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_sgd_001_fold2
    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: 0.8635607321131448

smids_1x_beit_base_sgd_001_fold2

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: 0.3600
Accuracy: 0.8636

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
1.0974	1.0	75	1.0410	0.4309
1.0056	2.0	150	0.9317	0.5424
0.8916	3.0	225	0.8446	0.5890
0.8349	4.0	300	0.7646	0.6473
0.7414	5.0	375	0.6971	0.7022
0.6784	6.0	450	0.6337	0.7571
0.7121	7.0	525	0.5878	0.7754
0.6558	8.0	600	0.5609	0.7787
0.6317	9.0	675	0.5312	0.8087
0.6518	10.0	750	0.5083	0.8136
0.5234	11.0	825	0.4912	0.8203
0.5342	12.0	900	0.4745	0.8236
0.5263	13.0	975	0.4621	0.8186
0.4728	14.0	1050	0.4552	0.8220
0.4696	15.0	1125	0.4418	0.8336
0.4875	16.0	1200	0.4387	0.8286
0.4719	17.0	1275	0.4281	0.8303
0.4659	18.0	1350	0.4174	0.8386
0.4608	19.0	1425	0.4192	0.8319
0.4678	20.0	1500	0.4085	0.8486
0.4982	21.0	1575	0.4035	0.8519
0.4136	22.0	1650	0.3939	0.8552
0.4205	23.0	1725	0.3934	0.8502
0.45	24.0	1800	0.3901	0.8519
0.4234	25.0	1875	0.3886	0.8536
0.3928	26.0	1950	0.3881	0.8486
0.4665	27.0	2025	0.3799	0.8636
0.416	28.0	2100	0.3843	0.8519
0.386	29.0	2175	0.3779	0.8619
0.3668	30.0	2250	0.3747	0.8552
0.3858	31.0	2325	0.3781	0.8602
0.3907	32.0	2400	0.3740	0.8602
0.4156	33.0	2475	0.3701	0.8619
0.4094	34.0	2550	0.3679	0.8619
0.3888	35.0	2625	0.3683	0.8586
0.3956	36.0	2700	0.3659	0.8636
0.3691	37.0	2775	0.3660	0.8636
0.4229	38.0	2850	0.3645	0.8669
0.308	39.0	2925	0.3651	0.8636
0.382	40.0	3000	0.3644	0.8602
0.4135	41.0	3075	0.3618	0.8652
0.3791	42.0	3150	0.3629	0.8636
0.3729	43.0	3225	0.3622	0.8586
0.3719	44.0	3300	0.3628	0.8669
0.3571	45.0	3375	0.3604	0.8636
0.3721	46.0	3450	0.3598	0.8652
0.381	47.0	3525	0.3604	0.8636
0.3882	48.0	3600	0.3603	0.8636
0.3411	49.0	3675	0.3601	0.8636
0.3299	50.0	3750	0.3600	0.8636

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0