<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
vit-base-HAM-10000-patch-16
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the ahishamm/HAM_db dataset. It achieves the following results on the evaluation set:
- Loss: 0.4333
- Accuracy: 0.8469
- Recall: 0.8469
- F1: 0.8469
- Precision: 0.8469
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
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | F1 | Precision |
---|---|---|---|---|---|---|---|
0.718 | 0.2 | 100 | 0.7957 | 0.7471 | 0.7471 | 0.7471 | 0.7471 |
0.7946 | 0.4 | 200 | 0.7330 | 0.7451 | 0.7451 | 0.7451 | 0.7451 |
0.6182 | 0.6 | 300 | 0.6105 | 0.7810 | 0.7810 | 0.7810 | 0.7810 |
0.7459 | 0.8 | 400 | 0.6417 | 0.7691 | 0.7691 | 0.7691 | 0.7691 |
0.6626 | 1.0 | 500 | 0.6412 | 0.7676 | 0.7676 | 0.7676 | 0.7676 |
0.4497 | 1.2 | 600 | 0.5908 | 0.7885 | 0.7885 | 0.7885 | 0.7885 |
0.4141 | 1.4 | 700 | 0.5313 | 0.8145 | 0.8145 | 0.8145 | 0.8145 |
0.5624 | 1.6 | 800 | 0.5296 | 0.8209 | 0.8209 | 0.8209 | 0.8209 |
0.4138 | 1.8 | 900 | 0.5069 | 0.8150 | 0.8150 | 0.8150 | 0.8150 |
0.3866 | 2.0 | 1000 | 0.4462 | 0.8374 | 0.8374 | 0.8374 | 0.8374 |
0.2498 | 2.2 | 1100 | 0.5281 | 0.8389 | 0.8389 | 0.8389 | 0.8389 |
0.289 | 2.4 | 1200 | 0.4333 | 0.8469 | 0.8469 | 0.8469 | 0.8469 |
0.23 | 2.59 | 1300 | 0.5256 | 0.8185 | 0.8185 | 0.8185 | 0.8185 |
0.2089 | 2.79 | 1400 | 0.5041 | 0.8394 | 0.8394 | 0.8394 | 0.8394 |
0.1201 | 2.99 | 1500 | 0.5277 | 0.8474 | 0.8474 | 0.8474 | 0.8474 |
0.0851 | 3.19 | 1600 | 0.5087 | 0.8613 | 0.8613 | 0.8613 | 0.8613 |
0.0446 | 3.39 | 1700 | 0.5383 | 0.8579 | 0.8579 | 0.8579 | 0.8579 |
0.0576 | 3.59 | 1800 | 0.5151 | 0.8673 | 0.8673 | 0.8673 | 0.8673 |
0.0691 | 3.79 | 1900 | 0.5331 | 0.8579 | 0.8579 | 0.8579 | 0.8579 |
0.0284 | 3.99 | 2000 | 0.5157 | 0.8628 | 0.8628 | 0.8628 | 0.8628 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3