Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
unlearn-cl_nlvr2_vilt_bad_teaching_10_42 – AI Model by jialicheng | AlphaNeural AI
You can deploy this model and start earning money today!
jialicheng
/
unlearn-cl_nlvr2_vilt_bad_teaching_10_42
like
0
safetensors
vilt
image-text-classification
generated_from_trainer
dandelin/vilt-b32-finetuned-nlvr2
finetune
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
nlvr2_42
This model is a fine-tuned version of
dandelin/vilt-b32-finetuned-nlvr2
on the nlvr2 dataset. It achieves the following results on the evaluation set:
Loss: 67.9681
Accuracy: 0.7442
Test Accuracy: 0.7442
Df Accuracy: 0.7836
Unlearn Overall Accuracy: 0.4803
Unlearn Time: 9091.6670
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: 32
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
Overall Accuracy
Unlearn Overall Accuracy
Time
0.0
1.0
4859
50.4927
0.8104
0.4566
0.4566
-1
0.0
2.0
9718
67.9681
0.7836
0.4803
0.4803
-1
Framework versions
Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.15.2
