<!-- 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-nlpfinalproject100-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: 3.3675
- Validation Loss: 3.0731
- Train Rouge1: 21.6320
- Train Rouge2: 4.1815
- Train Rougel: 16.7880
- Train Rougelsum: 16.8075
- Train Gen Len: 18.26
- Epoch: 4
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': 3e-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 |
---|---|---|---|---|---|---|---|
4.0261 | 3.4861 | 17.2949 | 2.5214 | 13.5817 | 13.5711 | 19.0 | 0 |
3.6457 | 3.2367 | 19.3042 | 3.2474 | 15.8225 | 15.8589 | 18.65 | 1 |
3.4972 | 3.1544 | 20.2614 | 3.5380 | 15.8853 | 15.8671 | 18.37 | 2 |
3.4228 | 3.1064 | 21.7547 | 4.0283 | 16.4961 | 16.4831 | 18.41 | 3 |
3.3675 | 3.0731 | 21.6320 | 4.1815 | 16.7880 | 16.8075 | 18.26 | 4 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.10.0
- Tokenizers 0.13.2