diff options
| author | YurenHao0426 <blackhao0426@gmail.com> | 2026-02-11 01:31:45 +0000 |
|---|---|---|
| committer | YurenHao0426 <blackhao0426@gmail.com> | 2026-02-11 01:31:45 +0000 |
| commit | 1b198877233afd9ffa0093f0c4e9c2959c2589e9 (patch) | |
| tree | 374c0da5c8d72c0faec3fce95dd2b6ebf9a17ff3 /collaborativeagents/training/grpo_verl/outputs/2026-01-11/03-50-42/.hydra | |
| parent | da40fccaa2176349482581bb0f7fb610e168f1b5 (diff) | |
Fix all-methods comparison: use same experiment run (fullscale 200p60s)
- Fullscale has all 6 methods in one run (fair comparison)
- Note: fullscale rag_vector is old version (no query_transform/global_prefs)
- Separate section for 60s experiments (new rag_vector, harder datasets)
- reflection dominates in fullscale (66.9%), rag/rag_vector ~52-53%
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Diffstat (limited to 'collaborativeagents/training/grpo_verl/outputs/2026-01-11/03-50-42/.hydra')
0 files changed, 0 insertions, 0 deletions