pre-training

Tag - pre-training
2026
LucidGPT: a closer look at the training loop
avatar
Jiazheng Li
Ph.D. student at Tsinghua University, advised by Jingzhao Zhang. Exploring LLM optimization, training dynamics and reinforcement learning.
Articles
6
Tags
17
Categories
3
GitHub
Announcement
An open notebook. Early ideas, negative results, and development logs belong here too.
Recent Posts
LucidGPT: a closer look at the training loop
What-s-up: building and checking a chat application
AI4Game: starting a project notebook
How to write up an experiment that didn't work
Why keep an open research notebook?
Categories
Tags
visualization workflow testing negative-results pre-training open-notebook optimization LucidGPT development evaluation research experiments software-engineering reproducibility What-s-up AI4Game writing
Archives