Spaces:

helloAK96
/

chaosops

Running

App Files Files Community

874 kB

Ctrl+K

Ctrl+K

2 contributors

History: 30 commits

helloAK96's picture

Claude Opus 4.7

README: add Training History section — 3,200 episodes across 6 GRPO runs

adbc390 14 days ago

__pycache__
Initializing space 15 days ago
agents
Phase A submission cleanup — OpenEnv compliance + composable rubrics + loud-fail trained lane 15 days ago
artifacts
Promote Phase 3A LoRA — Qwen 3B beats heuristic on HARD, 100% rogue catch 14 days ago
curriculum
Initializing space 15 days ago
dashboard
Initializing space 15 days ago
env
Initializing space 15 days ago
notebooks
Notebook: add Phase 8b — training history (3,200 episodes, 6-run ablation table) 14 days ago
rewards
GRPO: add --rogue-bonus-multiplier to amplify oversight gradient signal 14 days ago
scripts
GRPO: add --rogue-bonus-multiplier to amplify oversight gradient signal 14 days ago
train
GRPO: add --rogue-bonus-multiplier to amplify oversight gradient signal 14 days ago
.gitattributes

1.68 kB
Ship trained-policy artifact: learning_curve.png 14 days ago
.gitignore

606 Bytes
Ship baseline_curve.png so the Space README embed renders 15 days ago
BLOG.md

7.89 kB
Phase A submission cleanup — OpenEnv compliance + composable rubrics + loud-fail trained lane 15 days ago
Dockerfile

1.22 kB
rebuilding 15 days ago
FETCH_HEAD

0 Bytes
rebuilding 15 days ago
README.md

21.3 kB
README: add Training History section — 3,200 episodes across 6 GRPO runs 14 days ago
__init__.py

113 Bytes
Initializing space 15 days ago
app.py

10.9 kB
Phase A submission cleanup — OpenEnv compliance + composable rubrics + loud-fail trained lane 15 days ago
openenv.yaml

386 Bytes
Phase A submission cleanup — OpenEnv compliance + composable rubrics + loud-fail trained lane 15 days ago
py.typed

0 Bytes
Initializing space 15 days ago
requirements.txt

732 Bytes
Phase A submission cleanup — OpenEnv compliance + composable rubrics + loud-fail trained lane 15 days ago