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: 0.8886
Accuracy: 0.6889

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: 1e-05
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	1.2079	0.6
1.2767	2.0	12	1.0689	0.5778
1.2767	3.0	18	0.8710	0.7111
0.496	4.0	24	0.7898	0.7111
0.172	5.0	30	0.8332	0.6889
0.172	6.0	36	1.0763	0.5556
0.0549	7.0	42	0.6935	0.7556
0.0549	8.0	48	0.7853	0.6667
0.0174	9.0	54	0.7910	0.6889
0.0066	10.0	60	0.7721	0.7111
0.0066	11.0	66	0.7433	0.6889
0.0038	12.0	72	0.7425	0.6889
0.0038	13.0	78	0.7897	0.6667
0.003	14.0	84	0.8070	0.6889
0.0022	15.0	90	0.8283	0.6889
0.0022	16.0	96	0.8010	0.6889
0.0019	17.0	102	0.8154	0.6889
0.0019	18.0	108	0.8316	0.6889
0.0016	19.0	114	0.8425	0.6889
0.0014	20.0	120	0.8372	0.6889
0.0014	21.0	126	0.8392	0.6889
0.0013	22.0	132	0.8471	0.6889
0.0013	23.0	138	0.8542	0.7111
0.0012	24.0	144	0.8532	0.6889
0.001	25.0	150	0.8592	0.6889
0.001	26.0	156	0.8620	0.6889
0.001	27.0	162	0.8623	0.6889
0.001	28.0	168	0.8684	0.6889
0.0009	29.0	174	0.8656	0.6667
0.0009	30.0	180	0.8670	0.6889
0.0009	31.0	186	0.8710	0.6889
0.0008	32.0	192	0.8750	0.6889
0.0008	33.0	198	0.8785	0.6667
0.0008	34.0	204	0.8810	0.6667
0.0008	35.0	210	0.8827	0.6667
0.0008	36.0	216	0.8847	0.6889
0.0007	37.0	222	0.8870	0.6889
0.0007	38.0	228	0.8890	0.6889
0.0007	39.0	234	0.8882	0.6889
0.0007	40.0	240	0.8885	0.6889
0.0007	41.0	246	0.8887	0.6889
0.0007	42.0	252	0.8886	0.6889
0.0007	43.0	258	0.8886	0.6889
0.0007	44.0	264	0.8886	0.6889
0.0007	45.0	270	0.8886	0.6889
0.0007	46.0	276	0.8886	0.6889
0.0007	47.0	282	0.8886	0.6889
0.0007	48.0	288	0.8886	0.6889
0.0007	49.0	294	0.8886	0.6889
0.0007	50.0	300	0.8886	0.6889

Framework versions

Transformers 4.35.1
Pytorch 2.1.0+cu118
Datasets 2.14.7
Tokenizers 0.14.1

hkivancoral/hushem_1x_deit_small_rms_00001_fold1

hushem_1x_deit_small_rms_00001_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_1x_deit_small_rms_00001_fold1