Vilt B32 Mlm Finetuned Vqa 800

--- library_name: transformers tags: - generated_from_trainer datasets: - vqa model-index: - name: vilt-b32-mlm-finetuned-vqa-800 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # 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

Source context: 4 downloads · 0 likes · Pipeline visual-question-answering · Library transformers · Repo guo1006/vilt-b32-mlm-finetuned-vqa-800

Source context: 7 downloads · 0 likes · Pipeline visual-question-answering · Library transformers · Repo guo1006/vilt-b32-mlm-finetuned-vqa-800