<!-- 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-v2-sum-fine-tuned
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: 8.7918
- Validation Loss: 9.1352
- Epoch: 29
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 | Epoch |
|---|---|---|
| 14.5286 | 12.5993 | 0 |
| 13.7167 | 12.7206 | 1 |
| 13.7518 | 12.4721 | 2 |
| 13.5991 | 12.0654 | 3 |
| 13.0693 | 11.5237 | 4 |
| 12.8718 | 11.5755 | 5 |
| 12.6745 | 11.3361 | 6 |
| 12.4659 | 10.6694 | 7 |
| 12.2692 | 10.0483 | 8 |
| 12.2115 | 10.5089 | 9 |
| 11.9810 | 10.3895 | 10 |
| 11.6432 | 10.1090 | 11 |
| 11.6436 | 9.4868 | 12 |
| 11.3711 | 9.9035 | 13 |
| 11.1223 | 8.9180 | 14 |
| 10.9886 | 9.3682 | 15 |
| 10.8426 | 8.9964 | 16 |
| 10.5593 | 9.2168 | 17 |
| 10.5568 | 8.9877 | 18 |
| 10.1875 | 8.8072 | 19 |
| 10.1814 | 10.3268 | 20 |
| 10.0053 | 11.1192 | 21 |
| 9.6850 | 10.9950 | 22 |
| 9.6080 | 10.7909 | 23 |
| 9.4208 | 10.9226 | 24 |
| 9.3501 | 10.1040 | 25 |
| 9.2757 | 10.1148 | 26 |
| 9.1751 | 9.9607 | 27 |
| 8.9227 | 9.1899 | 28 |
| 8.7918 | 9.1352 | 29 |
Framework versions
- Transformers 4.30.2
- TensorFlow 2.11.0
- Datasets 2.13.1
- Tokenizers 0.12.1
