metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224-pt22k-ft22k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: Boya1_RMSProp_1-e5_20Epoch_09Momentum_Beit-base-patch16_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: 0.6555735930735931

Boya1_RMSProp_1-e5_20Epoch_09Momentum_Beit-base-patch16_fold3

This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 3.0039
Accuracy: 0.6556

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: 16
eval_batch_size: 16
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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1079	1.0	923	1.1521	0.6025
0.921	2.0	1846	1.0560	0.6326
0.6516	3.0	2769	1.0430	0.6442
0.3542	4.0	3692	1.2268	0.6399
0.2629	5.0	4615	1.3655	0.6496
0.2053	6.0	5538	1.6123	0.6415
0.0506	7.0	6461	1.9244	0.6383
0.0801	8.0	7384	2.1949	0.6334
0.079	9.0	8307	2.3005	0.6437
0.0549	10.0	9230	2.5668	0.6442
0.0012	11.0	10153	2.6623	0.6445
0.0562	12.0	11076	2.7298	0.6496
0.0187	13.0	11999	2.7730	0.6537
0.0405	14.0	12922	2.8958	0.6483
0.0037	15.0	13845	2.9177	0.6564
0.0009	16.0	14768	2.9650	0.6572
0.0001	17.0	15691	3.0071	0.6548
0.0009	18.0	16614	2.9743	0.6585
0.0024	19.0	17537	2.9839	0.6572
0.0003	20.0	18460	3.0039	0.6556

Framework versions

Transformers 4.35.0
Pytorch 2.1.0
Datasets 2.14.6
Tokenizers 0.14.1