metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_5x_beit_base_rms_001_fold3
    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: 0.7883333333333333

smids_5x_beit_base_rms_001_fold3

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: 1.2450
Accuracy: 0.7883

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
0.8383	1.0	375	0.9251	0.4967
0.7811	2.0	750	0.8274	0.55
0.7757	3.0	1125	0.8322	0.55
0.774	4.0	1500	0.7903	0.5667
0.7988	5.0	1875	0.7818	0.59
0.7926	6.0	2250	0.7711	0.595
0.7549	7.0	2625	0.7682	0.6267
0.7997	8.0	3000	0.7569	0.61
0.6926	9.0	3375	0.7561	0.6417
0.7413	10.0	3750	0.7251	0.6567
0.6722	11.0	4125	0.7285	0.6533
0.7582	12.0	4500	0.7029	0.66
0.6728	13.0	4875	0.7283	0.6433
0.6373	14.0	5250	0.7252	0.6333
0.648	15.0	5625	0.7000	0.67
0.6675	16.0	6000	0.7072	0.6683
0.7316	17.0	6375	0.7063	0.6717
0.7151	18.0	6750	0.6856	0.6683
0.6082	19.0	7125	0.6800	0.6817
0.6879	20.0	7500	0.6816	0.6733
0.5586	21.0	7875	0.6735	0.695
0.6065	22.0	8250	0.6507	0.71
0.5783	23.0	8625	0.6597	0.69
0.6456	24.0	9000	0.6102	0.74
0.5238	25.0	9375	0.6683	0.7117
0.5326	26.0	9750	0.6240	0.7183
0.5499	27.0	10125	0.6403	0.7083
0.5607	28.0	10500	0.5945	0.7417
0.4887	29.0	10875	0.6536	0.71
0.5354	30.0	11250	0.5785	0.725
0.5136	31.0	11625	0.6072	0.7517
0.5448	32.0	12000	0.6265	0.7383
0.4542	33.0	12375	0.6265	0.7417
0.4208	34.0	12750	0.6113	0.745
0.3509	35.0	13125	0.6279	0.7467
0.4112	36.0	13500	0.6145	0.74
0.3719	37.0	13875	0.6674	0.745
0.3029	38.0	14250	0.6977	0.7583
0.3416	39.0	14625	0.6751	0.7717
0.3246	40.0	15000	0.6878	0.7633
0.2432	41.0	15375	0.6417	0.79
0.2014	42.0	15750	0.7882	0.78
0.2354	43.0	16125	0.8175	0.7817
0.1797	44.0	16500	0.8553	0.79
0.1419	45.0	16875	0.9481	0.765
0.1815	46.0	17250	1.0306	0.765
0.1604	47.0	17625	1.0263	0.765
0.103	48.0	18000	1.1281	0.7833
0.0441	49.0	18375	1.2055	0.79
0.0741	50.0	18750	1.2450	0.7883

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2