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_fold4
    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: 0.6552845528455284

Boya1_RMSProp_1-e5_20Epoch_09Momentum_Beit-base-patch16_fold4

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: 3.1034
Accuracy: 0.6553

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
1.1966	1.0	923	1.1276	0.5995
1.0326	2.0	1846	1.0374	0.6360
0.6666	3.0	2769	1.0904	0.6415
0.4288	4.0	3692	1.2437	0.6474
0.2209	5.0	4615	1.4346	0.6404
0.1143	6.0	5538	1.6952	0.6442
0.1733	7.0	6461	1.9268	0.6547
0.0409	8.0	7384	2.2016	0.6518
0.0999	9.0	8307	2.4623	0.6485
0.0104	10.0	9230	2.6094	0.6534
0.0424	11.0	10153	2.7340	0.6558
0.0463	12.0	11076	2.8098	0.6599
0.0005	13.0	11999	2.9333	0.6553
0.0144	14.0	12922	2.9705	0.6531
0.0002	15.0	13845	3.0020	0.6566
0.0157	16.0	14768	3.0642	0.6588
0.0005	17.0	15691	3.0529	0.6575
0.0029	18.0	16614	3.0952	0.6558
0.0024	19.0	17537	3.0982	0.6572
0.0001	20.0	18460	3.1034	0.6553

Framework versions

Transformers 4.35.0
Pytorch 2.1.0
Datasets 2.14.6
Tokenizers 0.14.1