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: 0.0835
• Accuracy: 0.9745

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 308

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.043	0.2532	78	0.6808	0.8357
0.2329	1.2532	156	0.4166	0.8452
0.1877	2.2532	234	0.1584	0.9289
0.0429	3.2403	308	0.0736	0.9842

Framework versions

• Transformers 4.45.1
• Pytorch 2.3.0
• Datasets 2.19.1
• Tokenizers 0.20.0