README.md

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_adamax_0001_fold4
    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: 0.87

smids_1x_beit_base_adamax_0001_fold4

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: 1.1137
• Accuracy: 0.87

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: 0.0001
• 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
0.3443	1.0	75	0.4137	0.8583
0.258	2.0	150	0.4036	0.8483
0.1343	3.0	225	0.4810	0.8533
0.0768	4.0	300	0.5625	0.86
0.0189	5.0	375	0.6619	0.8617
0.0435	6.0	450	0.6679	0.875
0.0162	7.0	525	0.7878	0.86
0.0677	8.0	600	0.7298	0.875
0.0423	9.0	675	0.8935	0.855
0.0172	10.0	750	0.8762	0.8717
0.001	11.0	825	0.8614	0.865
0.0092	12.0	900	0.8623	0.8717
0.0016	13.0	975	0.8916	0.87
0.0049	14.0	1050	0.8926	0.88
0.0101	15.0	1125	0.9303	0.8683
0.0014	16.0	1200	0.9140	0.8783
0.001	17.0	1275	0.9424	0.8817
0.0053	18.0	1350	0.8806	0.8817
0.0012	19.0	1425	0.9188	0.8917
0.0147	20.0	1500	0.9436	0.8767
0.0025	21.0	1575	0.9848	0.88
0.0092	22.0	1650	0.9945	0.8817
0.0279	23.0	1725	1.0063	0.875
0.0046	24.0	1800	1.0539	0.8767
0.0043	25.0	1875	1.0635	0.8717
0.0045	26.0	1950	1.0471	0.8733
0.0	27.0	2025	1.0128	0.8783
0.0004	28.0	2100	1.0296	0.8717
0.0001	29.0	2175	1.0117	0.875
0.0001	30.0	2250	1.0423	0.87
0.0073	31.0	2325	1.0722	0.87
0.0	32.0	2400	1.0662	0.8767
0.0	33.0	2475	1.0416	0.8717
0.0	34.0	2550	1.0959	0.8717
0.0034	35.0	2625	1.1220	0.87
0.0	36.0	2700	1.1441	0.8733
0.0	37.0	2775	1.1553	0.8733
0.0022	38.0	2850	1.1117	0.8767
0.0	39.0	2925	1.1002	0.8717
0.0	40.0	3000	1.1022	0.8683
0.003	41.0	3075	1.1129	0.8667
0.008	42.0	3150	1.1397	0.8667
0.0	43.0	3225	1.1224	0.87
0.0	44.0	3300	1.1186	0.8717
0.0	45.0	3375	1.1121	0.87
0.0001	46.0	3450	1.1134	0.87
0.0	47.0	3525	1.1172	0.8683
0.0001	48.0	3600	1.1134	0.87
0.0023	49.0	3675	1.1139	0.87
0.0022	50.0	3750	1.1137	0.87

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0