metadata
license: other
tags:
- generated_from_keras_callback
model-index:
- name: ChristianMDahl/segFormer-b3-vertical
results: []
ChristianMDahl/segFormer-b3-vertical
This model is a fine-tuned version of nvidia/mit-b3 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1153
- Validation Loss: 0.1376
- Epoch: 13
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': 'Adam', 'learning_rate': 6e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 0.1926 | 0.1873 | 0 |
| 0.1677 | 0.1612 | 1 |
| 0.1578 | 0.1562 | 2 |
| 0.1509 | 0.1521 | 3 |
| 0.1451 | 0.1480 | 4 |
| 0.1395 | 0.1458 | 5 |
| 0.1343 | 0.1431 | 6 |
| 0.1314 | 0.1433 | 7 |
| 0.1274 | 0.1395 | 8 |
| 0.1247 | 0.1377 | 9 |
| 0.1218 | 0.1361 | 10 |
| 0.1199 | 0.1374 | 11 |
| 0.1173 | 0.1350 | 12 |
| 0.1153 | 0.1376 | 13 |
Framework versions
- Transformers 4.28.1
- TensorFlow 2.10.1
- Datasets 2.12.0
- Tokenizers 0.13.0.dev0