ELC-BERT-base 98M (zero init)

Reported on 3 benchmarks across 1 task · 1 paper

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

Natural Language Processing3 results

Natural Language InferenceonRTE
Accuracy· 2023-11-03
63
best: 86.8 (PSQ (Chen et al., 2020))
Not all layers are equally as important: Every Layer Counts BERT arXiv:2311.02265
Natural Language InferenceonMultiNLI
Matched· 2023-11-03
84.4
best: 92.6 (Turing NLR v5 XXL 5.4B (fine-tuned))
Not all layers are equally as important: Every Layer Counts BERT arXiv:2311.02265
Natural Language InferenceonMultiNLI
Mismatched· 2023-11-03
84.5
best: 92.4 (Turing NLR v5 XXL 5.4B (fine-tuned))
Not all layers are equally as important: Every Layer Counts BERT arXiv:2311.02265