Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[事前学習] - MoE Upcycle #106

Open
Taishi-N324 opened this issue Dec 28, 2024 · 0 comments
Open

[事前学習] - MoE Upcycle #106

Taishi-N324 opened this issue Dec 28, 2024 · 0 comments
Labels
pretrain Experiment of model pretrain

Comments

@Taishi-N324
Copy link
Member

Overview

#80 それぞれに関してDrop-Upcycle時に同じ傾向を示すか確認をする

Details

モデルカードPR: https://github.com/llm-jp/model-cards/pull/{id}

数パラグラフ以内で実験に関する詳細を説明してください。
関連するリンクがあれば適宜してください。

Resources

  • 計算機
    • クラスタ: FIXME Sakura (Ishikari)
    • ノード種別: FIXME gpu-small (H100x8)
    • ノード台数: FIXME 32
  • コード
  • 入力データ:
    • {name}: {physical path}
  • 出力データ:
    • 保存先: {cluster}:/data/experiments/{number}
    • データ内訳:
      • {name}: xxx TB (バッファ容量を含む)
  • W&B ログ:
  • 開始日: YYYY-MM-DD
  • 終了予定日: YYYY-MM-DD (バッファ期間を含む)
@Taishi-N324 Taishi-N324 added the pretrain Experiment of model pretrain label Dec 28, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
pretrain Experiment of model pretrain
Projects
None yet
Development

No branches or pull requests

1 participant