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: 1.5284
- Accuracy: 0.5563
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 9
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 40 | 1.4223 | 0.525 |
| No log | 2.0 | 80 | 1.5923 | 0.4938 |
| No log | 3.0 | 120 | 1.4860 | 0.5563 |
| No log | 4.0 | 160 | 1.4983 | 0.5625 |
| No log | 5.0 | 200 | 1.5151 | 0.5938 |
| No log | 6.0 | 240 | 1.6818 | 0.5062 |
| No log | 7.0 | 280 | 1.6757 | 0.5125 |
| No log | 8.0 | 320 | 1.4647 | 0.5875 |
| No log | 9.0 | 360 | 1.4922 | 0.5875 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2