<!-- 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-16
This model is a fine-tuned version of google/vit-large-patch16-224-in21k on the ahishamm/HAM_db dataset. It achieves the following results on the evaluation set:
- Loss: 0.5464
- Accuracy: 0.8095
- Recall: 0.8095
- F1: 0.8095
- Precision: 0.8095
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 |
---|---|---|---|---|---|---|---|
0.8281 | 0.2 | 100 | 0.9228 | 0.6788 | 0.6788 | 0.6788 | 0.6788 |
0.912 | 0.4 | 200 | 0.8353 | 0.7147 | 0.7147 | 0.7147 | 0.7147 |
0.6741 | 0.6 | 300 | 0.7841 | 0.7377 | 0.7377 | 0.7377 | 0.7377 |
0.8472 | 0.8 | 400 | 0.6710 | 0.7566 | 0.7566 | 0.7566 | 0.7566 |
0.7758 | 1.0 | 500 | 0.7587 | 0.7087 | 0.7087 | 0.7087 | 0.7087 |
0.5388 | 1.2 | 600 | 0.6607 | 0.7746 | 0.7746 | 0.7746 | 0.7746 |
0.5067 | 1.4 | 700 | 0.6133 | 0.7701 | 0.7701 | 0.7701 | 0.7701 |
0.4992 | 1.6 | 800 | 0.6075 | 0.7786 | 0.7786 | 0.7786 | 0.7786 |
0.5761 | 1.8 | 900 | 0.6286 | 0.7691 | 0.7691 | 0.7691 | 0.7691 |
0.5892 | 2.0 | 1000 | 0.5498 | 0.8035 | 0.8035 | 0.8035 | 0.8035 |
0.4258 | 2.2 | 1100 | 0.5901 | 0.7940 | 0.7940 | 0.7940 | 0.7940 |
0.4066 | 2.4 | 1200 | 0.5553 | 0.8025 | 0.8025 | 0.8025 | 0.8025 |
0.3032 | 2.59 | 1300 | 0.5754 | 0.8030 | 0.8030 | 0.8030 | 0.8030 |
0.3843 | 2.79 | 1400 | 0.5464 | 0.8095 | 0.8095 | 0.8095 | 0.8095 |
0.2679 | 2.99 | 1500 | 0.5683 | 0.8100 | 0.8100 | 0.8100 | 0.8100 |
0.1787 | 3.19 | 1600 | 0.5931 | 0.8195 | 0.8195 | 0.8195 | 0.8195 |
0.105 | 3.39 | 1700 | 0.6488 | 0.8279 | 0.8279 | 0.8279 | 0.8279 |
0.2138 | 3.59 | 1800 | 0.6414 | 0.8130 | 0.8130 | 0.8130 | 0.8130 |
0.1336 | 3.79 | 1900 | 0.5920 | 0.8264 | 0.8264 | 0.8264 | 0.8264 |
0.1246 | 3.99 | 2000 | 0.5999 | 0.8289 | 0.8289 | 0.8289 | 0.8289 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3