This model is a fine-tuned version of facebook/bart-base on the snli 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 | Accuracy |
|---|---|---|---|---|
| 0.3697 | 1.0 | 2146 | 0.2888 | 0.8993 |
| 0.3223 | 2.0 | 4292 | 0.2650 | 0.9075 |
| 0.2916 | 3.0 | 6438 | 0.2611 | 0.9083 |
model.safetensors 560 MBtraining_args.bin 4.9 kBfacebook/bart-base