Natural Language Understanding on Wikipedia corpus annotated (train)
36.46NLU ScoreLossH-Wiki
Evaluation results
| Method | Links | |
|---|---|---|
| LossH-Wikialpha (α)=0.7, Model size=110m2026.04 | 36.46 | |
| Random Baselinealpha (α)=0.3, Model size=110m2026.04 | 36.43 | |
| Random Baselinealpha (α)=0.5, Model size=110m2026.04 | 36.43 | |
| Random Baselinealpha (α)=0.9, Model size=110m2026.04 | 36.38 | |
| Random Baselinealpha (α)=1.0, Model size=110m2026.04 | 36.36 | |
| LossH-Wikialpha (α)=1.0, Model size=110m2026.04 | 36.36 | |
| LossH-Wikialpha (α)=0.3, Model size=110m2026.04 | 36.35 | |
| LossH-Wikialpha (α)=0.9, Model size=110m2026.04 | 36.33 | |
| LossH-Wikialpha (α)=0.6, Model size=110m2026.04 | 36.29 | |
| Random Baselinealpha (α)=0.8, Model size=110m2026.04 | 36.23 | |
| LossH-Wikialpha (α)=0.8, Model size=110m2026.04 | 36.13 | |
| LossH-Wikialpha (α)=0.5, Model size=110m2026.04 | 36.07 | |
| LossH-Wikialpha (α)=0.1, Model size=110m2026.04 | 36.06 | |
| LossH-Wikialpha (α)=0.2, Model size=110m2026.04 | 36.04 | |
| Random Baselinealpha (α)=0.2, Model size=110m2026.04 | 36.02 | |
| LossH-Wikialpha (α)=0.4, Model size=110m2026.04 | 35.98 | |
| Random Baselinealpha (α)=0.6, Model size=110m2026.04 | 35.97 | |
| Random Baselinealpha (α)=0.4, Model size=110m2026.04 | 35.93 | |
| Random Baselinealpha (α)=0.1, Model size=110m2026.04 | 35.83 | |
| Random Baselinealpha (α)=0.7, Model size=110m2026.04 | 35.8 |