vilt-b32-mlm-finetuned-vqa-800 – AI Model by guo1006 | AlphaNeural AI

You can deploy this model and start earning money today!

guo1006/
vilt-b32-mlm-finetuned-vqa-800

like

0

visual-question-answering

generated_from_trainer

endpoints_compatible

Views

No views yet

vilt-b32-mlm-finetuned-vqa-800

This model was trained from scratch on the vqa dataset. It achieves the following results on the evaluation set:

Loss: 6.9132

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
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.05
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
41.4022	2.2727	100	14.2966
7.169	4.5455	200	7.4662
6.1608	6.8182	300	7.0192
5.5909	9.0909	400	6.8976
4.8872	11.3636	500	6.9216
4.2963	13.6364	600	6.9069
3.8187	15.9091	700	6.8984
3.5386	18.1818	800	6.9082

Framework versions

Transformers 4.52.4
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.2