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: 0.3272
Accuracy: 0.8648

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
1.023	1.0	76	0.9338	0.5960
0.8695	2.0	152	0.7961	0.6962
0.7472	3.0	228	0.7107	0.7245
0.6931	4.0	304	0.6455	0.7579
0.6024	5.0	380	0.6009	0.7830
0.5887	6.0	456	0.5575	0.7896
0.5612	7.0	532	0.5303	0.7947
0.5261	8.0	608	0.5077	0.8197
0.5291	9.0	684	0.4867	0.8164
0.4139	10.0	760	0.4652	0.8230
0.4709	11.0	836	0.4493	0.8264
0.4127	12.0	912	0.4359	0.8397
0.419	13.0	988	0.4224	0.8381
0.4108	14.0	1064	0.4104	0.8481
0.5096	15.0	1140	0.4034	0.8497
0.4428	16.0	1216	0.3953	0.8548
0.4039	17.0	1292	0.3903	0.8598
0.3283	18.0	1368	0.3811	0.8598
0.4203	19.0	1444	0.3747	0.8681
0.449	20.0	1520	0.3742	0.8631
0.3886	21.0	1596	0.3668	0.8631
0.3947	22.0	1672	0.3711	0.8631
0.3271	23.0	1748	0.3637	0.8564
0.3744	24.0	1824	0.3594	0.8631
0.3021	25.0	1900	0.3558	0.8614
0.3505	26.0	1976	0.3515	0.8631
0.2842	27.0	2052	0.3497	0.8648
0.3503	28.0	2128	0.3458	0.8698
0.3076	29.0	2204	0.3443	0.8664
0.3164	30.0	2280	0.3411	0.8648
0.3293	31.0	2356	0.3409	0.8631
0.3108	32.0	2432	0.3378	0.8648
0.2993	33.0	2508	0.3374	0.8648
0.3123	34.0	2584	0.3356	0.8648
0.4733	35.0	2660	0.3344	0.8664
0.3442	36.0	2736	0.3328	0.8681
0.3357	37.0	2812	0.3329	0.8648
0.2903	38.0	2888	0.3325	0.8698
0.2981	39.0	2964	0.3300	0.8681
0.3433	40.0	3040	0.3301	0.8664
0.2756	41.0	3116	0.3304	0.8648
0.3213	42.0	3192	0.3307	0.8631
0.2954	43.0	3268	0.3290	0.8664
0.3403	44.0	3344	0.3293	0.8648
0.3019	45.0	3420	0.3281	0.8664
0.267	46.0	3496	0.3277	0.8664
0.3291	47.0	3572	0.3275	0.8664
0.2958	48.0	3648	0.3273	0.8664
0.2907	49.0	3724	0.3272	0.8648
0.2994	50.0	3800	0.3272	0.8648

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

hkivancoral/smids_1x_beit_base_sgd_001_fold1

smids_1x_beit_base_sgd_001_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_1x_beit_base_sgd_001_fold1