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 |
|---|---|---|
| RAG | 275 | 20.74% |
| Retrieval | 206 | 15.54% |
| Question Answering | 73 | 5.51% |
| Language Modelling | 58 | 4.37% |
| Language Modeling | 50 | 3.77% |
| Large Language Model | 42 | 3.17% |
| Information Retrieval | 24 | 1.81% |
| Text Classification | 22 | 1.66% |
| Text Generation | 20 | 1.51% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
