Boya1_3Class_RMSprop_1-e5_20Epoch_Beit-base-patch16_fold2

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: 1.7644
• Accuracy: 0.8232

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
0.4974	1.0	923	0.5529	0.7873
0.4125	2.0	1846	0.4400	0.8268
0.2808	3.0	2769	0.5196	0.8368
0.1527	4.0	3692	0.5655	0.8330
0.1865	5.0	4615	0.8608	0.8173
0.0741	6.0	5538	1.0784	0.8203
0.0819	7.0	6461	1.3435	0.8214
0.0017	8.0	7384	1.5429	0.8286
0.1022	9.0	8307	1.5116	0.8186
0.0532	10.0	9230	1.6291	0.8216
0.062	11.0	10153	1.6075	0.8227
0.0034	12.0	11076	1.6033	0.8278
0.0602	13.0	11999	1.6450	0.83
0.0052	14.0	12922	1.7169	0.8241
0.0005	15.0	13845	1.7681	0.8241
0.0002	16.0	14768	1.7020	0.8308
0.0	17.0	15691	1.7773	0.8286
0.0465	18.0	16614	1.7601	0.8249
0.0	19.0	17537	1.7672	0.8276
0.0006	20.0	18460	1.7644	0.8232

Framework versions

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