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

Loss: 0.3268
Accuracy: 0.8683

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
0.8132	1.0	375	0.8089	0.7267
0.5876	2.0	750	0.5635	0.8067
0.4083	3.0	1125	0.4614	0.8267
0.4267	4.0	1500	0.4160	0.8333
0.3511	5.0	1875	0.3904	0.845
0.2917	6.0	2250	0.3744	0.85
0.3158	7.0	2625	0.3647	0.8583
0.2749	8.0	3000	0.3555	0.86
0.3058	9.0	3375	0.3495	0.8583
0.2616	10.0	3750	0.3455	0.8667
0.2281	11.0	4125	0.3414	0.8683
0.2203	12.0	4500	0.3404	0.87
0.1983	13.0	4875	0.3366	0.8733
0.2917	14.0	5250	0.3335	0.875
0.2068	15.0	5625	0.3331	0.8767
0.1668	16.0	6000	0.3311	0.8767
0.2429	17.0	6375	0.3309	0.88
0.2255	18.0	6750	0.3295	0.8817
0.217	19.0	7125	0.3289	0.88
0.1858	20.0	7500	0.3267	0.875
0.1989	21.0	7875	0.3279	0.875
0.1971	22.0	8250	0.3262	0.8767
0.1898	23.0	8625	0.3266	0.875
0.1832	24.0	9000	0.3251	0.8767
0.2234	25.0	9375	0.3260	0.875
0.1745	26.0	9750	0.3248	0.8767
0.2157	27.0	10125	0.3261	0.875
0.1917	28.0	10500	0.3254	0.8717
0.169	29.0	10875	0.3264	0.87
0.238	30.0	11250	0.3268	0.8683
0.1975	31.0	11625	0.3288	0.87
0.139	32.0	12000	0.3247	0.8717
0.1975	33.0	12375	0.3257	0.8683
0.1914	34.0	12750	0.3239	0.875
0.1455	35.0	13125	0.3252	0.8717
0.1611	36.0	13500	0.3266	0.8683
0.2074	37.0	13875	0.3252	0.8767
0.1665	38.0	14250	0.3262	0.8683
0.2306	39.0	14625	0.3258	0.8683
0.1821	40.0	15000	0.3259	0.8683
0.154	41.0	15375	0.3262	0.8683
0.1817	42.0	15750	0.3261	0.8683
0.2063	43.0	16125	0.3258	0.8717
0.1391	44.0	16500	0.3266	0.8683
0.2228	45.0	16875	0.3270	0.8683
0.1476	46.0	17250	0.3269	0.87
0.2362	47.0	17625	0.3264	0.8683
0.1702	48.0	18000	0.3268	0.8683
0.1619	49.0	18375	0.3268	0.8683
0.1838	50.0	18750	0.3268	0.8683

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_5x_deit_base_sgd_001_fold4

smids_5x_deit_base_sgd_001_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_5x_deit_base_sgd_001_fold4