Learning Rate Schedules
Inverse Square Root Schedule
Inverse Square Root is a learning rate schedule 1 / $\sqrt{\max\left(n, k\right)}$ where $n$ is the current training iteration and $k$ is the number of warm-up steps. This sets a constant learning rate for the first $k$ steps, then exponentially decays the learning rate until pre-training is over.
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Language Modelling | 97 | 9.69% |
| Question Answering | 65 | 6.49% |
| Text Generation | 48 | 4.80% |
| Sentence | 44 | 4.40% |
| Translation | 32 | 3.20% |
| Retrieval | 30 | 3.00% |
| Machine Translation | 26 | 2.60% |
| Natural Language Understanding | 20 | 2.00% |
| Semantic Parsing | 19 | 1.90% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
