thu-ml / thu-ml/TurboDiffusion

How is the performance if we train with sCM loss only?

Open
#111 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.7k
Forks
277
Avg merge
2h 57m
Merged PRs (30d)
2

Description

Hi @zhengkw18,

In the paper, you compared the rCM with DMD loss, I am wondering what if you train the model with sCM loss only? Do I need to turn the hyperparameters a lot if I want to use sCM loss only?

Btw, would you mind sharing your loss curves/grad norms over training time?

Thanks in advance!
Meng

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue does not identify a file, test, or entry point to inspect. Begin by locating the training configuration and loss implementation for sCM, then compare sCM-only training with the paper's rCM and DMD setup. Done would include performance results, any required hyperparameter changes, and loss curves or gradient norms.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.