<!-- 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. -->
LucaReggiani/t5-small-nlpfinalproject-xsum
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 3.2811
- Validation Loss: 3.0854
- Train Rouge1: 22.6308
- Train Rouge2: 4.9619
- Train Rougel: 17.5478
- Train Rougelsum: 17.5354
- Train Gen Len: 18.66
- Epoch: 4
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': 1.9e-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 Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
|---|---|---|---|---|---|---|---|
| 3.8680 | 3.3244 | 18.4638 | 2.7676 | 14.7005 | 14.7614 | 18.64 | 0 |
| 3.5175 | 3.1977 | 20.3854 | 3.7061 | 15.7454 | 15.6946 | 18.25 | 1 |
| 3.4145 | 3.1415 | 22.1411 | 4.2107 | 16.9111 | 16.8849 | 18.54 | 2 |
| 3.3473 | 3.1096 | 21.8021 | 4.4683 | 16.6056 | 16.5965 | 18.3 | 3 |
| 3.2811 | 3.0854 | 22.6308 | 4.9619 | 17.5478 | 17.5354 | 18.66 | 4 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.9.0
- Tokenizers 0.13.2
