Continual Learning on MeetingBank
35.9Average AccuracyEWC
Evaluation results
| Method | Links | |
|---|---|---|
| EWCBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 35.9 | |
| SETABackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 33.21 | |
| Seq-TrainBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 31.2 | |
| ERBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 30.6 | |
| I-LoRABackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 30.6 | |
| GEMBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 28.3 | |
| A-GEMBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 28 | |
| PPBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 26.5 | |
| L2PBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 24 |