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: 0.3178
Accuracy: 0.8733

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
0.599	1.0	750	0.5727	0.805
0.4144	2.0	1500	0.4280	0.8367
0.3778	3.0	2250	0.3848	0.85
0.3651	4.0	3000	0.3623	0.8483
0.2724	5.0	3750	0.3497	0.8633
0.2557	6.0	4500	0.3423	0.865
0.2087	7.0	5250	0.3348	0.8617
0.2338	8.0	6000	0.3321	0.8667
0.2309	9.0	6750	0.3286	0.8683
0.222	10.0	7500	0.3223	0.8683
0.2535	11.0	8250	0.3209	0.8683
0.2943	12.0	9000	0.3182	0.865
0.2348	13.0	9750	0.3166	0.87
0.2428	14.0	10500	0.3176	0.865
0.1672	15.0	11250	0.3141	0.875
0.2041	16.0	12000	0.3122	0.8783
0.143	17.0	12750	0.3133	0.8717
0.1867	18.0	13500	0.3116	0.8767
0.2171	19.0	14250	0.3182	0.87
0.1733	20.0	15000	0.3144	0.8733
0.1721	21.0	15750	0.3128	0.875
0.1968	22.0	16500	0.3133	0.8717
0.1782	23.0	17250	0.3143	0.8717
0.2288	24.0	18000	0.3135	0.8717
0.1955	25.0	18750	0.3134	0.8733
0.1366	26.0	19500	0.3154	0.87
0.1576	27.0	20250	0.3131	0.8783
0.1394	28.0	21000	0.3139	0.8733
0.1334	29.0	21750	0.3147	0.8733
0.1696	30.0	22500	0.3135	0.8767
0.1131	31.0	23250	0.3147	0.8767
0.1384	32.0	24000	0.3141	0.8733
0.1516	33.0	24750	0.3150	0.875
0.19	34.0	25500	0.3153	0.8733
0.1122	35.0	26250	0.3150	0.8733
0.164	36.0	27000	0.3158	0.8717
0.1263	37.0	27750	0.3166	0.875
0.1818	38.0	28500	0.3156	0.8733
0.1588	39.0	29250	0.3163	0.8717
0.1761	40.0	30000	0.3172	0.8733
0.1577	41.0	30750	0.3157	0.8733
0.1328	42.0	31500	0.3172	0.875
0.1699	43.0	32250	0.3163	0.8733
0.1505	44.0	33000	0.3182	0.875
0.1595	45.0	33750	0.3176	0.8733
0.1562	46.0	34500	0.3182	0.8733
0.1053	47.0	35250	0.3176	0.875
0.1264	48.0	36000	0.3177	0.8733
0.1357	49.0	36750	0.3177	0.8733
0.0881	50.0	37500	0.3178	0.8733

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_10x_deit_base_sgd_001_fold4

smids_10x_deit_base_sgd_001_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_10x_deit_base_sgd_001_fold4