metadata

license: apache-2.0
base_model: microsoft/swinv2-tiny-patch4-window8-256
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: swinv2-tiny-patch4-window8-256-finetuned-gardner-exp-max
    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: 0.8355704697986577

swinv2-tiny-patch4-window8-256-finetuned-gardner-exp-max

This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window8-256 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.5500
Accuracy: 0.8356

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
1.6043	0.97	14	1.5288	0.5415
1.4967	2.0	29	1.1719	0.5415
1.1276	2.97	43	1.0525	0.5463
1.0796	4.0	58	0.9086	0.6537
0.9387	4.97	72	0.8500	0.6439
0.9232	6.0	87	0.8190	0.6732
0.8456	6.97	101	0.8042	0.6878
0.8348	8.0	116	0.7770	0.6927
0.8057	8.97	130	0.7457	0.7073
0.8033	10.0	145	0.7353	0.7024
0.7822	10.97	159	0.7166	0.7122
0.7594	12.0	174	0.7188	0.7171
0.7777	12.97	188	0.7086	0.7171
0.7445	14.0	203	0.7139	0.6878
0.7513	14.48	210	0.7139	0.6878

Framework versions

Transformers 4.36.2
Pytorch 2.1.2
Datasets 2.16.0
Tokenizers 0.15.0