<!-- 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. -->
mbart-finetune-ar-xlsum-fine-tuned
This model is a fine-tuned version of eslamxm/mbart-finetune-ar-xlsum on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 2.8386
- Validation Loss: 6.2675
- Train Lr: 2e-05
- Epoch: 9
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': 2e-05, '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 |
|---|---|---|---|
| 7.0615 | 6.1894 | 2e-05 | 0 |
| 5.7395 | 5.8670 | 2e-05 | 1 |
| 5.2896 | 5.7020 | 2e-05 | 2 |
| 4.9490 | 5.6279 | 2e-05 | 3 |
| 4.6278 | 5.6189 | 2e-05 | 4 |
| 4.3330 | 5.6275 | 2e-05 | 5 |
| 3.9812 | 5.7291 | 2e-05 | 6 |
| 3.6283 | 5.8438 | 2e-05 | 7 |
| 3.2183 | 6.0378 | 2e-05 | 8 |
| 2.8386 | 6.2675 | 2e-05 | 9 |
Framework versions
- Transformers 4.30.2
- TensorFlow 2.13.0
- Datasets 2.13.1
- Tokenizers 0.13.3
