Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
my_awesome_food_model – AI Model by mejdik | AlphaNeural AI
You can deploy this model and start earning money today!
mejdik
/
my_awesome_food_model
like
0
transformers
pytorch
tensorboard
vit
image-classification
generated_from_trainer
apache-2.0
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
my_awesome_food_model
This model is a fine-tuned version of
google/vit-base-patch16-224-in21k
on the None dataset. It achieves the following results on the evaluation set:
Loss: 1.6104
Accuracy: 0.888
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: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
2.7402
0.99
62
2.5338
0.83
1.8551
2.0
125
1.7845
0.871
1.5841
2.98
186
1.6104
0.888
Framework versions
Transformers 4.27.2
Pytorch 1.13.1+cu117
Datasets 2.11.0
Tokenizers 0.13.3
