<!-- 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-nlpfinalproject3-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: 2.9916
- Validation Loss: 2.9840
- Train Rouge1: 22.3282
- Train Rouge2: 4.7253
- Train Rougel: 17.9286
- Train Rougelsum: 17.9126
- Train Gen Len: 18.54
- 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': 5e-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 |
|---|---|---|---|---|---|---|---|
| 3.7453 | 3.2008 | 19.6619 | 3.4413 | 15.6174 | 15.6444 | 18.23 | 0 |
| 3.3973 | 3.1041 | 21.1867 | 4.1818 | 16.5584 | 16.4568 | 18.59 | 1 |
| 3.2886 | 3.0600 | 21.8364 | 4.3416 | 16.6696 | 16.6382 | 18.5 | 2 |
| 3.2216 | 3.0323 | 23.5970 | 5.3080 | 18.4737 | 18.3755 | 18.49 | 3 |
| 3.1462 | 3.0174 | 23.0720 | 5.3486 | 18.5011 | 18.4635 | 18.62 | 4 |
| 3.0860 | 3.0017 | 22.3949 | 4.7088 | 17.7759 | 17.7328 | 18.51 | 5 |
| 3.0436 | 2.9890 | 22.8096 | 4.9911 | 18.1200 | 18.0347 | 18.47 | 6 |
| 2.9916 | 2.9840 | 22.3282 | 4.7253 | 17.9286 | 17.9126 | 18.54 | 7 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.9.0
- Tokenizers 0.13.2
