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: 3.4047
Accuracy: 0.7073

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
1.4155	1.0	28	1.3777	0.2683
1.3848	2.0	56	1.2989	0.2927
1.3314	3.0	84	1.2733	0.4878
1.2486	4.0	112	1.0811	0.5122
1.2007	5.0	140	0.9236	0.5854
1.05	6.0	168	1.1380	0.5122
1.0162	7.0	196	0.9574	0.5854
0.9476	8.0	224	1.4400	0.4878
0.903	9.0	252	0.9012	0.6341
0.9351	10.0	280	1.0183	0.6829
0.8113	11.0	308	0.9612	0.6585
0.8131	12.0	336	1.6631	0.4878
0.7921	13.0	364	0.9316	0.6829
0.8114	14.0	392	1.3372	0.5854
0.7382	15.0	420	1.4796	0.6341
0.7119	16.0	448	1.9753	0.5366
0.6933	17.0	476	1.3458	0.7073
0.591	18.0	504	1.3968	0.6585
0.6986	19.0	532	1.4904	0.6829
0.6832	20.0	560	1.7362	0.6585
0.5173	21.0	588	1.5475	0.7317
0.5116	22.0	616	1.9547	0.6585
0.4833	23.0	644	2.1246	0.6341
0.4295	24.0	672	1.9058	0.7317
0.4431	25.0	700	2.4495	0.6585
0.3801	26.0	728	1.6867	0.7561
0.4263	27.0	756	2.1056	0.6585
0.3209	28.0	784	2.6127	0.6098
0.29	29.0	812	2.2833	0.6341
0.2306	30.0	840	2.6477	0.6341
0.2318	31.0	868	2.2205	0.6829
0.1766	32.0	896	2.1057	0.8293
0.1861	33.0	924	2.9102	0.6341
0.2172	34.0	952	2.3319	0.7317
0.1336	35.0	980	2.7931	0.7073
0.128	36.0	1008	3.2544	0.6098
0.1009	37.0	1036	2.3057	0.7805
0.1495	38.0	1064	2.9047	0.7317
0.0845	39.0	1092	3.1290	0.7317
0.064	40.0	1120	2.9682	0.7561
0.0399	41.0	1148	2.9364	0.7561
0.0198	42.0	1176	4.0340	0.6585
0.0179	43.0	1204	3.2313	0.7317
0.0799	44.0	1232	3.4340	0.7317
0.0495	45.0	1260	3.8737	0.6829
0.041	46.0	1288	3.5139	0.6829
0.0058	47.0	1316	3.4146	0.7073
0.0141	48.0	1344	3.4016	0.7073
0.0316	49.0	1372	3.4047	0.7073
0.0269	50.0	1400	3.4047	0.7073

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

hkivancoral/hushem_5x_beit_base_rms_0001_fold5

hushem_5x_beit_base_rms_0001_fold5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_5x_beit_base_rms_0001_fold5