Views
No views yet
sol-high — Codex / gpt-5.6-sol @ effort high.| field | value |
|---|---|
| plot cell | sol-high |
| driver | Codex / gpt-5.6-sol |
| reasoning effort | high |
| run boot (UTC) | 2026-08-08T07:28:19Z |
| role | intermediate |
| hours into run | h17.56 of 100 |
| checkpoint path in run | outputs/maxrl-rebase-wide/weights/step_1 |
| shards | 4 |
| size | 18.8 GB |
| base model | Qwen/Qwen3.5-9B-Base |
| eos_token_id | [248044, 248046] ✅ correct |
248046 is <|im_end|>, the token the Qwen3.5 chat template ends every assistant turn with.
Checkpoints missing it do not stop at end-of-turn and overrun the context window, so their
eval numbers are a floor, not a measurement — compare them only against other checkpoints
with the same eos status, or re-package before evaluating.{cell}.h{HHH}.{family}.{step}, where hHHH is the hour of the 100-hour run
at which this checkpoint was written — the same x-axis the sweep figures use for eval
panels (t_h). So a checkpoint drops onto the performance-over-time curve directly, and
sorting repo ids within a cell sorts them chronologically.hHHH is rounded down to whole hours for sortability; the exact value is the
hours into run row above, and in agentic-ptb/INDEX.