<!-- 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-nlpfinalproject8-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: 3.2182
- Validation Loss: 3.0587
- Train Rouge1: 23.0865
- Train Rouge2: 4.8003
- Train Rougel: 17.9960
- Train Rougelsum: 18.0946
- Train Gen Len: 18.55
- 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 |
|---|---|---|---|---|---|---|---|
| 3.7763 | 3.2470 | 21.4262 | 4.2720 | 16.5725 | 16.5534 | 18.43 | 0 |
| 3.5364 | 3.2217 | 21.1697 | 3.8502 | 16.3414 | 16.3954 | 18.37 | 1 |
| 3.4536 | 3.1145 | 19.5287 | 4.3369 | 15.5779 | 15.5442 | 18.19 | 2 |
| 3.3769 | 3.1012 | 22.5999 | 4.4527 | 17.0441 | 17.0541 | 18.77 | 3 |
| 3.4107 | 3.1015 | 22.5296 | 5.0335 | 17.5217 | 17.5162 | 18.44 | 4 |
| 3.3794 | 3.1174 | 22.2827 | 4.7022 | 17.4151 | 17.4512 | 18.55 | 5 |
| 3.3297 | 3.0885 | 22.4875 | 4.9262 | 17.5070 | 17.5261 | 18.42 | 6 |
| 3.2816 | 3.0969 | 23.0410 | 4.7992 | 17.4537 | 17.4863 | 18.58 | 7 |
| 3.2594 | 3.0720 | 22.4212 | 5.1127 | 17.6334 | 17.6794 | 18.53 | 8 |
| 3.2182 | 3.0587 | 23.0865 | 4.8003 | 17.9960 | 18.0946 | 18.55 | 9 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.9.0
- Tokenizers 0.13.2
