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: 0.2876
Accuracy: 0.8985

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
0.569	1.0	750	0.5992	0.7754
0.3171	2.0	1500	0.4389	0.8136
0.3055	3.0	2250	0.3875	0.8403
0.3488	4.0	3000	0.3592	0.8519
0.2869	5.0	3750	0.3460	0.8586
0.2849	6.0	4500	0.3276	0.8669
0.2527	7.0	5250	0.3203	0.8719
0.2343	8.0	6000	0.3120	0.8802
0.2514	9.0	6750	0.3061	0.8802
0.2509	10.0	7500	0.3037	0.8819
0.2672	11.0	8250	0.2976	0.8835
0.2698	12.0	9000	0.2941	0.8885
0.2268	13.0	9750	0.2935	0.8869
0.1786	14.0	10500	0.2916	0.8835
0.166	15.0	11250	0.2890	0.8885
0.192	16.0	12000	0.2883	0.8869
0.1507	17.0	12750	0.2880	0.8869
0.1815	18.0	13500	0.2859	0.8885
0.1982	19.0	14250	0.2882	0.8902
0.2	20.0	15000	0.2835	0.8869
0.1801	21.0	15750	0.2845	0.8902
0.1194	22.0	16500	0.2833	0.8918
0.1747	23.0	17250	0.2854	0.8935
0.1283	24.0	18000	0.2844	0.8935
0.1821	25.0	18750	0.2833	0.8952
0.2094	26.0	19500	0.2844	0.8918
0.1857	27.0	20250	0.2847	0.8985
0.1436	28.0	21000	0.2850	0.8952
0.1786	29.0	21750	0.2841	0.8985
0.1785	30.0	22500	0.2847	0.8952
0.1889	31.0	23250	0.2850	0.8952
0.1905	32.0	24000	0.2845	0.8968
0.1812	33.0	24750	0.2853	0.8935
0.1723	34.0	25500	0.2858	0.8952
0.1909	35.0	26250	0.2850	0.8952
0.1661	36.0	27000	0.2862	0.8985
0.1719	37.0	27750	0.2861	0.8935
0.156	38.0	28500	0.2859	0.9002
0.1428	39.0	29250	0.2859	0.8985
0.229	40.0	30000	0.2871	0.8985
0.2023	41.0	30750	0.2873	0.8968
0.1583	42.0	31500	0.2870	0.8968
0.1454	43.0	32250	0.2875	0.8985
0.1231	44.0	33000	0.2872	0.8985
0.1299	45.0	33750	0.2879	0.8985
0.1947	46.0	34500	0.2876	0.8985
0.1774	47.0	35250	0.2875	0.8985
0.1319	48.0	36000	0.2874	0.8968
0.1298	49.0	36750	0.2876	0.8985
0.1348	50.0	37500	0.2876	0.8985

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_fold2

smids_10x_deit_base_sgd_001_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_10x_deit_base_sgd_001_fold2