You can deploy this model and start earning money today!

KingTechnician/
videomae-small-finetuned-kinetics-finetuned-xd-violence

Name: videomae-small-finetuned-kinetics-finetuned-xd-violence
Availability: InStock

Views

No views yet

videomae-small-finetuned-kinetics-finetuned-xd-violence

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

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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
num_epochs: 15

Training Loss	Epoch	Step	Validation Loss	Average Precision	Roc Auc	F1	Precision	Recall
0.8099	1.0	394	0.6450	0.8198	0.8438	0.7392	0.6162	0.9235
0.7804	2.0	788	0.4504	0.8869	0.8806	0.7953	0.7911	0.7995
0.2893	3.0	1182	0.5552	0.9038	0.8964	0.6445	0.9583	0.4855
0.2545	4.0	1576	0.4545	0.8896	0.8823	0.7938	0.7758	0.8127
0.347	5.0	1970	0.4027	0.9090	0.8990	0.8166	0.8555	0.7810
1.0467	6.0	2364	0.3964	0.9273	0.9174	0.8301	0.8045	0.8575
0.0625	7.0	2758	0.3829	0.9217	0.9158	0.8289	0.7976	0.8628
0.7176	8.0	3152	0.4002	0.9229	0.9192	0.8333	0.7882	0.8839
0.241	9.0	3546	0.3717	0.9259	0.9208	0.8361	0.8669	0.8074
0.1018	10.0	3940	0.4070	0.9303	0.9242	0.8111	0.9112	0.7309
1.0353	11.0	4334	0.3647	0.9372	0.9342	0.848	0.8571	0.8391
0.1839	12.0	4728	0.3625	0.9324	0.9277	0.8479	0.8654	0.8311
0.0139	13.0	5122	0.3726	0.9325	0.9267	0.8450	0.88	0.8127
0.1475	14.0	5516	0.3698	0.9383	0.9330	0.8586	0.8444	0.8734
0.018	15.0	5910	0.3757	0.9380	0.9356	0.8612	0.8469	0.8760