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_1x_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: 0.92

smids_1x_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: 0.6179
• Accuracy: 0.92

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
0.378	1.0	75	0.2655	0.905
0.1995	2.0	150	0.2472	0.9067
0.1269	3.0	225	0.2601	0.9133
0.0982	4.0	300	0.2718	0.9183
0.0334	5.0	375	0.3064	0.9183
0.0325	6.0	450	0.3593	0.9017
0.0122	7.0	525	0.4158	0.9133
0.0276	8.0	600	0.3999	0.915
0.0023	9.0	675	0.4376	0.91
0.0029	10.0	750	0.4955	0.91
0.0282	11.0	825	0.4886	0.9133
0.0074	12.0	900	0.4903	0.9083
0.0119	13.0	975	0.4968	0.9183
0.0151	14.0	1050	0.4966	0.9067
0.0139	15.0	1125	0.4573	0.9267
0.0049	16.0	1200	0.4797	0.9267
0.0357	17.0	1275	0.4808	0.9317
0.0195	18.0	1350	0.5297	0.9133
0.0164	19.0	1425	0.5446	0.9233
0.0136	20.0	1500	0.5630	0.915
0.0002	21.0	1575	0.6196	0.9083
0.0053	22.0	1650	0.5529	0.915
0.002	23.0	1725	0.5621	0.9183
0.0001	24.0	1800	0.5333	0.9233
0.0008	25.0	1875	0.5371	0.9217
0.0014	26.0	1950	0.5172	0.93
0.0001	27.0	2025	0.5437	0.9233
0.0001	28.0	2100	0.5344	0.9283
0.0001	29.0	2175	0.5536	0.9183
0.0075	30.0	2250	0.6086	0.9083
0.0046	31.0	2325	0.5570	0.9133
0.0077	32.0	2400	0.6038	0.915
0.0016	33.0	2475	0.6324	0.9133
0.0004	34.0	2550	0.5847	0.9217
0.0039	35.0	2625	0.6482	0.9183
0.0029	36.0	2700	0.6146	0.9267
0.0076	37.0	2775	0.5750	0.9217
0.0017	38.0	2850	0.5846	0.9233
0.0	39.0	2925	0.5952	0.9233
0.0018	40.0	3000	0.6016	0.9217
0.0	41.0	3075	0.6081	0.9267
0.0026	42.0	3150	0.6036	0.9233
0.0001	43.0	3225	0.6419	0.915
0.0	44.0	3300	0.6346	0.915
0.0	45.0	3375	0.6400	0.915
0.0001	46.0	3450	0.6220	0.9233
0.0039	47.0	3525	0.6179	0.9233
0.0001	48.0	3600	0.6159	0.9183
0.0	49.0	3675	0.6170	0.92
0.0	50.0	3750	0.6179	0.92

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0