bytedance / bytedance/1d-tokenizer
how many steps can i get an equivalent result in titok?
- Dominant language
- Jupyter Notebook
- Stars
- 1.2k
- Forks
- 70
- PR merge metrics
- No merged PRs in 30d
Description
Hi!
I have read the code about titok and discovered you use 32 epochs for 100w steps in 32 GPUs. However, I just have 8 4090 GPUs and set the epoch to 16. I want to know how many steps should i set to get an equivalent and similar effects?
Thanks!
Contributor guide
No contributing guide indexed for this repository
Research direction
Read the training code and compare the reported 32-epoch, 100w-step run on 32 GPUs with the proposed 16-epoch run on 8 4090 GPUs. Determine what information is needed to define an equivalent step count, then document a supported calculation or explain why equivalence cannot be established from the issue alone.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100