fashion-images-perspectives-vit-large-patch16-384-v2
This model is a fine-tuned version of google/vit-large-patch16-384 on the /workspace/fashion-images-perspectives-v4 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1395
- Accuracy: 0.9655
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1747 | 1.0 | 5531 | 0.2032 | 0.9456 |
| 0.0836 | 2.0 | 11062 | 0.1395 | 0.9655 |
| 0.0479 | 3.0 | 16593 | 0.1564 | 0.9675 |
| 0.0156 | 4.0 | 22124 | 0.1745 | 0.9700 |
| 0.0065 | 5.0 | 27655 | 0.1948 | 0.9690 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1