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

Loss: 1.0780
Accuracy: 0.5854

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	5.8408	0.2683
4.7719	2.0	12	1.7477	0.2683
4.7719	3.0	18	1.7384	0.2683
1.932	4.0	24	1.4924	0.2439
1.6238	5.0	30	1.5127	0.2439
1.6238	6.0	36	1.7015	0.2683
1.5494	7.0	42	1.5012	0.2439
1.5494	8.0	48	1.4936	0.2683
1.5044	9.0	54	1.4046	0.2683
1.5179	10.0	60	1.4005	0.2439
1.5179	11.0	66	1.4179	0.2683
1.475	12.0	72	1.4436	0.2439
1.475	13.0	78	1.6356	0.2439
1.4371	14.0	84	1.3958	0.2683
1.4353	15.0	90	1.3814	0.2439
1.4353	16.0	96	1.5489	0.2439
1.4229	17.0	102	1.4209	0.2439
1.4229	18.0	108	1.3777	0.2439
1.4337	19.0	114	1.3611	0.3171
1.399	20.0	120	1.3904	0.4146
1.399	21.0	126	1.3106	0.3415
1.3792	22.0	132	1.5271	0.3171
1.3792	23.0	138	1.4354	0.3171
1.353	24.0	144	1.2465	0.3171
1.3278	25.0	150	1.4779	0.2683
1.3278	26.0	156	1.1238	0.6585
1.2815	27.0	162	1.0700	0.4878
1.2815	28.0	168	1.4309	0.2927
1.2766	29.0	174	1.1073	0.5854
1.2458	30.0	180	1.0518	0.5366
1.2458	31.0	186	1.0678	0.5366
1.196	32.0	192	1.0365	0.5122
1.196	33.0	198	1.0762	0.4878
1.1298	34.0	204	1.1843	0.4390
1.1053	35.0	210	0.9867	0.5610
1.1053	36.0	216	0.9844	0.5854
1.0778	37.0	222	1.2314	0.4878
1.0778	38.0	228	0.9827	0.5854
1.0269	39.0	234	1.0882	0.5854
0.9486	40.0	240	1.0901	0.5854
0.9486	41.0	246	1.0899	0.5854
0.9443	42.0	252	1.0780	0.5854
0.9443	43.0	258	1.0780	0.5854
0.8824	44.0	264	1.0780	0.5854
0.8971	45.0	270	1.0780	0.5854
0.8971	46.0	276	1.0780	0.5854
0.8963	47.0	282	1.0780	0.5854
0.8963	48.0	288	1.0780	0.5854
0.9026	49.0	294	1.0780	0.5854
0.9008	50.0	300	1.0780	0.5854

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

hkivancoral/hushem_1x_deit_small_rms_001_fold5

hushem_1x_deit_small_rms_001_fold5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_1x_deit_small_rms_001_fold5