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: 0.5459
Accuracy: 0.8521

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: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 500
num_epochs: 16
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6394	1.56	500	0.9654	0.6948
0.4475	3.12	1000	0.5877	0.7946
0.4785	4.67	1500	0.5604	0.7959
0.3922	6.23	2000	0.5464	0.8096
0.4523	7.79	2500	0.4912	0.8340
0.2246	9.35	3000	0.5322	0.8446
0.3309	10.9	3500	0.5195	0.8483
0.2458	12.46	4000	0.5645	0.8508
0.2353	14.02	4500	0.5430	0.8539
0.1077	15.58	5000	0.5459	0.8521

Framework versions

Transformers 4.38.1
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2

sharren/vit-dropout-v12

vit-dropout-v12

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

sharren/
vit-dropout-v12