metadata
license: other
tags:
- generated_from_keras_callback
model-index:
- name: ChristianMDahl/segFormer_ver1
results: []
ChristianMDahl/segFormer_ver1
This model is a fine-tuned version of nvidia/mit-b0 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1369
- Validation Loss: 0.1507
- Epoch: 19
Model description
Model for vertical lines
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 |
|---|---|---|
| 0.2161 | 0.1837 | 0 |
| 0.1855 | 0.1748 | 1 |
| 0.1767 | 0.1696 | 2 |
| 0.1707 | 0.1651 | 3 |
| 0.1665 | 0.1636 | 4 |
| 0.1624 | 0.1613 | 5 |
| 0.1593 | 0.1624 | 6 |
| 0.1568 | 0.1586 | 7 |
| 0.1539 | 0.1549 | 8 |
| 0.1515 | 0.1572 | 9 |
| 0.1496 | 0.1543 | 10 |
| 0.1483 | 0.1587 | 11 |
| 0.1462 | 0.1573 | 12 |
| 0.1447 | 0.1551 | 13 |
| 0.1433 | 0.1535 | 14 |
| 0.1420 | 0.1535 | 15 |
| 0.1402 | 0.1498 | 16 |
| 0.1395 | 0.1533 | 17 |
| 0.1383 | 0.1538 | 18 |
| 0.1369 | 0.1507 | 19 |
Framework versions
- Transformers 4.28.1
- TensorFlow 2.10.1
- Datasets 2.12.0
- Tokenizers 0.13.0.dev0