Spaces:

Chunchunmaru-101
/

wildfire-env

Running

App Files Files Community

2.16 MB

Ctrl+K

Ctrl+K

3 contributors

History: 91 commits

Chunchunmaru-101's picture

Chunchunmaru-101

Notebook: spell out OpenEnv EnvClient/WebSocket transport in eval section

36294b9 3 months ago

notebooks
Notebook: spell out OpenEnv EnvClient/WebSocket transport in eval section 3 months ago
replays
Add untrained replay 3 months ago
server
Finalize submission packaging and refine reward shaping 3 months ago
submission_artifacts
Submission: single notebook, restored Blog, eval comparison plot 3 months ago
tests
Use HTTP evaluator for final showcase 3 months ago
wildfire_env
Restore stashed work: notebooks, eval flags, plot helper, eval_policy wrapper 3 months ago
.gitignore

514 Bytes
Restore stashed work: notebooks, eval flags, plot helper, eval_policy wrapper 3 months ago
Blog.MD

12.6 kB
Fix Blog.MD wall-of-text by splitting megaparagraphs 3 months ago
Dockerfile

1.28 kB
Finalize submission packaging and refine reward shaping 3 months ago
README.md

9.94 kB
Submission: single notebook, restored Blog, eval comparison plot 3 months ago
RUN_HANDOFF.md

13.6 kB
Submission: single notebook, restored Blog, eval comparison plot 3 months ago
capture_replay.py

9.54 kB
Remove eval debug logging and _tmp_cache_smoke; trim cache comments 3 months ago
eval_policy.py

487 Bytes
Unify GRPO+eval in wildfire_train_eval_hf.ipynb; redirect legacy notebooks 3 months ago
eval_policy_http.py

25.1 kB
Remove submission_check.py; last strict run passed 3 months ago
eval_trained_run.log

23.7 kB
Add OpenEnv eval JSON and tee logs (untrained + trained, 5 seeds per task) 3 months ago
eval_untrained_run.log

24.9 kB
Add OpenEnv eval JSON and tee logs (untrained + trained, 5 seeds per task) 3 months ago
openenv.yaml

95 Bytes
Finalize submission packaging and refine reward shaping 3 months ago
plot_training_curves.py

18 kB
Restore stashed work: notebooks, eval flags, plot helper, eval_policy wrapper 3 months ago
pyproject.toml

772 Bytes
Add containment and spread-limit grader signals. 3 months ago
reward_audit.json

73.2 kB
Sync submission notebooks + consolidated README, drop redundant READMEs 3 months ago
reward_audit.py

20.4 kB
Upgrade RL defaults and add submission tooling 3 months ago
smoke_test.py

3.41 kB
Clean up deleted files and modify smoke_test, pyproject 3 months ago
train_grpo.py

56.7 kB
Move import unsloth to module level in train_grpo.py 3 months ago
uv.lock

576 kB
Finalize submission packaging and refine reward shaping 3 months ago