vivit-b-16x2-kinetics400-ft-48192

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7749
• Accuracy: 0.6772

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: 16
• eval_batch_size: 16
• 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: 55

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6106	1.0	55	0.7749	0.6772

Framework versions

• Transformers 4.41.2
• Pytorch 1.13.0+cu117
• Datasets 2.20.0
• Tokenizers 0.19.1