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: 0.2764
Accuracy: 0.895

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
0.5289	1.0	750	0.5577	0.7883
0.411	2.0	1500	0.4355	0.835
0.3696	3.0	2250	0.3887	0.85
0.3417	4.0	3000	0.3643	0.8517
0.3357	5.0	3750	0.3441	0.8617
0.2644	6.0	4500	0.3299	0.865
0.2577	7.0	5250	0.3164	0.8667
0.2725	8.0	6000	0.3096	0.875
0.2894	9.0	6750	0.3046	0.8717
0.2245	10.0	7500	0.2980	0.87
0.2663	11.0	8250	0.2930	0.8817
0.2488	12.0	9000	0.2925	0.8717
0.2365	13.0	9750	0.2865	0.88
0.2172	14.0	10500	0.2813	0.8833
0.2487	15.0	11250	0.2761	0.885
0.1796	16.0	12000	0.2827	0.8817
0.1959	17.0	12750	0.2794	0.8833
0.1795	18.0	13500	0.2745	0.8833
0.2262	19.0	14250	0.2788	0.885
0.1595	20.0	15000	0.2793	0.885
0.2022	21.0	15750	0.2745	0.8833
0.2023	22.0	16500	0.2758	0.8917
0.1864	23.0	17250	0.2773	0.8883
0.1869	24.0	18000	0.2763	0.8967
0.1883	25.0	18750	0.2788	0.89
0.1768	26.0	19500	0.2728	0.8967
0.1135	27.0	20250	0.2823	0.8867
0.1819	28.0	21000	0.2713	0.8933
0.1691	29.0	21750	0.2729	0.8967
0.1867	30.0	22500	0.2819	0.89
0.1549	31.0	23250	0.2710	0.8933
0.125	32.0	24000	0.2766	0.8917
0.1602	33.0	24750	0.2747	0.895
0.1131	34.0	25500	0.2730	0.9
0.1454	35.0	26250	0.2723	0.895
0.1829	36.0	27000	0.2731	0.8967
0.1	37.0	27750	0.2730	0.8967
0.1344	38.0	28500	0.2751	0.8983
0.1584	39.0	29250	0.2745	0.8983
0.1265	40.0	30000	0.2754	0.8967
0.1671	41.0	30750	0.2769	0.8967
0.147	42.0	31500	0.2744	0.8933
0.1588	43.0	32250	0.2753	0.8967
0.1433	44.0	33000	0.2767	0.9
0.1715	45.0	33750	0.2775	0.8967
0.1027	46.0	34500	0.2766	0.9
0.1628	47.0	35250	0.2771	0.8967
0.1468	48.0	36000	0.2769	0.895
0.1346	49.0	36750	0.2765	0.895
0.0897	50.0	37500	0.2764	0.895

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_10x_deit_small_sgd_001_fold5

smids_10x_deit_small_sgd_001_fold5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_10x_deit_small_sgd_001_fold5