Commonsense Reasoning on WinoGrande (Zero-shot)
52.54Zero-shot AccuracyCoLA
Evaluation results
| Method | Links | |
|---|---|---|
| CoLAEvaluation protocol=Zero-shot, Fine-tuning stage=Alpaca-cleaned SFT, Model scale=1B2026.06 | 52.54 | |
| Full-RankEvaluation protocol=Zero-shot, Fine-tuning stage=Alpaca-cleaned SFT, Model scale=1B2026.06 | 52.22 | |
| DLR + CoLAEvaluation protocol=Zero-shot, Fine-tuning stage=Alpaca-cleaned SFT, Model scale=1B2026.06 | 52.12 |