Common-sense Reasoning on ARC-Challenge In-Distribution Llama-3.1-8B (train test)
81.79AccuracyPoLAR-VBLL
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| PoLAR-VBLLBackbone=Llama-3.1-8B, Fine-tuning Steps=50002026.04 | 81.79 | 4.92 | 0.58 | |
| MLEBackbone=Llama-3.1-8B, Fine-tuning Steps=50002026.04 | 81.05 | 17.95 | 1.75 | |
| LABackbone=Llama-3.1-8B, Fine-tuning Steps=50002026.04 | 81.05 | 9.72 | 1.04 |