videomae-base-finetuned-cricket_shot_detection_18

This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.4708
• Accuracy: 0.5789
• F1: 0.5987
• Recall: 0.5789
• Precision: 0.7316

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: 6e-06
• train_batch_size: 12
• eval_batch_size: 12
• 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: 288

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Recall	Precision
1.7521	0.1701	49	1.7640	0.1579	0.1971	0.1579	0.2632
1.6025	1.1701	98	1.6926	0.2105	0.2205	0.2105	0.2782
1.3708	2.1701	147	1.6164	0.3158	0.3062	0.3158	0.3544
1.1786	3.1701	196	1.5217	0.4211	0.4042	0.4211	0.4158
1.0709	4.1701	245	1.4708	0.5789	0.5987	0.5789	0.7316
1.0057	5.1493	288	1.4721	0.5789	0.5982	0.5789	0.7246

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0