LAION-AI / LAION-AI/CLAP

Training time to recreate

Open
#103 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2.3k
Forks
213
PR merge metrics
No merged PRs in 30d

Description

Hello, I am trying to assess feasibility of continued training of a CLAP model. On your report of training on a single A100 on Clotho, https://stability.wandb.io/clap/clap/reports/CLAP-trained-on-Clotho-dataset--VmlldzoyNzY?accessToken=c0erq9hhp7h880jclihd9j9if679s6bylwto33vo14yo5jg40ppe38qeoafoonpz, the timing metrics are not shown (e.g. train/batch_time.) Can you share how long it takes approximately to train on the Clotho dataset or generally? Thank you!

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

Start by reviewing the linked Weights & Biases report for the CLAP model trained on the Clotho dataset and check whether train/batch_time or related timing metrics are available. Done means documenting an approximate training duration for a single A100 or explaining the generally expected training time.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
1/5
Estimated time
Under an hour
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.