test-hasy-2 – AI Model by khaingsmon | AlphaNeural AI

You can deploy this model and start earning money today!

khaingsmon/
test-hasy-2

like

0

image-classification

generated_from_trainer

google/vit-base-patch16-224-in21k

autotrain_compatible

endpoints_compatible

Views

No views yet

test-hasy-2

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

Loss: 4.5699
Accuracy: 0.0746

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: 0.005
train_batch_size: 64
eval_batch_size: 64
seed: 1787
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
5.2717	1.0	1893	5.1372	0.0461
5.0979	2.0	3786	5.0524	0.0480
5.0857	3.0	5679	5.0613	0.0504
5.0233	4.0	7572	5.0143	0.0474
4.9581	5.0	9465	4.8227	0.0612
4.9241	6.0	11358	4.8247	0.0568
4.8754	7.0	13251	4.7613	0.0693
4.7899	8.0	15144	4.7289	0.0737
4.7158	9.0	17037	4.6115	0.0737
4.647	10.0	18930	4.5699	0.0746

Framework versions

Transformers 4.38.2
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2