Boya1_3Class_RMSprop_1-e5_20Epoch_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: 1.7877
• Accuracy: 0.8310

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: 1e-05
• 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
0.5804	1.0	924	0.4986	0.8004
0.4299	2.0	1848	0.4370	0.8248
0.2235	3.0	2772	0.4410	0.8446
0.1347	4.0	3696	0.5720	0.8343
0.0488	5.0	4620	0.8207	0.8275
0.2009	6.0	5544	1.0317	0.8329
0.0566	7.0	6468	1.3823	0.8205
0.0733	8.0	7392	1.3466	0.8324
0.0357	9.0	8316	1.3267	0.8362
0.071	10.0	9240	1.5459	0.8264
0.0505	11.0	10164	1.6231	0.8280
0.1165	12.0	11088	1.6016	0.8297
0.0243	13.0	12012	1.7023	0.8351
0.0327	14.0	12936	1.6673	0.8354
0.002	15.0	13860	1.7768	0.8259
0.0008	16.0	14784	1.8057	0.8302
0.0117	17.0	15708	1.8092	0.8253
0.024	18.0	16632	1.7701	0.8324
0.0349	19.0	17556	1.7881	0.8291
0.0001	20.0	18480	1.7877	0.8310

Framework versions

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