vivit-b-16x2-kinetics400-finetuned-cricket_shot_detection_12

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: 0.9751
• Accuracy: 0.5789
• F1: 0.5857
• Recall: 0.5789
• Precision: 0.6053

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: 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
• training_steps: 1152

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Recall	Precision
1.3542	0.1259	145	1.2326	0.4737	0.5160	0.4737	0.6
0.6744	1.1259	290	1.1345	0.4737	0.4793	0.4737	0.5545
0.5513	2.1259	435	0.9751	0.5789	0.5857	0.5789	0.6053
0.3373	3.1259	580	0.9298	0.5789	0.5807	0.5789	0.6
0.4953	4.1259	725	0.9415	0.5789	0.6003	0.5789	0.6526
0.336	5.1259	870	0.8837	0.5789	0.5857	0.5789	0.6053

Framework versions

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