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_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: 0.8964941569282137

smids_5x_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: 1.0277
Accuracy: 0.8965

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
0.169	1.0	376	0.2845	0.8848
0.1527	2.0	752	0.2709	0.9132
0.1446	3.0	1128	0.3421	0.8998
0.0485	4.0	1504	0.4474	0.9065
0.0159	5.0	1880	0.4847	0.8965
0.0162	6.0	2256	0.6046	0.8982
0.0753	7.0	2632	0.6419	0.8898
0.0455	8.0	3008	0.7218	0.8965
0.0437	9.0	3384	0.8405	0.8815
0.007	10.0	3760	0.7349	0.9015
0.0254	11.0	4136	0.8461	0.8915
0.0214	12.0	4512	0.7638	0.8898
0.0283	13.0	4888	0.8735	0.8948
0.0331	14.0	5264	0.8577	0.8932
0.0029	15.0	5640	0.9013	0.8982
0.0041	16.0	6016	0.9992	0.8698
0.0007	17.0	6392	0.9147	0.8865
0.0019	18.0	6768	0.9339	0.8915
0.0002	19.0	7144	0.8625	0.8982
0.0341	20.0	7520	0.9287	0.8815
0.0	21.0	7896	1.0011	0.8831
0.0	22.0	8272	0.8805	0.8948
0.0028	23.0	8648	0.9347	0.8965
0.0001	24.0	9024	0.9930	0.8965
0.001	25.0	9400	1.0054	0.8982
0.029	26.0	9776	0.8994	0.8932
0.0028	27.0	10152	0.9209	0.8865
0.0009	28.0	10528	0.9409	0.8998
0.0018	29.0	10904	1.0441	0.8848
0.0163	30.0	11280	0.9017	0.9032
0.0	31.0	11656	0.8554	0.9015
0.0	32.0	12032	0.8702	0.9048
0.0001	33.0	12408	0.9551	0.8965
0.0	34.0	12784	0.9265	0.8982
0.0004	35.0	13160	1.0253	0.8865
0.0044	36.0	13536	0.9098	0.8948
0.0003	37.0	13912	0.9290	0.9032
0.0	38.0	14288	1.0072	0.8948
0.0	39.0	14664	1.0677	0.8948
0.0	40.0	15040	1.0064	0.8982
0.0	41.0	15416	0.9891	0.8982
0.0	42.0	15792	1.0628	0.8948
0.0	43.0	16168	1.0396	0.8915
0.0	44.0	16544	1.0033	0.8982
0.0	45.0	16920	1.0214	0.8998
0.0033	46.0	17296	1.0498	0.8898
0.0	47.0	17672	1.0375	0.8932
0.0	48.0	18048	1.0305	0.8898
0.0	49.0	18424	1.0285	0.8948
0.0028	50.0	18800	1.0277	0.8965

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2