Add more thorough log checks to see if the model server failed deployment during validation

[KaiyiLiu1234]

If the model server fails to access a model, it will produce a "failed to" log which is not picked up by the metal ci e2e. Resolve this by adding checks for failure.

[KaiyiLiu1234]

note: leverage model server exporter that will be implemented soon in the model server

[SamYuan1990]

we can use failure keywords. ref #288

[KaiyiLiu1234]

Referencing a major error: Did not check if the models, namely http://localhost:8080/AbsPower/BPFOnly/SGDRegressorTrainer_-1 existed or not. This name appears in the logs but it fails to check whether the url actually points to the model or not. Since the node index fix with hatch run, it should end with _0 and not _-1. Multiple runs for e2e failed to pick on this error.