resnet-50_rice-disease-02_111724
This model is a fine-tuned version of microsoft/resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6774
- Accuracy: 0.8044
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: 0.0003
- train_batch_size: 64
- eval_batch_size: 8
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1567 | 1.0 | 212 | 1.9092 | 0.5476 |
| 1.6124 | 2.0 | 424 | 1.3708 | 0.6773 |
| 1.2221 | 3.0 | 636 | 1.1384 | 0.7186 |
| 1.0356 | 4.0 | 848 | 0.9888 | 0.7339 |
| 0.9297 | 5.0 | 1060 | 0.9108 | 0.7425 |
| 0.8599 | 6.0 | 1272 | 0.8448 | 0.7538 |
| 0.8082 | 7.0 | 1484 | 0.8129 | 0.7645 |
| 0.7648 | 8.0 | 1696 | 0.7604 | 0.7864 |
| 0.7368 | 9.0 | 1908 | 0.7597 | 0.7738 |
| 0.7092 | 10.0 | 2120 | 0.7230 | 0.7884 |
| 0.6928 | 11.0 | 2332 | 0.7014 | 0.7884 |
| 0.6797 | 12.0 | 2544 | 0.6970 | 0.7917 |
| 0.6686 | 13.0 | 2756 | 0.6933 | 0.8017 |
| 0.6642 | 14.0 | 2968 | 0.6813 | 0.8024 |
| 0.6601 | 15.0 | 3180 | 0.6774 | 0.8044 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3