VideoMAEv2-Huge-finetuned-deception-dataset-mae-huge – AI Model by NiklasTUM | AlphaNeural AI

You can deploy this model and start earning money today!

NiklasTUM/
VideoMAEv2-Huge-finetuned-deception-dataset-mae-huge

like

0

video-classification

generated_from_trainer

OpenGVLab/VideoMAEv2-Huge

endpoints_compatible

Views

No views yet

VideoMAEv2-Huge-finetuned-deception-dataset-mae-huge

This model is a fine-tuned version of OpenGVLab/VideoMAEv2-Huge on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.3499
Accuracy: 0.4074

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
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: 0.1
training_steps: 300

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7736	1.0	38	0.9148	0.7037
0.6591	2.0	76	0.8406	0.3333
0.7471	3.0	114	0.9379	0.3086
0.702	4.0	152	0.9688	0.2840
0.6571	5.0	190	1.1333	0.3086
0.5764	6.0	228	1.3130	0.3457
0.5255	7.0	266	1.3296	0.3210
0.4883	7.8947	300	1.3499	0.4074

Framework versions

Transformers 4.48.0
Pytorch 2.1.0+cu121
Datasets 2.14.4
Tokenizers 0.21.1