Expert2-leaf-disease-convnextv2-base-1k-224-1_2_3
This model is a fine-tuned version of facebook/convnextv2-base-1k-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1892
- Accuracy: 0.9391
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: 5e-05
- train_batch_size: 300
- eval_batch_size: 300
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 1200
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.5107 | 0.96 | 13 | 1.0756 | 0.7422 |
| 1.0022 | 2.0 | 27 | 0.5781 | 0.7603 |
| 0.4503 | 2.96 | 40 | 0.3902 | 0.8697 |
| 0.3704 | 4.0 | 54 | 0.3101 | 0.9058 |
| 0.2996 | 4.96 | 67 | 0.2573 | 0.9165 |
| 0.2405 | 6.0 | 81 | 0.2647 | 0.9075 |
| 0.2268 | 6.96 | 94 | 0.2259 | 0.9233 |
| 0.2036 | 8.0 | 108 | 0.2126 | 0.9329 |
| 0.1957 | 8.96 | 121 | 0.2149 | 0.9329 |
| 0.1885 | 10.0 | 135 | 0.1974 | 0.9385 |
| 0.1866 | 10.96 | 148 | 0.1983 | 0.9318 |
| 0.1771 | 12.0 | 162 | 0.2066 | 0.9363 |
| 0.1752 | 12.96 | 175 | 0.1975 | 0.9357 |
| 0.1744 | 14.0 | 189 | 0.1893 | 0.9380 |
| 0.1636 | 14.96 | 202 | 0.1889 | 0.9391 |
| 0.1636 | 15.41 | 208 | 0.1892 | 0.9391 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.1