<!-- 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-huge-HAM-10000-patch-14
This model is a fine-tuned version of google/vit-huge-patch14-224-in21k on the ahishamm/HAM_db dataset. It achieves the following results on the evaluation set:
- Loss: 0.3807
- Accuracy: 0.8653
- Recall: 0.8653
- F1: 0.8653
- Precision: 0.8653
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 |
---|---|---|---|---|---|---|---|
0.7133 | 0.2 | 100 | 0.7307 | 0.7551 | 0.7551 | 0.7551 | 0.7551 |
0.7015 | 0.4 | 200 | 0.6770 | 0.7546 | 0.7546 | 0.7546 | 0.7546 |
0.5847 | 0.6 | 300 | 0.6005 | 0.7890 | 0.7890 | 0.7890 | 0.7890 |
0.6016 | 0.8 | 400 | 0.5909 | 0.7810 | 0.7810 | 0.7810 | 0.7810 |
0.585 | 1.0 | 500 | 0.4994 | 0.8175 | 0.8175 | 0.8175 | 0.8175 |
0.3114 | 1.2 | 600 | 0.4799 | 0.8354 | 0.8354 | 0.8354 | 0.8354 |
0.2868 | 1.4 | 700 | 0.5035 | 0.8140 | 0.8140 | 0.8140 | 0.8140 |
0.3178 | 1.6 | 800 | 0.4345 | 0.8544 | 0.8544 | 0.8544 | 0.8544 |
0.344 | 1.8 | 900 | 0.4539 | 0.8374 | 0.8374 | 0.8374 | 0.8374 |
0.3273 | 2.0 | 1000 | 0.3807 | 0.8653 | 0.8653 | 0.8653 | 0.8653 |
0.0903 | 2.2 | 1100 | 0.4843 | 0.8574 | 0.8574 | 0.8574 | 0.8574 |
0.1105 | 2.4 | 1200 | 0.4116 | 0.8788 | 0.8788 | 0.8788 | 0.8788 |
0.1551 | 2.59 | 1300 | 0.4446 | 0.8534 | 0.8534 | 0.8534 | 0.8534 |
0.0804 | 2.79 | 1400 | 0.4129 | 0.8778 | 0.8778 | 0.8778 | 0.8778 |
0.0811 | 2.99 | 1500 | 0.4459 | 0.8738 | 0.8738 | 0.8738 | 0.8738 |
0.0391 | 3.19 | 1600 | 0.4409 | 0.8878 | 0.8878 | 0.8878 | 0.8878 |
0.0075 | 3.39 | 1700 | 0.4671 | 0.8888 | 0.8888 | 0.8888 | 0.8888 |
0.0113 | 3.59 | 1800 | 0.4591 | 0.8788 | 0.8788 | 0.8788 | 0.8788 |
0.0079 | 3.79 | 1900 | 0.4695 | 0.8858 | 0.8858 | 0.8858 | 0.8858 |
0.021 | 3.99 | 2000 | 0.4705 | 0.8893 | 0.8893 | 0.8893 | 0.8893 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3