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: 0.6006
Accuracy: 0.7513

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: 0.0001
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
1.2428	1.0	226	1.2900	0.3139
1.1165	2.0	452	1.2280	0.3389
1.085	3.0	678	1.1717	0.3606
1.0873	4.0	904	1.1174	0.3973
1.0209	5.0	1130	1.0648	0.4207
0.9387	6.0	1356	1.0163	0.4741
0.9347	7.0	1582	0.9719	0.5175
0.8727	8.0	1808	0.9312	0.5626
0.8169	9.0	2034	0.8951	0.5993
0.861	10.0	2260	0.8623	0.6160
0.8138	11.0	2486	0.8344	0.6327
0.7635	12.0	2712	0.8096	0.6444
0.7469	13.0	2938	0.7879	0.6477
0.7457	14.0	3164	0.7697	0.6561
0.6958	15.0	3390	0.7527	0.6728
0.6961	16.0	3616	0.7374	0.6795
0.6436	17.0	3842	0.7245	0.6878
0.6513	18.0	4068	0.7127	0.6912
0.6672	19.0	4294	0.7016	0.6962
0.6558	20.0	4520	0.6918	0.7012
0.6466	21.0	4746	0.6834	0.7028
0.6561	22.0	4972	0.6751	0.7045
0.6208	23.0	5198	0.6670	0.7145
0.6499	24.0	5424	0.6602	0.7162
0.6316	25.0	5650	0.6537	0.7179
0.6488	26.0	5876	0.6486	0.7245
0.6013	27.0	6102	0.6431	0.7229
0.6349	28.0	6328	0.6385	0.7295
0.5571	29.0	6554	0.6343	0.7312
0.6883	30.0	6780	0.6303	0.7329
0.5874	31.0	7006	0.6269	0.7362
0.5957	32.0	7232	0.6236	0.7412
0.5454	33.0	7458	0.6209	0.7446
0.5392	34.0	7684	0.6182	0.7446
0.6014	35.0	7910	0.6160	0.7462
0.5394	36.0	8136	0.6140	0.7462
0.5557	37.0	8362	0.6119	0.7479
0.5868	38.0	8588	0.6101	0.7479
0.5673	39.0	8814	0.6084	0.7479
0.5576	40.0	9040	0.6071	0.7479
0.5598	41.0	9266	0.6057	0.7479
0.5493	42.0	9492	0.6045	0.7496
0.573	43.0	9718	0.6035	0.7513
0.5428	44.0	9944	0.6027	0.7513
0.6174	45.0	10170	0.6020	0.7513
0.5654	46.0	10396	0.6015	0.7513
0.5911	47.0	10622	0.6010	0.7513
0.5644	48.0	10848	0.6008	0.7513
0.5284	49.0	11074	0.6007	0.7513
0.5888	50.0	11300	0.6006	0.7513

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_3x_beit_base_sgd_0001_fold1

smids_3x_beit_base_sgd_0001_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_3x_beit_base_sgd_0001_fold1