vit-finetuned-1 – AI Model by DeepTrader | AlphaNeural AI

You can deploy this model and start earning money today!

DeepTrader/
vit-finetuned-1

like

0

image-classification

generated_from_trainer

google/vit-base-patch16-224

autotrain_compatible

endpoints_compatible

Views

No views yet

vit-finetuned-1

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

Loss: 1.2750
Accuracy: 0.5

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: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	0.1575	1.0
No log	2.0	2	0.1166	1.0
No log	3.0	3	0.2496	1.0
No log	4.0	4	0.4093	0.5
No log	5.0	5	0.6732	0.5
No log	6.0	6	0.9200	0.5
No log	7.0	7	1.0925	0.5
No log	8.0	8	1.1963	0.5
No log	9.0	9	1.2521	0.5
No log	10.0	10	1.2750	0.5

Framework versions

Transformers 4.46.1
Pytorch 2.5.1+cpu
Datasets 3.1.0
Tokenizers 0.20.1