| Benchmark | Model | Rank | Results |
|---|---|---|---|
| language-modelling-on-penn-treebank-word-level | BERT-Large-CAS | #2 | Test perplexity: 31.3Validation perplexity: 36.1Params: 395M |
| language-modelling-on-wikitext-2 | BERT-Large-CAS | #10 | Test perplexity: 34.1Validation perplexity: 37.7… |
| language-modelling-on-wikitext-103 | BERT-Large-CAS | #46 | Test perplexity: 20.4Validation perplexity: 19.6… |