<!-- 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-large-HAM-10000-patch-32
This model is a fine-tuned version of google/vit-large-patch32-224-in21k on the ahishamm/HAM_db dataset. It achieves the following results on the evaluation set:
- Loss: 0.4810
- Accuracy: 0.8364
- Recall: 0.8364
- F1: 0.8364
- Precision: 0.8364
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 |
---|---|---|---|---|---|---|---|
0.6405 | 0.2 | 100 | 0.7318 | 0.7481 | 0.7481 | 0.7481 | 0.7481 |
0.7062 | 0.4 | 200 | 0.7735 | 0.7416 | 0.7416 | 0.7416 | 0.7416 |
0.6334 | 0.6 | 300 | 0.6075 | 0.7781 | 0.7781 | 0.7781 | 0.7781 |
0.7102 | 0.8 | 400 | 0.6618 | 0.7661 | 0.7661 | 0.7661 | 0.7661 |
0.6814 | 1.0 | 500 | 0.5717 | 0.7890 | 0.7890 | 0.7890 | 0.7890 |
0.4618 | 1.2 | 600 | 0.5624 | 0.8030 | 0.8030 | 0.8030 | 0.8030 |
0.3824 | 1.4 | 700 | 0.5987 | 0.7766 | 0.7766 | 0.7766 | 0.7766 |
0.4191 | 1.6 | 800 | 0.5145 | 0.8190 | 0.8190 | 0.8190 | 0.8190 |
0.3998 | 1.8 | 900 | 0.5226 | 0.8090 | 0.8090 | 0.8090 | 0.8090 |
0.4677 | 2.0 | 1000 | 0.4927 | 0.8219 | 0.8219 | 0.8219 | 0.8219 |
0.2191 | 2.2 | 1100 | 0.5477 | 0.8284 | 0.8284 | 0.8284 | 0.8284 |
0.2302 | 2.4 | 1200 | 0.5018 | 0.8329 | 0.8329 | 0.8329 | 0.8329 |
0.191 | 2.59 | 1300 | 0.4810 | 0.8364 | 0.8364 | 0.8364 | 0.8364 |
0.1736 | 2.79 | 1400 | 0.5096 | 0.8334 | 0.8334 | 0.8334 | 0.8334 |
0.1049 | 2.99 | 1500 | 0.5944 | 0.8364 | 0.8364 | 0.8364 | 0.8364 |
0.0612 | 3.19 | 1600 | 0.5552 | 0.8464 | 0.8464 | 0.8464 | 0.8464 |
0.0181 | 3.39 | 1700 | 0.6199 | 0.8434 | 0.8434 | 0.8434 | 0.8434 |
0.0816 | 3.59 | 1800 | 0.5081 | 0.8534 | 0.8534 | 0.8534 | 0.8534 |
0.039 | 3.79 | 1900 | 0.5349 | 0.8544 | 0.8544 | 0.8544 | 0.8544 |
0.0208 | 3.99 | 2000 | 0.5445 | 0.8544 | 0.8544 | 0.8544 | 0.8544 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3