Commonsense Reasoning on HellaSwag (acc_norm)
28.55Normalized AccuracyMIR
Evaluation Results
| Method | Links | |
|---|---|---|
| MIRParameters=1.4B, Training Data=DCLM, Training Tokens=100M, Evaluation=Zero-shot2026.06 | 28.55 | |
| Regularized BaselineParameters=1.4B, Training Data=DCLM, Training Tokens=100M, Evaluation=Zero-shot2026.06 | 28.33 | |
| Random GuessParameters=1.4B, Training Data=DCLM, Training Tokens=100M, Evaluation=Zero-shot2026.06 | 25 |