metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_5x_beit_base_rms_0001_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: 0.905

smids_5x_beit_base_rms_0001_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: 1.0211
Accuracy: 0.905

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: 0.0001
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
0.3069	1.0	375	0.3920	0.8783
0.2324	2.0	750	0.2994	0.8883
0.2111	3.0	1125	0.4025	0.8883
0.1469	4.0	1500	0.4730	0.8933
0.1348	5.0	1875	0.5021	0.8667
0.1083	6.0	2250	0.5547	0.875
0.074	7.0	2625	0.8070	0.865
0.0264	8.0	3000	0.6666	0.8817
0.0566	9.0	3375	0.5845	0.8817
0.0498	10.0	3750	0.6165	0.8717
0.0562	11.0	4125	0.6616	0.9017
0.0419	12.0	4500	0.5768	0.9
0.042	13.0	4875	0.6169	0.89
0.0428	14.0	5250	0.6006	0.8967
0.065	15.0	5625	0.6268	0.875
0.0169	16.0	6000	0.6699	0.9017
0.0201	17.0	6375	0.7528	0.8933
0.0241	18.0	6750	0.6629	0.89
0.0027	19.0	7125	0.6425	0.9017
0.0221	20.0	7500	0.6769	0.8917
0.0018	21.0	7875	0.8187	0.8867
0.0303	22.0	8250	0.6653	0.8933
0.0112	23.0	8625	0.7146	0.88
0.002	24.0	9000	0.7847	0.8983
0.0001	25.0	9375	0.7706	0.8933
0.001	26.0	9750	0.8815	0.8933
0.0089	27.0	10125	0.9055	0.8833
0.0011	28.0	10500	0.8721	0.8883
0.0031	29.0	10875	0.8475	0.8917
0.0096	30.0	11250	0.7033	0.9067
0.0084	31.0	11625	0.7845	0.9033
0.0003	32.0	12000	0.8241	0.8967
0.0002	33.0	12375	0.7939	0.905
0.0	34.0	12750	0.8492	0.9117
0.0039	35.0	13125	0.7919	0.905
0.0	36.0	13500	0.9132	0.9017
0.001	37.0	13875	0.9026	0.91
0.0073	38.0	14250	0.9238	0.9
0.0	39.0	14625	1.0700	0.895
0.0	40.0	15000	1.0185	0.9083
0.0	41.0	15375	1.0113	0.9
0.0	42.0	15750	0.9606	0.9033
0.0	43.0	16125	1.0356	0.9
0.0	44.0	16500	1.0382	0.9017
0.0	45.0	16875	1.0522	0.9
0.0	46.0	17250	1.0733	0.8967
0.0031	47.0	17625	1.0418	0.9017
0.0	48.0	18000	1.0244	0.9067
0.0	49.0	18375	1.0206	0.905
0.0019	50.0	18750	1.0211	0.905

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2