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: 0.5141
Accuracy: 0.8063

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
1.073	1.0	376	1.0746	0.4391
1.0668	2.0	752	1.0543	0.4775
1.0508	3.0	1128	1.0329	0.5326
1.0204	4.0	1504	1.0085	0.5676
0.9684	5.0	1880	0.9803	0.6110
0.9344	6.0	2256	0.9504	0.6344
0.9026	7.0	2632	0.9203	0.6511
0.9041	8.0	3008	0.8901	0.6694
0.8974	9.0	3384	0.8608	0.6828
0.8237	10.0	3760	0.8327	0.6945
0.7953	11.0	4136	0.8062	0.6962
0.7905	12.0	4512	0.7820	0.7028
0.7556	13.0	4888	0.7593	0.7129
0.7345	14.0	5264	0.7385	0.7262
0.7177	15.0	5640	0.7192	0.7346
0.6509	16.0	6016	0.7013	0.7412
0.6656	17.0	6392	0.6845	0.7479
0.6821	18.0	6768	0.6693	0.7496
0.6446	19.0	7144	0.6551	0.7546
0.6223	20.0	7520	0.6422	0.7629
0.6135	21.0	7896	0.6303	0.7679
0.5755	22.0	8272	0.6195	0.7713
0.5973	23.0	8648	0.6095	0.7730
0.6156	24.0	9024	0.6004	0.7746
0.6003	25.0	9400	0.5920	0.7780
0.5642	26.0	9776	0.5842	0.7796
0.5302	27.0	10152	0.5770	0.7813
0.5137	28.0	10528	0.5704	0.7863
0.5415	29.0	10904	0.5643	0.7880
0.5224	30.0	11280	0.5587	0.7880
0.5509	31.0	11656	0.5535	0.7930
0.5721	32.0	12032	0.5488	0.7913
0.5247	33.0	12408	0.5445	0.7930
0.4916	34.0	12784	0.5406	0.7963
0.5191	35.0	13160	0.5369	0.7980
0.5171	36.0	13536	0.5337	0.8013
0.4685	37.0	13912	0.5307	0.8063
0.5439	38.0	14288	0.5280	0.8063
0.4686	39.0	14664	0.5255	0.8080
0.4898	40.0	15040	0.5234	0.8063
0.509	41.0	15416	0.5214	0.8063
0.4464	42.0	15792	0.5198	0.8063
0.4635	43.0	16168	0.5183	0.8063
0.5321	44.0	16544	0.5171	0.8063
0.4939	45.0	16920	0.5161	0.8063
0.4922	46.0	17296	0.5153	0.8063
0.4738	47.0	17672	0.5147	0.8063
0.5216	48.0	18048	0.5143	0.8063
0.4726	49.0	18424	0.5141	0.8063
0.4528	50.0	18800	0.5141	0.8063

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_5x_deit_base_sgd_0001_fold1

smids_5x_deit_base_sgd_0001_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_5x_deit_base_sgd_0001_fold1