<!-- 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-12nlpfinalproject15-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: 3.5850
- Validation Loss: 3.2639
- Train Rouge1: 18.8102
- Train Rouge2: 2.7207
- Train Rougel: 15.0053
- Train Rougelsum: 15.0497
- Train Gen Len: 18.64
- Epoch: 10
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-06, '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 |
---|---|---|---|---|---|---|---|
4.2808 | 4.0689 | 16.0766 | 2.2326 | 13.0430 | 13.1934 | 18.94 | 0 |
4.1592 | 3.9169 | 16.3671 | 2.1832 | 13.1457 | 13.1612 | 18.94 | 1 |
4.0568 | 3.7837 | 16.9390 | 2.4651 | 13.4669 | 13.3983 | 18.94 | 2 |
3.9491 | 3.6722 | 17.5351 | 2.5526 | 13.6178 | 13.5941 | 19.0 | 3 |
3.8595 | 3.5787 | 17.1791 | 2.2937 | 13.4932 | 13.6093 | 18.93 | 4 |
3.7966 | 3.4995 | 17.3785 | 2.5408 | 13.3783 | 13.5736 | 18.98 | 5 |
3.7362 | 3.4312 | 18.1473 | 2.7662 | 14.0010 | 14.1828 | 18.99 | 6 |
3.6869 | 3.3778 | 17.7556 | 2.6157 | 13.9773 | 13.9192 | 18.8 | 7 |
3.6454 | 3.3323 | 18.1910 | 2.3216 | 14.3097 | 14.3738 | 18.76 | 8 |
3.5987 | 3.2942 | 18.3254 | 2.5627 | 14.6577 | 14.7984 | 18.73 | 9 |
3.5850 | 3.2639 | 18.8102 | 2.7207 | 15.0053 | 15.0497 | 18.64 | 10 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.10.0
- Tokenizers 0.13.2