Skip to content

Bag of Tricks in Machine Learning

Public Personal Notebook

  • Home
  • random
  • paper
  • list
  • nlp
  • reinforcementlearning
  • gan
  • cv

Google’s Deep Learning Tuning Playbook

January 22, 2023 by admin

This guide has tons of tricks that are usually not covered in textbooks: https://github.com/google-research/tuning_playbook

Categories Uncategorized
Few-Shot Learning in NLP

Best practice to follow this website

  1. In Feedly, click “add content”
  2. Input the url “bagoftricks.ml” and follow

Shujian Follow

Software engineer @Google Travel. PhD in renewable energy from @UMassAmherst. @kaggle triple master. IR/NLP/ASR.

Shujian_Liu
Retweet on Twitter Shujian Retweeted
shayneredford Shayne Longpre @shayneredford ·
1 Feb

✨New Paper✨What’s the best completely public competitor to #ChatGPT?

Flan-T5 beats all public models we tested:
Flan-T5 3B ▶️ T0++ 3B ▶️ OPT-IML 175B ▶️ GLM-130B ▶️ Flan 2021 3B ▶️ NIv2 3B

We release the @GoogleAI 🌟Flan Collection🌟data + methods for Instruction Tuning!

1/

Reply on Twitter 1620805305801261058 Retweet on Twitter 1620805305801261058 235 Like on Twitter 1620805305801261058 1092 Twitter 1620805305801261058
Retweet on Twitter Shujian Retweeted
pitdesi Sheel Mohnot @pitdesi ·
20 Jan

Most popular car in Europe / most popular car in the US.

Reply on Twitter 1616442925876928513 Retweet on Twitter 1616442925876928513 1193 Like on Twitter 1616442925876928513 11233 Twitter 1616442925876928513
Retweet on Twitter Shujian Retweeted
omarsar0 elvis @omarsar0 ·
20 Jan

🐙 Deep Learning Tuning Playbook

Amazing resource released by Google. It shows tips on how to conduct DL experiments and get good results.

I think it's also super useful to design exercises and practice more with DL models.

https://github.com/google-research/tuning_playbook

Reply on Twitter 1616251426925121536 Retweet on Twitter 1616251426925121536 262 Like on Twitter 1616251426925121536 971 Twitter 1616251426925121536
Retweet on Twitter Shujian Retweeted
davisblalock Davis Blalock @davisblalock ·
13 Aug

"Language Models Can Teach Themselves to Program Better"

This paper changed my thinking about what future langauge models will be good at, mostly in a really concerning way. Let's start with some context: [1/11]

Reply on Twitter 1558347542101839873 Retweet on Twitter 1558347542101839873 679 Like on Twitter 1558347542101839873 3278 Twitter 1558347542101839873
Retweet on Twitter Shujian Retweeted
quocleix Quoc Le @quocleix ·
21 Oct

New open-source language model from Google AI: Flan-T5 🍮

Flan-T5 is instruction-finetuned on 1,800+ language tasks, leading to dramatically improved prompting and multi-step reasoning abilities.

Public models: https://bit.ly/3sbNPDJ
Paper: https://arxiv.org/abs/2210.11416

Reply on Twitter 1583523186376785921 Retweet on Twitter 1583523186376785921 500 Like on Twitter 1583523186376785921 2507 Twitter 1583523186376785921
Load More

Categories

  • ml (2)
  • nlp (15)
  • papers (4)
  • random (8)
  • reinforcementlearning (1)
  • search (1)
  • Uncategorized (59)

Tags

anomaly (1) automl (1) ctr (1) cv (2) data (1) distributedtraining (1) gan (1) kaggle (1) list (2) ml (2) NER (1) nlp (10) nn (1) paper (1) random (3) reinforcementlearning (1) sql (1)

Recent Posts

  • Google’s Deep Learning Tuning Playbook
  • Few-Shot Learning in NLP
  • (Very) Large Language Models in 2022
  • Airbnb Search Papers
  • Dense Retriever for Salient Phrase

Archives

  • January 2023 (1)
  • October 2022 (1)
  • August 2022 (3)
  • July 2022 (1)
  • July 2021 (2)
  • June 2021 (1)
  • May 2020 (1)
  • October 2019 (1)
  • August 2019 (11)
  • July 2019 (8)
  • June 2019 (6)
  • May 2019 (1)
  • April 2019 (11)
  • March 2019 (4)
  • February 2019 (2)
  • January 2019 (32)

Recent Comments

    January 2023
    M T W T F S S
     1
    2345678
    9101112131415
    16171819202122
    23242526272829
    3031  
    « Oct    

    • 0
    • 5
    • 90,381
    • 45,280
    • 86
    • 0

    Recent Posts

    • Google’s Deep Learning Tuning Playbook
    • Few-Shot Learning in NLP
    • (Very) Large Language Models in 2022
    • Airbnb Search Papers
    • Dense Retriever for Salient Phrase

    Categories

    • ml (2)
    • nlp (15)
    • papers (4)
    • random (8)
    • reinforcementlearning (1)
    • search (1)
    • Uncategorized (59)

    Meta

    • Log in
    • Entries feed
    • Comments feed
    • WordPress.org
    © 2023 Bag of Tricks in Machine Learning • Built with GeneratePress