exp_result1_resnet
This model is a fine-tuned version of microsoft/resnet-50 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6451
- Accuracy: 0.8670
- Precision: 0.8884
- Recall: 0.8670
- F1: 0.8765
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:
- learning_rate: 0.0001
- train_batch_size: 24
- eval_batch_size: 4
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.2343 | 1.0 | 759 | 0.4630 | 0.8271 | 0.8560 | 0.8271 | 0.8405 |
| 0.0895 | 2.0 | 1518 | 0.5436 | 0.8557 | 0.8589 | 0.8557 | 0.8573 |
| 0.0576 | 3.0 | 2277 | 0.6000 | 0.8709 | 0.8675 | 0.8709 | 0.8692 |
| 0.0442 | 4.0 | 3036 | 0.5490 | 0.8676 | 0.8808 | 0.8676 | 0.8738 |
| 0.0353 | 5.0 | 3795 | 0.6611 | 0.8612 | 0.8758 | 0.8612 | 0.8680 |
| 0.0234 | 6.0 | 4554 | 0.6407 | 0.8556 | 0.8932 | 0.8556 | 0.8710 |
| 0.0232 | 7.0 | 5313 | 0.6700 | 0.8738 | 0.8735 | 0.8738 | 0.8736 |
| 0.0206 | 8.0 | 6072 | 0.6441 | 0.8717 | 0.8925 | 0.8717 | 0.8808 |
| 0.0197 | 9.0 | 6831 | 0.7248 | 0.8517 | 0.8927 | 0.8517 | 0.8684 |
| 0.0161 | 10.0 | 7590 | 0.6451 | 0.8670 | 0.8884 | 0.8670 | 0.8765 |
Framework versions
- Transformers 4.53.0.dev0
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1