You can deploy this model and start earning money today!

jialicheng/
unlearn_nlvr2_vilt_bad_teaching_4_42

Name: unlearn_nlvr2_vilt_bad_teaching_4_42
Availability: InStock

transformers

safetensors

vilt

image-text-classification

generated_from_trainer

dandelin/vilt-b32-finetuned-nlvr2

finetune

apache-2.0

endpoints_compatible

Views

No views yet

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: 0.5265
Accuracy: 0.7343
Dt Accuracy: 0.7343
Df Accuracy: 0.8677
Unlearn Overall Accuracy: 0.6290
Unlearn Time: None

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: 1e-05
train_batch_size: 32
eval_batch_size: 64
seed: 42
optimizer: Use 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Overall Accuracy	Unlearn Overall Accuracy	Time
No log	1.0	216	0.5532	0.8941	0.6044	0.6044	None
No log	2.0	432	0.5348	0.8991	0.6012	0.6012	None
0.4692	3.0	648	0.5280	0.8872	0.6121	0.6121	None
0.4692	4.0	864	0.5273	0.8677	0.6289	0.6289	None
0.2457	5.0	1080	0.5265	0.8677	0.6290	0.6290	None

Framework versions

Transformers 4.48.0
Pytorch 2.3.0+cu121
Datasets 2.18.0
Tokenizers 0.21.0

jialicheng/unlearn_nlvr2_vilt_bad_teaching_4_42

42

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jialicheng/
unlearn_nlvr2_vilt_bad_teaching_4_42