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: 0.4509
Accuracy: 0.8217

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
1.119	1.0	375	1.2346	0.355
1.0823	2.0	750	1.1546	0.3883
0.9626	3.0	1125	1.0734	0.4317
0.8877	4.0	1500	0.9982	0.49
0.8704	5.0	1875	0.9307	0.5383
0.82	6.0	2250	0.8704	0.5833
0.7688	7.0	2625	0.8174	0.63
0.7442	8.0	3000	0.7715	0.6583
0.726	9.0	3375	0.7322	0.6833
0.6394	10.0	3750	0.6995	0.695
0.6379	11.0	4125	0.6704	0.7167
0.6169	12.0	4500	0.6463	0.735
0.5956	13.0	4875	0.6254	0.7483
0.617	14.0	5250	0.6064	0.7617
0.6108	15.0	5625	0.5908	0.7717
0.578	16.0	6000	0.5757	0.7767
0.591	17.0	6375	0.5636	0.7817
0.5966	18.0	6750	0.5528	0.785
0.6007	19.0	7125	0.5440	0.7883
0.5282	20.0	7500	0.5352	0.7983
0.5197	21.0	7875	0.5276	0.8033
0.5125	22.0	8250	0.5198	0.8067
0.5868	23.0	8625	0.5131	0.8083
0.5885	24.0	9000	0.5069	0.8117
0.5176	25.0	9375	0.5018	0.8133
0.5257	26.0	9750	0.4968	0.8167
0.563	27.0	10125	0.4923	0.8167
0.5177	28.0	10500	0.4880	0.815
0.5208	29.0	10875	0.4843	0.8183
0.4749	30.0	11250	0.4801	0.8183
0.5211	31.0	11625	0.4762	0.8167
0.5578	32.0	12000	0.4734	0.8167
0.5196	33.0	12375	0.4707	0.8183
0.5191	34.0	12750	0.4684	0.82
0.4852	35.0	13125	0.4662	0.82
0.4553	36.0	13500	0.4634	0.8183
0.4575	37.0	13875	0.4613	0.82
0.5121	38.0	14250	0.4600	0.82
0.4948	39.0	14625	0.4580	0.82
0.5112	40.0	15000	0.4566	0.82
0.5002	41.0	15375	0.4556	0.82
0.4865	42.0	15750	0.4545	0.82
0.5291	43.0	16125	0.4534	0.82
0.4479	44.0	16500	0.4529	0.82
0.4858	45.0	16875	0.4523	0.82
0.5195	46.0	17250	0.4518	0.82
0.5088	47.0	17625	0.4513	0.8217
0.4798	48.0	18000	0.4511	0.8217
0.4938	49.0	18375	0.4509	0.8217
0.4932	50.0	18750	0.4509	0.8217

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_fold5

smids_5x_beit_base_sgd_0001_fold5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hkivancoral/
smids_5x_beit_base_sgd_0001_fold5