skincancerclassification
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the SkinCancerClassification dataset. It achieves the following results on the evaluation set:
- Loss: 0.4969
- Accuracy: 0.8273
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 |
---|---|---|---|---|
0.7407 | 0.31 | 100 | 0.7736 | 0.7369 |
0.662 | 0.62 | 200 | 0.6556 | 0.7649 |
0.8726 | 0.93 | 300 | 0.6127 | 0.7783 |
0.5618 | 1.25 | 400 | 0.6259 | 0.7728 |
0.5202 | 1.56 | 500 | 0.6421 | 0.7958 |
0.4177 | 1.87 | 600 | 0.5702 | 0.7913 |
0.2606 | 2.18 | 700 | 0.5213 | 0.8268 |
0.2529 | 2.49 | 800 | 0.4969 | 0.8273 |
0.2153 | 2.8 | 900 | 0.5216 | 0.8233 |
0.0772 | 3.12 | 1000 | 0.5125 | 0.8402 |
0.0485 | 3.43 | 1100 | 0.5232 | 0.8492 |
0.081 | 3.74 | 1200 | 0.5426 | 0.8567 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 5