You can deploy this model and start earning money today!

jialicheng/
unlearn-so_nlvr2_vilt_salun_4_87

Name: unlearn-so_nlvr2_vilt_salun_4_87
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

87

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: 1.2330
Accuracy: 0.7352
Dt Accuracy: 0.7352
Df Accuracy: 0.2575
Unlearn Overall Accuracy: 0
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: 87
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
0.2861	1.0	2700	0.5951	0.7404	0.7404	0.7404	None
0.1969	2.0	5400	0.7431	0.5264	0.8837	0.8837	None
0.1218	3.0	8100	0.9643	0.3933	0.9568	0.9568	None
0.0752	4.0	10800	1.1514	0.3051	0.9703	0.9703	None
0.0507	5.0	13500	1.2330	0.2575	0	0	None

Framework versions

Transformers 4.48.0
Pytorch 2.3.0+cu121
Datasets 2.18.0
Tokenizers 0.21.0

jialicheng/unlearn-so_nlvr2_vilt_salun_4_87

87

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jialicheng/
unlearn-so_nlvr2_vilt_salun_4_87