems that hinder the performance improvement. First, as I know, previous papers use head words of entity mentions as the...

ontonote 4不是有18种实体类型？为什么下载的数据只有4种实体类型呢？

现在的代码支持actor和rollout分离吗

2

`self.hybrid_engine = config.actor_rollout_ref.hybrid_engine` `assert self.hybrid_engine, 'Currently, only support hybrid engine'` 根据代码来看，目前actor, rollout, ref必须在同一个worker上。 将来会考虑支持，将actor和rollout可以分配在不同的资源和worker上吗？