Natural Language Inference on RTE GLUE (test dev)
84AccuracyAdam
Evaluation results
| Method | Links | |
|---|---|---|
| AdamModel=Gemma2-2B, Evaluation Protocol=Fine-tuning2026.02 | 84 | |
| ZO-MuonModel=Gemma2-2B, Evaluation Protocol=Fine-tuning2026.02 | 63.2 | |
| LoRAModel=Gemma2-2B, Evaluation Protocol=Fine-tuning2026.02 | 57.8 | |
| SubZeroModel=Gemma2-2B, Evaluation Protocol=Fine-tuning2026.02 | 56.7 | |
| LOZOModel=Gemma2-2B, Evaluation Protocol=Fine-tuning2026.02 | 56.3 | |
| S-MeZOModel=Gemma2-2B, Evaluation Protocol=Fine-tuning2026.02 | 53.8 | |
| HiZOOModel=Gemma2-2B, Evaluation Protocol=Fine-tuning2026.02 | 53.1 | |
| MeZOModel=Gemma2-2B, Evaluation Protocol=Fine-tuning2026.02 | 53 |