Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule afterwards.
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Language Modelling | 66 | 9.24% |
Large Language Model | 42 | 5.88% |
Question Answering | 38 | 5.32% |
Retrieval | 29 | 4.06% |
Text Generation | 26 | 3.64% |
In-Context Learning | 22 | 3.08% |
Code Generation | 21 | 2.94% |
Sentence | 20 | 2.80% |
Prompt Engineering | 20 | 2.80% |