Boya1_3Class_RMSprop_1-e5_20Epoch_Beit-base-patch16_fold4

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: 1.8083
• Accuracy: 0.8233

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
0.3492	1.0	923	0.4516	0.8087
0.3947	2.0	1846	0.4372	0.8144
0.3321	3.0	2769	0.4856	0.8220
0.1372	4.0	3692	0.6093	0.8271
0.2202	5.0	4615	0.8876	0.8184
0.0611	6.0	5538	1.1112	0.8222
0.0654	7.0	6461	1.2516	0.8241
0.0494	8.0	7384	1.5011	0.8209
0.0614	9.0	8307	1.3879	0.8190
0.1723	10.0	9230	1.5852	0.8160
0.0314	11.0	10153	1.7058	0.8209
0.006	12.0	11076	1.7427	0.8233
0.0603	13.0	11999	1.6775	0.8206
0.0734	14.0	12922	1.7302	0.8257
0.0185	15.0	13845	1.7895	0.8236
0.0006	16.0	14768	1.7889	0.8220
0.0006	17.0	15691	1.8447	0.8198
0.0003	18.0	16614	1.8183	0.8184
0.0002	19.0	17537	1.8137	0.8176
0.0	20.0	18460	1.8083	0.8233

Framework versions

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