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: 0.9992
Accuracy: 0.8852

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
0.6049	1.0	225	0.5478	0.7787
0.4381	2.0	450	0.4409	0.8270
0.378	3.0	675	0.4173	0.8386
0.3898	4.0	900	0.3437	0.8636
0.2572	5.0	1125	0.5400	0.8153
0.2909	6.0	1350	0.3922	0.8686
0.2559	7.0	1575	0.3276	0.8669
0.1836	8.0	1800	0.4262	0.8536
0.1786	9.0	2025	0.4524	0.8652
0.114	10.0	2250	0.4178	0.8652
0.1999	11.0	2475	0.4725	0.8619
0.0816	12.0	2700	0.4168	0.8802
0.1006	13.0	2925	0.4871	0.8636
0.0621	14.0	3150	0.5045	0.8486
0.1207	15.0	3375	0.5359	0.8735
0.1626	16.0	3600	0.5831	0.8586
0.0687	17.0	3825	0.5917	0.8702
0.0286	18.0	4050	0.6265	0.8819
0.0163	19.0	4275	0.5886	0.8752
0.0426	20.0	4500	0.5976	0.8686
0.0173	21.0	4725	0.5968	0.8819
0.0472	22.0	4950	0.8302	0.8586
0.0232	23.0	5175	0.7287	0.8769
0.0189	24.0	5400	0.6779	0.8686
0.0355	25.0	5625	0.7090	0.8802
0.0055	26.0	5850	0.7826	0.8769
0.003	27.0	6075	0.6780	0.8752
0.0006	28.0	6300	0.8190	0.8652
0.0008	29.0	6525	0.8233	0.8602
0.01	30.0	6750	0.8980	0.8552
0.0041	31.0	6975	0.9765	0.8552
0.002	32.0	7200	0.9007	0.8619
0.0055	33.0	7425	0.9545	0.8735
0.0034	34.0	7650	0.8622	0.8719
0.0003	35.0	7875	0.9467	0.8785
0.0042	36.0	8100	0.8925	0.8819
0.0003	37.0	8325	0.9807	0.8802
0.0	38.0	8550	1.0504	0.8769
0.0067	39.0	8775	1.0615	0.8752
0.0017	40.0	9000	1.0987	0.8719
0.0011	41.0	9225	1.0223	0.8835
0.0001	42.0	9450	0.9989	0.8852
0.0	43.0	9675	0.9839	0.8852
0.0	44.0	9900	1.0002	0.8802
0.0	45.0	10125	0.9842	0.8869
0.0002	46.0	10350	0.9885	0.8885
0.0	47.0	10575	0.9981	0.8869
0.0	48.0	10800	0.9986	0.8852
0.0051	49.0	11025	0.9988	0.8835
0.0023	50.0	11250	0.9992	0.8852

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_3x_beit_base_adamax_001_fold2

smids_3x_beit_base_adamax_001_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_3x_beit_base_adamax_001_fold2