metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base-beans-demo-v5
results: []
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: 0.0498
- Accuracy: 0.9882
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1764 | 0.17 | 100 | 0.2424 | 0.9345 |
| 0.2401 | 0.34 | 200 | 0.2909 | 0.9160 |
| 0.1986 | 0.5 | 300 | 0.2258 | 0.9358 |
| 0.1579 | 0.67 | 400 | 0.2699 | 0.9240 |
| 0.21 | 0.84 | 500 | 0.1416 | 0.9635 |
| 0.0873 | 1.01 | 600 | 0.1724 | 0.9467 |
| 0.1594 | 1.17 | 700 | 0.2439 | 0.9320 |
| 0.0824 | 1.34 | 800 | 0.1039 | 0.9702 |
| 0.0888 | 1.51 | 900 | 0.1496 | 0.9547 |
| 0.1058 | 1.68 | 1000 | 0.1100 | 0.9748 |
| 0.077 | 1.85 | 1100 | 0.0784 | 0.9757 |
| 0.0486 | 2.01 | 1200 | 0.0997 | 0.9710 |
| 0.0087 | 2.18 | 1300 | 0.0704 | 0.9811 |
| 0.0382 | 2.35 | 1400 | 0.0910 | 0.9761 |
| 0.046 | 2.52 | 1500 | 0.0588 | 0.9840 |
| 0.0163 | 2.68 | 1600 | 0.0609 | 0.9836 |
| 0.0876 | 2.85 | 1700 | 0.0689 | 0.9811 |
| 0.0072 | 3.02 | 1800 | 0.0632 | 0.9861 |
| 0.0022 | 3.19 | 1900 | 0.0670 | 0.9845 |
| 0.0018 | 3.36 | 2000 | 0.0705 | 0.9845 |
| 0.0023 | 3.52 | 2100 | 0.0588 | 0.9861 |
| 0.0017 | 3.69 | 2200 | 0.0490 | 0.9882 |
| 0.0248 | 3.86 | 2300 | 0.0498 | 0.9882 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3