metadata

base_model: MBZUAI/swiftformer-xs
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
  - precision
  - recall
model-index:
  - name: swiftformer-xs
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.73
          - name: Precision
            type: precision
            value: 0.5329
          - name: Recall
            type: recall
            value: 0.73

swiftformer-xs

This model is a fine-tuned version of MBZUAI/swiftformer-xs on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.5838
Accuracy: 0.73
Precision: 0.5329
Recall: 0.73
F1 Score: 0.6161

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1 Score
No log	1.0	4	0.6209	0.7292	0.6273	0.7292	0.6259
No log	2.0	8	0.7514	0.3875	0.5947	0.3875	0.3910
No log	3.0	12	0.7574	0.3292	0.6284	0.3292	0.2679
0.6558	4.0	16	0.7080	0.5042	0.6591	0.5042	0.5279
0.6558	5.0	20	0.6566	0.6458	0.6859	0.6458	0.6604
0.6558	6.0	24	0.6509	0.65	0.6810	0.65	0.6621
0.6558	7.0	28	0.6438	0.6375	0.6639	0.6375	0.6484
0.5697	8.0	32	0.6455	0.65	0.6845	0.65	0.6631
0.5697	9.0	36	0.6480	0.6458	0.6823	0.6458	0.6596
0.5697	10.0	40	0.6438	0.6542	0.6867	0.6542	0.6667
0.5697	11.0	44	0.6366	0.6583	0.6924	0.6583	0.6711
0.5232	12.0	48	0.6391	0.6625	0.7016	0.6625	0.6764
0.5232	13.0	52	0.6386	0.6583	0.6924	0.6583	0.6711
0.5232	14.0	56	0.6403	0.6667	0.7038	0.6667	0.68
0.5068	15.0	60	0.6459	0.6708	0.7131	0.6708	0.6851

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3