mruby/reef_classifier
This model is a fine-tuned version of microsoft/resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.2128
- Validation Loss: 0.1995
- Train Accuracy: 0.9365
- Epoch: 4
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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 18885, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|---|---|---|---|
| 0.6048 | 0.5326 | 0.8392 | 0 |
| 0.4152 | 0.3764 | 0.8878 | 1 |
| 0.2911 | 0.2649 | 0.9259 | 2 |
| 0.2399 | 0.2350 | 0.9217 | 3 |
| 0.2128 | 0.1995 | 0.9365 | 4 |
Framework versions
- Transformers 4.27.4
- TensorFlow 2.8.0
- Datasets 2.12.0
- Tokenizers 0.13.3