This model is a fine-tuned version of microsoft/beit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 1.1524
Accuracy: 0.3706

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: 1e-05
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
1.2623	1.0	376	1.3473	0.3088
1.2409	2.0	752	1.3383	0.3122
1.2444	3.0	1128	1.3298	0.3105
1.1982	4.0	1504	1.3215	0.3105
1.2082	5.0	1880	1.3136	0.3105
1.1814	6.0	2256	1.3057	0.3139
1.1633	7.0	2632	1.2980	0.3172
1.2064	8.0	3008	1.2906	0.3205
1.1298	9.0	3384	1.2834	0.3205
1.1231	10.0	3760	1.2765	0.3322
1.171	11.0	4136	1.2696	0.3372
1.1505	12.0	4512	1.2632	0.3439
1.1137	13.0	4888	1.2569	0.3472
1.1229	14.0	5264	1.2508	0.3456
1.1641	15.0	5640	1.2450	0.3439
1.1335	16.0	6016	1.2391	0.3439
1.0584	17.0	6392	1.2337	0.3439
1.1251	18.0	6768	1.2284	0.3456
1.105	19.0	7144	1.2233	0.3506
1.0972	20.0	7520	1.2186	0.3506
1.0751	21.0	7896	1.2139	0.3539
1.0864	22.0	8272	1.2094	0.3539
1.1021	23.0	8648	1.2051	0.3539
1.1159	24.0	9024	1.2011	0.3539
1.0862	25.0	9400	1.1972	0.3556
1.0706	26.0	9776	1.1934	0.3589
1.0809	27.0	10152	1.1898	0.3589
1.0663	28.0	10528	1.1865	0.3589
1.0982	29.0	10904	1.1833	0.3606
1.1121	30.0	11280	1.1802	0.3623
1.0485	31.0	11656	1.1773	0.3656
1.0472	32.0	12032	1.1746	0.3656
1.0601	33.0	12408	1.1721	0.3689
1.0381	34.0	12784	1.1697	0.3689
1.072	35.0	13160	1.1675	0.3689
1.087	36.0	13536	1.1654	0.3689
1.0074	37.0	13912	1.1635	0.3706
1.0562	38.0	14288	1.1618	0.3689
1.0371	39.0	14664	1.1602	0.3689
1.0517	40.0	15040	1.1588	0.3706
1.0384	41.0	15416	1.1575	0.3706
1.0222	42.0	15792	1.1563	0.3706
1.0143	43.0	16168	1.1553	0.3706
0.9973	44.0	16544	1.1545	0.3689
1.0445	45.0	16920	1.1538	0.3689
1.0408	46.0	17296	1.1532	0.3706
1.0166	47.0	17672	1.1528	0.3706
1.0266	48.0	18048	1.1525	0.3706
1.0337	49.0	18424	1.1524	0.3706
1.0214	50.0	18800	1.1524	0.3706

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_5x_beit_base_sgd_00001_fold1

smids_5x_beit_base_sgd_00001_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_5x_beit_base_sgd_00001_fold1