You can deploy this model and start earning money today!

jialicheng/
unlearn_nlvr2_vilt_salun_8_42

Name: unlearn_nlvr2_vilt_salun_8_42
Availability: InStock

safetensors

vilt

image-text-classification

generated_from_trainer

dandelin/vilt-b32-finetuned-nlvr2

finetune

apache-2.0

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: 0.9895
Accuracy: 0.7286
Dt Accuracy: 0.7286
Df Accuracy: 0.4455
Unlearn Overall Accuracy: 0.4620
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Overall Accuracy	Unlearn Overall Accuracy	Time
0.3576	1.0	2700	0.5401	0.8633	0.3184	0.3184	None
0.2904	2.0	5400	0.6146	0.7006	0.3844	0.3844	None
0.2304	3.0	8100	0.7177	0.5879	0.4224	0.4224	None
0.1933	4.0	10800	0.8702	0.5048	0.4463	0.4463	None
0.1478	5.0	13500	0.9445	0.4640	0.4573	0.4573	None
0.1158	6.0	16200	0.9895	0.4455	0.4620	0.4620	None

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.18.0
Tokenizers 0.15.2

jialicheng/unlearn_nlvr2_vilt_salun_8_42

42

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jialicheng/
unlearn_nlvr2_vilt_salun_8_42