Boya1_SGD_1-e3_20Epoch_09Momentum_Beit-base-patch16_fold2

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: 1.8092
• Accuracy: 0.4170

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
2.364	1.0	923	2.4299	0.2108
2.3719	2.0	1846	2.2817	0.2649
2.2408	3.0	2769	2.1860	0.2889
2.1829	4.0	3692	2.1102	0.3143
2.0369	5.0	4615	2.0577	0.3241
2.061	6.0	5538	2.0066	0.3419
1.9167	7.0	6461	1.9797	0.3568
2.0057	8.0	7384	1.9411	0.3673
2.0098	9.0	8307	1.9258	0.3722
1.9046	10.0	9230	1.9019	0.3822
1.862	11.0	10153	1.8785	0.3922
1.8051	12.0	11076	1.8624	0.3973
1.8752	13.0	11999	1.8478	0.3981
1.9831	14.0	12922	1.8389	0.4032
1.8913	15.0	13845	1.8338	0.4051
1.9373	16.0	14768	1.8269	0.4086
1.8457	17.0	15691	1.8202	0.4089
1.7936	18.0	16614	1.8117	0.4159
1.7608	19.0	17537	1.8101	0.4168
1.9672	20.0	18460	1.8092	0.4170

Framework versions

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