vivit-b-16x2-kinetics400-finetuned-cricket_shot_detection_14

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: 1.0573
• Accuracy: 0.6316
• F1: 0.6559
• Recall: 0.6316
• Precision: 0.7018

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: 7e-06
• 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: 0.2
• training_steps: 576

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Recall	Precision
1.6885	0.1267	73	1.7082	0.1579	0.1853	0.1579	0.4684
1.2348	1.1267	146	1.3958	0.4211	0.4354	0.4211	0.5088
0.8271	2.1267	219	1.1646	0.4737	0.5416	0.4737	0.6754
0.688	3.1267	292	1.0573	0.6316	0.6559	0.6316	0.7018
0.6263	4.1267	365	1.0327	0.5789	0.5982	0.5789	0.6579
0.4942	5.1267	438	1.0107	0.6316	0.6333	0.6316	0.6535
0.3217	6.1267	511	1.0271	0.5789	0.5982	0.5789	0.6579

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0