Boya1_RMSProp_1-e5_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: 3.1823
• Accuracy: 0.6499

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
1.1635	1.0	924	1.1860	0.5948
1.0619	2.0	1848	1.0310	0.6455
0.646	3.0	2772	1.0620	0.6509
0.3294	4.0	3696	1.2169	0.6599
0.2648	5.0	4620	1.4374	0.6455
0.1957	6.0	5544	1.7164	0.6420
0.131	7.0	6468	2.0272	0.6488
0.0817	8.0	7392	2.2750	0.6447
0.0483	9.0	8316	2.4384	0.6431
0.0451	10.0	9240	2.6186	0.6447
0.0224	11.0	10164	2.7368	0.6463
0.0134	12.0	11088	2.9439	0.6477
0.0023	13.0	12012	2.9691	0.6520
0.0074	14.0	12936	3.0721	0.6450
0.0231	15.0	13860	3.1373	0.6499
0.0004	16.0	14784	3.2089	0.6474
0.0062	17.0	15708	3.1483	0.6493
0.0132	18.0	16632	3.1830	0.6515
0.0034	19.0	17556	3.1843	0.6474
0.0796	20.0	18480	3.1823	0.6499

Framework versions

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