Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
FINAL_FT_blur_vit_train_severity_4_subset_10000_balanced_ep-10_pat-4 – AI Model by CVPROJ25 | AlphaNeural AI
You can deploy this model and start earning money today!
CVPROJ25
/
FINAL_FT_blur_vit_train_severity_4_subset_10000_balanced_ep-10_pat-4
like
0
transformers
safetensors
vit
image-classification
generated_from_trainer
google/vit-base-patch16-224
finetune
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
FINAL_FT_blur_vit_train_severity_4_subset_10000_balanced_ep-10_pat-4
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: 1.1924
Accuracy: 0.717
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: 5e-05
train_batch_size: 512
eval_batch_size: 16
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
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
1.1393
1.0
16
1.1169
0.727
0.5593
2.0
32
1.1045
0.732
0.4031
3.0
48
1.1346
0.7285
0.2130
4.0
64
1.1611
0.7215
0.1215
5.0
80
1.1778
0.7215
0.0832
6.0
96
1.1924
0.717
Framework versions
Transformers 5.2.0
Pytorch 2.5.1
Datasets 4.6.1
Tokenizers 0.22.1
