Natural Language Processing on SuperGLUE 100 samples, excl. ReCoRD (dev)
59.88Macro Avg ScoreMulti-CLS BERT
Evaluation Results
| Method | Links | |
|---|---|---|
| Multi-CLS BERTBackbone=BERT Large, Model Size=350.9M, K=5, lambda=0.12022.10 | 59.88 | |
| Multi-CLS BERTBackbone=BERT Large, Model Size=350.9M, K=5, lambda=02022.10 | 59.46 | |
| Multi-CLS BERTBackbone=BERT Large, Model Size=350.9M, K=5, lambda=0.52022.10 | 59.42 | |
| MTLBackbone=BERT Large, Model Size=335.2M2022.10 | 59.03 | |
| Multi-CLS BERTBackbone=BERT Large, Model Size=350.9M, K=5, lambda=12022.10 | 58.74 | |
| Multi-CLS BERTBackbone=BERT Base, Model Size=118.4M, K=5, lambda=0.52022.10 | 58.41 | |
| Multi-CLS BERTBackbone=BERT Base, Model Size=118.4M, K=5, lambda=02022.10 | 58.29 | |
| Multi-CLS BERTBackbone=BERT Base, Model Size=118.4M, K=5, lambda=0.12022.10 | 58.2 | |
| Multi-CLS BERTBackbone=BERT Base, Model Size=118.4M, K=5, lambda=12022.10 | 57.84 | |
| MTLBackbone=BERT Base, Model Size=109.5M2022.10 | 57.5 | |
| Multi-CLS BERTBackbone=BERT Large, Model Size=338.3M, K=12022.10 | 57.35 | |
| Multi-CLS BERTBackbone=BERT Base, Model Size=111.3M, K=12022.10 | 57.31 | |
| PretrainedBackbone=BERT Base, Model Size=109.5M2022.10 | 57.18 |