bytedance / bytedance/1d-tokenizer

Training on new dataset

Open
#36 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
1.2k
Forks
70
PR merge metrics
No merged PRs in 30d

Description

Hi I am looking to train this tokenizer on a sign language dataset CSL-Daily so that I can compress video frames into 32 tokens.
However, I am not getting very good results (attached below). I would like to check if all I have to do is download the pretrained model and then run it as:

WANDB_MODE=offline accelerate launch --num_machines=1 --num_processes=2 --machine_rank=0 --main_process_ip=127.0.0.1 --main_process_port=9999 --same_network scripts/train_titok.py config=configs/training/stage1/titok_;32.yaml \
    experiment.project="titok_l32_stage1" \
    experiment.name="titok_;32_stage1_run1" \
    experiment.output_dir="titok_l32_stage1_run1" \
    training.per_gpu_batch_size=32

00862136_s-001
00862136_s-000

Please advice! Thanks!

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 scripts/train_titok.py and configs/training/stage1/titok_;32.yaml, then compare the reported CSL-Daily results with the training command in the issue. Done means determining whether this pretrained-model workflow is sufficient for the requested 32-token sign-language dataset training and documenting the required setup or changes.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning
Issue type
Feature
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.