Instruction Following on AlpacaFarm (test)
387.196Reward ScoreBoNWD
Evaluation Results
| Method | Links | |
|---|---|---|
| BoNWDN=202025.12 | 387.196 | |
| pBoNWDN=202025.12 | 385.97 | |
| pBoNWDN=602025.12 | 371.915 | |
| pBoNWDN=402025.12 | 364.229 | |
| BoNWDN=602025.12 | 359.87 | |
| BoNWDN=402025.12 | 358.807 | |
| pBoNWDN=802025.12 | 355.405 | |
| BoNWDN=802025.12 | 352.948 | |
| pBoNWDN=1282025.12 | 345.891 | |
| BoNWDN=1282025.12 | 342.466 | |
| pBoNLN=402025.12 | 325.268 | |
| BoNLN=402025.12 | 322.004 | |
| pBoNLN=602025.12 | 319.242 | |
| pBoNLN=802025.12 | 318.669 | |
| BoNLN=602025.12 | 317.209 | |
| BoNLN=802025.12 | 314.396 | |
| pBoNN=402025.12 | 299.786 | |
| pBoNLN=1282025.12 | 298.759 | |
| BoNLN=1282025.12 | 297.97 | |
| pBoNLN=202025.12 | 295.606 | |
| BoNLN=202025.12 | 295.178 | |
| BoNN=402025.12 | 294.718 | |
| pBoNN=602025.12 | 281.903 | |
| BoNN=602025.12 | 276.195 | |
| pBoNN=802025.12 | 261.588 | |
| BoNN=802025.12 | 258.863 | |
| pBoNN=202025.12 | 254.729 | |
| BoNN=202025.12 | 253.035 | |
| pBoNN=1282025.12 | 249.733 | |
| pBoNKLN=402025.12 | 246.798 | |
| BoNKLN=402025.12 | 246.544 | |
| BoNN=1282025.12 | 244.257 | |
| pBoNKLN=202025.12 | 237.498 | |
| BoNKLN=602025.12 | 234.598 | |
| pBoNKLN=602025.12 | 234.109 | |
| BoNKLN=202025.12 | 232.696 | |
| pBoNKLN=802025.12 | 221.263 | |
| BoNKLN=802025.12 | 220.471 | |
| BoNKLN=1282025.12 | 213.974 | |
| pBoNKLN=1282025.12 | 212.828 |