Multi-task Language Understanding on MMLU (Loss, Accuracy, PPL)
1.33Loss (FT)
MobileFineTuner
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.12 | 1.33 | 0.2672 | 3.81 | |
2025.12 | 1.35 | 0.2918 | 3.89 | |
2025.12 | 1.37 | 0.3006 | 3.87 | |
2025.12 | 1.38 | 0.2353 | 3.88 | |
2025.12 | 1.39 | 0.2545 | 4 | |
2025.12 | 1.45 | 0.2516 | 4.28 | |
2025.12 | 1.46 | 0.4147 | 3.2 | |
2025.12 | 1.48 | 0.3902 | 3.4 | |
2025.12 | 1.65 | 0.4028 | 3.82 | |
2025.12 | 1.7 | 0.3712 | 3.95 |