plant-seedlings-model-beit
This model is a fine-tuned version of microsoft/beit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3466
- Accuracy: 0.8969
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 12
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4966 | 0.8 | 100 | 1.2583 | 0.5909 |
| 0.8239 | 1.6 | 200 | 0.9266 | 0.6979 |
| 0.7583 | 2.4 | 300 | 0.6527 | 0.7834 |
| 0.5222 | 3.2 | 400 | 0.5186 | 0.8035 |
| 0.5233 | 4.0 | 500 | 0.5527 | 0.8060 |
| 0.516 | 4.8 | 600 | 0.5558 | 0.8148 |
| 0.4848 | 5.6 | 700 | 0.4780 | 0.8409 |
| 0.1949 | 6.4 | 800 | 0.5876 | 0.8320 |
| 0.2581 | 7.2 | 900 | 0.4364 | 0.8482 |
| 0.2748 | 8.0 | 1000 | 0.3565 | 0.8777 |
| 0.2973 | 8.8 | 1100 | 0.4623 | 0.8615 |
| 0.1655 | 9.6 | 1200 | 0.3700 | 0.8875 |
| 0.1744 | 10.4 | 1300 | 0.3751 | 0.8905 |
| 0.3044 | 11.2 | 1400 | 0.3799 | 0.8919 |
| 0.0981 | 12.0 | 1500 | 0.3466 | 0.8969 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3