Boya1_3Class_RMSprop_1-e5_20Epoch_Beit-base-patch16_fold3

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: 1.8476
• Accuracy: 0.8222

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
0.4509	1.0	923	0.4494	0.8149
0.3482	2.0	1846	0.4215	0.8328
0.2766	3.0	2769	0.4845	0.8241
0.1282	4.0	3692	0.6763	0.8333
0.0823	5.0	4615	0.8609	0.8252
0.2362	6.0	5538	1.1571	0.8163
0.0242	7.0	6461	1.3157	0.8203
0.0078	8.0	7384	1.5067	0.8063
0.0045	9.0	8307	1.5694	0.8182
0.0161	10.0	9230	1.6636	0.8168
0.005	11.0	10153	1.7056	0.8185
0.0057	12.0	11076	1.6400	0.8222
0.0001	13.0	11999	1.7600	0.8258
0.0671	14.0	12922	1.8091	0.8241
0.0041	15.0	13845	1.8050	0.8225
0.0	16.0	14768	1.8120	0.8222
0.0556	17.0	15691	1.8242	0.8212
0.0	18.0	16614	1.8578	0.8214
0.0	19.0	17537	1.8441	0.8217
0.0099	20.0	18460	1.8476	0.8222

Framework versions

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