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: 3.6981
Accuracy: 0.4444

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
No log	1.0	6	1.5800	0.2444
2.0893	2.0	12	1.3869	0.3333
2.0893	3.0	18	1.3893	0.2444
1.4148	4.0	24	1.3366	0.3333
1.3117	5.0	30	1.3938	0.2889
1.3117	6.0	36	1.5221	0.3778
1.2096	7.0	42	1.7519	0.4222
1.2096	8.0	48	1.6213	0.2444
1.1162	9.0	54	1.4721	0.2889
1.0871	10.0	60	1.3748	0.3333
1.0871	11.0	66	1.7274	0.4667
1.0753	12.0	72	3.1976	0.3333
1.0753	13.0	78	1.3693	0.4222
1.2635	14.0	84	1.5090	0.3778
0.9248	15.0	90	1.4886	0.5333
0.9248	16.0	96	1.4765	0.4444
0.8798	17.0	102	1.9348	0.4222
0.8798	18.0	108	1.3064	0.4667
0.8666	19.0	114	1.5832	0.4444
0.7171	20.0	120	2.1360	0.4444
0.7171	21.0	126	1.7636	0.4444
0.7588	22.0	132	2.3529	0.3556
0.7588	23.0	138	2.7880	0.3556
0.6002	24.0	144	1.8764	0.4222
0.5204	25.0	150	2.9921	0.4
0.5204	26.0	156	2.6311	0.4444
0.4748	27.0	162	2.1490	0.4889
0.4748	28.0	168	2.4874	0.4889
0.4423	29.0	174	1.9273	0.4444
0.3826	30.0	180	3.0375	0.4222
0.3826	31.0	186	3.0775	0.4667
0.3486	32.0	192	2.5400	0.4
0.3486	33.0	198	3.1424	0.4444
0.3116	34.0	204	2.9144	0.4667
0.2168	35.0	210	3.3792	0.4444
0.2168	36.0	216	3.7895	0.4667
0.2383	37.0	222	3.1800	0.4889
0.2383	38.0	228	3.3532	0.4444
0.1463	39.0	234	3.6524	0.4222
0.1584	40.0	240	3.6346	0.4444
0.1584	41.0	246	3.6838	0.4444
0.1431	42.0	252	3.6981	0.4444
0.1431	43.0	258	3.6981	0.4444
0.1356	44.0	264	3.6981	0.4444
0.139	45.0	270	3.6981	0.4444
0.139	46.0	276	3.6981	0.4444
0.1502	47.0	282	3.6981	0.4444
0.1502	48.0	288	3.6981	0.4444
0.128	49.0	294	3.6981	0.4444
0.1474	50.0	300	3.6981	0.4444

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

hkivancoral/hushem_1x_beit_base_adamax_001_fold1

hushem_1x_beit_base_adamax_001_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
hushem_1x_beit_base_adamax_001_fold1