fix(ci,train): run fast-integ-tests in CodeBuild and give shallow RLVR cases a reward signal - #6207

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 54.84%. Comparing base (a248126) to head (479a85e).
⚠️ Report is 1 commits behind head on master.

❌ Your project check has failed because the head coverage (54.84%) is below the target coverage (65.00%). You can increase the head coverage or adjust the target coverage.

❗ There is a different number of reports uploaded between BASE (a248126) and HEAD (479a85e). Click for more details.

HEAD has 9 uploads less than BASE

Flag	BASE (a248126)	HEAD (479a85e)
	12	3

@@             Coverage Diff             @@
##           master    #6207       +/-   ##
===========================================
- Coverage   70.78%   54.84%   -15.94%     
===========================================
  Files         553      553               
  Lines       67930    67930               
===========================================
- Hits        48082    37258    -10824     
- Misses      19848    30672    +10824