plant-seedlings-freeze-0-6-aug-3-no-lr-decay
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.4328
- Accuracy: 0.8772
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: 13
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.546 | 1.59 | 100 | 0.7861 | 0.7421 |
| 0.4435 | 3.17 | 200 | 0.6630 | 0.7785 |
| 0.4183 | 4.76 | 300 | 0.5526 | 0.8286 |
| 0.2947 | 6.35 | 400 | 0.4689 | 0.8625 |
| 0.0971 | 7.94 | 500 | 0.4795 | 0.8620 |
| 0.1414 | 9.52 | 600 | 0.4423 | 0.8708 |
| 0.1034 | 11.11 | 700 | 0.4327 | 0.8806 |
| 0.0293 | 12.7 | 800 | 0.4328 | 0.8772 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3