<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
plant-seedlings-model-freeze-2
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: 0.1729
- Accuracy: 0.9720
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0346 | 0.25 | 100 | 0.2971 | 0.9573 |
| 0.158 | 0.51 | 200 | 0.3343 | 0.9452 |
| 0.0218 | 0.76 | 300 | 0.5939 | 0.9051 |
| 0.0525 | 1.02 | 400 | 0.3253 | 0.9446 |
| 0.0177 | 1.27 | 500 | 0.3484 | 0.9465 |
| 0.034 | 1.53 | 600 | 0.1919 | 0.9637 |
| 0.001 | 1.78 | 700 | 0.1797 | 0.9643 |
| 0.0093 | 2.04 | 800 | 0.1854 | 0.9682 |
| 0.0598 | 2.29 | 900 | 0.2082 | 0.9624 |
| 0.0008 | 2.54 | 1000 | 0.2089 | 0.9567 |
| 0.0501 | 2.8 | 1100 | 0.2640 | 0.9567 |
| 0.0015 | 3.05 | 1200 | 0.1899 | 0.9650 |
| 0.0431 | 3.31 | 1300 | 0.1866 | 0.9669 |
| 0.007 | 3.56 | 1400 | 0.1962 | 0.9707 |
| 0.005 | 3.82 | 1500 | 0.2161 | 0.9624 |
| 0.0009 | 4.07 | 1600 | 0.1618 | 0.9656 |
| 0.0011 | 4.33 | 1700 | 0.1340 | 0.9662 |
| 0.0008 | 4.58 | 1800 | 0.1606 | 0.9688 |
| 0.0221 | 4.83 | 1900 | 0.1498 | 0.9707 |
| 0.0085 | 5.09 | 2000 | 0.2956 | 0.9490 |
| 0.0018 | 5.34 | 2100 | 0.1322 | 0.9745 |
| 0.0002 | 5.6 | 2200 | 0.2376 | 0.9592 |
| 0.0285 | 5.85 | 2300 | 0.1476 | 0.9707 |
| 0.0001 | 6.11 | 2400 | 0.1968 | 0.9618 |
| 0.0 | 6.36 | 2500 | 0.1780 | 0.9656 |
| 0.0001 | 6.62 | 2600 | 0.1731 | 0.9682 |
| 0.0 | 6.87 | 2700 | 0.1729 | 0.9694 |
| 0.0 | 7.12 | 2800 | 0.1684 | 0.9713 |
| 0.0 | 7.38 | 2900 | 0.1692 | 0.9713 |
| 0.0 | 7.63 | 3000 | 0.1699 | 0.9713 |
| 0.0 | 7.89 | 3100 | 0.1708 | 0.9713 |
| 0.0 | 8.14 | 3200 | 0.1708 | 0.9720 |
| 0.0 | 8.4 | 3300 | 0.1712 | 0.9720 |
| 0.0 | 8.65 | 3400 | 0.1718 | 0.9720 |
| 0.0 | 8.91 | 3500 | 0.1721 | 0.9720 |
| 0.0 | 9.16 | 3600 | 0.1725 | 0.9720 |
| 0.0 | 9.41 | 3700 | 0.1727 | 0.9720 |
| 0.0 | 9.67 | 3800 | 0.1728 | 0.9720 |
| 0.0 | 9.92 | 3900 | 0.1729 | 0.9720 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
