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.
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Retrieval | 149 | 15.27% |
Language Modelling | 90 | 9.22% |
Question Answering | 68 | 6.97% |
Large Language Model | 42 | 4.30% |
Sentence | 31 | 3.18% |
Text Classification | 26 | 2.66% |
Text Generation | 24 | 2.46% |
Information Retrieval | 24 | 2.46% |
Sentiment Analysis | 21 | 2.15% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |