This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.3066
Accuracy: 0.9417
Precision: 0.9483
Recall: 0.9417
F1: 0.9388

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: 0.0002
train_batch_size: 32
eval_batch_size: 8
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 15
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.056	0.6667	100	0.4899	0.85	0.8963	0.85	0.8476
0.0229	1.3333	200	0.5003	0.8792	0.9087	0.8792	0.8645
0.0082	2.0	300	0.3076	0.8883	0.9190	0.8883	0.8891
0.0049	2.6667	400	0.4297	0.9067	0.9307	0.9067	0.9055
0.0355	3.3333	500	0.7084	0.8325	0.9102	0.8325	0.8265
0.0752	4.0	600	0.5323	0.875	0.8919	0.875	0.8602
0.0025	4.6667	700	0.4350	0.8983	0.9142	0.8983	0.8952
0.0018	5.3333	800	0.3244	0.935	0.9428	0.935	0.9310
0.0014	6.0	900	0.3183	0.9367	0.9443	0.9367	0.9328
0.0012	6.6667	1000	0.3114	0.9367	0.9441	0.9367	0.9330
0.0011	7.3333	1100	0.3090	0.9367	0.9442	0.9367	0.9330
0.0009	8.0	1200	0.3078	0.9392	0.9463	0.9392	0.9359
0.0008	8.6667	1300	0.3077	0.94	0.9470	0.94	0.9369
0.0008	9.3333	1400	0.3068	0.9408	0.9476	0.9408	0.9378
0.0007	10.0	1500	0.3068	0.9417	0.9483	0.9417	0.9388
0.0007	10.6667	1600	0.3066	0.9417	0.9483	0.9417	0.9388
0.0006	11.3333	1700	0.3078	0.9425	0.9490	0.9425	0.9398
0.0006	12.0	1800	0.3080	0.9425	0.9490	0.9425	0.9398
0.0006	12.6667	1900	0.3086	0.9433	0.9499	0.9433	0.9406
0.0005	13.3333	2000	0.3091	0.9433	0.9499	0.9433	0.9406
0.0005	14.0	2100	0.3093	0.9433	0.9499	0.9433	0.9406
0.0005	14.6667	2200	0.3095	0.9433	0.9499	0.9433	0.9406

Framework versions

Transformers 4.48.2
Pytorch 2.6.0+cu126
Datasets 3.2.0
Tokenizers 0.21.0

Ivanrs/vit-base-kidney-stone-Jonathan_El-Beze_-w256_1k_v1-_SEC

vit-base-kidney-stone-Jonathan_El-Beze_-w256_1k_v1-_SEC

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Ivanrs/
vit-base-kidney-stone-Jonathan_El-Beze_-w256_1k_v1-_SEC