metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_3x_beit_base_sgd_001_fold1
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: test
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8681135225375626

smids_3x_beit_base_sgd_001_fold1

This model is a fine-tuned version of microsoft/beit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.3433
Accuracy: 0.8681

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: 0.001
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8537	1.0	226	0.8519	0.6194
0.627	2.0	452	0.6595	0.7162
0.5599	3.0	678	0.5836	0.7563
0.5294	4.0	904	0.5378	0.7830
0.541	5.0	1130	0.5094	0.7930
0.4706	6.0	1356	0.4828	0.8030
0.4252	7.0	1582	0.4633	0.8264
0.4132	8.0	1808	0.4456	0.8214
0.3872	9.0	2034	0.4395	0.8197
0.4235	10.0	2260	0.4220	0.8347
0.363	11.0	2486	0.4107	0.8414
0.3912	12.0	2712	0.4033	0.8381
0.304	13.0	2938	0.4009	0.8381
0.3002	14.0	3164	0.4007	0.8414
0.3207	15.0	3390	0.3907	0.8431
0.3295	16.0	3616	0.3840	0.8481
0.2579	17.0	3842	0.3879	0.8447
0.2728	18.0	4068	0.3774	0.8514
0.2754	19.0	4294	0.3738	0.8514
0.2647	20.0	4520	0.3691	0.8531
0.2981	21.0	4746	0.3671	0.8548
0.2768	22.0	4972	0.3598	0.8614
0.3183	23.0	5198	0.3674	0.8548
0.2945	24.0	5424	0.3555	0.8598
0.2478	25.0	5650	0.3546	0.8648
0.325	26.0	5876	0.3592	0.8564
0.2291	27.0	6102	0.3605	0.8548
0.2815	28.0	6328	0.3547	0.8564
0.2072	29.0	6554	0.3519	0.8614
0.3343	30.0	6780	0.3526	0.8631
0.2535	31.0	7006	0.3589	0.8614
0.25	32.0	7232	0.3529	0.8648
0.21	33.0	7458	0.3549	0.8581
0.2119	34.0	7684	0.3504	0.8598
0.2671	35.0	7910	0.3485	0.8648
0.2299	36.0	8136	0.3541	0.8614
0.2465	37.0	8362	0.3470	0.8631
0.2631	38.0	8588	0.3446	0.8648
0.239	39.0	8814	0.3471	0.8598
0.1883	40.0	9040	0.3479	0.8648
0.226	41.0	9266	0.3450	0.8681
0.258	42.0	9492	0.3451	0.8698
0.2562	43.0	9718	0.3456	0.8681
0.1938	44.0	9944	0.3435	0.8681
0.2807	45.0	10170	0.3449	0.8664
0.253	46.0	10396	0.3419	0.8698
0.2465	47.0	10622	0.3435	0.8664
0.2602	48.0	10848	0.3432	0.8664
0.2179	49.0	11074	0.3434	0.8681
0.2786	50.0	11300	0.3433	0.8681

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2