NiklasTUM/videomae-large-finetuned-deception-dataset_v2

<!-- 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. -->

videomae-large-finetuned-deception-dataset_v2

This model is a fine-tuned version of MCG-NJU/videomae-large on an unknown dataset. It achieves the following results on the evaluation set:

• —Loss: 1.1396
• —Accuracy: 0.6543

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: 3e-05
• —trainbatchsize: 5
• —evalbatchsize: 5
• —seed: 42
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 40
• —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: linear
• —lrschedulerwarmup_ratio: 0.1
• —training_steps: 120

Training results

Framework versions

• —Transformers 4.48.0
• —Pytorch 2.1.0+cu121
• —Datasets 2.14.4
• —Tokenizers 0.21.1