Boya1_RMSProp_1-e5_20Epoch_09Momentum_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: 3.0645
• Accuracy: 0.6533

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: 0.0001
• 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
1.1014	1.0	924	1.1155	0.6131
0.917	2.0	1848	1.0767	0.6242
0.7533	3.0	2772	1.0565	0.6473
0.493	4.0	3696	1.1952	0.6530
0.482	5.0	4620	1.3688	0.6473
0.1989	6.0	5544	1.6284	0.6435
0.1622	7.0	6468	2.0114	0.6373
0.0666	8.0	7392	2.2124	0.6541
0.0417	9.0	8316	2.4424	0.6389
0.0196	10.0	9240	2.5614	0.6397
0.0323	11.0	10164	2.8070	0.6443
0.0014	12.0	11088	2.8503	0.6506
0.001	13.0	12012	2.8885	0.6497
0.0706	14.0	12936	3.0224	0.6462
0.0003	15.0	13860	3.0064	0.6465
0.0013	16.0	14784	3.0115	0.6552
0.0316	17.0	15708	3.0514	0.6563
0.0002	18.0	16632	3.0348	0.6568
0.0	19.0	17556	3.0737	0.6508
0.0494	20.0	18480	3.0645	0.6533

Framework versions

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