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: 0.2653
Accuracy: 0.89

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
0.816	1.0	375	0.8299	0.6983
0.6079	2.0	750	0.5776	0.79
0.4275	3.0	1125	0.4639	0.815
0.435	4.0	1500	0.4090	0.8217
0.3764	5.0	1875	0.3770	0.83
0.3648	6.0	2250	0.3546	0.8333
0.2762	7.0	2625	0.3403	0.8383
0.295	8.0	3000	0.3285	0.85
0.2923	9.0	3375	0.3205	0.8517
0.2438	10.0	3750	0.3147	0.855
0.2438	11.0	4125	0.3070	0.86
0.2431	12.0	4500	0.3020	0.8667
0.2192	13.0	4875	0.2993	0.865
0.2554	14.0	5250	0.2960	0.8717
0.2885	15.0	5625	0.2913	0.8783
0.1896	16.0	6000	0.2879	0.88
0.3057	17.0	6375	0.2870	0.8733
0.2444	18.0	6750	0.2845	0.88
0.2179	19.0	7125	0.2810	0.8783
0.1663	20.0	7500	0.2810	0.8783
0.2067	21.0	7875	0.2763	0.8833
0.197	22.0	8250	0.2779	0.8817
0.3036	23.0	8625	0.2762	0.8817
0.2123	24.0	9000	0.2743	0.8817
0.2471	25.0	9375	0.2741	0.8783
0.2004	26.0	9750	0.2742	0.88
0.2358	27.0	10125	0.2736	0.88
0.2033	28.0	10500	0.2701	0.88
0.2195	29.0	10875	0.2687	0.8833
0.1807	30.0	11250	0.2702	0.8817
0.2285	31.0	11625	0.2693	0.8833
0.2043	32.0	12000	0.2686	0.8883
0.2113	33.0	12375	0.2682	0.89
0.253	34.0	12750	0.2667	0.8883
0.1854	35.0	13125	0.2674	0.885
0.1505	36.0	13500	0.2668	0.8867
0.2105	37.0	13875	0.2666	0.885
0.184	38.0	14250	0.2661	0.8867
0.1486	39.0	14625	0.2664	0.8867
0.2231	40.0	15000	0.2660	0.8883
0.185	41.0	15375	0.2658	0.8867
0.166	42.0	15750	0.2657	0.8883
0.1944	43.0	16125	0.2649	0.8933
0.1752	44.0	16500	0.2656	0.8883
0.1859	45.0	16875	0.2655	0.89
0.2257	46.0	17250	0.2655	0.8867
0.2194	47.0	17625	0.2653	0.8883
0.1536	48.0	18000	0.2653	0.8883
0.1835	49.0	18375	0.2652	0.89
0.1852	50.0	18750	0.2653	0.89

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_fold5

smids_5x_deit_base_sgd_001_fold5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_5x_deit_base_sgd_001_fold5