---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- seizure-detection
- generated_from_trainer
model-index:
- name: seizure_vit_jlb_231108_iir_adjusted
  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. -->

# seizure_vit_jlb_231108_iir_adjusted

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 JLB-JLB/seizure_eeg_iirFilter_greyscale_224x224_6secWindow_adjusted dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4198
- Roc Auc: 0.7773

## 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: 1e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Roc Auc |
|:-------------:|:-----:|:-----:|:---------------:|:-------:|
| 0.3803        | 0.34  | 1000  | 0.4734          | 0.7746  |
| 0.3456        | 0.68  | 2000  | 0.4863          | 0.7782  |
| 0.2831        | 1.02  | 3000  | 0.4817          | 0.7897  |
| 0.2781        | 1.36  | 4000  | 0.5418          | 0.7656  |
| 0.2355        | 1.7   | 5000  | 0.5398          | 0.7786  |
| 0.1978        | 2.04  | 6000  | 0.6121          | 0.7649  |
| 0.149         | 2.38  | 7000  | 0.6402          | 0.7706  |
| 0.1766        | 2.72  | 8000  | 0.6768          | 0.7610  |
| 0.1496        | 3.06  | 9000  | 0.6239          | 0.7733  |
| 0.155         | 3.4   | 10000 | 0.7333          | 0.7602  |
| 0.1238        | 3.75  | 11000 | 0.6513          | 0.7726  |
| 0.1054        | 4.09  | 12000 | 0.7551          | 0.7667  |
| 0.1076        | 4.43  | 13000 | 0.8132          | 0.7627  |
| 0.1321        | 4.77  | 14000 | 0.8152          | 0.7587  |

![image/png](https://cdn-uploads.huggingface.co/production/uploads/640b79908a08d0ca79456a04/K8ORF3q_Eyp_q2VjHSg_F.png)


![image/png](https://cdn-uploads.huggingface.co/production/uploads/640b79908a08d0ca79456a04/Hi6zx6Abb_Y4AbpEveBHX.png)

### Framework versions

- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1