Question Answering on SQuAD 1.1 (test)
72.73Rouge-LTANDEM
Evaluation results
| Method | Links | |
|---|---|---|
| TANDEMModel Size=500M, Base Model=Qwen-2, Training Steps=2000, Batch Size=32, Context Length=512, K=20, E=102026.06 | 72.73 | |
| UniformModel Size=500M, Base Model=Qwen-2, Training Steps=2000, Batch Size=32, Context Length=512, K=20, E=102026.06 | 72.62 | |
| AioliModel Size=500M, Base Model=Qwen-2, Training Steps=2000, Batch Size=32, Context Length=512, K=20, E=102026.06 | 72.35 | |
| Skill-ItModel Size=500M, Base Model=Qwen-2, Training Steps=2000, Batch Size=32, Context Length=512, K=20, E=102026.06 | 72.14 | |
| DoReMiModel Size=500M, Base Model=Qwen-2, Training Steps=2000, Batch Size=32, Context Length=512, K=20, E=102026.06 | 71.4 | |
| DoGEModel Size=500M, Base Model=Qwen-2, Training Steps=2000, Batch Size=32, Context Length=512, K=20, E=102026.06 | 71.26 |