<!-- 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. -->
vit-base-beans-demo-v5
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the bact dataset. It achieves the following results on the evaluation set:
- Loss: 0.0612
- Accuracy: 0.9874
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: 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0007 | 0.17 | 100 | 0.1211 | 0.9748 |
| 0.0005 | 0.34 | 200 | 0.1027 | 0.9786 |
| 0.0195 | 0.5 | 300 | 0.0869 | 0.9836 |
| 0.0025 | 0.67 | 400 | 0.0823 | 0.9845 |
| 0.0154 | 0.84 | 500 | 0.0888 | 0.9828 |
| 0.0004 | 1.01 | 600 | 0.0781 | 0.9853 |
| 0.0004 | 1.17 | 700 | 0.0931 | 0.9832 |
| 0.0004 | 1.34 | 800 | 0.0995 | 0.9811 |
| 0.0004 | 1.51 | 900 | 0.0925 | 0.9832 |
| 0.0003 | 1.68 | 1000 | 0.0857 | 0.9836 |
| 0.0364 | 1.85 | 1100 | 0.0788 | 0.9845 |
| 0.0003 | 2.01 | 1200 | 0.0775 | 0.9840 |
| 0.0003 | 2.18 | 1300 | 0.0718 | 0.9857 |
| 0.0003 | 2.35 | 1400 | 0.0804 | 0.9849 |
| 0.0003 | 2.52 | 1500 | 0.0751 | 0.9836 |
| 0.0003 | 2.68 | 1600 | 0.0659 | 0.9870 |
| 0.0002 | 2.85 | 1700 | 0.0612 | 0.9874 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
