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: 1.0796
Accuracy: 0.8883

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
0.2789	1.0	375	0.3658	0.8517
0.2051	2.0	750	0.3746	0.855
0.0849	3.0	1125	0.3986	0.87
0.1357	4.0	1500	0.4367	0.8633
0.0524	5.0	1875	0.4518	0.8867
0.0622	6.0	2250	0.5510	0.8867
0.0413	7.0	2625	0.6374	0.8767
0.0498	8.0	3000	0.6614	0.88
0.0181	9.0	3375	0.6937	0.8867
0.013	10.0	3750	0.7663	0.8817
0.0051	11.0	4125	0.8001	0.8783
0.0188	12.0	4500	0.8577	0.8817
0.0009	13.0	4875	0.8978	0.8783
0.0123	14.0	5250	0.9022	0.885
0.0631	15.0	5625	0.9459	0.875
0.0113	16.0	6000	0.9699	0.8717
0.0335	17.0	6375	0.9476	0.8867
0.014	18.0	6750	0.9219	0.8833
0.0214	19.0	7125	0.9440	0.8833
0.0134	20.0	7500	0.9965	0.8883
0.0053	21.0	7875	0.9823	0.8883
0.0026	22.0	8250	1.0367	0.8817
0.0174	23.0	8625	1.0171	0.8833
0.0002	24.0	9000	1.0087	0.8817
0.032	25.0	9375	1.0135	0.8917
0.0014	26.0	9750	1.0465	0.885
0.0249	27.0	10125	1.0322	0.8833
0.0001	28.0	10500	1.0170	0.8917
0.0002	29.0	10875	1.0011	0.8933
0.0298	30.0	11250	1.0259	0.89
0.006	31.0	11625	1.0094	0.8867
0.0305	32.0	12000	1.0462	0.885
0.0001	33.0	12375	1.0305	0.8917
0.0011	34.0	12750	1.0273	0.89
0.0001	35.0	13125	1.0726	0.89
0.0022	36.0	13500	1.0573	0.8917
0.0086	37.0	13875	1.0713	0.8833
0.0263	38.0	14250	1.0516	0.89
0.0001	39.0	14625	1.0815	0.8867
0.0002	40.0	15000	1.0626	0.8833
0.0099	41.0	15375	1.0610	0.8883
0.0004	42.0	15750	1.0801	0.885
0.0001	43.0	16125	1.0685	0.8867
0.007	44.0	16500	1.0616	0.8967
0.0	45.0	16875	1.0741	0.8917
0.0172	46.0	17250	1.0800	0.8883
0.004	47.0	17625	1.0888	0.89
0.0113	48.0	18000	1.0832	0.8867
0.0002	49.0	18375	1.0808	0.8867
0.0001	50.0	18750	1.0796	0.8883

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_3x_beit_base_adamax_00001_fold4

smids_3x_beit_base_adamax_00001_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_3x_beit_base_adamax_00001_fold4