GL-LWGC + AWD-MoS-LSTM + dynamic eval

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

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

Medical4 results

Language ModellingonPenn Treebank (Word Level)
Test perplexity· 2017-08-29
46.34
best: 20.5 (GPT-3 (Zero-Shot))
SOTA
Gradual Learning of Recurrent Neural Networks arXiv:1708.08863
Language ModellingonPenn Treebank (Word Level)
Validation perplexity· 2017-08-29
46.64
best: 36.1 (BERT-Large-CAS)
SOTA
Gradual Learning of Recurrent Neural Networks arXiv:1708.08863
Language ModellingonWikiText-2
Test perplexity· 2017-08-29
40.46
best: 8.21 (SparseGPT (175B, 50% Sparsity))
SOTA
Gradual Learning of Recurrent Neural Networks arXiv:1708.08863
Language ModellingonWikiText-2
Validation perplexity· 2017-08-29
42.19
best: 15.69 (GPT-2 (fine-tuned))
SOTA
Gradual Learning of Recurrent Neural Networks arXiv:1708.08863