Text Classification on Mixed BERT-base (test)
83.3AccuracyAdapterFusion
Evaluation results
| Method | Links | |
|---|---|---|
| AdapterFusionNum Params=470 M, Backbone=BERT-base2022.03 | 83.3 | |
| AdaptersNum Params=470 M, Backbone=BERT-base2022.03 | 82 | |
| ADA (K=4) - TransRateNum Params=128 M, Backbone=BERT-base2022.03 | 81.2 | |
| ADA (K=4) - LEEPNum Params=128 M, Backbone=BERT-base2022.03 | 79.5 | |
| ADA (K=1)Num Params=120.8 M, Backbone=BERT-base2022.03 | 72.9 |