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: 0.7081
Accuracy: 0.8965

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
0.3415	1.0	76	0.3600	0.8531
0.1821	2.0	152	0.2813	0.8865
0.1106	3.0	228	0.2915	0.8965
0.0837	4.0	304	0.4355	0.8748
0.0461	5.0	380	0.3524	0.8831
0.0314	6.0	456	0.3471	0.9065
0.052	7.0	532	0.3906	0.9032
0.0094	8.0	608	0.4902	0.8998
0.0397	9.0	684	0.5074	0.8848
0.0068	10.0	760	0.5396	0.8965
0.0009	11.0	836	0.4910	0.9032
0.0007	12.0	912	0.5441	0.8982
0.0176	13.0	988	0.5729	0.8965
0.008	14.0	1064	0.5831	0.8965
0.0023	15.0	1140	0.6581	0.8982
0.0112	16.0	1216	0.6373	0.9048
0.0122	17.0	1292	0.6091	0.8982
0.0218	18.0	1368	0.7005	0.8965
0.0052	19.0	1444	0.6533	0.8998
0.0143	20.0	1520	0.5987	0.9048
0.0047	21.0	1596	0.6407	0.8982
0.005	22.0	1672	0.7577	0.8898
0.0133	23.0	1748	0.7568	0.8848
0.0064	24.0	1824	0.6963	0.8915
0.0056	25.0	1900	0.6832	0.8982
0.0033	26.0	1976	0.6578	0.8982
0.0048	27.0	2052	0.6821	0.9032
0.0003	28.0	2128	0.6751	0.8998
0.0002	29.0	2204	0.6826	0.8998
0.0054	30.0	2280	0.7208	0.8965
0.0234	31.0	2356	0.7169	0.8915
0.0066	32.0	2432	0.7161	0.8982
0.0078	33.0	2508	0.6895	0.8982
0.004	34.0	2584	0.7616	0.8982
0.0117	35.0	2660	0.7211	0.9032
0.0	36.0	2736	0.6772	0.8982
0.0027	37.0	2812	0.6751	0.8998
0.0023	38.0	2888	0.7465	0.9082
0.0025	39.0	2964	0.6434	0.9132
0.0043	40.0	3040	0.6803	0.9032
0.005	41.0	3116	0.6970	0.8982
0.0	42.0	3192	0.6953	0.8998
0.0002	43.0	3268	0.6864	0.8982
0.0001	44.0	3344	0.6955	0.9015
0.0058	45.0	3420	0.7259	0.8948
0.0	46.0	3496	0.7126	0.9032
0.0044	47.0	3572	0.7081	0.8965
0.0032	48.0	3648	0.7104	0.8965
0.0023	49.0	3724	0.7077	0.8965
0.0057	50.0	3800	0.7081	0.8965

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

hkivancoral/smids_1x_beit_base_rms_00001_fold1

smids_1x_beit_base_rms_00001_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_1x_beit_base_rms_00001_fold1