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: 0.2756
Accuracy: 0.9017

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
0.8095	1.0	375	0.8274	0.695
0.5875	2.0	750	0.5872	0.8033
0.4116	3.0	1125	0.4743	0.83
0.3737	4.0	1500	0.4186	0.855
0.4258	5.0	1875	0.3874	0.86
0.3489	6.0	2250	0.3641	0.8633
0.3464	7.0	2625	0.3477	0.8667
0.3297	8.0	3000	0.3357	0.8667
0.277	9.0	3375	0.3288	0.8683
0.2815	10.0	3750	0.3210	0.8733
0.2355	11.0	4125	0.3122	0.8767
0.2863	12.0	4500	0.3078	0.8833
0.2701	13.0	4875	0.3051	0.8833
0.2736	14.0	5250	0.3025	0.8833
0.2395	15.0	5625	0.2961	0.885
0.2031	16.0	6000	0.2952	0.885
0.2473	17.0	6375	0.2943	0.885
0.2814	18.0	6750	0.2910	0.8883
0.2316	19.0	7125	0.2893	0.89
0.2303	20.0	7500	0.2871	0.8883
0.1561	21.0	7875	0.2852	0.8883
0.1795	22.0	8250	0.2878	0.8933
0.2424	23.0	8625	0.2847	0.8933
0.234	24.0	9000	0.2843	0.89
0.2148	25.0	9375	0.2840	0.8883
0.2353	26.0	9750	0.2810	0.8967
0.2055	27.0	10125	0.2823	0.895
0.2361	28.0	10500	0.2802	0.8967
0.1834	29.0	10875	0.2796	0.895
0.2029	30.0	11250	0.2813	0.8967
0.2296	31.0	11625	0.2806	0.8983
0.2077	32.0	12000	0.2800	0.8983
0.2574	33.0	12375	0.2785	0.8983
0.1786	34.0	12750	0.2764	0.8967
0.1549	35.0	13125	0.2758	0.9
0.1665	36.0	13500	0.2763	0.8983
0.187	37.0	13875	0.2766	0.9
0.1745	38.0	14250	0.2765	0.9
0.1886	39.0	14625	0.2765	0.9
0.1628	40.0	15000	0.2755	0.9017
0.1471	41.0	15375	0.2749	0.9017
0.1795	42.0	15750	0.2759	0.9017
0.2305	43.0	16125	0.2754	0.9017
0.168	44.0	16500	0.2757	0.9017
0.1598	45.0	16875	0.2757	0.9033
0.1914	46.0	17250	0.2755	0.9017
0.2052	47.0	17625	0.2754	0.9017
0.1945	48.0	18000	0.2755	0.9017
0.1764	49.0	18375	0.2755	0.9017
0.1798	50.0	18750	0.2756	0.9017

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_fold3

smids_5x_deit_base_sgd_001_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_5x_deit_base_sgd_001_fold3