OSINT / config

Commit History

Make self-play training resilient to HF Space restarts
2e14f6d

siddeshwar-kagatikar commited on

Minor config changes
3e893cd

ritishshrirao commited on

Update training config, add checkpointing on HF
e44cdee

ritishshrirao commited on

Sync current main to Hugging Face Space
fe1f842

siddeshwar-kagatikar commited on

fix(rewards): never crash GRPO on malformed completions
d814291

siddeshwar-kagatikar commited on