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

Loss: 0.0013
Accuracy: 1.0

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: 16
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: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1405	0.3448	100	0.0269	0.9981
0.0862	0.6897	200	0.0432	0.9865
0.0058	1.0345	300	0.0057	1.0
0.0038	1.3793	400	0.0037	1.0
0.0028	1.7241	500	0.0028	1.0
0.0022	2.0690	600	0.0022	1.0
0.0019	2.4138	700	0.0018	1.0
0.0016	2.7586	800	0.0016	1.0
0.0015	3.1034	900	0.0015	1.0
0.0014	3.4483	1000	0.0014	1.0
0.0013	3.7931	1100	0.0013	1.0

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

ishaansaxena/vit-base-beans

vit-base-beans

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

ishaansaxena/
vit-base-beans