smids_5x_deit_small_rms_0001_fold1

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

• Loss: 0.9277
• Accuracy: 0.9048

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
0.2576	1.0	376	0.2886	0.8915
0.132	2.0	752	0.3675	0.8881
0.153	3.0	1128	0.3722	0.8815
0.1012	4.0	1504	0.5411	0.8715
0.0774	5.0	1880	0.4743	0.8881
0.0966	6.0	2256	0.5187	0.8831
0.02	7.0	2632	0.7637	0.8548
0.0255	8.0	3008	0.5858	0.8982
0.0535	9.0	3384	0.7179	0.8798
0.0051	10.0	3760	0.4830	0.9132
0.0623	11.0	4136	0.6803	0.8898
0.032	12.0	4512	0.6393	0.8831
0.0049	13.0	4888	0.6430	0.8965
0.0375	14.0	5264	0.6697	0.8948
0.0305	15.0	5640	0.4958	0.9165
0.0041	16.0	6016	0.6462	0.8965
0.0225	17.0	6392	0.6064	0.9065
0.0015	18.0	6768	0.7328	0.8865
0.0129	19.0	7144	0.6712	0.8848
0.0072	20.0	7520	0.7644	0.8881
0.002	21.0	7896	0.6536	0.9065
0.0135	22.0	8272	0.7707	0.8881
0.0245	23.0	8648	0.6111	0.8948
0.0006	24.0	9024	0.7622	0.8881
0.0001	25.0	9400	0.7257	0.9015
0.0065	26.0	9776	0.7266	0.8948
0.0001	27.0	10152	0.7834	0.9082
0.0001	28.0	10528	0.7481	0.9032
0.0047	29.0	10904	0.8083	0.8915
0.0032	30.0	11280	0.7670	0.8948
0.0008	31.0	11656	0.8608	0.8881
0.0001	32.0	12032	0.7792	0.8948
0.0001	33.0	12408	0.8789	0.8932
0.0	34.0	12784	0.7571	0.9015
0.0	35.0	13160	0.7309	0.9115
0.0002	36.0	13536	0.7237	0.9082
0.0	37.0	13912	0.8459	0.9015
0.0	38.0	14288	0.8205	0.9082
0.0	39.0	14664	0.8617	0.9048
0.0	40.0	15040	0.8709	0.8932
0.0	41.0	15416	0.8732	0.8915
0.0	42.0	15792	0.8524	0.8982
0.0	43.0	16168	0.8924	0.9048
0.0	44.0	16544	0.8692	0.8898
0.0	45.0	16920	0.8944	0.9015
0.0031	46.0	17296	0.8984	0.9032
0.0	47.0	17672	0.9119	0.9032
0.0	48.0	18048	0.9192	0.9048
0.0	49.0	18424	0.9260	0.9032
0.0023	50.0	18800	0.9277	0.9048

Framework versions

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