SaladSlayer00/new_model
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: 1.2935
- Validation Loss: 1.6986
- Validation Accuracy: 0.5619
- Epoch: 11
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': 5e-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 |
Validation Accuracy |
Epoch |
| 7.0613 |
4.8451 |
0.0134 |
0 |
| 4.6529 |
4.5201 |
0.0658 |
1 |
| 4.3215 |
4.1158 |
0.0992 |
2 |
| 3.8808 |
3.6981 |
0.1806 |
3 |
| 3.4497 |
3.2741 |
0.2553 |
4 |
| 3.0361 |
2.9681 |
0.3177 |
5 |
| 2.6734 |
2.6529 |
0.3690 |
6 |
| 2.3306 |
2.3803 |
0.4091 |
7 |
| 2.0284 |
2.1731 |
0.4738 |
8 |
| 1.7542 |
1.9839 |
0.4883 |
9 |
| 1.5084 |
1.8335 |
0.5284 |
10 |
| 1.2935 |
1.6986 |
0.5619 |
11 |
Framework versions
- Transformers 4.36.2
- TensorFlow 2.15.0
- Datasets 2.16.0
- Tokenizers 0.15.0
