<!-- 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. -->
Evangeliaa/t5-small-finetuned-xsum_3epoch_batch8
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: 2.5788
- Validation Loss: 2.3359
- Train Rouge1: 31.0775
- Train Rouge2: 10.1573
- Train Rougel: 24.2688
- Train Rougelsum: 24.2581
- Train Gen Len: 18.9
- Epoch: 1
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 |
|---|---|---|---|---|---|---|---|
| 2.7182 | 2.3968 | 30.5611 | 10.2967 | 24.3620 | 24.3750 | 18.845 | 0 |
| 2.5788 | 2.3359 | 31.0775 | 10.1573 | 24.2688 | 24.2581 | 18.9 | 1 |
Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
