This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 2.0481 | 1.0 | 63 | 1.9149 | 0.184 | 0.1081 | 0.1652 | 0.173 |
| 1.7799 | 2.0 | 126 | 1.8636 | 0.202 | 0.1142 | 0.1774 | 0.1883 |
| 1.5662 | 3.0 | 189 | 1.8301 | 0.1937 | 0.1107 | 0.1695 | 0.1787 |
| 1.4463 | 4.0 | 252 | 1.8581 | 0.1973 | 0.1166 | 0.174 | 0.1851 |
| 1.2893 | 5.0 | 315 | 1.8600 | 0.1885 | 0.1069 | 0.166 | 0.175 |
| 1.232 | 6.0 | 378 | 1.8637 | 0.1942 | 0.1115 | 0.1704 | 0.1808 |
| 1.1332 | 7.0 | 441 | 1.8797 | 0.194 | 0.1143 | 0.1725 | 0.1823 |
| 1.1014 | 8.0 | 504 | 1.8960 | 0.197 | 0.116 | 0.1733 | 0.1853 |
model.safetensors 558 MBtraining_args.bin 5.6 kBfacebook/bart-base