DistilBERT-uncased-PruneOFA (85% unstruct sparse)

Reported on 4 benchmarks across 2 tasks · 1 paper

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

Natural Language Processing4 results

Question AnsweringonSQuAD1.1 dev
EM· 2021-11-10
78.1
best: 90.06 (T5-11B)
Prune Once for All: Sparse Pre-Trained Language Models arXiv:2111.05754
Question AnsweringonSQuAD1.1 dev
F1· 2021-11-10
85.82
best: 95.77 (XLNet+DSC)
Prune Once for All: Sparse Pre-Trained Language Models arXiv:2111.05754
Natural Language InferenceonMultiNLI Dev
Matched· 2021-11-10
81.35
best: 84.5 (TinyBERT-6 67M)
Prune Once for All: Sparse Pre-Trained Language Models arXiv:2111.05754
Natural Language InferenceonMultiNLI Dev
Mismatched· 2021-11-10
82.03
best: 84.5 (TinyBERT-6 67M)
Prune Once for All: Sparse Pre-Trained Language Models arXiv:2111.05754