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_adamax_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: 0.91

smids_1x_beit_base_adamax_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: 0.5920
Accuracy: 0.91

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
0.4085	1.0	75	0.3406	0.8733
0.3125	2.0	150	0.2766	0.905
0.272	3.0	225	0.2526	0.9117
0.2066	4.0	300	0.2426	0.9167
0.1315	5.0	375	0.2415	0.9233
0.1338	6.0	450	0.2667	0.9133
0.095	7.0	525	0.2679	0.9183
0.1144	8.0	600	0.2699	0.9267
0.038	9.0	675	0.2963	0.9183
0.0367	10.0	750	0.3153	0.925
0.0325	11.0	825	0.3378	0.92
0.0172	12.0	900	0.3441	0.9183
0.0285	13.0	975	0.3703	0.9217
0.0132	14.0	1050	0.3979	0.9117
0.0356	15.0	1125	0.3938	0.9167
0.0285	16.0	1200	0.4361	0.9117
0.0435	17.0	1275	0.4564	0.905
0.0412	18.0	1350	0.4606	0.905
0.0106	19.0	1425	0.4449	0.9133
0.0192	20.0	1500	0.4442	0.9167
0.0051	21.0	1575	0.4723	0.9117
0.0266	22.0	1650	0.5052	0.9117
0.0217	23.0	1725	0.4785	0.915
0.0019	24.0	1800	0.5058	0.9117
0.0069	25.0	1875	0.5124	0.91
0.0008	26.0	1950	0.5249	0.9117
0.0081	27.0	2025	0.5029	0.91
0.0213	28.0	2100	0.4919	0.9167
0.0025	29.0	2175	0.5055	0.9167
0.0366	30.0	2250	0.5226	0.9117
0.0192	31.0	2325	0.5652	0.91
0.0012	32.0	2400	0.5128	0.92
0.0191	33.0	2475	0.5580	0.9117
0.0168	34.0	2550	0.5615	0.905
0.0045	35.0	2625	0.5647	0.9133
0.0069	36.0	2700	0.5389	0.91
0.021	37.0	2775	0.5519	0.9133
0.0264	38.0	2850	0.5472	0.9117
0.0403	39.0	2925	0.5693	0.91
0.001	40.0	3000	0.5532	0.91
0.0004	41.0	3075	0.5673	0.9117
0.0344	42.0	3150	0.5624	0.9067
0.0221	43.0	3225	0.5673	0.91
0.0004	44.0	3300	0.5783	0.91
0.0156	45.0	3375	0.5833	0.9083
0.021	46.0	3450	0.5741	0.9117
0.0145	47.0	3525	0.5806	0.91
0.0049	48.0	3600	0.5891	0.91
0.0162	49.0	3675	0.5932	0.9083
0.0336	50.0	3750	0.5920	0.91

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0