agentic-ptb/kimi.h045.rl_v8.step_20

kimi.h054.rl_v9.step_30

AgentPTB sweep checkpoint. Cell kimi — kimi-code / kimi-k3 @ effort high.

field	value
plot cell	kimi
driver	kimi-code / kimi-k3
reasoning effort	high
run boot (UTC)	2026-08-15T21:03:17Z
role	intermediate
hours into run	h54.53 of 100
checkpoint path in run	runs/rl_v9/weights/step_30
shards	4
size	18.8 GB
base model	Qwen/Qwen3.5-9B-Base
eos_token_id	[248044] ⚠️ MISSING 248046

Reading the eos field

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.

Mapping back to the figures

The repo id is {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.