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_3x_beit_base_rms_00001_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: 0.8998330550918197

smids_3x_beit_base_rms_00001_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: 0.8235
• Accuracy: 0.8998

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: 1e-05
• 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
0.3449	1.0	226	0.2404	0.8982
0.164	2.0	452	0.2594	0.9098
0.0958	3.0	678	0.3903	0.8715
0.1173	4.0	904	0.3785	0.8982
0.071	5.0	1130	0.3702	0.9032
0.0146	6.0	1356	0.5160	0.8932
0.004	7.0	1582	0.5036	0.8965
0.0021	8.0	1808	0.5998	0.9015
0.0217	9.0	2034	0.6221	0.8998
0.0119	10.0	2260	0.6511	0.9082
0.0029	11.0	2486	0.6550	0.8932
0.0209	12.0	2712	0.5564	0.9082
0.0119	13.0	2938	0.7071	0.9015
0.0109	14.0	3164	0.6721	0.8965
0.0179	15.0	3390	0.6523	0.8965
0.0016	16.0	3616	0.6369	0.9149
0.0197	17.0	3842	0.8098	0.8932
0.0022	18.0	4068	0.7112	0.8948
0.017	19.0	4294	0.8580	0.8898
0.0002	20.0	4520	0.8600	0.8915
0.014	21.0	4746	0.8484	0.8932
0.0155	22.0	4972	0.7756	0.8932
0.0055	23.0	5198	0.7307	0.9082
0.016	24.0	5424	0.7520	0.9065
0.0	25.0	5650	0.6900	0.9165
0.0009	26.0	5876	0.7482	0.8998
0.0	27.0	6102	0.6921	0.9032
0.0022	28.0	6328	0.6800	0.9098
0.0	29.0	6554	0.6295	0.9215
0.0004	30.0	6780	0.6201	0.9182
0.0	31.0	7006	0.6546	0.9182
0.0	32.0	7232	0.6675	0.9098
0.0055	33.0	7458	0.7721	0.9048
0.0014	34.0	7684	0.8129	0.8965
0.0	35.0	7910	0.8045	0.8998
0.0	36.0	8136	0.7737	0.8998
0.0005	37.0	8362	0.7575	0.9065
0.0	38.0	8588	0.7935	0.9098
0.0001	39.0	8814	0.8075	0.8948
0.0	40.0	9040	0.7870	0.9065
0.0033	41.0	9266	0.7830	0.8965
0.0059	42.0	9492	0.8352	0.9015
0.0	43.0	9718	0.7765	0.9098
0.0	44.0	9944	0.8178	0.9065
0.0123	45.0	10170	0.8336	0.8982
0.0	46.0	10396	0.8075	0.9048
0.0	47.0	10622	0.8113	0.9048
0.0	48.0	10848	0.8125	0.9032
0.0	49.0	11074	0.8258	0.8982
0.0	50.0	11300	0.8235	0.8998

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2