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: 1.0773
Accuracy: 0.8867

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
0.0052	11.0	4125	0.8001	0.8783
0.0189	12.0	4500	0.8578	0.8833
0.0009	13.0	4875	0.8974	0.88
0.0122	14.0	5250	0.9013	0.885
0.0628	15.0	5625	0.9434	0.875
0.0114	16.0	6000	0.9650	0.8733
0.0367	17.0	6375	0.9453	0.885
0.0138	18.0	6750	0.9235	0.8833
0.0185	19.0	7125	0.9504	0.8783
0.0147	20.0	7500	0.9928	0.8883
0.0067	21.0	7875	0.9826	0.8867
0.0174	22.0	8250	1.0361	0.8817
0.0198	23.0	8625	1.0257	0.8767
0.0001	24.0	9000	1.0258	0.885
0.0333	25.0	9375	1.0061	0.885
0.0008	26.0	9750	1.0277	0.8867
0.014	27.0	10125	1.0251	0.8833
0.0001	28.0	10500	1.0047	0.89
0.0006	29.0	10875	0.9963	0.89
0.0315	30.0	11250	1.0164	0.8833
0.0036	31.0	11625	1.0188	0.8883
0.0321	32.0	12000	1.0423	0.885
0.0001	33.0	12375	1.0241	0.89
0.0007	34.0	12750	1.0270	0.8883
0.0001	35.0	13125	1.0742	0.89
0.0009	36.0	13500	1.0587	0.8883
0.0086	37.0	13875	1.0716	0.8833
0.0329	38.0	14250	1.0601	0.8917
0.0002	39.0	14625	1.0796	0.8867
0.0003	40.0	15000	1.0705	0.88
0.0076	41.0	15375	1.0541	0.8833
0.0006	42.0	15750	1.0775	0.885
0.0002	43.0	16125	1.0701	0.885
0.0068	44.0	16500	1.0578	0.8933
0.0	45.0	16875	1.0747	0.8883
0.0158	46.0	17250	1.0767	0.89
0.0066	47.0	17625	1.0837	0.89
0.0106	48.0	18000	1.0810	0.8867
0.0002	49.0	18375	1.0785	0.885
0.0001	50.0	18750	1.0773	0.8867

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2

hkivancoral/smids_5x_beit_base_adamax_00001_fold4

smids_5x_beit_base_adamax_00001_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_5x_beit_base_adamax_00001_fold4