Continual Learning on 20Minuten
30.47Average AccuracySETA
Evaluation results
| Method | Links | |
|---|---|---|
| SETABackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 30.47 | |
| I-LoRABackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 28.82 | |
| EWCBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 26.2 | |
| PPBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 25.9 | |
| A-GEMBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 22.6 | |
| GEMBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 17.7 | |
| ERBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 16.5 | |
| L2PBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 15.4 | |
| Seq-TrainBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 13.6 |