Methods › General › Learning Rate Schedules › Linear Warmup With Linear Decay

Linear Warmup With Linear Decay

7,076 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for n updates and then linearly decay afterwards.

Papers archive 2025-07-28

30 shown of 7,076, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 1,195 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
RAG1,279
Retrieval1,261
Language Modelling1,149
Retrieval-augmented Generation1,086
Language Modeling929
Question Answering765
Sentence745
Sentiment Analysis412
Text Classification393
text-classification347
Transfer Learning313
Classification266
Word Embeddings258
Information Retrieval244
Named Entity Recognition244
Natural Language Understanding235
named-entity-recognition234
Named Entity Recognition (NER)231
Large Language Model218
Articles197

Usage over time archive 2025-07-28

Papers per year tagged with Linear Warmup With Linear Decay: 2017 to 2025, peak 1,390 1,390 0 2017: 1 paper 2017 2018: 7 papers 2018 2019: 580 papers 2019 2020: 1248 papers 2020 2021: 1334 papers 2021 2022: 842 papers 2022 2023: 859 papers 2023 2024: 1390 papers 2024 2025: 815 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (7,076 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Learning Rate Schedules

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections