smids_5x_deit_base_rms_0001_fold1

This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.8795
• Accuracy: 0.9082

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: 32
• eval_batch_size: 32
• 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.232	1.0	376	0.3558	0.8531
0.1372	2.0	752	0.3215	0.8898
0.1203	3.0	1128	0.3886	0.8881
0.0697	4.0	1504	0.4340	0.8765
0.0324	5.0	1880	0.5132	0.8865
0.0728	6.0	2256	0.5310	0.8881
0.0495	7.0	2632	0.6186	0.8781
0.0797	8.0	3008	0.5758	0.8881
0.0121	9.0	3384	0.5420	0.8998
0.0399	10.0	3760	0.6888	0.8815
0.0293	11.0	4136	0.5816	0.9065
0.0382	12.0	4512	0.6430	0.8781
0.0148	13.0	4888	0.8464	0.8781
0.0249	14.0	5264	0.5972	0.8848
0.0008	15.0	5640	0.6413	0.8965
0.0409	16.0	6016	0.7158	0.8798
0.0202	17.0	6392	0.7167	0.8815
0.0253	18.0	6768	0.6005	0.8998
0.0002	19.0	7144	0.6775	0.8948
0.0275	20.0	7520	0.7685	0.8948
0.0272	21.0	7896	0.6847	0.8965
0.0003	22.0	8272	0.7613	0.8915
0.0008	23.0	8648	0.7342	0.8865
0.0001	24.0	9024	0.7590	0.8698
0.0	25.0	9400	0.7885	0.8898
0.0032	26.0	9776	0.6867	0.8982
0.0	27.0	10152	0.7507	0.8948
0.0003	28.0	10528	0.7142	0.8848
0.0043	29.0	10904	0.6904	0.8881
0.0066	30.0	11280	0.7736	0.8898
0.0007	31.0	11656	0.7358	0.8998
0.0006	32.0	12032	1.0875	0.8598
0.0	33.0	12408	0.7340	0.9015
0.0	34.0	12784	0.7139	0.8982
0.0	35.0	13160	0.7525	0.9115
0.0002	36.0	13536	0.7504	0.8982
0.0	37.0	13912	0.8006	0.8982
0.0	38.0	14288	0.7615	0.9015
0.0	39.0	14664	0.7609	0.9115
0.0	40.0	15040	0.8059	0.9015
0.0	41.0	15416	0.8037	0.9032
0.0	42.0	15792	0.8697	0.9048
0.0	43.0	16168	0.8414	0.9115
0.0	44.0	16544	0.8687	0.9098
0.0	45.0	16920	0.8833	0.9065
0.0031	46.0	17296	0.8963	0.9065
0.0	47.0	17672	0.8765	0.9082
0.0	48.0	18048	0.8724	0.9082
0.0	49.0	18424	0.8783	0.9082
0.0025	50.0	18800	0.8795	0.9082

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2