image_classification
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.7520
- Accuracy: 0.2875
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 40 | 2.0583 | 0.1688 |
| No log | 2.0 | 80 | 2.0009 | 0.2562 |
| No log | 3.0 | 120 | 1.9418 | 0.2625 |
| No log | 4.0 | 160 | 1.8934 | 0.275 |
| No log | 5.0 | 200 | 1.8221 | 0.2812 |
| No log | 6.0 | 240 | 1.7694 | 0.3 |
| No log | 7.0 | 280 | 1.7509 | 0.3063 |
| No log | 8.0 | 320 | 1.7311 | 0.2562 |
| No log | 9.0 | 360 | 1.7143 | 0.3 |
| No log | 10.0 | 400 | 1.7058 | 0.3 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3