Continual Learning on ScienceQA
40.1Average AccuracyI-LoRA
Evaluation results
| Method | Links | |
|---|---|---|
| I-LoRABackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 40.1 | |
| EWCBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 38.5 | |
| SETABackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 36.92 | |
| A-GEMBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 36.9 | |
| ERBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 29.4 | |
| PPBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 28.3 | |
| Seq-TrainBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 27.4 | |
| GEMBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 27.4 | |
| L2PBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 26.4 |