Boya1_SGD_1-e3_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: 1.7941
• Accuracy: 0.4141

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: 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
2.4306	1.0	923	2.4407	0.2095
2.409	2.0	1846	2.3053	0.2534
2.2629	3.0	2769	2.2093	0.2808
2.1047	4.0	3692	2.1337	0.3
2.0899	5.0	4615	2.0657	0.3271
2.0152	6.0	5538	2.0140	0.3350
2.1479	7.0	6461	1.9759	0.3439
2.0267	8.0	7384	1.9443	0.3607
2.0062	9.0	8307	1.9180	0.3675
1.9883	10.0	9230	1.8909	0.3770
1.8727	11.0	10153	1.8694	0.3875
1.9236	12.0	11076	1.8511	0.3919
1.9423	13.0	11999	1.8378	0.3981
1.9526	14.0	12922	1.8261	0.3965
1.8178	15.0	13845	1.8139	0.4068
1.9548	16.0	14768	1.8071	0.4041
1.8676	17.0	15691	1.7999	0.4103
1.7727	18.0	16614	1.7976	0.4144
1.7795	19.0	17537	1.7949	0.4141
1.9062	20.0	18460	1.7941	0.4141

Framework versions

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