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: 1.3415
Accuracy: 0.2439

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
1.4294	1.0	28	1.3731	0.1951
1.4335	2.0	56	1.3715	0.1707
1.422	3.0	84	1.3699	0.1951
1.4098	4.0	112	1.3685	0.1951
1.4327	5.0	140	1.3671	0.1951
1.4151	6.0	168	1.3658	0.1951
1.4318	7.0	196	1.3646	0.1951
1.4306	8.0	224	1.3633	0.1951
1.4139	9.0	252	1.3622	0.1951
1.3993	10.0	280	1.3610	0.1951
1.4169	11.0	308	1.3598	0.1951
1.4153	12.0	336	1.3588	0.1951
1.3944	13.0	364	1.3578	0.2195
1.3902	14.0	392	1.3568	0.2439
1.4112	15.0	420	1.3559	0.2439
1.3995	16.0	448	1.3550	0.2439
1.3975	17.0	476	1.3541	0.2195
1.4069	18.0	504	1.3533	0.2195
1.4187	19.0	532	1.3524	0.2195
1.4025	20.0	560	1.3517	0.2195
1.3945	21.0	588	1.3509	0.2195
1.3823	22.0	616	1.3502	0.2195
1.3849	23.0	644	1.3496	0.2195
1.3949	24.0	672	1.3489	0.2195
1.3838	25.0	700	1.3483	0.2195
1.3842	26.0	728	1.3477	0.2195
1.3834	27.0	756	1.3472	0.2195
1.3887	28.0	784	1.3466	0.2195
1.381	29.0	812	1.3461	0.2195
1.4001	30.0	840	1.3457	0.2439
1.3827	31.0	868	1.3452	0.2439
1.3845	32.0	896	1.3448	0.2439
1.3786	33.0	924	1.3444	0.2439
1.3866	34.0	952	1.3440	0.2439
1.3704	35.0	980	1.3437	0.2439
1.3751	36.0	1008	1.3433	0.2439
1.3701	37.0	1036	1.3431	0.2439
1.3624	38.0	1064	1.3428	0.2439
1.3758	39.0	1092	1.3426	0.2439
1.3768	40.0	1120	1.3423	0.2439
1.3757	41.0	1148	1.3422	0.2439
1.3802	42.0	1176	1.3420	0.2439
1.38	43.0	1204	1.3418	0.2439
1.3821	44.0	1232	1.3417	0.2439
1.3878	45.0	1260	1.3417	0.2439
1.3547	46.0	1288	1.3416	0.2439
1.3794	47.0	1316	1.3416	0.2439
1.3781	48.0	1344	1.3415	0.2439
1.373	49.0	1372	1.3415	0.2439
1.3839	50.0	1400	1.3415	0.2439

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

hkivancoral/hushem_5x_deit_base_sgd_0001_fold5

hushem_5x_deit_base_sgd_0001_fold5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_5x_deit_base_sgd_0001_fold5