what should be the ideal mAP0.95 should be?

[saumya221]

Hi,
I am training yolor_csp with a single class of ~1500 images, where 400 images are negative images. train test split is of the ratio 80:20. While training with fine-tune hyper parameters for 1280 size for 5000 epochs, best_overall is being generated around epoch #900. after than mAP values are going down.
The best mAP0.5:0.95 is coming around 0.85.
My query is , is that value too high ? or is it expected? Am I overfitting the data ? Shall I continue training beyond 5000 epochs?
Kindly give your valuable feedback.

[SanKumSan]

What do you mean by Negative Samples ?

[saumya221]

Negative sample means images not having the object of interest.