Comments (1)
GaoPeng97
commented on August 16, 2024
So embarrassed, it is my mistake. test.txt is the zhihu dataset mentioned in readme. And you should use test_base_gpu.sh( not zhihu_base_gpu.sh) to generate result. BTW, zhihu_base_gpu.sh is for a training on 500M zhihu dataset at first, and model did not converge well on so large a dataset. So I select 20M to get better result.
from transformer-xl-chinese.
Related Issues (20)
- 模型层缺少encoder层
- infernence出现的问题 HOT 6
- 请问1080Ti能训练 shi这个训练集吗 HOT 1
- transformer-xl in 1-billion experiment with base model configuration
- 有关cache memory的问题
- 怎么在训练的时候添加样本的权重
- AttributeError: module 'tensorflow.sparse' has no attribute 'to_dense' HOT 1
- 如何用transformerXL做文本摘要任务 HOT 1
- 关于 inference HOT 1
- seed text干什么用的？ HOT 6
- inference的时候出现报错
- 你好，我发了邮件给[email protected]，请查看下哦
- 你好，请问ppl到多少停止训练比较合适 HOT 2
- 改变输入样本的格式
- inference 在哪里分词，也不知道有没有人回复
- why takes only 135M gpu memory but takes 10-50G cpu memory?
- inference中的sess.run
- 请问tf.model中rel_multihead_attn的w是一个batch还是单条数据？
- inference 中的saver.restore(sess, eval_ckpt_path)模型恢復不出來 HOT 2
- 请问训练Doupo这个模型需要多大的显存？ HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from transformer-xl-chinese.