Suggest y'all take a look at this: weigh-scale design issues
A few quotes and comments:
Quote: "Load cells...drift over time....the drift is not temperature-related."
Comment: Load cells also have hysteresis and gain drift with temperature. Either of those could be part or all of the reason jhondel2015's output doesn't go back to zero when the load is removed.
Quote: "The resolutions of typical weigh-scale systems, as seen by the user, range from a count of 1:3,000 at the low end up to 1:10,000 for high-end solutions."
Comment: Ammasi wants a resolution of 1:50,000, beyond even "high-end" solutions.
Quote: "In order to guarantee that this resolution is met accurately, the internal resolution of the system must be better by at least an order of magnitude. In fact, some standards dictate that the internal count of the system be a factor of 20 times better than that of the external count."
Comment: therefore Ammasi needs an internal resolution of at least 1:500,000 or maybe even 1:1,000,000. Considering that the full-scale range of the ADC is unlikely to be used, and considering the other factors mentioned in the linked PDF, that will be very difficult to achieve.
At this forum link you can see some of my test results with a 200 gram load cell and a HX711. The graphs show the drift over several days with constant load of various magnitudes.