metadata
license: apache-2.0
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base-beans-demo-v5
results: []
vit-base-beans-demo-v5
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the diabetic-retinopathy-classification dataset. It achieves the following results on the evaluation set:
- Loss: 0.7260
- Accuracy: 0.7263
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 |
|---|---|---|---|---|
| 0.9235 | 0.47 | 100 | 0.8972 | 0.6493 |
| 0.9253 | 0.95 | 200 | 0.9151 | 0.6635 |
| 0.8371 | 1.42 | 300 | 0.8071 | 0.6931 |
| 0.7355 | 1.9 | 400 | 0.7563 | 0.7073 |
| 0.6532 | 2.37 | 500 | 0.7543 | 0.6896 |
| 0.5982 | 2.84 | 600 | 0.7260 | 0.7263 |
| 0.4276 | 3.32 | 700 | 0.7346 | 0.7239 |
| 0.4935 | 3.79 | 800 | 0.7490 | 0.7133 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2