opus-max.soup_base_sft

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/soup_base_sft
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
11
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.h088.soup_base_sft

Finetuned
(582)
this model