mitegvg/videomae-tiny-finetuned-kinetics-finetuned-sports-videos-in-the-wild

videomae-base-finetuned-kinetics-finetuned-sports-videos-in-the-wild

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

• Loss: 1.9210
• Accuracy: 0.4659
• Macro Precision: 0.3938
• Macro Recall: 0.4489
• Macro F1: 0.4007
• Weighted Precision: 0.4987
• Weighted Recall: 0.4659
• Weighted F1: 0.4613

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: 0.0005
• 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: 0.1
• training_steps: 8400

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Macro Precision	Macro Recall	Macro F1	Weighted Precision	Weighted Recall	Weighted F1
2.9626	0.0501	421	2.7906	0.2195	0.1161	0.1519	0.1070	0.2141	0.2195	0.1965
2.5842	1.0501	842	2.8099	0.2494	0.1654	0.2218	0.1441	0.2625	0.2494	0.2014
2.6205	2.0501	1263	2.5678	0.2603	0.2323	0.2441	0.1927	0.3526	0.2603	0.2535
2.6291	3.0501	1684	2.4386	0.3256	0.2617	0.2725	0.2380	0.3552	0.3256	0.3169
2.6426	4.0501	2105	2.3998	0.3380	0.2961	0.2888	0.2537	0.3914	0.3380	0.3318
2.3348	5.0501	2526	2.3434	0.3230	0.2693	0.3114	0.2395	0.3982	0.3230	0.2966
2.0078	6.0501	2947	2.3699	0.3328	0.3123	0.3292	0.2734	0.4285	0.3328	0.3271
1.9522	7.0501	3368	2.2550	0.3722	0.3517	0.3427	0.2978	0.4422	0.3722	0.3688
2.1432	8.0501	3789	2.1527	0.3832	0.3581	0.3516	0.3042	0.4461	0.3832	0.3696
2.001	9.0501	4210	2.1392	0.4189	0.3563	0.3938	0.3431	0.4775	0.4189	0.4071
2.1731	10.0501	4631	2.1665	0.4065	0.3527	0.3772	0.3215	0.4499	0.4065	0.3869
1.8674	11.0501	5052	2.0639	0.4367	0.3765	0.4068	0.3620	0.4888	0.4367	0.4332
2.1969	12.0501	5473	2.1350	0.4240	0.3609	0.3921	0.3439	0.4717	0.4240	0.4144
1.6659	13.0501	5894	1.9765	0.4448	0.3715	0.4046	0.3631	0.4803	0.4448	0.4350
1.9602	14.0501	6315	2.0385	0.4258	0.3756	0.3993	0.3537	0.4910	0.4258	0.4229
1.6218	15.0501	6736	2.0035	0.4517	0.3815	0.4311	0.3795	0.4958	0.4517	0.4450
1.6883	16.0501	7157	2.0044	0.4367	0.3913	0.4252	0.3795	0.4992	0.4367	0.4364
1.5521	17.0501	7578	1.9295	0.4568	0.3847	0.4350	0.3869	0.4823	0.4568	0.4452
1.5913	18.0501	7999	1.9850	0.4491	0.3732	0.4316	0.3804	0.4880	0.4491	0.4438
1.8007	19.0477	8400	1.9210	0.4659	0.3938	0.4489	0.4007	0.4987	0.4659	0.4613

Framework versions

• Transformers 4.51.3
• Pytorch 2.1.0+cu118
• Datasets 3.6.0
• Tokenizers 0.21.1