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

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

• Loss: 1.2459
• Accuracy: 0.7390
• Macro Precision: 0.6841
• Macro Recall: 0.7041
• Macro F1: 0.6794
• Weighted Precision: 0.7585
• Weighted Recall: 0.7390
• Weighted F1: 0.7387

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
1.2204	0.0501	421	1.1108	0.6894	0.6924	0.6300	0.6008	0.7884	0.6894	0.6892
1.7618	1.0501	842	2.7681	0.2486	0.4176	0.2548	0.2091	0.5022	0.2486	0.2358
1.7638	2.0501	1263	1.9365	0.4506	0.4132	0.4221	0.3617	0.5364	0.4506	0.4388
1.8434	3.0501	1684	1.5640	0.5341	0.5409	0.4817	0.4486	0.6391	0.5341	0.5364
1.5955	4.0501	2105	1.5658	0.5286	0.5077	0.4801	0.4426	0.6269	0.5286	0.5313
1.5636	5.0501	2526	1.5974	0.5231	0.5107	0.4845	0.4298	0.6333	0.5231	0.5234
1.1748	6.0501	2947	1.6057	0.5272	0.5018	0.5118	0.4664	0.6058	0.5272	0.5330
1.1044	7.0501	3368	1.6165	0.5417	0.5590	0.5376	0.4829	0.6586	0.5417	0.5507
1.1299	8.0501	3789	1.2119	0.6416	0.6008	0.5956	0.5717	0.6872	0.6416	0.6439
1.0032	9.0501	4210	1.2500	0.6329	0.5785	0.6167	0.5724	0.6862	0.6329	0.6356
0.868	10.0501	4631	1.2941	0.6486	0.6050	0.6134	0.5797	0.7012	0.6486	0.6571
0.8019	11.0501	5052	1.2717	0.6464	0.6060	0.6011	0.5751	0.6786	0.6464	0.6444
0.6542	12.0501	5473	1.3538	0.6723	0.6311	0.6304	0.6022	0.7141	0.6723	0.6722
0.4904	13.0501	5894	1.2139	0.6854	0.6597	0.6489	0.6288	0.7221	0.6854	0.6869
0.4932	14.0501	6315	1.3426	0.6872	0.6418	0.6527	0.6218	0.7203	0.6872	0.6827
0.3553	15.0501	6736	1.1960	0.7094	0.6566	0.6612	0.6379	0.7378	0.7094	0.7110
0.2959	16.0501	7157	1.3035	0.7036	0.6523	0.6686	0.6424	0.7339	0.7036	0.7072
0.2581	17.0501	7578	1.2599	0.7193	0.6591	0.6807	0.6610	0.7355	0.7193	0.7205
0.3225	18.0501	7999	1.2928	0.7258	0.6699	0.6941	0.6676	0.7488	0.7258	0.7247
0.0969	19.0477	8400	1.2459	0.7390	0.6841	0.7041	0.6794	0.7585	0.7390	0.7387

Framework versions

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