Commonsense Reasoning on CQA (evaluation)
79.2AccuracyRoBERTa-L + MUPPET
Evaluation results
| Method | Links | |
|---|---|---|
| RoBERTa-L + MUPPETModel Size=Large, Backbone=RoBERTa, Training Strategy=MUPPET2021.01 | 79.2 | |
| T5-11BModel Size=11B, Backbone=T52021.01 | 78.9 | |
| RoBERTa-LModel Size=Large, Backbone=RoBERTa2021.01 | 78.1 | |
| BARTBackbone=BART2021.01 | 78.1 | |
| T5-LModel Size=Large, Backbone=T52021.01 | 75.6 | |
| BART + MUPPETBackbone=BART, Training Strategy=MUPPET2021.01 | 74.8 | |
| RoBERTa-B + MUPPETModel Size=Base, Backbone=RoBERTa, Training Strategy=MUPPET2021.01 | 69.4 | |
| RoBERTa-BModel Size=Base, Backbone=RoBERTa2021.01 | 66.2 |