<!-- 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. -->
leonardo-simao/t5-small-finetuned-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: 2.3942
- Validation Loss: 2.2286
- Train Rouge1: 33.3833
- Train Rouge2: 10.8793
- Train Rougel: 26.0564
- Train Rougelsum: 26.0512
- Train Gen Len: 27.1770
- 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': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
---|---|---|---|---|---|---|---|
2.7789 | 2.4538 | 30.3134 | 8.5372 | 23.4244 | 23.4213 | 26.4852 | 0 |
2.6453 | 2.3911 | 31.1672 | 9.2021 | 24.1447 | 24.1417 | 26.7193 | 1 |
2.5853 | 2.3522 | 31.6995 | 9.5664 | 24.5990 | 24.5978 | 26.7451 | 2 |
2.5415 | 2.3241 | 32.1058 | 9.8659 | 24.9344 | 24.9268 | 27.0580 | 3 |
2.5079 | 2.3014 | 32.2524 | 9.9560 | 25.0746 | 25.0706 | 26.9969 | 4 |
2.4789 | 2.2830 | 32.4974 | 10.1997 | 25.2473 | 25.2441 | 27.0349 | 5 |
2.4532 | 2.2672 | 32.7655 | 10.3607 | 25.4207 | 25.4145 | 27.0304 | 6 |
2.4324 | 2.2546 | 33.0104 | 10.6010 | 25.6580 | 25.6574 | 27.0998 | 7 |
2.4126 | 2.2416 | 33.3930 | 10.8337 | 26.0110 | 26.0049 | 27.1842 | 8 |
2.3942 | 2.2286 | 33.3833 | 10.8793 | 26.0564 | 26.0512 | 27.1770 | 9 |
Framework versions
- Transformers 4.27.4
- TensorFlow 2.11.0
- Datasets 2.11.0
- Tokenizers 0.13.3