metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-diabetic-retinopathy-classification
results: []
vit-diabetic-retinopathy-classification
This model is a fine-tuned version of Kontawat/vit-diabetic-retinopathy-classification on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0460
- Accuracy: 0.7287
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5645 | 0.94 | 100 | 0.7731 | 0.7239 |
| 0.3971 | 1.89 | 200 | 0.8123 | 0.7038 |
| 0.3239 | 2.83 | 300 | 0.8204 | 0.7239 |
| 0.2178 | 3.77 | 400 | 0.9085 | 0.7204 |
| 0.18 | 4.72 | 500 | 1.0284 | 0.7310 |
| 0.0501 | 5.66 | 600 | 1.0460 | 0.7287 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2