<!-- 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-nlpfinalproject2-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: 3.1399
- Validation Loss: 3.0183
- Train Rouge1: 23.2180
- Train Rouge2: 5.1740
- Train Rougel: 18.3975
- Train Rougelsum: 18.4246
- Train Gen Len: 18.5
- Epoch: 7
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': 'Adam', '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.98, 'epsilon': 1e-06, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
|---|---|---|---|---|---|---|---|
| 3.8670 | 3.3126 | 18.0994 | 2.9443 | 14.8574 | 14.8089 | 18.69 | 0 |
| 3.5043 | 3.1732 | 20.2677 | 3.9191 | 15.8137 | 15.8748 | 18.53 | 1 |
| 3.4010 | 3.1149 | 21.9985 | 4.4897 | 16.7720 | 16.8119 | 18.36 | 2 |
| 3.3235 | 3.0830 | 20.6948 | 3.9055 | 15.9707 | 15.9961 | 18.49 | 3 |
| 3.2700 | 3.0611 | 21.2726 | 3.8497 | 16.5193 | 16.5449 | 18.64 | 4 |
| 3.2309 | 3.0456 | 22.2643 | 4.5285 | 17.6124 | 17.6095 | 18.53 | 5 |
| 3.1842 | 3.0302 | 22.3951 | 4.7814 | 18.0792 | 18.0771 | 18.4 | 6 |
| 3.1399 | 3.0183 | 23.2180 | 5.1740 | 18.3975 | 18.4246 | 18.5 | 7 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.9.0
- Tokenizers 0.13.2
