T5-Base 220M (fine-tuned)

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 AnsweringonCOPA
Accuracy· 2019-10-23
71.2
best: 100 (PaLM 540B (finetuned) )
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683
Question AnsweringonBoolQ
Accuracy· 2019-10-23
81.4
best: 99.87 (Mistral-Nemo 12B (HPT))
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683
Natural Language InferenceonCommitmentBank
Accuracy· 2019-10-23
94
best: 100 (PaLM 540B (finetuned))
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683
Natural Language InferenceonCommitmentBank
F1· 2019-10-23
86.2
best: 100 (PaLM 540B (finetuned))
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer arXiv:1910.10683