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_adamax_0001_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: 0.9115191986644408

smids_3x_beit_base_adamax_0001_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: 0.7494
• Accuracy: 0.9115

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
0.3678	1.0	226	0.3292	0.8614
0.2124	2.0	452	0.3720	0.8815
0.1134	3.0	678	0.4692	0.8631
0.0789	4.0	904	0.3549	0.9032
0.0454	5.0	1130	0.4305	0.9048
0.0205	6.0	1356	0.5024	0.9149
0.001	7.0	1582	0.5548	0.9065
0.0104	8.0	1808	0.5394	0.8998
0.0382	9.0	2034	0.5732	0.9149
0.0007	10.0	2260	0.6012	0.9098
0.0391	11.0	2486	0.5763	0.9082
0.0059	12.0	2712	0.6108	0.9065
0.0173	13.0	2938	0.5672	0.9115
0.017	14.0	3164	0.7490	0.8982
0.011	15.0	3390	0.6808	0.9065
0.0001	16.0	3616	0.6376	0.9115
0.01	17.0	3842	0.6232	0.9065
0.001	18.0	4068	0.6761	0.8982
0.0042	19.0	4294	0.7354	0.9115
0.0001	20.0	4520	0.6861	0.9098
0.0007	21.0	4746	0.7202	0.9065
0.0044	22.0	4972	0.6969	0.9082
0.0048	23.0	5198	0.6620	0.9199
0.0	24.0	5424	0.7820	0.8998
0.0	25.0	5650	0.6630	0.9149
0.0	26.0	5876	0.6962	0.9165
0.0	27.0	6102	0.7046	0.9149
0.0119	28.0	6328	0.8033	0.9032
0.0	29.0	6554	0.6906	0.9115
0.0002	30.0	6780	0.6827	0.9098
0.0002	31.0	7006	0.7730	0.9065
0.0	32.0	7232	0.8017	0.9015
0.004	33.0	7458	0.7703	0.9098
0.0001	34.0	7684	0.7283	0.9098
0.0	35.0	7910	0.7503	0.9065
0.0	36.0	8136	0.7083	0.9149
0.0	37.0	8362	0.7770	0.9048
0.0	38.0	8588	0.7053	0.9165
0.0	39.0	8814	0.7150	0.9165
0.0	40.0	9040	0.7204	0.9182
0.0022	41.0	9266	0.7127	0.9165
0.0033	42.0	9492	0.7275	0.9149
0.0	43.0	9718	0.7350	0.9165
0.0	44.0	9944	0.7337	0.9149
0.0	45.0	10170	0.7372	0.9115
0.0002	46.0	10396	0.7514	0.9165
0.0	47.0	10622	0.7501	0.9115
0.0	48.0	10848	0.7502	0.9149
0.0	49.0	11074	0.7494	0.9098
0.0	50.0	11300	0.7494	0.9115

Framework versions

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