We present an empirical study of price reversion after the executed metaorders. We use a data set with more than 8 million metaorders executed by institutional investors in the US equity market. We show that relaxation takes place as soon as the metaorder ends:{while at the end of the same day it is on average ≈2/3 of the peak impact, the decay continues the next days, following a power-law function at short time scales, and converges to a non-zero asymptotic value at long time scales (∼50 days) equal to ≈1/2 of the impact at the end of the first day.} Due to a significant, multiday correlation of the sign of executed metaorders, a careful deconvolution of the \emph{observed} impact must be performed to extract the estimate of the impact decay of isolated metaorders.