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_fold3
    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: 0.93

smids_3x_beit_base_rms_00001_fold3

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: 0.7714
• Accuracy: 0.93

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
0.2858	1.0	225	0.2465	0.9067
0.1768	2.0	450	0.2541	0.9117
0.0881	3.0	675	0.2719	0.9133
0.0505	4.0	900	0.3645	0.9083
0.0569	5.0	1125	0.3912	0.9117
0.0143	6.0	1350	0.5093	0.91
0.0377	7.0	1575	0.6703	0.895
0.0322	8.0	1800	0.5423	0.9067
0.0082	9.0	2025	0.5861	0.92
0.0276	10.0	2250	0.6888	0.9133
0.0302	11.0	2475	0.6182	0.92
0.0237	12.0	2700	0.7796	0.9067
0.006	13.0	2925	0.6569	0.9217
0.0168	14.0	3150	0.6640	0.925
0.0004	15.0	3375	0.7467	0.9083
0.0142	16.0	3600	0.8289	0.9033
0.001	17.0	3825	0.7332	0.9183
0.0	18.0	4050	0.7402	0.9167
0.0125	19.0	4275	0.7537	0.9183
0.0043	20.0	4500	0.7046	0.9233
0.0	21.0	4725	0.7969	0.9067
0.0052	22.0	4950	0.7422	0.9217
0.0	23.0	5175	0.7848	0.9083
0.0005	24.0	5400	0.8567	0.9133
0.0301	25.0	5625	0.7666	0.9267
0.0039	26.0	5850	0.7330	0.9217
0.0001	27.0	6075	0.7599	0.9233
0.0002	28.0	6300	0.8806	0.9083
0.0061	29.0	6525	0.7763	0.92
0.004	30.0	6750	0.8161	0.9117
0.0022	31.0	6975	0.8369	0.9217
0.0	32.0	7200	0.7564	0.9283
0.0005	33.0	7425	0.7872	0.9283
0.0001	34.0	7650	0.8316	0.9183
0.0001	35.0	7875	0.8563	0.915
0.0	36.0	8100	0.7792	0.9267
0.0	37.0	8325	0.8267	0.9217
0.0	38.0	8550	0.8036	0.9233
0.0003	39.0	8775	0.8623	0.9217
0.0	40.0	9000	0.8053	0.9167
0.0004	41.0	9225	0.7926	0.93
0.0	42.0	9450	0.7751	0.9267
0.0	43.0	9675	0.8025	0.9267
0.0	44.0	9900	0.7634	0.925
0.0	45.0	10125	0.7768	0.9283
0.0175	46.0	10350	0.8501	0.92
0.0025	47.0	10575	0.7670	0.93
0.0003	48.0	10800	0.7741	0.925
0.0	49.0	11025	0.7719	0.9283
0.0001	50.0	11250	0.7714	0.93

Framework versions

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