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: 1.7903
Accuracy: 0.6098

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
No log	1.0	6	1.6663	0.2683
2.1037	2.0	12	1.5022	0.2439
2.1037	3.0	18	1.3886	0.2439
1.5578	4.0	24	1.5306	0.2683
1.3692	5.0	30	1.1860	0.4390
1.3692	6.0	36	1.1738	0.4634
1.2281	7.0	42	1.1634	0.4146
1.2281	8.0	48	1.0062	0.4878
1.0442	9.0	54	1.0814	0.5366
0.7932	10.0	60	1.0549	0.5366
0.7932	11.0	66	1.1757	0.5610
0.3677	12.0	72	1.3513	0.6829
0.3677	13.0	78	1.1722	0.6098
0.2156	14.0	84	1.5096	0.5854
0.0882	15.0	90	1.2491	0.6341
0.0882	16.0	96	1.4974	0.6098
0.0242	17.0	102	1.6715	0.6341
0.0242	18.0	108	1.6860	0.5854
0.0023	19.0	114	1.6856	0.5854
0.0006	20.0	120	1.6918	0.5854
0.0006	21.0	126	1.7001	0.5854
0.0004	22.0	132	1.7120	0.5854
0.0004	23.0	138	1.7178	0.5854
0.0003	24.0	144	1.7236	0.6098
0.0003	25.0	150	1.7313	0.6098
0.0003	26.0	156	1.7370	0.6098
0.0002	27.0	162	1.7449	0.6098
0.0002	28.0	168	1.7492	0.6098
0.0002	29.0	174	1.7547	0.6098
0.0002	30.0	180	1.7601	0.6098
0.0002	31.0	186	1.7659	0.6098
0.0002	32.0	192	1.7694	0.6098
0.0002	33.0	198	1.7734	0.6098
0.0002	34.0	204	1.7771	0.6098
0.0002	35.0	210	1.7802	0.6098
0.0002	36.0	216	1.7829	0.6098
0.0002	37.0	222	1.7850	0.6098
0.0002	38.0	228	1.7868	0.6098
0.0002	39.0	234	1.7883	0.6098
0.0001	40.0	240	1.7895	0.6098
0.0001	41.0	246	1.7900	0.6098
0.0002	42.0	252	1.7903	0.6098
0.0002	43.0	258	1.7903	0.6098
0.0002	44.0	264	1.7903	0.6098
0.0002	45.0	270	1.7903	0.6098
0.0002	46.0	276	1.7903	0.6098
0.0002	47.0	282	1.7903	0.6098
0.0002	48.0	288	1.7903	0.6098
0.0002	49.0	294	1.7903	0.6098
0.0001	50.0	300	1.7903	0.6098

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

hkivancoral/hushem_1x_deit_tiny_rms_0001_fold5

hushem_1x_deit_tiny_rms_0001_fold5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_1x_deit_tiny_rms_0001_fold5