metadata

library_name: transformers
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: 0.8709677419354839

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: 0.3968
Accuracy: 0.8710

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: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 256
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.8889	2	1.7756	0.2258
No log	1.7778	4	1.6784	0.2581
No log	2.6667	6	1.5861	0.3226
No log	4.0	9	1.3571	0.4194
No log	4.8889	11	1.0993	0.5484
No log	5.7778	13	0.9242	0.6452
1.4667	6.6667	15	0.7538	0.7097
1.4667	8.0	18	0.6294	0.7742
1.4667	8.8889	20	0.5326	0.7097
1.4667	9.7778	22	0.4848	0.7419
1.4667	10.6667	24	0.4832	0.7742
1.4667	12.0	27	0.4483	0.7742
1.4667	12.8889	29	0.4296	0.7742
0.5925	13.7778	31	0.4023	0.7742
0.5925	14.6667	33	0.4111	0.8387
0.5925	16.0	36	0.3873	0.8065
0.5925	16.8889	38	0.4029	0.8065
0.5925	17.7778	40	0.4065	0.8065
0.5925	18.6667	42	0.3864	0.8065
0.3285	20.0	45	0.3968	0.8710
0.3285	20.8889	47	0.3930	0.8710
0.3285	21.7778	49	0.3871	0.8710
0.3285	22.6667	51	0.3779	0.8065
0.3285	24.0	54	0.3698	0.8065
0.3285	24.8889	56	0.3726	0.8387
0.3285	25.7778	58	0.3732	0.8387
0.2621	26.6667	60	0.3732	0.8387

Framework versions

Transformers 4.45.1
Pytorch 2.4.0
Datasets 3.0.1
Tokenizers 0.20.0