<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
bart-large-cnn-sum-fine-tuned
This model is a fine-tuned version of facebook/bart-large-cnn on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.9008
- Validation Loss: 1.3671
- Train Lr: 7.3575857e-06
- Epoch: 19
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 7.3575857e-06, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Lr | Epoch |
|---|---|---|---|
| 1.9649 | 1.6269 | 2e-05 | 0 |
| 1.5294 | 1.4905 | 2e-05 | 1 |
| 1.4205 | 1.4433 | 2e-05 | 2 |
| 1.3544 | 1.4030 | 2e-05 | 3 |
| 1.3136 | 1.4009 | 2e-05 | 4 |
| 1.2611 | 1.3879 | 2e-05 | 5 |
| 1.2306 | 1.3604 | 2e-05 | 6 |
| 1.1927 | 1.3526 | 2e-05 | 7 |
| 1.1622 | 1.3445 | 2e-05 | 8 |
| 1.1242 | 1.3454 | 2e-05 | 9 |
| 1.0950 | 1.3505 | 1.8096747e-05 | 10 |
| 1.0654 | 1.3528 | 1.6374614e-05 | 11 |
| 1.0412 | 1.3494 | 1.4816363e-05 | 12 |
| 1.0166 | 1.3356 | 1.34063985e-05 | 13 |
| 0.9902 | 1.3303 | 1.213061e-05 | 14 |
| 0.9721 | 1.3331 | 1.09762295e-05 | 15 |
| 0.9436 | 1.3353 | 9.931703e-06 | 16 |
| 0.9317 | 1.3506 | 8.986576e-06 | 17 |
| 0.9211 | 1.3422 | 8.13139e-06 | 18 |
| 0.9008 | 1.3671 | 7.3575857e-06 | 19 |
Framework versions
- Transformers 4.30.2
- TensorFlow 2.13.0
- Datasets 2.13.1
- Tokenizers 0.13.3
