smids_5x_deit_base_rms_00001_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: 0.7394
• Accuracy: 0.9098

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: 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
0.1851	1.0	376	0.2437	0.8998
0.1172	2.0	752	0.2452	0.9065
0.078	3.0	1128	0.3051	0.9032
0.0038	4.0	1504	0.3755	0.9149
0.0013	5.0	1880	0.4803	0.9048
0.0105	6.0	2256	0.5332	0.8948
0.0008	7.0	2632	0.5088	0.9015
0.0133	8.0	3008	0.5291	0.9149
0.0349	9.0	3384	0.6409	0.9048
0.0001	10.0	3760	0.6103	0.8998
0.0039	11.0	4136	0.6150	0.9065
0.0005	12.0	4512	0.7088	0.8948
0.0	13.0	4888	0.6260	0.8965
0.0213	14.0	5264	0.6512	0.9065
0.0001	15.0	5640	0.6705	0.8965
0.0	16.0	6016	0.6402	0.9098
0.0	17.0	6392	0.7356	0.9015
0.0	18.0	6768	0.6866	0.8932
0.0035	19.0	7144	0.7211	0.8982
0.0098	20.0	7520	0.7353	0.8982
0.0	21.0	7896	0.7497	0.9032
0.0001	22.0	8272	0.7881	0.9015
0.0	23.0	8648	0.7075	0.9065
0.0	24.0	9024	0.8340	0.8948
0.0	25.0	9400	0.8050	0.9032
0.0028	26.0	9776	0.7114	0.8982
0.0	27.0	10152	0.6978	0.9048
0.0	28.0	10528	0.7140	0.9032
0.0032	29.0	10904	0.6871	0.9098
0.0032	30.0	11280	0.7619	0.9032
0.0	31.0	11656	0.7031	0.9082
0.0	32.0	12032	0.7126	0.9082
0.0	33.0	12408	0.7501	0.9082
0.0	34.0	12784	0.7212	0.9149
0.0	35.0	13160	0.7433	0.9098
0.0	36.0	13536	0.7330	0.9132
0.0	37.0	13912	0.7531	0.9065
0.0	38.0	14288	0.7193	0.9098
0.0	39.0	14664	0.7113	0.9132
0.0	40.0	15040	0.7484	0.9149
0.0	41.0	15416	0.7482	0.9132
0.0	42.0	15792	0.7262	0.9132
0.0	43.0	16168	0.7432	0.9149
0.0	44.0	16544	0.7418	0.9149
0.0	45.0	16920	0.7350	0.9115
0.0025	46.0	17296	0.7363	0.9115
0.0	47.0	17672	0.7386	0.9098
0.0	48.0	18048	0.7382	0.9098
0.0	49.0	18424	0.7382	0.9098
0.0023	50.0	18800	0.7394	0.9098

Framework versions

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