<!-- 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. -->
mt5-small-summarization
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 2.9665
- Validation Loss: 2.4241
- Train Rouge1: 23.5645
- Train Rouge2: 8.2413
- Train Rougel: 19.7515
- Train Rougelsum: 19.9204
- Train Gen Len: 19.0
- Epoch: 2
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 |
|---|---|---|---|---|---|---|---|
| 4.7187 | 2.6627 | 19.5921 | 5.9723 | 16.6769 | 16.8456 | 18.955 | 0 |
| 3.1929 | 2.4941 | 21.2334 | 6.9784 | 18.2158 | 18.2062 | 18.99 | 1 |
| 2.9665 | 2.4241 | 23.5645 | 8.2413 | 19.7515 | 19.9204 | 19.0 | 2 |
Framework versions
- Transformers 4.19.2
- TensorFlow 2.8.2
- Datasets 2.2.2
- Tokenizers 0.12.1
