Text Classification on Wiki-30K BERT-base (test)
86.7AccuracyAdapterFusion
Evaluation Results
| Method | Links | |
|---|---|---|
| AdapterFusionNum Params=326 M, Backbone=BERT-base2022.03 | 86.7 | |
| ADA (K=4) - TransRateNum Params=128 M, Backbone=BERT-base2022.03 | 85.8 | |
| AdaptersNum Params=326 M, Backbone=BERT-base2022.03 | 84.7 | |
| ADA (K=4) - LEEPNum Params=128 M, Backbone=BERT-base2022.03 | 84.2 | |
| ADA (K=1)Num Params=120.8 M, Backbone=BERT-base2022.03 | 77 |