Add W&B training run link to blog

Fix training rc=127 by using python -m fallback and tee logs to stdout

Document all Space variables and secrets in README

Fix LaTeX math rendering in blog (use \$\$ and \$ delimiters)

Add Trace Net blog post with final checkpoint link

Add TraceNet slide deck link to README

Remove stale COMPARE_FINETUNED_DASHBOARD references (fix 500 on Space)

Stop training failures from killing the API server (fixes 500 on Space)

Fix dashboard 404 by shipping artifacts/ into the Space image

Add missing post_training_benchmark_dashboard.html to HF Space

Always render Pre/Post-Training dashboard buttons; drop snapshot+difficulty cards

Add pre/post benchmark dashboard options in Space UI

added images (hf-space text-only subset)

Add evaluation, minor updates to HF space

Add per-batch generation liveness logging

Upload intermediate GRPO checkpoints to HF Hub on every save

Make self-play training resilient to HF Space restarts

feat(training): improve self-play progress visibility and reward diagnostics

Minor config changes

Update training config, add checkpointing on HF

test hf space commit

Sync current main to Hugging Face Space

fix(rewards): never crash GRPO on malformed completions