metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
base_model: google/vit-base-patch16-224-in21k
model-index:
- name: vit-focal-skin
results: []
vit-focal-skin
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5830
- Accuracy: 0.8497
- F1: 0.8472
- Precision: 0.8527
- Recall: 0.8497
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: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.1586 | 1.0 | 626 | 0.3295 | 0.8808 | 0.8764 | 0.9007 | 0.8808 |
| 0.096 | 2.0 | 1252 | 0.4315 | 0.8601 | 0.8562 | 0.8600 | 0.8601 |
| 0.0181 | 3.0 | 1878 | 0.4395 | 0.8756 | 0.8685 | 0.8799 | 0.8756 |
| 0.0058 | 4.0 | 2504 | 0.5563 | 0.8549 | 0.8571 | 0.8653 | 0.8549 |
| 0.0004 | 5.0 | 3130 | 0.6044 | 0.8653 | 0.8619 | 0.8688 | 0.8653 |
| 0.0003 | 6.0 | 3756 | 0.5830 | 0.8497 | 0.8472 | 0.8527 | 0.8497 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.13.1
- Datasets 2.14.5
- Tokenizers 0.13.3