Commit History

Add session checkpoint: v3 launch decision with full context
bead5cb
verified

rtferraz commited on

apply v3 task-aware thinking controls and delete deprecated notebook
1d514ac

rtferraz commited on

Add v3 thinking control patch - task-aware system prompts + think efficiency reward
0f39df7
verified

rtferraz commited on

Initial commit: Tucano2-Commerce GRPO v3 training pipeline
fa4a874

rtferraz Claude Opus 4.6 commited on

Upload grpo_vertex_v3.ipynb
c9b11b9
verified

rtferraz commited on

Rename notebooks/grpo_vertex_v3.ipynb to notebooks/DEPRECATED_grpo_vertex_v3.ipynb
a62f1dc
verified

rtferraz commited on

Delete grpo_vertex_v3.md
b110818
verified

rtferraz commited on

tools: add md-to-ipynb converter script
734569e
verified

rtferraz commited on

feat: add v3 notebook (.ipynb) — ready for Vertex AI Workbench
6c51e5f
verified

rtferraz commited on

feat: add GRPO v3 implementation with entropy collapse fixes
a6a8b11
verified

rtferraz commited on

Create grpo_vertex_v2_ipynb.md
042d2b9
verified

rtferraz commited on

docs: add ADR-001 next steps with detailed execution plans
b47b36b
verified

rtferraz commited on

docs: add project documentation
aa71b0c
verified

rtferraz commited on

initial commit
901bdc7
verified

rtferraz commited on