<!-- 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-nlpfinalproject99-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: 3.0379
- Validation Loss: 2.9903
- Train Rouge1: 23.6196
- Train Rouge2: 5.8829
- Train Rougel: 18.9509
- Train Rougelsum: 19.0041
- Train Gen Len: 18.6
- 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': 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 |
---|---|---|---|---|---|---|---|
3.8865 | 3.3185 | 17.9926 | 2.6334 | 14.3776 | 14.4109 | 18.74 | 0 |
3.5092 | 3.1756 | 19.9492 | 3.6172 | 15.6914 | 15.7191 | 18.31 | 1 |
3.4012 | 3.1160 | 21.2372 | 4.0016 | 16.5756 | 16.5655 | 18.45 | 2 |
3.3268 | 3.0809 | 21.5751 | 4.0776 | 16.5050 | 16.5345 | 18.58 | 3 |
3.2660 | 3.0550 | 21.7071 | 4.1832 | 16.8604 | 16.8708 | 18.64 | 4 |
3.2125 | 3.0377 | 21.9791 | 4.8202 | 17.3234 | 17.3660 | 18.46 | 5 |
3.1829 | 3.0218 | 22.4277 | 5.0402 | 17.7633 | 17.8109 | 18.64 | 6 |
3.1358 | 3.0142 | 23.5653 | 5.3418 | 18.8989 | 18.9198 | 18.64 | 7 |
3.1011 | 3.0042 | 23.1459 | 5.0797 | 18.3238 | 18.3087 | 18.62 | 8 |
3.0681 | 2.9995 | 22.9719 | 4.9597 | 17.9675 | 17.9490 | 18.57 | 9 |
3.0379 | 2.9903 | 23.6196 | 5.8829 | 18.9509 | 19.0041 | 18.6 | 10 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.10.0
- Tokenizers 0.13.2