Adaptive Input Large

Reported on 2 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Language ModellingonOne Billion Word
Validation perplexity· 2018-09-28
23.83
best: 20.25 (H-Transformer-1D Nr=16 (Large))
SOTA
Adaptive Input Representations for Neural Language Modeling arXiv:1809.10853
Language ModellingonOne Billion Word
PPL· 2018-09-28
23.91
best: 20.09 (MDLM (AR baseline))
Adaptive Input Representations for Neural Language Modeling arXiv:1809.10853