Spaces:
Running
Running
Commit History
-
Make OpenEnv training+API judge-proof
Hugging Face Jobs runs were failing due to torch/torchvision mismatches triggered by dependency resolution. The GRPO training script now avoids optional vision deps for text-only runs and emits real artifacts (log history + reward curve + sampled before/after execution reward) instead of illustrative charts. Also hardens the reviewer flow and aligns the public contract: adds a state->observation builder for reviewer rejections, keeps reviewer rewards inside strict (0,1), updates the manifest + README for the finance task, and adds socketless API integration tests via FastAPI TestClient. Restores a root-level baseline inference runner as documented. Constraint: HF Jobs images may ship torch/torchvision stacks that become incompatible after pip resolution Constraint: Judges need rerunnable training evidence (plots/logs) sourced from real runs Rejected: Force-pin torch/torchvision via pip | large downloads and brittle across images Confidence: high Scope-risk: moderate Reversibility: cl…d061422 -
Deploy: SOTA RL Cartesian Task and Unsloth Scripts
6518b31
-
Harden strict (0,1) scoring boundaries across runtime and config.
Clamp reward outputs to non-boundary values, align schema ranges, and remove inference fallbacks that could emit 0.0 or 1.0 during evaluation. ss:9b71d1b -
Initialize runtime score fields with strict non-boundary minimum
8e7c622 -
Enforce strict (0,1) task score outputs for validators
bc9f459 -
Initial OpenEnv SQL debug environment
30cf758