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_001_fold5
    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: 0.8816666666666667

smids_3x_beit_base_adamax_001_fold5

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: 1.1371
• Accuracy: 0.8817

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
0.4638	1.0	225	0.4831	0.8
0.3593	2.0	450	0.4972	0.8017
0.3188	3.0	675	0.4598	0.8167
0.3007	4.0	900	0.3652	0.8567
0.1782	5.0	1125	0.4943	0.8467
0.2023	6.0	1350	0.3456	0.8833
0.1823	7.0	1575	0.4718	0.8517
0.2135	8.0	1800	0.4289	0.8333
0.1901	9.0	2025	0.3868	0.8767
0.1186	10.0	2250	0.5005	0.8567
0.1591	11.0	2475	0.4399	0.8633
0.1322	12.0	2700	0.4503	0.88
0.1689	13.0	2925	0.5822	0.855
0.1287	14.0	3150	0.5651	0.8533
0.0522	15.0	3375	0.6382	0.875
0.0395	16.0	3600	0.6522	0.88
0.0429	17.0	3825	0.6980	0.875
0.0661	18.0	4050	0.7096	0.855
0.0192	19.0	4275	0.7298	0.8733
0.0389	20.0	4500	0.7458	0.875
0.0026	21.0	4725	0.7349	0.88
0.0037	22.0	4950	0.8178	0.8833
0.006	23.0	5175	0.9683	0.8667
0.0578	24.0	5400	0.7875	0.8817
0.049	25.0	5625	0.7063	0.87
0.0011	26.0	5850	0.8220	0.8717
0.0006	27.0	6075	0.7462	0.8833
0.0152	28.0	6300	0.8411	0.8817
0.0204	29.0	6525	0.9258	0.875
0.0002	30.0	6750	0.8705	0.8683
0.0004	31.0	6975	0.8382	0.88
0.0001	32.0	7200	0.8871	0.8767
0.0069	33.0	7425	0.6754	0.8983
0.0062	34.0	7650	0.7823	0.8983
0.003	35.0	7875	0.8358	0.8883
0.0	36.0	8100	0.9463	0.885
0.0144	37.0	8325	1.0937	0.8717
0.0078	38.0	8550	1.0295	0.8867
0.0	39.0	8775	1.0240	0.8883
0.0001	40.0	9000	1.0443	0.8833
0.0	41.0	9225	1.0675	0.8933
0.0	42.0	9450	1.1657	0.8767
0.0035	43.0	9675	1.1312	0.8717
0.0	44.0	9900	1.1156	0.885
0.0	45.0	10125	1.1160	0.8817
0.0	46.0	10350	1.1325	0.8833
0.0008	47.0	10575	1.1407	0.8817
0.0	48.0	10800	1.1472	0.88
0.0001	49.0	11025	1.1387	0.8817
0.0	50.0	11250	1.1371	0.8817

Framework versions

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