<!-- 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-nlpfinalproject11-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: 3.1319
- Validation Loss: 3.0594
- Train Rouge1: 22.8208
- Train Rouge2: 5.2987
- Train Rougel: 18.5401
- Train Rougelsum: 18.5836
- Train Gen Len: 18.56
- 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': 'AdamWeightDecay', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.001}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
|---|---|---|---|---|---|---|---|
| 3.9188 | 3.3668 | 17.8424 | 2.8848 | 14.3980 | 14.5050 | 18.68 | 0 |
| 3.5063 | 3.2153 | 21.0986 | 4.0935 | 16.5510 | 16.5097 | 18.47 | 1 |
| 3.3880 | 3.1603 | 20.8573 | 4.1833 | 16.0084 | 15.9659 | 18.35 | 2 |
| 3.3316 | 3.1250 | 20.9563 | 3.7170 | 15.9813 | 16.0007 | 18.5 | 3 |
| 3.2669 | 3.1022 | 21.2349 | 4.1598 | 16.4493 | 16.4961 | 18.7 | 4 |
| 3.2154 | 3.0849 | 22.4905 | 4.9861 | 17.5689 | 17.5992 | 18.62 | 5 |
| 3.1727 | 3.0708 | 23.4926 | 5.5226 | 18.4502 | 18.4874 | 18.58 | 6 |
| 3.1319 | 3.0594 | 22.8208 | 5.2987 | 18.5401 | 18.5836 | 18.56 | 7 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.10.0
- Tokenizers 0.13.2
