vivit-b-16x2-kinetics400-finetuned-cricket_shot_detection_31

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: 1.0141
• Accuracy: 0.6667
• F1: 0.6537
• Recall: 0.6667
• Precision: 0.75

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: 4e-06
• train_batch_size: 4
• eval_batch_size: 4
• 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: 0.1
• training_steps: 4624

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Recall	Precision
1.7482	0.0314	145	1.7665	0.2	0.1133	0.2	0.0794
1.3969	1.0314	290	1.5064	0.6	0.5700	0.6	0.6422
1.0075	2.0314	435	1.2230	0.5333	0.5467	0.5333	0.5778
0.805	3.0314	580	0.9838	0.6667	0.6537	0.6667	0.75
0.9045	4.0314	725	1.0228	0.6	0.5676	0.6	0.5444
0.4916	5.0314	870	1.0251	0.6667	0.6448	0.6667	0.7056
0.2283	6.0314	1015	1.0003	0.6667	0.6537	0.6667	0.75

Framework versions

• Transformers 4.47.0
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0