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: 2.7065
Accuracy: 0.6977

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
1.4764	1.0	28	1.3308	0.4651
1.3399	2.0	56	1.2727	0.5116
1.2309	3.0	84	1.0539	0.5349
1.0517	4.0	112	1.0384	0.6279
0.9736	5.0	140	1.1313	0.5349
1.0108	6.0	168	0.6569	0.8140
0.9287	7.0	196	0.7779	0.7674
0.9063	8.0	224	0.8802	0.5581
0.7994	9.0	252	1.1244	0.5581
0.8319	10.0	280	0.7284	0.7209
0.8096	11.0	308	0.7775	0.7209
0.8274	12.0	336	0.7683	0.6744
0.798	13.0	364	0.8219	0.6512
0.6756	14.0	392	0.5656	0.7442
0.9098	15.0	420	0.6922	0.6279
0.6261	16.0	448	1.0949	0.5814
0.6243	17.0	476	0.7154	0.7209
0.7247	18.0	504	0.6429	0.7674
0.6106	19.0	532	0.7927	0.6744
0.4831	20.0	560	0.6060	0.7674
0.5359	21.0	588	1.2593	0.5349
0.429	22.0	616	1.0232	0.6744
0.4536	23.0	644	1.2564	0.6744
0.2969	24.0	672	1.2153	0.6279
0.3018	25.0	700	1.3650	0.5814
0.2695	26.0	728	1.6759	0.6279
0.2235	27.0	756	1.8158	0.5814
0.2674	28.0	784	1.7475	0.6977
0.1711	29.0	812	1.5630	0.7209
0.1241	30.0	840	1.5976	0.7442
0.1378	31.0	868	1.8498	0.7209
0.1016	32.0	896	2.3022	0.6279
0.1245	33.0	924	2.0178	0.6047
0.1029	34.0	952	2.0725	0.6744
0.0329	35.0	980	1.6046	0.7674
0.1038	36.0	1008	2.3364	0.6047
0.055	37.0	1036	3.1044	0.5581
0.0031	38.0	1064	2.6896	0.6512
0.0537	39.0	1092	3.2350	0.6047
0.0484	40.0	1120	3.5002	0.5814
0.0311	41.0	1148	3.0948	0.6512
0.0491	42.0	1176	2.8268	0.6977
0.0023	43.0	1204	2.5306	0.6977
0.0192	44.0	1232	2.3977	0.6977
0.0339	45.0	1260	2.5488	0.6977
0.0369	46.0	1288	2.5878	0.7209
0.049	47.0	1316	2.7159	0.6977
0.0044	48.0	1344	2.7074	0.6977
0.0183	49.0	1372	2.7065	0.6977
0.0409	50.0	1400	2.7065	0.6977

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

hkivancoral/hushem_5x_beit_base_adamax_001_fold3

hushem_5x_beit_base_adamax_001_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_5x_beit_base_adamax_001_fold3