Asadali12/Cricket_Shot_Detection_vivit_finetuned_1

results

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: 0.3873
• Accuracy: 0.875
• F1: 0.8562
• Recall: 0.875
• Precision: 0.9167

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-06
• 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: cosine
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 2532

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Recall	Precision
1.1366	0.1252	317	1.0356	0.6875	0.6801	0.6875	0.8125
0.5459	1.1252	634	0.7478	0.75	0.7467	0.75	0.8781
0.2704	2.1252	951	0.5667	0.75	0.7240	0.75	0.8625
0.4092	3.1252	1268	0.3873	0.875	0.8562	0.875	0.9167
0.3253	4.1252	1585	0.3657	0.875	0.8562	0.875	0.9167
0.1802	5.1252	1902	0.3425	0.875	0.8646	0.875	0.9375
0.1428	6.1252	2219	0.3689	0.8125	0.8003	0.8125	0.8906

Framework versions

• Transformers 4.44.2
• Pytorch 1.13.1+cu117
• Datasets 3.2.0
• Tokenizers 0.19.1