<!-- 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-nlpfinalproject6-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: 3.2353
- Validation Loss: 3.0599
- Train Rouge1: 22.5358
- Train Rouge2: 5.0856
- Train Rougel: 18.0719
- Train Rougelsum: 17.9968
- Train Gen Len: 18.63
- 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': 'SGD', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 0.01, 'momentum': 0.9, 'nesterov': False}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
|---|---|---|---|---|---|---|---|
| 3.7556 | 3.2663 | 19.3840 | 2.9375 | 14.9798 | 14.9281 | 18.39 | 0 |
| 3.6968 | 3.2062 | 21.0908 | 3.6469 | 16.6707 | 16.6671 | 18.41 | 1 |
| 3.5174 | 3.1468 | 21.6752 | 4.1271 | 16.6825 | 16.6673 | 18.43 | 2 |
| 3.4244 | 3.1258 | 21.6981 | 3.7590 | 16.7374 | 16.7752 | 18.48 | 3 |
| 3.3662 | 3.1039 | 22.3971 | 5.0108 | 17.1479 | 17.1045 | 18.5 | 4 |
| 3.3238 | 3.0882 | 21.3558 | 4.5247 | 17.2331 | 17.2621 | 18.57 | 5 |
| 3.3024 | 3.1200 | 21.5447 | 4.2584 | 16.5791 | 16.5393 | 18.72 | 6 |
| 3.2894 | 3.0992 | 22.5846 | 4.4822 | 17.5903 | 17.6008 | 18.75 | 7 |
| 3.2499 | 3.0860 | 22.5308 | 4.3384 | 17.4898 | 17.5104 | 18.72 | 8 |
| 3.2353 | 3.0599 | 22.5358 | 5.0856 | 18.0719 | 17.9968 | 18.63 | 9 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.9.0
- Tokenizers 0.13.2
