Boya1_SGD_1-e3_20Epoch_09Momentum_Beit-base-patch16_fold5

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: 1.7637
• Accuracy: 0.4277

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
2.3338	1.0	924	2.4489	0.2086
2.3427	2.0	1848	2.3125	0.2517
2.1284	3.0	2772	2.2064	0.2853
2.0324	4.0	3696	2.1236	0.3106
1.929	5.0	4620	2.0514	0.3369
1.9691	6.0	5544	1.9984	0.3537
2.0646	7.0	6468	1.9525	0.3653
1.8686	8.0	7392	1.9172	0.3813
1.972	9.0	8316	1.8843	0.3916
2.0678	10.0	9240	1.8632	0.3973
1.8342	11.0	10164	1.8414	0.3976
1.9641	12.0	11088	1.8250	0.4057
1.6663	13.0	12012	1.8107	0.4093
1.7839	14.0	12936	1.7966	0.4193
1.7724	15.0	13860	1.7857	0.4258
1.7746	16.0	14784	1.7787	0.4245
1.9266	17.0	15708	1.7714	0.4261
1.8612	18.0	16632	1.7673	0.4280
1.7224	19.0	17556	1.7664	0.4291
1.7078	20.0	18480	1.7637	0.4277

Framework versions

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