This model is a fine-tuned version of google/vit-base-patch16-224 on the pcuenq/oxford-pets dataset. It achieves the following results on the evaluation set:
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 93 | 0.6027 | 0.8958 |
| 1.5772 | 2.0 | 186 | 0.3632 | 0.9161 |
| 0.3807 | 3.0 | 279 | 0.3124 | 0.9202 |
| 0.2645 | 4.0 | 372 | 0.2945 | 0.9242 |
| 0.2288 | 5.0 | 465 | 0.2890 | 0.9242 |
Model used: openai/clip-vit-large-patch14
Oxford-Pet Dataset
model.safetensors 343 MBtraining_args.bin 5.4 kBgoogle/vit-base-patch16-224