videomae-base-finetuned-ucf101-subset

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: 0.6489
• Accuracy: 0.5728

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 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: 0.05
• training_steps: 3500

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2468	0.0503	176	0.4671	0.8314
0.0679	1.0503	352	0.5236	0.6416
0.2776	2.0503	528	0.8299	0.5188
0.1569	3.0503	704	1.3045	0.6399
0.0234	4.0503	880	0.8917	0.6448
0.0085	5.0503	1056	1.0954	0.6481

Framework versions

• Transformers 4.48.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0