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: 0.5648
Accuracy: 0.8670

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 500
num_epochs: 20
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6877	1.56	500	0.8813	0.7185
0.509	3.12	1000	0.5928	0.7834
0.4729	4.67	1500	0.5438	0.8015
0.5043	6.23	2000	0.5439	0.8102
0.456	7.79	2500	0.4814	0.8246
0.2336	9.35	3000	0.5169	0.8452
0.3513	10.9	3500	0.4543	0.8527
0.2456	12.46	4000	0.5365	0.8583
0.2029	14.02	4500	0.5582	0.8489
0.0715	15.58	5000	0.5121	0.8633
0.0561	17.13	5500	0.5564	0.8702
0.035	18.69	6000	0.5648	0.8670

Framework versions

Transformers 4.38.1
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2

sharren/vit-dropout-v5

vit-dropout-v5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

sharren/
vit-dropout-v5