metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-ori-dataset-exp
results: []
vit-ori-dataset-exp
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: 0.6257
- Accuracy: 0.8506
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6531 | 0.31 | 100 | 0.6383 | 0.7718 |
| 0.6366 | 0.62 | 200 | 0.8169 | 0.7302 |
| 0.7064 | 0.93 | 300 | 0.6012 | 0.7840 |
| 0.4821 | 1.25 | 400 | 0.8299 | 0.7063 |
| 0.474 | 1.56 | 500 | 0.6822 | 0.7885 |
| 0.3619 | 1.87 | 600 | 0.5275 | 0.8076 |
| 0.1723 | 2.18 | 700 | 0.6328 | 0.7868 |
| 0.2579 | 2.49 | 800 | 0.5694 | 0.8121 |
| 0.1422 | 2.8 | 900 | 0.6486 | 0.8245 |
| 0.0528 | 3.12 | 1000 | 0.5941 | 0.8398 |
| 0.0203 | 3.43 | 1100 | 0.6370 | 0.8502 |
| 0.011 | 3.74 | 1200 | 0.6257 | 0.8506 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2