Spaces:

openenv-community
/

test-local-nested-envs

Running on T4

App Files Files Community

test-local-nested-envs

163 kB

Ctrl+K

Ctrl+K

4 contributors

History: 59 commits

Claude

Add training results visualization with reward trend chart

19157df unverified about 2 months ago

assets
Add train.sh startup script and assets folder about 2 months ago
layer0
Improve reward function to break refuse-everything local minimum and scale training about 2 months ago
layer1
Pre-format SFT dataset as text column, drop formatting_func about 2 months ago
layer2
Switch Llama 3.1 8B to ungated unsloth mirror about 2 months ago
personas
Clean up dead code, unused imports, and move hardcoded values to config.yaml about 2 months ago
scripts
Make Supabase uploads incremental — upload after every step about 2 months ago
tests
Improve reward function to break refuse-everything local minimum and scale training about 2 months ago
.gitignore

126 Bytes
Implement self-improving AI oversight system with nested RL environments about 2 months ago
Dockerfile

199 Bytes
Add supabase to Dockerfile pip install about 2 months ago
README.md

18.3 kB
Add HF Spaces config metadata to README about 2 months ago
app.py

8.36 kB
Add training results visualization with reward trend chart about 2 months ago
config.yaml

4.31 kB
Increase training scale: more steps, episodes, and SFT epochs about 2 months ago
config_loader.py

5.69 kB
Add SFT warm start before GRPO and DB connectivity init check about 2 months ago
pyproject.toml

917 Bytes
Move supabase to core dependencies about 2 months ago
train.sh

1.04 kB
Add train.sh startup script and assets folder about 2 months ago