Natural Language Processing on GLUE 1k samples (dev)
76.27Macro Avg ScoreMulti-CLS BERT
Evaluation Results
| Method | Links | |
|---|---|---|
| Multi-CLS BERTBackbone=BERT Large, Model Size=350.9M, K=5, lambda=0.12022.10 | 76.27 | |
| Multi-CLS BERTBackbone=BERT Large, Model Size=350.9M, K=5, lambda=0.52022.10 | 75.95 | |
| Multi-CLS BERTBackbone=BERT Large, Model Size=350.9M, K=5, lambda=12022.10 | 75.85 | |
| Multi-CLS BERTBackbone=BERT Large, Model Size=350.9M, K=5, lambda=02022.10 | 75.73 | |
| Multi-CLS BERTBackbone=BERT Large, Model Size=338.3M, K=12022.10 | 75.35 | |
| MTLBackbone=BERT Large, Model Size=335.2M2022.10 | 75.3 | |
| Multi-CLS BERTBackbone=BERT Base, Model Size=118.4M, K=5, lambda=02022.10 | 74.14 | |
| Multi-CLS BERTBackbone=BERT Base, Model Size=118.4M, K=5, lambda=0.12022.10 | 74.1 | |
| Multi-CLS BERTBackbone=BERT Base, Model Size=118.4M, K=5, lambda=0.52022.10 | 74.02 | |
| Multi-CLS BERTBackbone=BERT Base, Model Size=118.4M, K=5, lambda=12022.10 | 73.75 | |
| Multi-CLS BERTBackbone=BERT Base, Model Size=111.3M, K=12022.10 | 73.28 | |
| MTLBackbone=BERT Base, Model Size=109.5M2022.10 | 73.26 | |
| PretrainedBackbone=BERT Base, Model Size=109.5M2022.10 | 71.67 |