videomae-base-finetuned-4p6

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: 0.6323
• Accuracy: 0.6366
• Precision: 0.6981
• Recall: 0.5896
• F1: 0.3536

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
• 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: 444

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.691	0.2523	112	0.7054	0.4968	0.4941	0.4940	0.4514
0.6241	1.2523	224	0.6614	0.6178	0.6754	0.5723	0.3103
0.5912	2.2523	336	0.6556	0.6083	0.6084	0.5755	0.4058
0.5839	3.2432	444	0.6975	0.6146	0.6329	0.5757	0.3665

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu118
• Datasets 3.5.0
• Tokenizers 0.21.1