| language-modelling-on-enwiki8 | SRU++ Large | #3 | Bit per Character (BPC): 0.95Number of params: 195M |
| language-modelling-on-enwiki8 | SRU++ Base | #8 | Bit per Character (BPC): 0.97Number of params: 108M |
| language-modelling-on-one-billion-word | SRU++ Large | #9 | PPL: 23.5Number of params: 465M |
| language-modelling-on-one-billion-word | SRU++ | #13 | PPL: 25.1Number of params: 328M |
| language-modelling-on-wikitext-103 | SRU++ Large | #22 | Test perplexity: 17.1Validation perplexity: 16.4… |
| language-modelling-on-wikitext-103 | SRU++ Base | #34 | Test perplexity: 18.3Validation perplexity: 17.5… |