metadata

base_model: /content/drive/MyDrive/Seizure_EEG_Research/ViT_Seizure_Detection
tags:
  - image-classification
  - generated_from_trainer
datasets:
  - arrow
metrics:
  - matthews_correlation
model-index:
  - name: ViT_Seizure_Detection
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: JLB-JLB/seizure_eeg_greyscale_224x224_6secWindow
          type: arrow
          config: default
          split: test
          args: default
        metrics:
          - name: Matthews Correlation
            type: matthews_correlation
            value: 0.41096197273922397

ViT_Seizure_Detection

This model is a fine-tuned version of /content/drive/MyDrive/Seizure_EEG_Research/ViT_Seizure_Detection on the JLB-JLB/seizure_eeg_greyscale_224x224_6secWindow dataset. It achieves the following results on the evaluation set:

Loss: 0.1622
Matthews Correlation: 0.4110

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: 0.0001
train_batch_size: 64
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	Matthews Correlation
0.0742	0.79	10000	0.2080	0.4431
0.0409	1.57	20000	0.2175	0.4470
0.0345	2.36	30000	0.2514	0.4717
0.0184	3.14	40000	0.3040	0.4261
0.0092	3.93	50000	0.3495	0.4389

Framework versions

Transformers 4.34.1
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1