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 | 116 | 12.21% |
| Language Modelling | 109 | 11.47% |
| Question Answering | 60 | 6.32% |
| Large Language Model | 39 | 4.11% |
| Sentence | 34 | 3.58% |
| Sentiment Analysis | 33 | 3.47% |
| Text Classification | 30 | 3.16% |
| Information Retrieval | 22 | 2.32% |
| Text Generation | 19 | 2.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
