Boya1_3Class_RMSprop_1-e5_20Epoch_Beit-base-patch16_fold1

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: 1.7955
• Accuracy: 0.8260

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: 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
0.4439	1.0	924	0.4590	0.8091
0.3875	2.0	1848	0.4469	0.8227
0.2939	3.0	2772	0.5412	0.8154
0.1247	4.0	3696	0.6692	0.8213
0.1513	5.0	4620	0.8256	0.8227
0.1409	6.0	5544	1.1386	0.8181
0.0278	7.0	6468	1.3459	0.8189
0.013	8.0	7392	1.5383	0.8175
0.0037	9.0	8316	1.5542	0.8254
0.0119	10.0	9240	1.6982	0.8178
0.0008	11.0	10164	1.7834	0.8178
0.0799	12.0	11088	1.6908	0.8230
0.0845	13.0	12012	1.7310	0.8200
0.0588	14.0	12936	1.7389	0.8235
0.0004	15.0	13860	1.8086	0.8246
0.0004	16.0	14784	1.8040	0.8262
0.0009	17.0	15708	1.7272	0.8243
0.0021	18.0	16632	1.7738	0.8238
0.0559	19.0	17556	1.8013	0.8254
0.0	20.0	18480	1.7955	0.8260

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0
• Datasets 2.14.6
• Tokenizers 0.14.1