videomae-small-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: 1.8809
• Accuracy: 0.4885
• Macro Precision: 0.4193
• Macro Recall: 0.4615
• Macro F1: 0.4211
• Weighted Precision: 0.5286
• Weighted Recall: 0.4885
• Weighted F1: 0.4912

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: 0.0003
• 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
2.9749	0.0501	421	2.8242	0.2173	0.1185	0.1514	0.1106	0.2292	0.2173	0.2043
2.6206	1.0501	842	2.9475	0.1903	0.1594	0.1931	0.1184	0.2354	0.1903	0.1529
2.613	2.0501	1263	2.4696	0.2887	0.2318	0.2691	0.2027	0.3583	0.2887	0.2657
2.6323	3.0501	1684	2.4388	0.3343	0.2885	0.2806	0.2276	0.3987	0.3343	0.3145
2.5162	4.0501	2105	2.3297	0.3595	0.2928	0.3087	0.2545	0.4058	0.3595	0.3391
2.2705	5.0501	2526	2.2225	0.3595	0.3278	0.3469	0.2809	0.4444	0.3595	0.3428
1.9641	6.0501	2947	2.3600	0.3365	0.3708	0.3335	0.2857	0.4769	0.3365	0.3327
2.0005	7.0501	3368	2.2221	0.3828	0.3515	0.3602	0.3079	0.4536	0.3828	0.3791
1.9682	8.0501	3789	2.1732	0.3784	0.3590	0.3550	0.3065	0.4540	0.3784	0.3731
1.8685	9.0501	4210	2.0484	0.4273	0.3963	0.4070	0.3686	0.5218	0.4273	0.4289
1.8785	10.0501	4631	2.1011	0.4196	0.3903	0.3817	0.3435	0.4751	0.4196	0.4110
1.5658	11.0501	5052	2.0113	0.4386	0.3928	0.3924	0.3597	0.4963	0.4386	0.4375
1.7904	12.0501	5473	2.0118	0.4404	0.3921	0.4118	0.3725	0.4953	0.4404	0.4390
1.5856	13.0501	5894	1.9331	0.4604	0.4076	0.4213	0.3922	0.5053	0.4604	0.4600
1.7294	14.0501	6315	1.9973	0.4444	0.3914	0.4208	0.3812	0.5031	0.4444	0.4490
1.3241	15.0501	6736	1.9553	0.4612	0.4010	0.4344	0.3879	0.5226	0.4612	0.4616
1.3435	16.0501	7157	1.9768	0.4645	0.4060	0.4474	0.3969	0.5299	0.4645	0.4625
1.2306	17.0501	7578	1.9022	0.4728	0.4078	0.4367	0.4016	0.5212	0.4728	0.4723
1.2575	18.0501	7999	1.8809	0.4816	0.4117	0.4529	0.4118	0.5295	0.4816	0.4841
1.3788	19.0477	8400	1.8809	0.4885	0.4193	0.4615	0.4211	0.5286	0.4885	0.4912

Framework versions

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