<!-- 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. -->
gogzy/t5-base-finetuned_renre_2021_40
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 5.4875
- Validation Loss: 8.0355
- Train Rouge1: 7.0588
- Train Rouge2: 0.0
- Train Rougel: 4.7059
- Train Rougelsum: 4.7059
- Train Gen Len: 19.0
- 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': 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 |
|---|---|---|---|---|---|---|---|
| 5.2501 | 9.8474 | 19.5652 | 11.1111 | 13.0435 | 19.5652 | 19.0 | 0 |
| 7.5344 | 9.4134 | 7.0588 | 0.0 | 4.7059 | 4.7059 | 19.0 | 1 |
| 5.0059 | 8.9935 | 7.0588 | 0.0 | 4.7059 | 4.7059 | 19.0 | 2 |
| 5.3830 | 8.5525 | 7.0588 | 0.0 | 4.7059 | 4.7059 | 19.0 | 3 |
| 5.4875 | 8.0355 | 7.0588 | 0.0 | 4.7059 | 4.7059 | 19.0 | 4 |
Framework versions
- Transformers 4.24.0
- TensorFlow 2.9.2
- Datasets 2.6.1
- Tokenizers 0.13.2
