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:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.071 | 1.0 | 10 | 2.0532 | 0.2125 |
| 1.9763 | 2.0 | 20 | 1.9614 | 0.3312 |
| 1.8031 | 3.0 | 30 | 1.8326 | 0.4562 |
| 1.6168 | 4.0 | 40 | 1.7015 | 0.5125 |
| 1.4508 | 5.0 | 50 | 1.6065 | 0.5188 |
| 1.3037 | 6.0 | 60 | 1.5397 | 0.5375 |
| 1.1709 | 7.0 | 70 | 1.4836 | 0.55 |
| 1.0481 | 8.0 | 80 | 1.4248 | 0.5813 |
| 0.9441 | 9.0 | 90 | 1.3915 | 0.5625 |
| 0.8551 | 10.0 | 100 | 1.3586 | 0.6 |
| 0.7772 | 11.0 | 110 | 1.3315 | 0.6 |
| 0.7174 | 12.0 | 120 | 1.3057 | 0.6062 |
| 0.6721 | 13.0 | 130 | 1.2936 | 0.6188 |
| 0.642 | 14.0 | 140 | 1.2933 | 0.6 |
| 0.6252 | 15.0 | 150 | 1.2826 | 0.625 |
model.safetensors 343 MBtraining_args.bin 5.2 kBgoogle/vit-base-patch16-224-in21k