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

Loss: 0.3792
Accuracy: 0.845

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: 0.001
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
0.9374	1.0	225	0.9137	0.535
0.637	2.0	450	0.7038	0.6933
0.528	3.0	675	0.5838	0.745
0.4807	4.0	900	0.5174	0.7967
0.4652	5.0	1125	0.4857	0.8033
0.3253	6.0	1350	0.4581	0.8083
0.3966	7.0	1575	0.4373	0.8233
0.4286	8.0	1800	0.4298	0.81
0.368	9.0	2025	0.4134	0.8233
0.3027	10.0	2250	0.4061	0.8417
0.3611	11.0	2475	0.4002	0.8233
0.3327	12.0	2700	0.3930	0.8483
0.2879	13.0	2925	0.3875	0.835
0.2362	14.0	3150	0.3833	0.845
0.2472	15.0	3375	0.3854	0.85
0.2412	16.0	3600	0.3772	0.8483
0.2474	17.0	3825	0.3765	0.8433
0.2597	18.0	4050	0.3736	0.8467
0.2836	19.0	4275	0.3755	0.85
0.19	20.0	4500	0.3722	0.8467
0.2408	21.0	4725	0.3732	0.8483
0.2395	22.0	4950	0.3728	0.8433
0.2175	23.0	5175	0.3773	0.8417
0.2295	24.0	5400	0.3700	0.8517
0.2109	25.0	5625	0.3716	0.8467
0.1922	26.0	5850	0.3714	0.8517
0.1883	27.0	6075	0.3724	0.8517
0.1939	28.0	6300	0.3739	0.85
0.1633	29.0	6525	0.3736	0.8567
0.1934	30.0	6750	0.3747	0.8533
0.1648	31.0	6975	0.3737	0.8467
0.1378	32.0	7200	0.3775	0.845
0.2214	33.0	7425	0.3749	0.85
0.1912	34.0	7650	0.3749	0.845
0.1512	35.0	7875	0.3732	0.8483
0.2352	36.0	8100	0.3763	0.845
0.2012	37.0	8325	0.3753	0.845
0.1968	38.0	8550	0.3756	0.85
0.1845	39.0	8775	0.3769	0.8483
0.215	40.0	9000	0.3781	0.8483
0.1756	41.0	9225	0.3779	0.8483
0.1667	42.0	9450	0.3792	0.8467
0.1672	43.0	9675	0.3791	0.8467
0.2264	44.0	9900	0.3791	0.8467
0.1992	45.0	10125	0.3783	0.8483
0.1804	46.0	10350	0.3789	0.8483
0.177	47.0	10575	0.3795	0.8483
0.2026	48.0	10800	0.3789	0.8467
0.1973	49.0	11025	0.3793	0.8483
0.1685	50.0	11250	0.3792	0.845

Framework versions

Transformers 4.32.1
Pytorch 2.1.1+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_3x_deit_tiny_sgd_001_fold4

smids_3x_deit_tiny_sgd_001_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_3x_deit_tiny_sgd_001_fold4