Learning Rate Schedules
Linear Warmup With Linear Decay
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
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| 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% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
