mvit_v2_s_transf_BLANK_RWF-2000_DETECTION

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

• Loss: 0.5664
• Accuracy: 0.7087
• F1: 0.7077
• Precision: 0.7117

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: 1e-05
• train_batch_size: 10
• eval_batch_size: 10
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 3040

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision
0.7914	0.05	152	0.6987	0.5	0.4244	0.5
0.7892	1.05	304	0.6575	0.6438	0.6437	0.6438
0.5806	2.05	456	0.6574	0.6188	0.5947	0.6558
0.6487	3.05	608	0.6248	0.6312	0.5996	0.692
0.668	4.05	760	0.6245	0.6438	0.6375	0.6544
0.7398	5.05	912	0.5888	0.6687	0.6629	0.6812
0.6621	6.05	1064	0.6173	0.6625	0.6423	0.7098
0.5945	7.05	1216	0.5816	0.6937	0.6801	0.7335
0.5693	8.05	1368	0.6057	0.6562	0.6561	0.6565
0.5848	9.05	1520	0.5924	0.7125	0.7096	0.7214
0.6631	10.05	1672	0.5978	0.6625	0.6623	0.6629
0.6597	11.05	1824	0.5847	0.7063	0.7029	0.7160
0.5901	12.05	1976	0.5658	0.7375	0.7368	0.7399
0.5397	13.05	2128	0.5914	0.7188	0.7179	0.7216
0.5744	14.05	2280	0.5554	0.7312	0.7282	0.7422
0.5553	15.05	2432	0.5852	0.7	0.6952	0.7133
0.5694	16.05	2584	0.6053	0.6813	0.6802	0.6836
0.4737	17.05	2736	0.5840	0.7125	0.7123	0.7130

Framework versions

• Transformers 4.44.2
• Pytorch 2.0.1+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1