results.yml

results:
- task:
    type: Language Modelling
    name: Language Modelling
  dataset:
    name: WikiText-2
    type: wikitext-2
    config: wikitext-2-raw-v1
    split: test
  metrics:
  - type: Perplexity
    value: 29.4
    name: Perplexity
    verified: false
- task:
    type: Language Modelling
    name: Language Modelling
  dataset:
    name: WikiText-103
    type: wikitext-103
    config: wikitext-103-raw-v1
    split: test
  metrics:
  - type: Perplexity
    value: 36.1
    name: Perplexity
    verified: false
- task:
    type: Long-context Language Modelling
    name: Long-context LM
  dataset:
    name: LongBench
    type: longbench
    split: test
  metrics:
  - type: Average Score
    value: 53.4
    name: Average Score
    verified: false