Boya1_SGD_1-e3_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: 1.7764
• Accuracy: 0.4291

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
2.4699	1.0	923	2.4335	0.2140
2.3722	2.0	1846	2.2936	0.2643
2.248	3.0	2769	2.1974	0.2884
2.1383	4.0	3692	2.1137	0.3217
2.0587	5.0	4615	2.0507	0.3404
2.0732	6.0	5538	2.0041	0.3501
2.0202	7.0	6461	1.9644	0.3693
2.0361	8.0	7384	1.9326	0.3764
1.9433	9.0	8307	1.8973	0.3926
1.9102	10.0	9230	1.8743	0.3877
1.9324	11.0	10153	1.8539	0.3950
1.943	12.0	11076	1.8379	0.4061
1.8903	13.0	11999	1.8194	0.4113
1.8833	14.0	12922	1.8092	0.4172
1.8296	15.0	13845	1.8007	0.4205
1.8152	16.0	14768	1.7910	0.4256
2.0261	17.0	15691	1.7844	0.4283
1.8132	18.0	16614	1.7806	0.4283
1.8172	19.0	17537	1.7782	0.4294
1.867	20.0	18460	1.7764	0.4291

Framework versions

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