Monitor Experiment Results

Workflow

Step 1: Check What's Running

ssh <server> "screen -ls"

Step 2: Collect Output from Each Screen

ssh <server> "screen -S <name> -X hardcopy /tmp/screen_<name>.txt && tail -50 /tmp/screen_<name>.txt"

Step 3: Check for JSON Result Files

ssh <server> "ls -lt <results_dir>/*.json 2>/dev/null | head -20"

ssh <server> "cat <results_dir>/<latest>.json"

Step 4: Summarize Results

| Experiment | Metric | Delta vs Baseline | Status |
|-----------|--------|-------------------|--------|
| Baseline  | X.XX   | —                 | done   |
| Method A  | X.XX   | +Y.Y              | done   |

Step 5: Interpret

• Compare against known baselines
• Flag unexpected results (negative delta, NaN, divergence)
• Suggest next steps based on findings

Step 6: Feishu Notification (if configured)

~/.claude/feishu.json

• Send

  experiment_done

  notification: results summary table, delta vs baseline
• If config absent or mode

  "off"

  : skip entirely (no-op)

Key Rules

• Always show raw numbers before interpretation
• Compare against the correct baseline (same config)
• Note if experiments are still running (check progress bars, iteration counts)
• If results look wrong, check training logs for errors before concluding