Spaces:
Running
Running
Commit History
-
Mock vllm to bypass TRL missing module error
1bc1daa -
Downgrade TRL to <0.24.0 to fix missing dependency chain
397face -
Add TRANSFORMERS_CACHE mock to fix TRL/llm_blender crash
16dd181 -
Fix llm-blender ModuleNotFoundError
1cd9ac8 -
Ensure TRL GRPO imports by installing mergekit
TRL's GRPO trainer path imports mergekit utilities unconditionally in recent releases; without mergekit present the job fails before training starts.\n\nInstall mergekit during bootstrap so GRPOConfig/GRPOTrainer imports succeed in HF Jobs containers. Constraint: HF Jobs run with ephemeral, system-managed Python (PEP-668)\nRejected: Pin older TRL | risk of drifting from Unsloth-supported TRL range\nConfidence: medium\nScope-risk: narrow\nDirective: If TRL relaxes this dependency again, mergekit can be removed to reduce install time\nTested: python -m py_compile ultimate_sota_training.py\nNot-tested: HF Jobs end-to-end run6d0b5c3 -
Prevent torchvision import crashes in HF Jobs
HF base images can include torchvision, and pip uninstall may be blocked by PEP-668 unless break-system-packages is enabled. When Unsloth's dependency resolution downgrades torch, any remaining torchvision can crash transformers/trl imports (torchvision::nms).\n\nSet TRANSFORMERS_NO_TORCHVISION early, opt into PIP_BREAK_SYSTEM_PACKAGES for all pip ops, and uninstall torchvision/torchaudio both before and after Unsloth install so text-only training stays stable. Constraint: HF Jobs run on externally-managed system Python (PEP-668)\nRejected: Pin torch/torchvision versions | pip resolver still drags heavy CUDA wheels and increases cost\nConfidence: high\nScope-risk: narrow\nDirective: Keep torchvision out of text-only training images unless you also pin torch+torchvision compat\nTested: python -m py_compile ultimate_sota_training.py\nNot-tested: HF Jobs end-to-end run8b3c03a -
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 -
Add --break-system-packages for Ubuntu 24.04 (PEP-668)
830c039 -
Fix TRL and Torchao dependency conflicts
d118f9f -
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 -
Keep task scores strictly inside (0,1) in inference logs
941f5f8 -
Enforce strict (0,1) task score outputs for validators
bc9f459 -
Restore full README content under HF metadata
87464f9 -
Align inference env var handling with submission checklist.
Require HF_TOKEN at runtime, keep defaults only for API_BASE_URL and MODEL_NAME, and wire OpenAI client auth directly to HF_TOKEN.e7c61ad -
initial commit
74e3e43 -
Expand README with lifecycle and validation details
da4c99f -
Polish README hero and add quick links
bad2f97 -
initial commit
03d6772 -
Add HF Space metadata frontmatter
157ae69 -
Initial OpenEnv SQL debug environment
35a5127 -
initial commit
c193516 -
Initial OpenEnv SQL debug environment
00849df -
Expand README with lifecycle and validation details
18e112b -
initial commit
c7d8ccb -
Polish README hero and add quick links
06729fc -
initial commit
959117b -
Add HF Space metadata frontmatter
5fb3e9e -
Initial OpenEnv SQL debug environment
65def40 -
initial commit
7c1365c -
Initial OpenEnv SQL debug environment
765dffd -
Polish README hero and add quick links
070f20e -
initial commit
23c3767 -
Add HF Space metadata frontmatter
d7e90b4 -
Initial OpenEnv SQL debug environment
9fafc85 -
initial commit
4bd4b79 -
Initial OpenEnv SQL debug environment
8ae4239 -
Polish README for final submission presentation.
Add a professional badge header, architecture diagram, and explicit project structure to make evaluation and navigation easier while keeping stack usage transparent.25c431b -
Add HF Space metadata frontmatter
7dd64a8 -
Initial OpenEnv SQL debug environment
2d7cbd5 -
initial commit
530e6d5 -
Initial OpenEnv SQL debug environment
541186b -
Add HF Space metadata frontmatter
b8ddd72 -
Initial OpenEnv SQL debug environment
dd04366 -
initial commit
f55f42f -
Initial OpenEnv SQL debug environment
d43209e -
Set deployed HF Space base URL
555678d -
Initial OpenEnv SQL debug environment
30cf758 -
initial commit
825ffea