metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_1x_beit_base_rms_0001_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: 0.7133333333333334

smids_1x_beit_base_rms_0001_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: 0.7846
Accuracy: 0.7133

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
1.1199	1.0	75	1.1044	0.325
1.1759	2.0	150	1.1239	0.47
1.1465	3.0	225	0.9168	0.5
0.8955	4.0	300	0.8917	0.5017
0.8948	5.0	375	0.8301	0.5533
0.9774	6.0	450	0.8272	0.5467
0.8001	7.0	525	0.8058	0.5567
0.7633	8.0	600	0.8140	0.545
0.7814	9.0	675	0.7815	0.5733
0.8175	10.0	750	0.7839	0.5633
0.7605	11.0	825	0.7664	0.615
0.762	12.0	900	0.7781	0.59
0.6797	13.0	975	0.7875	0.575
0.7699	14.0	1050	0.7772	0.6117
0.6167	15.0	1125	0.8129	0.585
0.7106	16.0	1200	0.7392	0.6633
0.7174	17.0	1275	0.7176	0.6717
0.704	18.0	1350	0.7772	0.63
0.6617	19.0	1425	0.7359	0.65
0.6722	20.0	1500	0.7009	0.6783
0.676	21.0	1575	0.6946	0.6667
0.6441	22.0	1650	0.7089	0.6917
0.6565	23.0	1725	0.7160	0.665
0.6009	24.0	1800	0.6902	0.6783
0.6592	25.0	1875	0.7159	0.665
0.6628	26.0	1950	0.7741	0.6233
0.6044	27.0	2025	0.7147	0.66
0.585	28.0	2100	0.6827	0.69
0.5831	29.0	2175	0.6975	0.6833
0.6301	30.0	2250	0.6815	0.6633
0.6457	31.0	2325	0.6813	0.6817
0.6492	32.0	2400	0.6894	0.6783
0.5418	33.0	2475	0.7461	0.6783
0.5925	34.0	2550	0.6773	0.6933
0.5913	35.0	2625	0.6656	0.7083
0.5761	36.0	2700	0.6491	0.7133
0.528	37.0	2775	0.6784	0.7
0.5718	38.0	2850	0.7007	0.6783
0.5083	39.0	2925	0.6815	0.7
0.5069	40.0	3000	0.6638	0.71
0.4838	41.0	3075	0.6813	0.7167
0.5071	42.0	3150	0.6709	0.7183
0.5091	43.0	3225	0.6746	0.7167
0.4355	44.0	3300	0.7138	0.71
0.4287	45.0	3375	0.7080	0.7133
0.3954	46.0	3450	0.7468	0.7
0.3389	47.0	3525	0.7428	0.7183
0.3613	48.0	3600	0.7469	0.725
0.388	49.0	3675	0.7685	0.7167
0.2972	50.0	3750	0.7846	0.7133

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0