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: 0.5159
Accuracy: 0.7947

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
1.1623	1.0	376	1.2650	0.3406
1.0872	2.0	752	1.1797	0.3656
0.9959	3.0	1128	1.0972	0.4040
0.9117	4.0	1504	1.0182	0.4641
0.8307	5.0	1880	0.9466	0.5359
0.8065	6.0	2256	0.8845	0.5943
0.7607	7.0	2632	0.8316	0.6277
0.7796	8.0	3008	0.7902	0.6477
0.7103	9.0	3384	0.7560	0.6611
0.6802	10.0	3760	0.7267	0.6745
0.6695	11.0	4136	0.7035	0.6945
0.6571	12.0	4512	0.6839	0.6995
0.6174	13.0	4888	0.6660	0.7045
0.6036	14.0	5264	0.6517	0.7145
0.6026	15.0	5640	0.6384	0.7212
0.5646	16.0	6016	0.6262	0.7312
0.5262	17.0	6392	0.6162	0.7396
0.5941	18.0	6768	0.6069	0.7412
0.5547	19.0	7144	0.5985	0.7513
0.5277	20.0	7520	0.5904	0.7529
0.5447	21.0	7896	0.5840	0.7563
0.4895	22.0	8272	0.5780	0.7613
0.5534	23.0	8648	0.5722	0.7613
0.5434	24.0	9024	0.5667	0.7629
0.5157	25.0	9400	0.5616	0.7696
0.521	26.0	9776	0.5574	0.7763
0.5165	27.0	10152	0.5535	0.7780
0.4725	28.0	10528	0.5496	0.7796
0.5119	29.0	10904	0.5463	0.7780
0.5112	30.0	11280	0.5429	0.7746
0.5018	31.0	11656	0.5394	0.7796
0.5237	32.0	12032	0.5367	0.7846
0.4645	33.0	12408	0.5340	0.7863
0.4409	34.0	12784	0.5315	0.7896
0.4837	35.0	13160	0.5294	0.7880
0.4766	36.0	13536	0.5273	0.7863
0.4405	37.0	13912	0.5255	0.7880
0.4999	38.0	14288	0.5239	0.7930
0.4612	39.0	14664	0.5226	0.7913
0.4901	40.0	15040	0.5213	0.7913
0.5002	41.0	15416	0.5202	0.7930
0.4394	42.0	15792	0.5193	0.7930
0.4541	43.0	16168	0.5184	0.7913
0.463	44.0	16544	0.5178	0.7947
0.4704	45.0	16920	0.5171	0.7930
0.5003	46.0	17296	0.5167	0.7913
0.4732	47.0	17672	0.5163	0.7947
0.4967	48.0	18048	0.5161	0.7947
0.455	49.0	18424	0.5159	0.7947
0.4609	50.0	18800	0.5159	0.7947

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_5x_beit_base_sgd_0001_fold1

smids_5x_beit_base_sgd_0001_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_5x_beit_base_sgd_0001_fold1