<!-- 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. -->
Eliac11/FitModel
This model is a fine-tuned version of Eliac11/tinkNLP on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.5899
- Validation Loss: 2.1619
- Epoch: 23
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': 0.005}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 2.7611 | 3.2917 | 0 |
| 2.5272 | 3.1344 | 1 |
| 2.3172 | 2.9982 | 2 |
| 2.1298 | 2.8936 | 3 |
| 1.9620 | 2.7805 | 4 |
| 1.8145 | 2.6929 | 5 |
| 1.6762 | 2.6139 | 6 |
| 1.5531 | 2.5450 | 7 |
| 1.4394 | 2.4895 | 8 |
| 1.3463 | 2.4272 | 9 |
| 1.2504 | 2.3718 | 10 |
| 1.1740 | 2.3381 | 11 |
| 1.0953 | 2.3067 | 12 |
| 1.0245 | 2.2730 | 13 |
| 0.9623 | 2.2482 | 14 |
| 0.9074 | 2.2176 | 15 |
| 0.8601 | 2.2021 | 16 |
| 0.8079 | 2.1901 | 17 |
| 0.7651 | 2.1776 | 18 |
| 0.7242 | 2.1688 | 19 |
| 0.6864 | 2.1613 | 20 |
| 0.6494 | 2.1500 | 21 |
| 0.6192 | 2.1510 | 22 |
| 0.5899 | 2.1619 | 23 |
Framework versions
- Transformers 4.33.1
- TensorFlow 2.12.0
- Datasets 2.14.5
- Tokenizers 0.13.3
