metadata

license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: swin-tiny-patch4-window7-224-finetuned-mobile-eye-tracking-dataset-v2
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8653366583541147

swin-tiny-patch4-window7-224-finetuned-mobile-eye-tracking-dataset-v2

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.3944
Accuracy: 0.8653

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: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3648	0.99	59	0.3998	0.8653
0.3789	2.0	119	0.4005	0.8653
0.3572	2.99	178	0.4006	0.8653
0.3842	4.0	238	0.3905	0.8653
0.356	4.99	297	0.3894	0.8653
0.3564	6.0	357	0.3936	0.8653
0.3668	6.99	416	0.3934	0.8653
0.3538	8.0	476	0.3882	0.8653
0.353	8.99	535	0.3870	0.8653
0.3481	10.0	595	0.3867	0.8653
0.3315	10.99	654	0.3949	0.8653
0.3456	12.0	714	0.3919	0.8678
0.3329	12.99	773	0.3905	0.8653
0.3409	14.0	833	0.3930	0.8653
0.313	14.87	885	0.3944	0.8653

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.0