|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- image-classification |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: vit-base-images |
|
results: [] |
|
--- |
|
|
|
<!-- 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-images |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the marmal88/skin_cancer dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0918 |
|
- Accuracy: 0.981 |
|
|
|
## 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 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.8785 | 0.4 | 100 | 0.7795 | 0.711 | |
|
| 0.7076 | 0.8 | 200 | 0.5421 | 0.818 | |
|
| 0.4283 | 1.2 | 300 | 0.3951 | 0.876 | |
|
| 0.4251 | 1.6 | 400 | 0.3818 | 0.864 | |
|
| 0.335 | 2.0 | 500 | 0.2474 | 0.924 | |
|
| 0.2286 | 2.4 | 600 | 0.1675 | 0.952 | |
|
| 0.1523 | 2.8 | 700 | 0.1641 | 0.954 | |
|
| 0.1346 | 3.2 | 800 | 0.1120 | 0.969 | |
|
| 0.0638 | 3.6 | 900 | 0.1025 | 0.978 | |
|
| 0.0574 | 4.0 | 1000 | 0.0918 | 0.981 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|