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: 1.5885
Accuracy: 0.2889

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
No log	1.0	6	4.1632	0.2444
4.2585	2.0	12	2.5063	0.2444
4.2585	3.0	18	1.7281	0.2444
1.7534	4.0	24	1.3946	0.2444
1.5909	5.0	30	1.5054	0.2444
1.5909	6.0	36	1.6818	0.2444
1.5201	7.0	42	1.5863	0.3556
1.5201	8.0	48	1.5570	0.2667
1.4849	9.0	54	1.5043	0.4667
1.4118	10.0	60	1.4204	0.2444
1.4118	11.0	66	1.4708	0.2667
1.4258	12.0	72	1.4115	0.2444
1.4258	13.0	78	1.5806	0.2667
1.444	14.0	84	1.3600	0.3111
1.4369	15.0	90	1.4011	0.2667
1.4369	16.0	96	1.2994	0.4889
1.4072	17.0	102	1.3804	0.4222
1.4072	18.0	108	2.3179	0.2444
1.3585	19.0	114	1.4391	0.3111
1.3358	20.0	120	2.0579	0.2667
1.3358	21.0	126	1.3519	0.3333
1.432	22.0	132	1.4609	0.2889
1.432	23.0	138	2.1987	0.2444
1.3028	24.0	144	1.5480	0.2444
1.282	25.0	150	1.3898	0.2889
1.282	26.0	156	1.2611	0.2444
1.2714	27.0	162	1.7016	0.2444
1.2714	28.0	168	1.3743	0.2889
1.2632	29.0	174	1.4836	0.3778
1.176	30.0	180	1.3073	0.4
1.176	31.0	186	1.4096	0.2667
1.1646	32.0	192	1.4023	0.4222
1.1646	33.0	198	1.4449	0.4
1.1055	34.0	204	1.6514	0.2889
1.1692	35.0	210	1.4679	0.3111
1.1692	36.0	216	1.6234	0.2667
1.1228	37.0	222	1.6770	0.3333
1.1228	38.0	228	1.5646	0.2667
1.0125	39.0	234	1.5851	0.2889
1.0301	40.0	240	1.5653	0.2889
1.0301	41.0	246	1.5924	0.2667
1.0049	42.0	252	1.5885	0.2889
1.0049	43.0	258	1.5885	0.2889
1.0088	44.0	264	1.5885	0.2889
0.9822	45.0	270	1.5885	0.2889
0.9822	46.0	276	1.5885	0.2889
0.9822	47.0	282	1.5885	0.2889
0.9822	48.0	288	1.5885	0.2889
0.9898	49.0	294	1.5885	0.2889
0.9935	50.0	300	1.5885	0.2889

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_001_fold1

hushem_1x_deit_tiny_rms_001_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_1x_deit_tiny_rms_001_fold1