Spaces:
Sleeping
Sleeping
Commit History
-
fix: GRPO zero-gradient trap, DSL prompt seed, best_reward, teacher oracle
0b77231 -
training results
ede0718
-
discovery plot
1edadfb -
reward curve
8c686ce -
imp DSL, reward structure, paradigm shift
8270f31 -
submodule access,timeout, gro checkpoints, mdl penalty
92e9724 -
V1
Ankitbe9f416