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: 0.5241
Accuracy: 0.9070

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
0.7661	1.0	28	0.5413	0.7907
0.1086	2.0	56	0.1845	0.9535
0.0112	3.0	84	0.3881	0.9070
0.0076	4.0	112	0.3276	0.9070
0.0043	5.0	140	0.4248	0.9070
0.0016	6.0	168	0.2522	0.9302
0.0099	7.0	196	0.2768	0.9070
0.0014	8.0	224	0.2639	0.9302
0.0013	9.0	252	0.3818	0.9070
0.0009	10.0	280	0.1248	0.9535
0.0006	11.0	308	0.2509	0.9070
0.0003	12.0	336	0.2923	0.9070
0.001	13.0	364	0.5107	0.8837
0.0019	14.0	392	0.3339	0.9535
0.0002	15.0	420	0.3891	0.9070
0.0003	16.0	448	0.4248	0.9070
0.0005	17.0	476	0.2832	0.9535
0.0003	18.0	504	0.3491	0.9070
0.0002	19.0	532	0.4104	0.9070
0.0001	20.0	560	0.4255	0.9070
0.0009	21.0	588	0.4651	0.9070
0.0015	22.0	616	0.4792	0.9070
0.0001	23.0	644	0.4509	0.9070
0.0006	24.0	672	0.5680	0.9302
0.0001	25.0	700	0.3224	0.9070
0.0001	26.0	728	0.3096	0.9302
0.0001	27.0	756	0.6066	0.9070
0.0001	28.0	784	0.3940	0.9070
0.0001	29.0	812	0.3550	0.9070
0.0	30.0	840	0.4157	0.9070
0.0001	31.0	868	0.4340	0.9070
0.0166	32.0	896	0.6996	0.9070
0.0001	33.0	924	0.5595	0.9070
0.0	34.0	952	0.3606	0.9070
0.0001	35.0	980	0.4821	0.9070
0.0013	36.0	1008	0.4503	0.9070
0.0001	37.0	1036	0.4301	0.9070
0.0001	38.0	1064	0.4884	0.9070
0.0	39.0	1092	0.4958	0.9070
0.0009	40.0	1120	0.5821	0.9070
0.0001	41.0	1148	0.4696	0.9070
0.0	42.0	1176	0.4577	0.9070
0.0	43.0	1204	0.4998	0.9070
0.0	44.0	1232	0.5154	0.9070
0.0001	45.0	1260	0.5227	0.9070
0.0003	46.0	1288	0.5170	0.9070
0.0001	47.0	1316	0.5187	0.9070
0.0001	48.0	1344	0.5241	0.9070
0.0	49.0	1372	0.5241	0.9070
0.0	50.0	1400	0.5241	0.9070

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_00001_fold3

hushem_5x_beit_base_rms_00001_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_5x_beit_base_rms_00001_fold3