| { |
| "project": "TIL-26-AE Bomberman Agent", |
| "repo": "E-Rong/til-26-ae-agent", |
| "space": "e-rong/til-26-ae", |
| "last_updated": "2026-05-14", |
| "current_phase": 2, |
| "phases": { |
| "1": { |
| "status": "COMPLETE", |
| "timesteps": 500352, |
| "checkpoint": "phase1_final.zip", |
| "eval_win_rate": "92.0%", |
| "eval_avg_reward": 180.1, |
| "eval_survival": "100.0%", |
| "completed_at": "2026-05-14T04:30:00Z" |
| }, |
| "2": { |
| "status": "IN_PROGRESS", |
| "started_from": "phase1_final.zip", |
| "latest_checkpoint": "phase2_ckpt_600352.zip", |
| "latest_timestep": 600352, |
| "target_timestep": 1000352, |
| "remaining_steps": 400000, |
| "shaping": { |
| "method": "visit_count_adaptive", |
| "k": 1.2, |
| "base_weight": 0.5 |
| }, |
| "note": "Training crashed during sandbox session. Need to resume from checkpoint.", |
| "blockers": [ |
| "HF Job git clone auth failure for private TIL repo", |
| "sandbox process died without detection, kept billing empty" |
| ] |
| }, |
| "3": { |
| "status": "PENDING", |
| "duration": 1000000, |
| "opponents": "rule_based_curriculum", |
| "teams": 3 |
| } |
| }, |
| "mistakes_log": [ |
| { |
| "date": "2026-05-14", |
| "mistake": "Used sandboxes for 3+ hour training runs", |
| "cost": "~$4.87", |
| "why_wrong": "Sandboxes are interactive dev environments, not batch compute. They recycle/timeout and keep billing when empty.", |
| "fix": "Use HF Jobs for any training >30 minutes" |
| }, |
| { |
| "date": "2026-05-14", |
| "mistake": "git clone private repo in HF Job without auth", |
| "cost": "~$0.10", |
| "why_wrong": "HF Jobs have HF_TOKEN env var, but git clone doesn't use it automatically. Need snapshot_download or token-in-URL.", |
| "fix": "Use huggingface_hub.snapshot_download() which auto-uses HF_TOKEN" |
| }, |
| { |
| "date": "2026-05-14", |
| "mistake": "No session state persistence on Hub", |
| "cost": "Time lost reconstructing state", |
| "why_wrong": "Relied on ephemeral /app files instead of pushing state to Hub repo after every milestone.", |
| "fix": "This file. Push/pull session_state.json from Hub at every session boundary." |
| } |
| ], |
| "scripts": { |
| "phase1_training": "/app/phase1_script.py (lost in sandbox reset)", |
| "phase2_training": "phase2_job.py in Hub repo", |
| "inference": "ae_manager.py in Hub repo (also in e-rong/til-26-ae ae/src/)" |
| }, |
| "next_steps": [ |
| "Fix HF Job script to use snapshot_download instead of git clone", |
| "Test with 5-minute smoke job before full submission", |
| "Resume Phase 2 from phase2_ckpt_600352.zip to 1,000,352 steps", |
| "Run evaluation vs random opponents", |
| "Proceed to Phase 3 curriculum" |
| ] |
| } |
