videomae-base-furtos

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

• Loss: 0.3726
• Accuracy: 0.95

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 64

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.125	8	0.7644	0.4
0.7578	1.125	16	0.8079	0.55
0.6084	2.125	24	0.7155	0.55
0.6016	3.125	32	0.6016	0.6
0.5236	4.125	40	0.6041	0.65
0.5236	5.125	48	0.4796	0.75
0.547	6.125	56	0.3917	0.95
0.4097	7.125	64	0.3726	0.95

Framework versions

• Transformers 4.44.2
• Pytorch 2.3.1+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1