|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: vit-base-brain-alzheimer-detection |
|
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-brain-alzheimer-detection |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2428 |
|
- Accuracy: 0.9508 |
|
|
|
## 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: 2e-05 |
|
- 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 |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 20 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-------:|:----:|:---------------:|:--------:| |
|
| 0.9772 | 0.7812 | 200 | 0.9400 | 0.5801 | |
|
| 0.7451 | 1.5625 | 400 | 0.7947 | 0.6553 | |
|
| 0.5701 | 2.3438 | 600 | 0.7642 | 0.7236 | |
|
| 0.3704 | 3.125 | 800 | 0.5532 | 0.7744 | |
|
| 0.2906 | 3.9062 | 1000 | 0.4423 | 0.8555 | |
|
| 0.1636 | 4.6875 | 1200 | 0.3226 | 0.9004 | |
|
| 0.0837 | 5.4688 | 1400 | 0.3483 | 0.9023 | |
|
| 0.0368 | 6.25 | 1600 | 0.2423 | 0.9395 | |
|
| 0.063 | 7.0312 | 1800 | 0.3091 | 0.9277 | |
|
| 0.047 | 7.8125 | 2000 | 0.3907 | 0.9023 | |
|
| 0.0127 | 8.5938 | 2200 | 0.2002 | 0.9561 | |
|
| 0.0102 | 9.375 | 2400 | 0.3001 | 0.9307 | |
|
| 0.0086 | 10.1562 | 2600 | 0.1998 | 0.9512 | |
|
| 0.0073 | 10.9375 | 2800 | 0.1932 | 0.9590 | |
|
| 0.0064 | 11.7188 | 3000 | 0.1988 | 0.9561 | |
|
| 0.0056 | 12.5 | 3200 | 0.1993 | 0.9580 | |
|
| 0.0049 | 13.2812 | 3400 | 0.2047 | 0.9590 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
