vit-base-patch16-224-Diastarallclasses
This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0345
- Accuracy: 0.9811
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.2142 | 1.0 | 459 | 0.0876 | 0.9643 |
0.1826 | 2.0 | 918 | 0.0658 | 0.9685 |
0.1469 | 3.0 | 1377 | 0.0527 | 0.9721 |
0.1637 | 4.0 | 1836 | 0.0463 | 0.9737 |
0.111 | 5.0 | 2295 | 0.0476 | 0.9748 |
0.1467 | 6.0 | 2754 | 0.0393 | 0.9777 |
0.1284 | 7.0 | 3213 | 0.0382 | 0.9787 |
0.1025 | 8.0 | 3672 | 0.0396 | 0.9777 |
0.1301 | 9.0 | 4131 | 0.0378 | 0.9782 |
0.0829 | 10.0 | 4590 | 0.0345 | 0.9811 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.