videomae-base-ssv2-binary-finetuned-xd-violence

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-ssv2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6173
• Accuracy: 0.6712
• F1: 0.4986
• Precision: 0.5807
• Recall: 0.4368
• Specificity: 0.8114
• True Positives: 5887
• True Negatives: 18284
• False Positives: 4250
• False Negatives: 7590

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: 0.0005
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use 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: 1684

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Specificity	True Positives	True Negatives	False Positives	False Negatives
0.6785	0.2506	422	0.6556	0.6638	0.4328	0.5870	0.3427	0.8558	4619	19284	3250	8858
0.6774	1.2506	844	0.6571	0.6407	0.5602	0.5169	0.6115	0.6582	8241	14832	7702	5236
0.6654	2.2506	1266	0.6169	0.6635	0.5385	0.5532	0.5246	0.7466	7070	16823	5711	6407
0.5013	3.2482	1684	0.6173	0.6712	0.4986	0.5807	0.4368	0.8114	5887	18284	4250	7590

Framework versions

• Transformers 4.51.3
• Pytorch 2.1.0+cu118
• Datasets 3.6.0
• Tokenizers 0.21.1