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_00001_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: 0.9083333333333333

smids_3x_beit_base_adamax_00001_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: 0.7471
Accuracy: 0.9083

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
0.342	1.0	225	0.2883	0.8833
0.2244	2.0	450	0.2463	0.9083
0.1906	3.0	675	0.2773	0.905
0.095	4.0	900	0.2495	0.9033
0.0664	5.0	1125	0.2917	0.9033
0.0453	6.0	1350	0.2947	0.9067
0.0969	7.0	1575	0.3330	0.9117
0.0514	8.0	1800	0.3802	0.9117
0.1005	9.0	2025	0.4648	0.9083
0.0165	10.0	2250	0.4638	0.895
0.0269	11.0	2475	0.5851	0.8883
0.0652	12.0	2700	0.5785	0.8917
0.081	13.0	2925	0.5841	0.8983
0.0377	14.0	3150	0.5798	0.905
0.03	15.0	3375	0.6329	0.89
0.0242	16.0	3600	0.5810	0.895
0.0266	17.0	3825	0.5680	0.9167
0.0329	18.0	4050	0.5701	0.9183
0.0582	19.0	4275	0.6235	0.9083
0.0028	20.0	4500	0.6525	0.905
0.0003	21.0	4725	0.6853	0.9067
0.022	22.0	4950	0.6544	0.905
0.0045	23.0	5175	0.6759	0.9033
0.0351	24.0	5400	0.6446	0.9117
0.0333	25.0	5625	0.6670	0.9083
0.0143	26.0	5850	0.6937	0.91
0.008	27.0	6075	0.6634	0.9083
0.0281	28.0	6300	0.6712	0.9133
0.0182	29.0	6525	0.6482	0.9083
0.0111	30.0	6750	0.7204	0.905
0.0002	31.0	6975	0.7191	0.9067
0.0002	32.0	7200	0.7356	0.9
0.0144	33.0	7425	0.6757	0.905
0.0023	34.0	7650	0.6796	0.9067
0.0353	35.0	7875	0.7115	0.905
0.0002	36.0	8100	0.6973	0.9117
0.0038	37.0	8325	0.7036	0.9067
0.0007	38.0	8550	0.7201	0.91
0.0032	39.0	8775	0.7280	0.91
0.0003	40.0	9000	0.7519	0.9067
0.0013	41.0	9225	0.7411	0.8983
0.0003	42.0	9450	0.7547	0.91
0.0145	43.0	9675	0.7708	0.905
0.0125	44.0	9900	0.7613	0.905
0.001	45.0	10125	0.7388	0.91
0.0492	46.0	10350	0.7435	0.9033
0.0003	47.0	10575	0.7445	0.9083
0.002	48.0	10800	0.7444	0.9083
0.0063	49.0	11025	0.7475	0.91
0.0048	50.0	11250	0.7471	0.9083

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2