vivit-b-16x2-kinetics400-finetuned-0505-mediapipe

This model is a fine-tuned version of google/vivit-b-16x2-kinetics400 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3416
• Accuracy: 0.54

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: 2
• eval_batch_size: 2
• 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: 520

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.5013	0.1019	53	2.4211	0.1
2.2648	1.1019	106	2.2881	0.16
1.6509	2.1019	159	2.2324	0.28
0.6919	3.1019	212	1.5626	0.54
0.3172	4.1019	265	1.3768	0.56
0.0896	5.1019	318	1.3324	0.54
0.0149	6.1019	371	1.3616	0.58
0.0057	7.1019	424	1.3328	0.54
0.0029	8.1019	477	1.3432	0.58
0.003	9.0827	520	1.3416	0.54

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1