opus-max.sft_cont2.step_900

AgentPTB sweep checkpoint. Cell opus-max — Claude Code / claude-opus-5 @ effort max.

field value
plot cell opus-max
driver Claude Code / claude-opus-5
reasoning effort max
run boot (UTC) 2026-08-13T14:28:54Z
role intermediate
checkpoint path in run ckpt/sft_cont2/weights/step_900
shards 4
size 18.8 GB
base model Qwen/Qwen3.5-9B-Base
eos_token_id [248044, 248046] ✅ correct

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

Join on plot cell above. The sweep figures are keyed by these same cell names.

Downloads last month
6
Safetensors
Model size
9B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for agentic-ptb/opus-max.h043.sft_cont2.step_900

Finetuned
(384)
this model